Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 44
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

A Learnheuristic Algorithm Based on Thompson Sampling for the Heterogeneous and Dynamic Team Orienteering Problem

  • Rodríguez Uguina, Antonio|||0009-0001-5506-1674
  • Gómez González, Juan Francisco|||0000-0001-7692-9922
  • Panadero, Javier|||0000-0002-3793-3328
  • Martínez-Gavara, Anna|||0000-0001-9995-010X
  • Juan, Ángel A|||0000-0003-1392-1776
The team orienteering problem (TOP) is a well-studied optimization challenge in the field of Operations Research, where multiple vehicles aim to maximize the total collected rewards within a given time limit by visiting a subset of nodes in a network. With the goal of including dynamic and uncertain conditions inherent in real-world transportation scenarios, we introduce a novel dynamic variant of the TOP that considers real-time changes in environmental conditions affecting reward acquisition at each node. Specifically, we model the dynamic nature of environmental factors-such as traffic congestion, weather conditions, and battery level of each vehicle-to reflect their impact on the probability of obtaining the reward when visiting each type of node in a heterogeneous network. To address this problem, a learnheuristic optimization framework is proposed. It combines a metaheuristic algorithm with Thompson sampling to make informed decisions in dynamic environments. Furthermore, we conduct empirical experiments to assess the impact of varying reward probabilities on resource allocation and route planning within the context of this dynamic TOP, where nodes might offer a different reward behavior depending upon the environmental conditions. Our numerical results indicate that the proposed learnheuristic algorithm outperforms static approaches, achieving up to 25% better performance in highly dynamic scenarios. Our findings highlight the effectiveness of our approach in adapting to dynamic conditions and optimizing decision-making processes in transportation systems.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

An Agile Adaptive Biased-Randomized Discrete-Event Heuristic for the Resource-Constrained Project Scheduling Problem

  • Martin, Xabier A.|||0000-0003-4182-0120
  • Herrero, Rosa|||0000-0003-3575-0963
  • Juan, Ángel A|||0000-0003-1392-1776
  • Panadero, Javier|||0000-0002-3793-3328
In industries such as aircraft or train manufacturing, large-scale manufacturing companies often manage several complex projects. Each of these projects includes multiple tasks that share a set of limited resources. Typically, these tasks are also subject to time dependencies among them. One frequent goal in these scenarios is to minimize the makespan, or total time required to complete all the tasks within the entire project. Decisions revolve around scheduling these tasks, determining the sequence in which they are processed, and allocating shared resources to optimize efficiency while respecting the time dependencies among tasks. This problem is known in the scientific literature as the Resource-Constrained Project Scheduling Problem (RCPSP). Being an NP-hard problem with time dependencies and resource constraints, several optimization algorithms have already been proposed to tackle the RCPSP. In this paper, a novel discrete-event heuristic is introduced and later extended into an agile biased-randomized algorithm complemented with an adaptive capability to tune the parameters of the algorithm. The results underscore the effectiveness of the algorithm in finding competitive solutions for this problem within short computing times.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Artificial intelligence use in collaborative network processes

  • Andres, B.|||0000-0002-7920-7711
  • Urze, P.
  • Araujo, E.
  • Camarinha-Matos, L.M.
[EN] This paper reviews the literature to analyse the use of artificial intelligence (AI) in collaborative processes among supply chain (SC) partners, thereby forming a collaborative network (CN). Given the growth of AI and its limited exploration in many business strategies, especially when collaboration among SC partners¿ is established, this paper focuses on defining the lines of research and application of AI in CN processes, by presenting insights into how AI can improve the resilience and the antifragility. It examines the integration of AI in CN processes from the following perspectives: (i) the collaborative processes addressed among the CN partners, (ii) the decision-making level of the collaborative processes performed, (iii) the SC partners involved in the collaboration; (iv) the technologies combined with AI to support CN processes; (v) the programming languages implemented to develop AI algorithms; (vi) the SC sectors in which AI is mainly implemented to perform collaborative processes; and (vii) the potential of implementing AI in CN processes, in an increasingly turbulent and disruptive business world. The study focuses on SC in various sectors, including food, transport, logistics, manufacturing, healthcare or electronics, among others. In addition, the review provides a comprehensive understanding of the interplay between collaborative processes and AI-driven advances, identifying the technologies that can merge with AI to support CN processes. The results have enabled the development of a conceptual framework for AI use collaborative processes and outline the benefits, risks and challenges associated with the use of AI in CN, while proposing future research directions in this area., The research that led to these findings received funding from the Horizon Europe Framework Programme (HORIZON) with Grant Agreement No 101057294 "AI-Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability, and Resilience (AIDEAS)". First research projects aimed at research staff of the Universitat Politecnica de Valencia in the framework of the Vice-Rectorate for Research (PAID-06-23) "Algorithms and intelligent optimisation models for production planning and replenishment (ATENNEA)". Grant program for carrying out of stays of doctor research staff in companies of the Valencian Community, Spain (AEST/2023) CIAEST/2022/39 "Development of Optimisation Models and Heuristic Algorithms for Inventory Management and the Optimisation of Replenishment and Production Plans in a company in the agri-food industry machinery manufacturing sector".
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Strategical and tactical supply chain optimisation for smart production planning and control 4.0

  • Cañas-Sánchez, Hector Enrique
  • Campuzano-Bolarín, Francisco
  • Mula, Josefa|||0000-0002-8447-3387
[EN] Industry 4.0 (I4.0) technologies generate new opportunities for developing smart models, algorithms and tools to support supply chain (SC) production planning and control (PPC), or smart PPC (SPPC 4.0). Paired with opportunities, challenges arise in integrating sustainability and resilience in SC network design (SCND) according under I4.0. The main novelty of this paper is to propose two multi-objective models that integrate strategical and tactical PPC decisions into a sustainable-resilient SC under I4.0 towards SPPC 4.0. Sustainability is incorporated in terms of reducing costs and CO2 emissions, and a job creation factor. Resilience is incorporated in terms of contracting support suppliers. To solve the multi-objective models, the augmented epsilon constraint method (AUGMECON) was used. This algorithm minimises a target objective function while it treats the others as constraints. Our experiments indicate that AUGMECON is sensitive to the choice of epsilon values. Furthermore, a synthetic data generation tool called SR1-SR2_SynthDataGenerator was developed. This tool generates input datasets to validate and evaluate our models against benchmarks. A stochastic model (SR2) is also proposed that, with small datasets, takes 8.39 seconds to solve. The proposed models can be useful for industries that seek sustainable and resilient SCs to adapt to changing environments., The research that has led to the present results has received funding from: the MCIN/AEI/10.13039/501100011033 and by European Union Next GenerationEU/PRTR with grant agreement PDC2022-133957-I00); and the Regional Department of Innovation, Universities, Science and Digital Society of the Generalitat Valenciana entitled 'Industrial Production and Logistics Optimization in Industry 4.0' (i4OPT) (Ref. PROMETEO/2021/065); and from the European Union Horizon Europe program under grant agreements No. 101070076 'Optimizing Production and Logistic Resources in the Time-critical Bio Production Industries in Europe' (CLARUS) and No. 101057294 'AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability and Resilience' (AIDEAS).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Dynamic Reactive Assignment of Tasks in Real-Time Automated Guided Vehicle Environments with Potential Interruptions

  • Martín, Xabier A.
  • Hatami, Sara
  • Calvet, Laura
  • Peyman, Mohammad
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] An efficient management of production plants has to consider several external and internal factors, such as potential interruptions of the ongoing processes. Automated guided vehicles (AGVs) are becoming a widespread technology that offers many advantages. These AGVs can perform complex tasks in an autonomous way. However, an inefficient schedule of the tasks assigned to an AGV can suffer from unwanted interruptions and idle times, which in turn will affect the total time required by the AGV to complete its assigned tasks. In order to avoid these issues, this paper proposes a heuristic-based approach that: (i) makes use of a delay matrix to estimate circuit delays for different daily times; (ii) employs these estimates to define an initial itinerary of tasks for an AGV; and (iii) dynamically adjusts the initial agenda as new information on actual delays is obtained by the system. The objective is to minimize the total time required for the AGV to complete all the assigned tasks, taking into account situations that generate unexpected disruptions along the circuits that the AGV follows. In order to test and validate the proposed approach, a series of computational experiments utilizing real-life data are carried out. These experiments allow us to measure the improvement gap with respect to the former policy used by the system managers., This work has been partially supported by the Spanish Ministry of Industry, Commerce and Tourism (AEI-010500-2021b-54), the EU Comission (HORIZON-CL4-2021-TWIN-TRANSITION-01-07, 101057294 AIDEAS), and the Generalitat Valenciana (PROMETEO/2021/065).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Alignment and Improvement of Shape-From-Silhouette Reconstructed 3D Objects

  • Pérez Jiménez, Alberto José|||0000-0001-9059-0128
  • Perez-Cortes, Juan-Carlos|||0000-0001-6506-090X
  • Guardiola Garcia, Jose Luis|||0000-0002-1100-4950
  • Perez-Soler, Javier
[EN] 3D object alignment is essential in multiple fields. For instance, to allow precise measurements in metrology, to perform surface/volumetric checks or quality control in industrial inspection, to align partial captures of a 3D object during object scanning, to simplify object recognition or classification in pattern recognition, accuracy and speed, being opposed, are desirable features of those algorithms. Nevertheless, they can be more or less critical depending on the application area. In the present work, we propose a methodology to improve the alignment of 3D objects reconstructed using shape-from-silhouette techniques. This reconstruction technique produces objects with small synthetic bulges, making them more difficult to align accurately. On the one hand, prealignment and branch-and-bound techniques are used to improve the convergence and speed of the alignment algorithms. On the other hand, a method to obtain a precise alignment even in the presence of bulges is presented. Finally, a refinement of the shape-from-silhouettes technique is shown. This technique uses multiple captures to refine object reconstruction and reduce or eliminate, among other improvements, synthetic bulges., This work was supported in part by European Union Horizon Europe Programme Artificial Intelligence Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability and Resilience (AIDEAS) under Grant 101057294; and in part by the Generalitat Valenciana through Instituto Valenciano de Competitividad Empresarial [Valencian Institute of Business Competitiveness (IVACE)] Distributed Nominatively to Valencian Technological Innovation Centres under Project IMAMCA/2023/11.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Inteligencia Artificial para el soporte a la toma de decisiones en el ciclo de vida de los equipos industriales., Artificial Intelligence for decision support in the lifecycle of industrial equipment

  • Mateo-Casalí, Miguel Ángel|||0000-0001-5086-9378
  • Fiesco-Muñoz, Juan Pablo|||0009-0008-3369-4607
  • Andres, B.|||0000-0002-7920-7711
  • Poler, R.|||0000-0003-4475-6371
[ES] Este artículo realiza una revisión de la literatura sobre las aplicaciones de la IA en cada fase del ciclo de vida de los equipos industriales, incluyendo el diseño, la fabricación el uso y la reparación/reutilización/reciclado. Sobre la base del proyecto europeo AIDEAS, un conjunto de soluciones basadas en IA se conceptualiza. Estas soluciones se contextualizan en un piloto industrial que se dedica a la fabricación de equipos para la inspección y clasificación de alimentos. Las líneas futuras de investigación se dirigen hacia el desarrollo de las tecnologías de IA conceptualizadas, y su implementación en el piloto industrial objeto de estudio., La investigación que ha conducido a estos resultados ha recibido financiación del Programa Marco Horizonte Europa (HORIZONTE) con el acuerdo de subvención nº 101057294 "AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability, and Resilience (AIDEAS)", de la Conselleria de Innovación, Universidades, Ciencia y Sociedad Digital de la Generalitat Valenciana "Programa Investigo" (ref. INVEST/2022/330), apoyado por la Unión Europea - NextGenerationEU dentro del Plan de Recuperación, Transformación y Resiliencia.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

An Agile Adaptive Biased-Randomized Discrete-Event Heuristic for the Resource-Constrained Project Scheduling Problem

  • Martín, Xabier A.
  • Herrero, Rosa
  • Panadero, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] In industries such as aircraft or train manufacturing, large-scale manufacturing companies often manage several complex projects. Each of these projects includes multiple tasks that share a set of limited resources. Typically, these tasks are also subject to time dependencies among them. One frequent goal in these scenarios is to minimize the makespan, or total time required to complete all the tasks within the entire project. Decisions revolve around scheduling these tasks, determining the sequence in which they are processed, and allocating shared resources to optimize efficiency while respecting the time dependencies among tasks. This problem is known in the scientific literature as the Resource-Constrained Project Scheduling Problem (RCPSP). Being an NP-hard problem with time dependencies and resource constraints, several optimization algorithms have already been proposed to tackle the RCPSP. In this paper, a novel discrete-event heuristic is introduced and later extended into an agile biased-randomized algorithm complemented with an adaptive capability to tune the parameters of the algorithm. The results underscore the effectiveness of the algorithm in finding competitive solutions for this problem within short computing times., This work has been partially funded by the Horizon Europe program (HORIZON-CL4-2022-HUMAN-01-14-101092612 SUN and HORIZON-CL4-2021-TWIN-TRANSITION-01-07-101057294 AIDEAS), as well as by the Spanish Ministry of Science and Innovation (PID2022-138860NB-I00, RED2022-134703-T).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Reference Architecture for AI-Driven Industrial Equipment Life Cycle Boosting Agility, Sustainability and Resilience

  • Mateo-Casalí, Miguel Ángel|||0000-0001-5086-9378
  • Escamilla-Fuster, Joan
  • Poler, R.|||0000-0003-4475-6371
  • Ferreira, José
  • Calado, Jorge
  • Afolaranmi, Samuel Olaiya
  • Martinez Lastra, Jose Luis
  • Tzionis, Grigoris
  • Apostolou, Georgia
  • Cosa-Liñán, Alejandro
[EN] This paper presents the Reference Architecture (RA) framework of AIDEAS project and the Machine Passport, aiming to improve European machine manufacturing companies' sustainability, agility, and resilience within the industry 4.0 paradigm. This AIDEAS reference architecture, representing a three-tier pattern of Edge, Platform/Data and Enterprise layers as well as four functional domains, namely Application, Business, Information and Edge, provides a structured view of the infrastructure from the immediate interactions at the edge to the overall management of business processes and data flow and serves as basis for the description of solutions developed in AIDEAS. The Machine Passport, a core element of the AIDEAS ecosystem, is an intelligent platform that facilitates acquiring, managing, and exchanging manufacturing data at various lifecycle stages. This solution ensures traceability, scalability, security, and interoperability, contributing to the comprehensive monitoring of machine conditions throughout the lifecycles of industrial assets. In the context of Industry 4.0, the AIDEAS project presents an innovative approach to industrial data management, fostering sustainability and advancing the capabilities of European machine manufacturing companies., The research that led to these findings received funding from the Horizon Europe Framework Programme (HORIZON) with Grant Agreement No. 101057294 "AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability, and Resilience (AIDEAS)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Biased-Randomized Discrete Event Algorithm to Improve the Productivity of Automated Storage and Retrieval Systems in the Steel Industry

  • Neroni, Mattia
  • Bertolini, Massimo
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] In automated storage and retrieval systems (AS/RSs), the utilization of intelligent algorithms can reduce the makespan required to complete a series of input/output operations. This paper introduces a simulation optimization algorithm designed to minimize the makespan in a realistic AS/RS commonly found in the steel sector. This system includes weight and quality constraints for the selected items. Our hybrid approach combines discrete event simulation with biased-randomized heuristics. This combination enables us to efficiently address the complex time dependencies inherent in such dynamic scenarios. Simultaneously, it allows for intelligent decision making, resulting in feasible and high-quality solutions within seconds. A series of computational experiments illustrates the potential of our approach, which surpasses an alternative method based on traditional simulated annealing., This work was partially funded by the Horizon Europe program (HORIZON-CL4-2022-HUMAN-01-14-101092612 SUN and HORIZON-CL4-2021-TWIN-TRANSITION-01-07-101057294 AIDEAS), as well as by the Generalitat Valenciana (PROMETEO/2021/065)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Relational network of innovation ecosystems generated by digital innovation hubs: a conceptual framework for the interaction processes of DIHs from the perspective of collaboration within and between their relationship levels

  • Serrano-Ruiz, Julio Cesar|||0000-0002-6671-7077
  • Ortiz Bas, Ángel|||0000-0001-5690-0807
  • Ferreira, José
  • Jardim-Goncalves, R.
[EN] Collaboration plays a key role in the success attained to date by networks of innovation ecosystems generated around entities known as Digital Innovation Hubs (DIHs), recently created following European Commission initiatives to boost the digitisation of the European economic fabric. This article proposes a conceptual framework that brings together, defines, structures and relates the concepts involved in the collaborative interaction processes within and between these innovation ecosystems to allow comprehensive conceptualisation. The developed framework also provides an approach that helps to tangibilise collaboration as a management process. Here the goal is to ultimately move towards not only qualitative, but also quantitative modelling to bridge the research gap in the state of the art in this respect. The data-driven business-ecosystem-skills-technology (D-BEST) model, devised to configure DIHs service portfolios in a collaborative context, provides the reference basis for the interorganisational asset transfer methodology (IOATM). This is the keystone that structures the framework and constitutes its main contribution. Through the IOATM, this conceptual framework points out collaboration quantification, and serves as a lever for its modelling to deal with collaboration accounting by: turning it into a more controllable management element; guiding practitioners' efforts to improve collaborative processes efficiency with an approach that pursues objectivity and maximises synergies., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. The research leading to these results received funding from the European Union H2020 Research and Innovation Programme with Grant Agreements No. 872548 Fostering DIHs for Embedding Interoperability in Cyber Physical Systems of European SMEs (DIH4CPS), No. 825631 Zero-Defect Manufacturing Platform (ZDMP), and No. 958205 Industrial Data Services for Quality Control in Smart Manufacturing (i4Q) , from the European Union Horizon Europe Programme with Grant Agreement No. 101057294 AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability and Resilience (AIDEAS), and from the Regional Department of Innovation, Universities, Science and Digital Society of the Generalitat Valenciana entitled Industrial Production and Logistics Optimisation in Industry 4.0 (i4OPT, Ref. PROMETEO/2021/065).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Facilitating AI-Based Solutions Integration in Production Planning: Development of an Interoperable Data Model

  • Andres, B.|||0000-0002-7920-7711
  • Fiesco-Muñoz, Juan Pablo|||0009-0008-3369-4607
  • Poler, R.|||0000-0003-4475-6371
  • Mateo-Casalí, Miguel Ángel|||0000-0001-5086-9378
[EN] Industries strive to improve efficiency, minimise environmental impacts and ensure operational continuity. Enterprises digitisation favours the achievement of these challenges. AI-based tools play a significant role in improving enterprise digitisation by offering capabilities that enhance efficiency and decision making across various functions of an organization¿s operations, processes, and systems. This article delves into planning processes by proposing the use of an interoperable data model to integrate AI-based solutions developed to support the optimisation of production plans. The proposed data model facilitates interoperability between enterprise legacy systems and AI-based manufacturing solutions to support seamless communication between them, thus, assist replenishment and manufacturing decisions., The research received funding from the Horizon Europe Framework Programme (HORIZON) with Grant Agreement No. 101057294 AI-Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability, and Resilience (AIDEAS) . The Regional Department of Innovation, Universities, Science, and Digital Society of the Generalitat Valenciana Programa Investigo (ref. INVEST/2022/330), which the European Union supported - NextGenerationEU with Plan de Recuperación, Transformación y Resiliencia. The Generalitat Valenciana with program Subvenciones para la realización de estancias de personal investigador doctor en empresas de la Comunitat Valenciana (ref. CIAEST/2022/39).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Job shop smart manufacturing scheduling by deep reinforcement learning

  • Serrano-Ruiz, Julio Cesar|||0000-0002-6671-7077
  • Mula, Josefa|||0000-0002-8447-3387
  • Poler, R.|||0000-0003-4475-6371
[EN] Smart manufacturing scheduling (SMS) requires a high degree of flexibility to successfully cope with changes in operational decision level planning processes in today's production environments, which are usually subject to high uncertainty. In such a unique and complex scenario as the real job shop, the modelling of SMS as a Markov decision process (MDP), and its approach by deep reinforcement learning (DRL), is a research field of growing interest given its characteristics. It allows us to consider achieving high flexibility levels by promoting process automation, autonomy in decision making, and the ability to act in real time when faced with disturbances and disruptions in a highly dynamic environment. This paper addresses the problem of scheduling a quasi-realistic job shop environment characterised by machines receiving jobs from buffers that accumulate numerous jobs using a wide variety of parts and multimachine routes with a diverse number of operation phases by developing a digital twin of the job shop based on a MDP with the DRL methodology. This is approached by: modelling the job shop scheduling environment with OpenAI Gym; designing an observation space with 18 job features; designing an action space composed of three priority heuristic rules; shaping a single reward function with a multi-objective characteristic; using the implementation of the proximal policy optimisation (PPO) algorithm from the Stable Baselines 3 library. This modelling approach, dubbed as job shop smart manufacturing scheduling (JS-SMS), is characterised by deterministic formulation and implementation. The model is subjected to validation by comparing it to several of the best-known heuristic priority rules. The main findings of this methodology allow to replicate, to a great extent, the positive aspects of heuristic rules and to mitigate the negative ones, which achieves more balanced behaviour in most of the measures established as performance indicators and outperforms heuristic rules from this multi-objective perspective. Finally, further research is oriented to dynamic and stochastic approaches to address the job shop reality in an Industry 4.0 context., The research leading to these results received funding from the following projects: "Industrial Production and Logistics Optimization in Industry 4.0″ (i4OPT) (Ref. PROMETEO/2021/065) granted by the Valencian Regional Government; CADS4.0-II (PDC2022 133957-I00) funded by MCIN/AEI /10.13039/501100011033 and by European Union Next GenerationEU/PRTR; the EU H2020 research and innovation programme with grant number 958205 "Industrial Data Services for Quality Control in Smart Manufacturing (i4Q)" and from the European Union Horizon Europe program with grant agreement No. 101057294 AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability and Resilience (AIDEAS).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Artificial Intelligence Decision Systems to Support Industrial Equipment Manufacturing

  • Andres, B.|||0000-0002-7920-7711
  • Mateo-Casalí, Miguel Ángel|||0000-0001-5086-9378
  • Fiesco-Muñoz, Juan Pablo|||0009-0008-3369-4607
  • Poler, R.|||0000-0003-4475-6371
[EN] This article discusses how integrating artificial intelligence (AI) into Industry 4.0 can promote sustainability and resilience in production systems. It addresses the lifecycle manufacturing concept, which aims to minimise waste and reduce the environmental impact of manufacturing operations. This paper focuses on the specific machine tool production sector and how AI technology can optimise production processes by reducing downtimes and improving overall manufactur- ing efficiency. Accordingly, the article aims to identify the needs that industrial equipment manufacturers have during the replenishment, production and delivery processes, and how AI could fulfil these needs. By leveraging AI technologies, manufacturers can significantly improve efficiency, profitability and customer sat- isfaction, which results in improved performance and business growth. The paper also introduces European HORIZON project AIDEAS, which aim to develop AI technologies to support the manufacturing phase of the industrial equipment life cycle., The research that led to these findings received funding from two sources. The first source was from the Horizon Europe Framework Programme (HORIZON) with Grant Agreement No. 101057294 AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability, and Resilience (AIDEAS) . The second source of funding was from the Regional Department of Innovation, Universities, Science, and Digital Society of the Generalitat Valenciana Programa Investigo (ref. INVEST/2022/330), which the European Union supported - NextGenerationEU under the Plan de Recuperación, Transformación y Resiliencia.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A literature review of existing state-of-the-art approaches for the dynamic scheduling and rescheduling problem

  • Fiesco-Muñoz, Juan Pablo|||0009-0008-3369-4607
  • Esteso, Ana|||0000-0003-0379-8786
  • Poler, R.|||0000-0003-4475-6371
[EN] This paper reviews existing state-of-the-art articles that address the dynamic scheduling (DS) and rescheduling (RS) problem. Unlike traditional static scheduling, which assumes fixed and predictable conditions, DS must continuously adapt to operational disruptions. In actual industrial environments and smart manufacturing (SM) factories, real-time adjustments are necessary to optimize production and resource usage. This review analyzes 10 state-of-the-art, selected for their explicit focus on DS/RS, detailed methodology, and relevance to SM and sustainability. The results highlight the existence of different terminologies for the DS problem and the absence of a standardized framework to classify all its characteristics. It was also found that the state of the art does not provide detailed and clear analyses of the integration of SM technologies into real-world manufacturing challenges. The approaches to sustainability aspects in the reviews analyzed focus on different aspects, such as energy efficiency, resource use and alignment with the SDGs, highlighting the need for a more holistic approach. The paper proposes future research directions, including updated reviews that integrate SM technologies, sustainability, and a standardized framework, encompassing real-time data, robust and agile tools, artificial intelligence and internet of things., This research has been partially funded by Horizon Europe Ref. 101057294 AI-Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability, and Resilience (AIDEAS) ; and the Conselleria de Educación, Investigación, Cultura y Deporte - Generalitat Valenciana for hiring predoctoral research staff with Grant (CIACIF/2023/245).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Artificial Intelligence and Optimization Models for Agile and Resilient Production Planning and Control

  • Fiesco-Muñoz, Juan Pablo|||0009-0008-3369-4607
  • Esteso, Ana|||0000-0003-0379-8786
  • Poler, R.|||0000-0003-4475-6371
[EN] The increasing uncertainty in the manufacturing industry, driven by disruptive events and market fluctuations, highlights the need for more agile and resilient Production Planning and Control (PPC) strategies. This research focuses on addressing the Capacitated Lot Sizing and Scheduling (CLSS) for medium-term planning and Dynamic Scheduling (DS) for short-term decision-making by integrating Mathematical Programming, Artificial Intelligence (AI), and Smart Manufacturing (SM) technologies. A systematic review of CLSS and DS models identifies gaps in modeling uncertainty and adapting to real-time disruptions. A conceptual framework is proposed to standardize CLSS characteristics, while a matheuristic approach combines metaheuristics and mathematical programming to optimize sustainability-driven lot sizing decisions. Additionally, an AI-based tool dynamically reschedules production in response to real-time factory data. The research further develops a scalable architecture for industrial implementation, leveraging IoT and AI for enhanced decision-making. Validation is conducted through real and synthetic case studies, assessing solution quality and computational efficiency. This work aims to bridge the gap between traditional optimization techniques and smart, data-driven SM environments., This research has been partially funded by Horizon Europe Ref. 101057294 AI-Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability, and Resilience (AIDEAS) ; and the Conselleria de Educación, Investigación, Cultura y Deporte - Generalitat Valenciana for hiring predoctoral research staff with Grant (CIACIF/2023/245).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Manufacturing and AI - Industrial Machine Data Generation and Artificial Optimisation

  • Dörner, Marius
  • Schulz, Alexander
  • Martínez, Félix
  • Murn, Damjan
  • Radolovic, Dragan
  • Mateo-Casalí, Miguel Ángel|||0000-0001-5086-9378
  • Poler, R.|||0000-0003-4475-6371
[EN] The AIDEAS project targets the development of AI technologies strategically designed to improve European engineering companies' sustainability, agility, and resilience throughout the lifecycle of industrial assets, i.e., in the design, manufacturing, and repair/reuse/recycling phases. In the context of the AIDEAS project, this workshop paper focuses on the early stages of the product development process to accelerate the development process with the help of AI-supported tools. The results of some of these AI solutions will also help at a later stage to decide which machine parameters need to be considered and optimised during product development to optimise the later life cycle according to the current requirements of the repair, reuse, and recycle phases., This paper was funded by European Union s Horizon Europe research and innovation programme under grant agreement No. 101057294, project AIDEAS (AI Driven industrial Equipment product life cycle boosting Agility, Sustainability, and resilience).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Enhancing Machinery Design by Using Artificial Intelligence

  • Fiesco-Muñoz, Juan Pablo|||0009-0008-3369-4607
  • Mateo-Casalí, Miguel Ángel|||0000-0001-5086-9378
  • Andres, B.|||0000-0002-7920-7711
  • Poler, R.|||0000-0003-4475-6371
[EN] This paper examines the significance of Industry 4.0 and artificial intelligence (AI) in the manufacturing sector, particularly by emphasising the role of design phase in the machinery life cycle. The design phase of a machine is a complex task that requires an advanced engineering and physics knowledge level. Nevertheless in the technology era, computer-aided design tools facilitate the design task. The area of data execution and simulation of machine behaviour in different scenarios is being researched and exploited by technologies, such as the Internet of Things (IoT) or AI. With this paper, three AI-based tools are proposed and conceptualised to support AI-assisted optimisation to generate design proposals to manufacture industrial equipment, structural components, mechanisms and control components., The research that led to these findings received funding from two sources. The first source of fundingwas from the HorizonEurope Framework Programme(HORIZON) with Grant Agreement No. 101057294 "AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability, and Resilience (AIDEAS)". The second source of funding was from the Regional Department of Innovation, Universities, Science, and Digital Society of the Generalitat Valenciana "Programa Investigo" (ref. INVEST/2022/330), which the European Union supported -NextGenerationEU under the Plan de Recuperacion, Transformacion y Resiliencia.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Conceptual Framework for the Optimization of Capacitated Lot-Sizing and Scheduling Problem

  • Fiesco-Muñoz, Juan Pablo|||0009-0008-3369-4607
  • Esteso, Ana|||0000-0003-0379-8786
  • Alemany Díaz, María Del Mar|||0000-0002-0992-8441
  • Poler, R.|||0000-0003-4475-6371
[EN] The complex nature of the capacitated lot-sizing problem, particularly within the scheduling, requires a holistic approach that considers multiple factors and their intricate interactions. In this context, a novel conceptual framework (CF) to support the combined Capacitated Lot-Sizing and Scheduling Problem (CLSSP) through mathematical modelling is proposed. The CF is developed through a rigorous methodology that combines data collection, data analysis, literature review and conceptual framework definition. It is composed by seven dimensions, with different categories, in turn made up of elements related to different aspects of the problem and its modelling. The CF serves a dual purpose: as a comprehensive tool for the structured analysis of existing models facilitating the gaps identification and as a guide for proposing novel mathematical programming models to address the combined complexities of the CLSSP including those not yet covered., This research has been partially funded by Horizon Europe Ref. 101057294 AI-Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability, and Resilience (AIDEAS) and Ref. 101070076 Optimizing Production And Logistic Resources In The Time-Critical Bio Production Industries In Europe (CLARUS) ; and the Regional Department of Innovation, Universities, Science, and Digital Society of the Generalitat Valenciana Programa Investigo Ref. INVEST/2022/330, which the European Union supported - NextGenerationEU with Plan de Recuperación, Transformación y Resiliencia
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Using Transformers and Reinforcement Learning for the Team Orienteering Problem Under Dynamic Conditions

  • Guerrero, Antoni
  • Ammouriova, Majsa
  • Escoto-Gomar, Marc
  • Yangchongyi, Men
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] This paper presents a reinforcement learning (RL) approach for solving the team orienteering problem under both deterministic and dynamic travel time conditions. The proposed method builds on the transformer architecture and is trained to construct routes that adapt to real-time variations, such as traffic and environmental changes. A key contribution of this work is the model's ability to generalize across problem instances with varying numbers of nodes and vehicles, eliminating the need for retraining when problem size changes. To assess performance, a comprehensive set of experiments involving 27,000 synthetic instances is conducted, comparing the RL model with a variable neighborhood search metaheuristic. The results indicate that the RL model achieves competitive solution quality while requiring significantly less computational time. Moreover, the RL approach consistently produces feasible solutions across all dynamic instances, demonstrating strong robustness in meeting time constraints. These findings suggest that learning-based methods can offer efficient, scalable, and adaptable solutions for routing problems in dynamic and uncertain environments., The present work has been partially supported by the Spanish Government (IA4TES project 'Artificial Intelligence for Sustainable Energy Transition'), the Spanish Ministry of Science-AEI (PID2022- 138860NB-I00 and RED2022-134703-T), the European Commission (AIDEAS HORIZON-CL4- 2021-TWIN-TRANSITION-01-07-101057294). This publication is also part of the DIN2024-013395 grant, funded by MICIU/AEI/ 10.13039/501100011033.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Smart master production scheduling by deep reinforcement learning: an exploratory analysis

  • Serrano-Ruiz, Julio Cesar|||0000-0002-6671-7077
  • Mula, Josefa|||0000-0002-8447-3387
  • Poler, R.|||0000-0003-4475-6371
  • Díaz-Madroñero Boluda, Francisco Manuel|||0000-0003-1693-2876
[EN] By providing a consolidated view of demand, production capacity and inventory status, the master production schedule (MPS) enables collaborative networks to be optimised, planned and coordinated, which leads to more robust strategic decision making. In this context, flexibility, agility and automation are key elements to consider, and make machine-learning methods strong candidates for problem modelling. This paper researches some modelling alternatives to address the MPS problem subject to the eventuality of unsatisfied demand due to production capacity and inventory constraints by the deep reinforcement learning (DRL) method. The modelling of observation space, action space and reward function, and the choice of the DRL algorithm, among some of those currently at the forefront of the technique, are analysed and discussed. The sensitivity to the problem dimension, as a function that depends mostly on the number of considered product references, is also approached. As a major contribution, this study constitutes a valuable step prior to final modelling and subsequent validation by clearing the way for a wide range of possible implementations., The research leading to these results received funding from the EU Horizon Europe Programmes with grant agreement No. 101057294 AI-Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability and Resilience (AIDEAS), from the Valencian Regional Government with Ref. PROMETEO/2021/065 "Industrial Production and Logistics Optimisation in Industry 4.0 (i4OPT), and from the MCIN/AEI/10.13039/501100011033 with Ref. PDC2022 133957-I00 Validation of transferable results of optimisation of zero-defect enabling production technologies for Supply Chain 4.0 (CADS4.0-II).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Learnheuristic Algorithm Based on Thompson Sampling for the Heterogeneous and Dynamic Team Orienteering Problem

  • Uguina, Antonio R.
  • Gomez, Juan F
  • Panadero, Javier
  • Martínez-Gavara, Anna
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] The team orienteering problem (TOP) is a well-studied optimization challenge in the field of Operations Research, where multiple vehicles aim to maximize the total collected rewards within a given time limit by visiting a subset of nodes in a network. With the goal of including dynamic and uncertain conditions inherent in real-world transportation scenarios, we introduce a novel dynamic variant of the TOP that considers real-time changes in environmental conditions affecting reward acquisition at each node. Specifically, we model the dynamic nature of environmental factors-such as traffic congestion, weather conditions, and battery level of each vehicle-to reflect their impact on the probability of obtaining the reward when visiting each type of node in a heterogeneous network. To address this problem, a learnheuristic optimization framework is proposed. It combines a metaheuristic algorithm with Thompson sampling to make informed decisions in dynamic environments. Furthermore, we conduct empirical experiments to assess the impact of varying reward probabilities on resource allocation and route planning within the context of this dynamic TOP, where nodes might offer a different reward behavior depending upon the environmental conditions. Our numerical results indicate that the proposed learnheuristic algorithm outperforms static approaches, achieving up to 25% better performance in highly dynamic scenarios. Our findings highlight the effectiveness of our approach in adapting to dynamic conditions and optimizing decision-making processes in transportation systems., This work has been partially funded by the Spanish Ministry of Science and Innovation (PID2022-138860NB-I00, RED2022-134703-T) as well as by the SUN (HORIZON-CL4-2022-HUMAN01-14-101092612) and AIDEAS (HORIZON-CL4-2021-TWIN-TRANSITION-01-07-101057294) projects of the Horizon Europe program.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Optimization Challenges in Vehicle-to-Grid (V2G) Systems and Artificial Intelligence Solving Methods

  • Escoto-Gomar, Marc
  • Juan, Angel A.|||0000-0003-1392-1776
  • Guerrero, Antoni
  • Ghorbani, E.
[EN] Vehicle-to-grid (V2G) systems play a key role in the integration of electric vehicles (EVs) into smart grids by enabling bidirectional energy flows between EVs and the grid. Optimizing V2G operations poses significant challenges due to the dynamic nature of energy demand, grid constraints, and user preferences. This paper addresses the optimization challenges in V2G systems and explores the use of artificial intelligence (AI) methods to tackle these challenges. The paper provides a comprehensive analysis of existing work on optimization in V2G systems and identifies gaps where AI-driven algorithms, machine learning, metaheuristic extensions, and agile optimization concepts can be applied. Case studies and examples demonstrate the efficacy of AI-driven algorithms in optimizing V2G operations, leading to improved grid stability, cost optimization, and user satisfaction. Furthermore, agile optimization concepts are introduced to enhance flexibility and responsiveness in V2G optimization. The paper concludes with a discussion on the challenges and future directions for integrating AI-driven methods into V2G systems, highlighting the potential for these intelligent algorithms and methods., This work has been partially funded by the Spanish Government with the European Union Next Generation funds (TSI-100408-2021-0), the Spanish Ministry of Science and Innovation (PID2022-138860NB-I00, RED2022-134703-T), and the Horizon Europe program (HORIZON-CL4-2021-TWIN-TRANSITION-01-07 101057294 AIDEAS).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Hybrid Simulation and Reinforcement Learning Algorithm for Enhancing Efficiency in Warehouse Operations

  • Leon, Jonas F.
  • Li, Yuda
  • Martin, Xabier A.
  • Calvet, Laura
  • Panadero, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] The use of simulation and reinforcement learning can be viewed as a flexible approach to aid managerial decision-making, particularly in the face of growing complexity in manufacturing and logistic systems. Efficient supply chains heavily rely on steamlined warehouse operations, and therefore, having a well-informed storage location assignment policy is crucial for their improvement. The traditional methods found in the literature for tackling the storage location assignment problem have certain drawbacks, including the omission of stochastic process variability or the neglect of interaction between various warehouse workers. In this context, we explore the possibilities of combining simulation with reinforcement learning to develop effective mechanisms that allow for the quick acquisition of information about a complex environment, the processing of that information, and then the decision-making about the best storage location assignment. In order to test these concepts, we will make use of the FlexSim commercial simulator., This work has been supported by the European Commission (SUN HORIZON-CL4-2022-HUMAN-01-14-101092612 and AIDEAS HORIZON-CL4-2021-TWIN-TRANSITION-01-07-101057294),FlexSim, Spindox, the Industrial Doctorate Program of the Catalan Government (2020-DI-116), and the Investigo Program of the Generalitat Valenciana (INVEST/2022/342).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Optimising Machinery Utilisation by Applying Artificial Intelligence

  • Mateo-Casalí, Miguel Ángel|||0000-0001-5086-9378
  • Fiesco-Muñoz, Juan Pablo|||0009-0008-3369-4607
  • Andres, B.|||0000-0002-7920-7711
  • Poler, R.|||0000-0003-4475-6371
[EN] The article discusses the importance of smart production during the progress of Industry 4.0 and the challenges that Big Data analytics and artificial intelligence (AI) tools face. Using AI tools, such as predictive maintenance, production optimisation and quality control systems, can improve production efficiency, quality and safety. This article also highlights the goals of AI technologies, such as reducing production downtimes, optimising production, improving product quality and safety, and increasing automation to achieve the zero-defect philosophy. It concludes that applying AI solutions can help to reduce defects, waste and errors in production processes, which will result in increasing the efficiency and quality of production processes., The research that led to these findings received funding from two sources. The first source of funding was from the Horizon Europe Framework Programme (HORIZON) with Grant Agreement No. 101057294 AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability, and Resilience (AIDEAS) . The second source of funding was from the Regional Department of Innovation, Universities, Science, and Digital Society of the Generalitat Valenciana Programa Investigo (ref. INVEST/2022/330), which the European Union supported - NextGenerationEU under the Plan de Recuperación, Transformación y Resiliencia.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Model for the Multidepot Multiple Travelling Salesman Problem and Advanced Resolution Strategies

  • Fiesco-Muñoz, Juan Pablo|||0009-0008-3369-4607
  • Andres, B.|||0000-0002-7920-7711
  • Poler, R.|||0000-0003-4475-6371
[EN] This paper delves into the Multidepot Multiple Travelling Salesman Problem (MDMTSP), an extension of the TSP that presents additional complexities. A review of the state of the art is performed, from which a MDMTSP mixed integer linear programming model is extracted. For this model, a new objective function and new variables are added to cover the need to balance the number of cities to be visited by each salesman. Various strategies are also investigated to reduce the computation times associated with the NP-Hard MDMTSP. The proposed mathematical model is not only an abstract theory, but will also be integrated into the AI-Delivery Optimiser solution of the AIDEAS project. This integration represents a step towards the manufacturing industry of the future, where artificial intelligence and process optimisation will work together to drive competitiveness and business success., The research that led to these findings received funding from the Horizon Europe Ref.101057294 AI-Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability, and Resilience (AIDEAS) ; the Regional Department of Innovation, Universities, Science, and Digital Society of the Generalitat Valenciana Programa Investigo Ref. INVEST/2022/330, which the European Union supported - NextGenerationEU with Plan de Recuperación, Transformación y Resiliencia; the Regional Department of Innovation, Universities, Science, and Digital Society of the Generalitat Valenciana Ref. CIAEST/2022/39 Doctoral research staff to carry out research stays in companies in the Valencia Region ; and the Vice-Rectorate for Research of the Universitat Politècnica de València Ref. PAID-06-23 Intelligent optimisation algorithms and models for production planning and replenishment (ATENNEA) .
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Smart Tuning of Algorithm Parameters by Deep Reinforcement Learning

  • Serrano-Ruiz, Julio Cesar|||0000-0002-6671-7077
  • Mula, Josefa|||0000-0002-8447-3387
  • Poler, R.|||0000-0003-4475-6371
[EN] In the field of algorithm optimisation, finding the optimal configuration of parameters is essential for achieving peak performance. Traditional methods usually rely on manual tuning or exhaustive search techniques, which can be time-consuming and inefficient. This paper proposes a novel approach utilising deep reinforcement learning (DRL) for automatically tuning the parameters of those algorithms that require it. By formulating the parameter tuning problem of the Holt-Winters algorithm as a reinforcement learning task, this research provides an example of the use of this method, which enables algorithms to autonomously tune their parameters based on feedback from the environment shaped by the problem. Leveraging an advantage actor-critic algorithm (A2C), our framework learns optimal parameter settings through exploration and exploitation strategies. The main findings highlight the versatility and efficiency of this DRL-based method for parameter tuning in optimising algorithms, paving the way for more adaptive and self-improving systems in various domains., The research leading to these results received funding from the EU Horizon Europe Programme with grant agreement No. 101057294 AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability and Resilience (AIDEAS), from the Valencian Regional Government with Ref. PROMETEO/2021/065 "Industrial Production and Logistics Optimization in Industry 4.0 (i4OPT), and from the MCIN/AEI /https://doi.org/10.13039/501 100011033 with Ref. PDC2022 133957-I00 Validation of transferable results of optimisation of zero-defect enabling production technologies for Supply Chain 4.0 (CADS4.0-II).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Using Reinforcement Learning in a Dynamic Team Orienteering Problem with Electric Batteries

  • Ammouriova, Majsa
  • Guerrero, Antoni
  • Tsertsvadze, Verónika
  • Schumacher, Christin
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] This paper addresses the team orienteering problem (TOP) with vehicles equipped with electric batteries under dynamic travel conditions influenced by weather and traffic, which impact travel times between nodes and hence might have a critical effect on the battery capacity to cover the planned route. The study incorporates a novel approach for solving the dynamic TOP, comparing two solution methodologies: a merging heuristic and a reinforcement learning (RL) algorithm. The heuristic combines routes using calculated savings and a biased-randomized strategy, while the RL model leverages a transformer-based encoder-decoder architecture to sequentially construct solutions. We perform computational experiments on 50 problem instances, each subjected to 200 dynamic conditions, for a total of 10,000 problems solved. The results demonstrate that while the deterministic heuristic provides an upper bound for rewards, the RL model consistently yields robust solutions with lower variability under dynamic conditions. However, the dynamic heuristic, with a 20 s time limit for solving each instance, outperformed the RL model by 3.35% on average. The study highlights the trade-offs between solution quality, computational resources, and time when dealing with dynamic environments in the TOP., The present work has been partially funded by the Spanish Government (IA4TES project 'Artificial Intelligence for Sustainable Energy Transition'), the Spanish Ministry of Science-AEI (PID2022- 138860NB-I00 and RED2022-134703-T), as well as the European Commission (SUN HORIZON-CL4- 2022-HUMAN-01-14-101092612, AIDEAS HORIZON-CL4- 2021-TWIN-TRANSITION-01-07-101057294).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Adaptive Production Rescheduling System for Managing Unforeseen Disruptions

  • Figueroa, Andy J.
  • Poler, R.|||0000-0003-4475-6371
  • Andres, B.|||0000-0002-7920-7711
[EN] This work presents a mixed-integer linear programming (MILP) model to solve the production rescheduling problem in a job shop manufacturing system impacted by unexpected events, aiming to minimize production costs and disruptions to the initial schedule. The approach begins by generating an optimal production plan through batch assignments to machines. When unforeseen events, such as machine breakdowns or raw material shortages, occur, a dynamic rescheduling process is triggered, employing an iterative and reactive algorithm to adapt the plan to the real-time conditions on the shop floor. The results demonstrate that this rescheduling method efficiently adjusts to the new conditions while minimizing deviations from the original schedule, achieving solutions within acceptable computational times., The research leading to these results received funding from the European Union Horizon Europe programme under grant agreements No. 101057294 "AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability and Resilience" (AIDEAS) and No. 101058589 "AI Powered human-centred Robot Interactions for Smart Manufacturing" (AI-PRISM); from the Regional Department of Innovation, Universities, Science and Digital Society of the Generalitat Valenciana under Ref. PROMETEO/2021/065 "Industrial Production and Logistics Optimization in Industry 4.0" (i4OPT); and from the Vice-Rectorate for Research of the Universitat Politecnica de Valencia under Ref. PAID-06-23 "Intelligent optimization algorithms and models for production planning and replenishment" (ATENNEA).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Artificial Intelligence to Support Collaboration in the Industrial Equipment Life Cycle

  • Andres, B.|||0000-0002-7920-7711
  • Mateo-Casalí, Miguel Ángel|||0000-0001-5086-9378
  • Fiesco-Muñoz, Juan Pablo|||0009-0008-3369-4607
  • Poler, R.|||0000-0003-4475-6371
[EN] This paper explores the potential of artificial intelligence (AI) to support collaboration in the industrial equipment life cycle. The industrial equipment industry involves complex multidisciplinary collaboration with suppliers and customers across many machinery life cycle stages, including design, manufacturing, use and end-of-life. This paper conceptualises a set of AI-enabled digital solutions within the AIDEAS European project scope. With a case study of an industrial equipment company, we illustrate how AI solutions can be used to support collaboration in the supply chain across machinery life cycles., The research that led to these findings received funding from the Horizon Europe Framework Programme (HORIZON) with Grant Agreement No. 101057294 "AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability, and Resilience (AIDEAS)", the Regional Department of Innovation, Universities, Science, and Digital Society of the Generalitat Valenciana "Programa Investigo" (ref. INVEST/2022/330), which the European Union supported - NextGenerationEU under the Plan de Recuperación, Transformación y Resiliencia.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Tesis doctoral (DoctoralThesis)

Job shop smart manufacturing scheduling by deep reinforcement learning for Industry 4.0

  • Serrano-Ruiz, Julio Cesar|||0000-0002-6671-7077
[ES] El paradigma de la Industria 4.0 (I4.0) gravita en gran medida sobre el potencial de las tecnologías de la información y la comunicación (TIC) para mejorar la competitividad y sostenibilidad de las industrias. El concepto de Smart Manufacturing Scheduling (SMS) surge y se inspira de ese potencial. SMS, como estrategia de transformación digital, aspira a optimizar los procesos industriales mediante la aplicación de tecnologías como el gemelo digital o digital twin (DT), el modelo de gestión zero-defect manufacturing (ZDM), y el aprendizaje por refuerzo profundo o deep reinforcement learning (DRL), con el propósito final de orientar los procesos de programación de operaciones hacia una automatización adaptativa en tiempo real y una reducción de las perturbaciones en los sistemas de producción. SMS se basa en cuatro principios de diseño del espectro I4.0: automatización, autonomía, capacidad de acción en tiempo real e interoperabilidad. A partir de estos principios clave, SMS combina las capacidades de la tecnología DT para simular, analizar y predecir; la del modelo ZDM para prevenir perturbaciones en los sistemas de planificación y control de la producción; y la del enfoque de modelado DRL para mejorar la toma de decisiones en tiempo real. Este enfoque conjunto orienta los procesos de programación de operaciones hacia una mayor eficiencia y, con ello, hacia un mayor rendimiento y resiliencia del sistema productivo. Esta investigación emprende, en primer lugar, una revisión exhaustiva del estado del arte sobre SMS. Con la revisión efectuada como referencia, la investigación plantea un modelo conceptual de SMS como estrategia de transformación digital en el contexto del proceso de programación del taller de trabajos o job shop. Finalmente, la investigación propone un modelo basado en DRL para abordar la implementación de los elementos clave del modelo conceptual: el DT del taller de trabajos y el agente programador. Los algoritmos que integran este modelo se han programado en Python y han sido validados contra varias de las más conocidas reglas heurísticas de prioridad. El desarrollo del modelo y los algoritmos supone una contribución académica y gerencial en el área de la planificación y control de la producción., [CA] El paradigma de la Indústria 4.0 (I4.0) gravita en gran mesura sobre el potencial de les tecnologies de la informació i la comunicació (TIC) per millorar la competitivitat i la sostenibilitat de les indústries. El concepte d'smart manufacturing scheduling (SMS) sorgeix i inspira a partir d'aquest potencial. SMS, com a estratègia de transformació digital, aspira a optimitzar els processos industrials mitjançant l'aplicació de tecnologies com el bessó digital o digital twin (DT), el model de gestió zero-defect manufacturing (ZDM), i l'aprenentatge per reforçament profund o deep reinforcement learning (DRL), amb el propòsit final dorientar els processos de programació doperacions cap a una automatització adaptativa en temps real i una reducció de les pertorbacions en els sistemes de producció. SMS es basa en quatre principis de disseny de l'espectre I4.0: automatització, autonomia, capacitat d¿acció en temps real i interoperabilitat. A partir d'aquests principis clau, SMS combina les capacitats de la tecnologia DT per simular, analitzar i predir; la del model ZDM per prevenir pertorbacions en els sistemes de planificació i control de la producció; i la de de l'enfocament de modelatge DRL per millorar la presa de decisions en temps real. Aquest enfocament conjunt orienta els processos de programació d'operacions cap a una eficiència més gran i, amb això, cap a un major rendiment i resiliència del sistema productiu. Aquesta investigació emprèn, en primer lloc, una exhaustiva revisió de l'estat de l'art sobre SMS. Amb la revisió efectuada com a referència, la investigació planteja un model conceptual de SMS com a estratègia de transformació digital en el context del procés de programació del taller de treballs o job shop. Finalment, la investigació proposa un model basat en DRL per abordar la implementació dels elements claus del model conceptual: el DT del taller de treballs i l'agent programador. Els algorismes que integren aquest model s'han programat a Python i han estat validats contra diverses de les més conegudes regles heurístiques de prioritat. El desenvolupament del model i els algorismes suposa una contribució a nivell acadèmic i gerencial a l'àrea de la planificació i control de la producció., [EN] The Industry 4.0 (I4.0) paradigm relies, to a large extent, on the potential of information and communication technologies (ICT) to improve the competitiveness and sustainability of industries. The smart manufacturing scheduling (SMS) concept arises and draws inspiration from this potential. As a digital transformation strategy, SMS aims to optimise industrial processes through the application of technologies, such as the digital twin (DT), the zero-defect manufacturing (ZDM) management model and deep reinforcement learning (DRL), for the ultimate purpose of guiding operations scheduling processes towards real-time adaptive automation and to reduce disturbances in production systems. SMS is based on four design principles of the I4.0 spectrum: automation, autonomy, real-time capability and interoperability. Based on these key principles, SMS combines the capabilities of the DT technology to simulate, analyse and predict; with the ZDM model, to prevent disturbances in production planning and control systems; by the DRL modelling approach, to improve real-time decision making. This joint approach orients operations scheduling processes towards greater efficiency and, with it, a better performing and more resilient production system. This research firstly undertakes a comprehensive review of the state of the art on SMS. By taking the review as a reference, the research proposes a conceptual model of SMS as a digital transformation strategy in the job shop scheduling process context. Finally, it proposes a DRL-based model to address the implementation of the key elements of the conceptual model: the job shop DT and the scheduling agent. The algorithms that integrate this model have been programmed in Python and validated against several of the most well-known heuristic priority rules. The development of the model and algorithms is an academic and managerial contribution in the production planning and control area., This thesis was developed with the support of the Research Centre on Production Management and Engineering (CIGIP) of the Universitat Politècnica de València and received funding from: the European Union H2020 programme under grant agreement No. 825631, “Zero Defect Manufacturing Platform (ZDMP)”; the European Union H2020 programme under grant agreement No. 872548, "Fostering DIHs for Embedding Interoperability in Cyber-Physical Systems of European SMEs (DIH4CPS)"; the European Union H2020 programme under grant agreement No. 958205, “Industrial Data Services for Quality Control in Smart Manufacturing (i4Q)”; the European Union Horizon Europe programme under grant agreement No. 101057294, “AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability and Resilience” (AIDEAS); the Spanish Ministry of Science, Innovation and Universities under grant agreement RTI2018-101344-B-I00, "Optimisation of zero-defects production technologies enabling supply chains 4.0 (CADS4.0)"; the Valencian Regional Government, in turn funded from grant RTI2018- 101344-B-I00 by MCIN/AEI/10.13039/501100011033 and by “ERDF A way of making Europe”, "Industrial Production and Logistics optimization in Industry 4.0" (i4OPT) (Ref. PROMETEO/2021/065); and the grant PDC2022-133957- I00, “Validation of transferable results of optimisation of zero-defect enabling production technologies for supply chain 4.0” (CADS4.0-II) funded by MCIN/AEI/10.13039/501100011033 and by European Union Next GenerationEU/PRTR.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Using Heuristics to Enhance Real-Life Warehouse Replenishment Processes in the Fashion Industry

  • Castaneda, Juliana
  • Herrera, Erika M.
  • Londoño, Julio C.
  • Panadero, Javier
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] The fashion industry is currently facing a phenomenon known as fast fashion. It is due to the high variation in product types and consumer tastes. The uncertainty generated by this phenomenon is forcing logistics warehouses in the sector to rely on innovative tools based on new technologies. These must guarantee that order preparation is performed efficiently through the autonomous and optimal management of the location of the products in the warehouses. Instead of building new areas to accommodate incoming products, companies are looking to optimize the reallocation of the existing lots. The aim is to generate savings in terms of costs and movements within the warehouse. Based on the assumption that picking at height is more costly for the warehouse when picking an order, this paper proposes a storage location assignment system based on data analysis and fast heuristics to assist in making decisions about the relocation of existing stock-keeping units, either on the floor or on shelves. This model is tested in a warehouse of a fashion company to demonstrate how the use of optimization tools can help generate operational and economic savings., This work has been partially supported by the EU Comission (HORIZON-CL4-2021-TWIN- 429 TRANSITION01-07, 101057294 AIDEAS), and the Generalitat Valenciana (PROMETEO/2021/065).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Simulation of Heuristics for Automated Guided Vehicle Task Sequencing with Resource Sharing and Dynamic Queues

  • Leon, Jonas F.
  • Peyman, Mohammad
  • Martín, Xabier A.
  • Juan, Angel A.|||0000-0003-1392-1776
[EN] Automated guided vehicles (AGVs) stand out as a paradigmatic application of Industry 4.0, requiring the seamless integration of new concepts and technologies to enhance productivity while reducing labor costs, energy consumption, and emissions. In this context, specific industrial use cases can present a significant technological and scientific challenge. This study was inspired by a real industrial application for which the existing AGV literature did not contain an already well-studied solution. The problem is related to the sequencing of assigned tasks, where the queue formation dynamics and the resource sharing define the scheduling. The combinatorial nature of the problem requires the use of advanced mathematical tools such as heuristics, simulations, or a combination of both. A heuristic procedure was developed that generates candidate task sequences, which are, in turn, evaluated in a discrete-event simulation model developed in Simul8. This combined approach allows high-quality solutions to be generated and realistically evaluated, even graphically, by stakeholders and decision makers. A number of computational experiments were developed to validate the proposed method, which opens up some future lines of research, especially when considering stochastic settings., This work was supported by the European Commission (AIDEAS HORIZON-CL4-2021- TWIN-TRANSITION-01-07-101057294 and SUN HORIZON-CL4-2022-HUMAN-01-14-101092612), Simul8, Spindox, AGAUR (2020-DI-116), and the Spanish Ministry of Science and Innovation (PRE2020-091842).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Framework for characterising mathematical programming models for capacitated lot-sizing and scheduling problem

  • Fiesco-Muñoz, Juan Pablo|||0009-0008-3369-4607
  • Esteso, Ana|||0000-0003-0379-8786
  • Alemany Díaz, María Del Mar|||0000-0002-0992-8441
  • Poler, R.|||0000-0003-4475-6371
[EN] The Capacitated Lot-Sizing and Scheduling Problem (CLSSP) integrates production planning and scheduling decisions under capacity constraints. It combines multiple complex subproblems, including lot-sizing, production assignment, sequencing, and timing (often subject to dependent setup times), as well as inventory management across periods. Although several mathematical programming models have been proposed to address this problem, the literature lacks a structured framework to systematically characterise and compare these formulations. To fill this gap, this paper presents a novel framework specifically designed for characterising mathematical programming models for the CLSSP. The framework consists of seven dimensions, each developed through a structured methodology combining a PRISMA-based systematic literature review of related works, an in-depth analysis of selected papers. It was validated both by applying it to existing optimisation models in the literature and through a real-world industrial case study. The validation results demonstrate the framework s applicability in literature reviews, as it captured all modelled characteristics from the analysed selected studies, enabling the identification of emerging trends and research gaps in CLSSP modelling. As for its application in industry, the target users of the framework are described and its use is illustrated through a industrial case study based on a real problem. Therefore, the proposed framework offers three main functionalities: i) providing a structured basis to characterise the CLSSP, ii) enabling systematic analysis and comparison of existing mathematical programming models for the CLSSP, and iii) supporting the design of new optimisation models to effectively address the CLSSP in real-world industrial settings., Horizon Europe
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Using Reinforcement Learning to Solve a Dynamic Orienteering Problem with Random Rewards Affected by the Battery Status

  • Juan, Angel A.|||0000-0003-1392-1776
  • Marugan, Carolina A.
  • Ahsini, Yusef
  • Fornes, Rafael
  • Panadero, Javier
  • Martín, Xabier A.
[EN] This paper discusses an orienteering optimization problem where a vehicle using electric batteries must travel from an origin depot to a destination depot while maximizing the total reward collected along its route. The vehicle must cross several consecutive regions, with each region containing different types of charging nodes. A charging node has to be selected in each region, and the reward for visiting each node¿in terms of a `satisfactory¿ charging process¿is a binary random variable that depends upon dynamic factors such as the type of charging node, weather conditions, congestion, battery status, etc. To learn how to efficiently operate in this dynamic environment, a hybrid methodology combining simulation with reinforcement learning is proposed. The reinforcement learning component is able to make informed decisions at each stage, while the simulation component is employed to validate the learning process. The computational experiments show how the proposed methodology is capable of design routing plans that are significantly better than non-informed decisions, thus allowing for an efficient management of the vehicle¿s battery under such dynamic conditions., This work was partially funded by the European Commission projects SUN (HORIZONCL4-2022-HUMAN-01-14-101092612), and AIDEAS (HORIZON-CL4-2021-TWIN-TRANSITION-01-07-101057294).
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

A comprehensive literature review of the applications of AI techniques through the lifecycle of industrial equipment

  • Elahi, Mahboob
  • Afolaranmi, Samuel Olaiya
  • Martinez Lastra, Jose Luis
  • Pérez García, José Antonio
Driven by the ongoing migration towards Industry 4.0, the increasing adoption of artificial intelligence (AI) has empowered smart manufacturing and digital transformation. AI enhances the migration towards industry 4.0 through AI-based decision-making by analyzing real-time data to optimize different processes such as production planning, predictive maintenance, quality control etc., thus guaranteeing reduced costs, high precision, efficiency and accuracy. This paper explores AI-driven smart manufacturing, revolutionizing traditional approaches and unlocking new possibilities throughout the major phases of the industrial equipment lifecycle. Through a comprehensive review, we delve into a wide range of AI techniques employed to tackle challenges such as optimizing process control, machining parameters, facilitating decision-making, and elevating maintenance strategies within the major phases of an industrial equipment lifecycle. These phases encompass design, manufacturing, maintenance, and recycling/retrofitting. As reported in the 2022 McKinsey Global Survey ( https://www.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai-in-2022-and-a-half-decade-in-review ), the adoption of AI has witnessed more than a two-fold increase since 2017. This has contributed to an increase in AI research within the last six years. Therefore, from a meticulous search of relevant electronic databases, we carefully selected and synthesized 42 articles spanning from 01 January 2017 to 20 May 2023 to highlight and review the most recent research, adhering to specific inclusion and exclusion criteria, and shedding light on the latest trends and popular AI techniques adopted by researchers. This includes AI techniques such as Convolutional Neural Networks (CNN), Generative Adversarial Networks (GAN), Bayesian Networks, Support Vector Machines (SVM) etc., which are extensively discussed in this paper. Additionally, we provide insights into the advantages (e.g., enhanced decision making) and challenges (e.g., AI integration with legacy systems due to technical complexities and compatibilities) of integrating AI across the major stages of industrial equipment operations. Strategically implementing AI techniques in each phase enables industries to achieve enhanced productivity, improved product quality, cost-effectiveness, and sustainability. This exploration of the potential of AI in smart manufacturing fosters agile and resilient processes, keeping industries at the forefront of technological advancements and harnessing the full potential of AI-driven solutions to improve manufacturing processes and products.
RUC. Repositorio da Universidade da Coruña
Publication Contribución de congreso (ConferenceOutput)

Modelado integrado de fuerzas y motores de inducción aplicado al proceso de fresado, Integrated Modeling of Forces and Induction Motors in the Milling Process

  • Trojaola, Ignacio
  • Elorza, Iker
  • Nieto Ramos, Estela
[Resumen] En este artículo se propone un modelo para el proceso de fresado que integra el modelado de los actuadores de la fresadora y las fuerzas generadas durante dicho proceso. El modelado de las fuerzas se realiza directamente a partir de los componentes de fuerza tangencial, axial y radial. Además, se desarrolla el modelado matemático de los motores de inducción, encargados de realizar el control de posición y velocidad de la fresadora. El modelado se lleva a cabo utilizando la librería Simscape de MATLAB, lo que proporciona una herramienta intuitiva y reproducible para simular el proceso de fresado bajo diferentes condiciones de ensayo. Los resultados de las simulaciones muestran cómo las dinámicas de los motores de inducción se ven afectadas por las fuerzas y los pares generados durante el proceso, lo cual permite adecuar los lazos de control de los motores a ellas., [Abstract] This article proposes a model for the milling process that integrates the modeling of the milling machine’s actuators and the forces generated during the process. The modeling of the forces is directly calculated based on the components of tangential, axial, and radial force. Furthermore, a model of the induction motors is developed, encompassing both steady-state and dynamic states. The modeling is conducted using the Simscape library in MATLAB, providing an intuitive and reproducible tool for simulating complex physical systems under different test conditions. The simulation results demonstrate how the dynamics of the induction motors are affected by the forces and torques generated during the milling process., Gobierno Vasco; KK-2022/00106
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Dynamic reactive assignment of tasks in real-time automated guided vehicle environments with potential interruptions

  • Martin Solano, Xabier Andoni
  • Hatami, Sara|||0000-0002-8000-4989
  • Calvet Liñán, Laura
  • Peyman, Mohammad
  • Juan Pérez, Ángel Alejandro
An efficient management of production plants has to consider several external and internal factors, such as potential interruptions of the ongoing processes. Automated guided vehicles (AGVs) are becoming a widespread technology that offers many advantages. These AGVs can perform complex tasks in an autonomous way. However, an inefficient schedule of the tasks assigned to an AGV can suffer from unwanted interruptions and idle times, which in turn will affect the total time required by the AGV to complete its assigned tasks. In order to avoid these issues, this paper proposes a heuristic-based approach that: (i) makes use of a delay matrix to estimate circuit delays for different daily times; (ii) employs these estimates to define an initial itinerary of tasks for an AGV; and (iii) dynamically adjusts the initial agenda as new information on actual delays is obtained by the system. The objective is to minimize the total time required for the AGV to complete all the assigned tasks, taking into account situations that generate unexpected disruptions along the circuits that the AGV follows. In order to test and validate the proposed approach, a series of computational experiments utilizing real-life data are carried out. These experiments allow us to measure the improvement gap with respect to the former policy used by the system managers., This work has been partially supported by the Spanish Ministry of Industry, Commerce and Tourism (AEI-010500-2021b-54), the EU Comission (HORIZON-CL4-2021-TWIN-TRANSITION-01-07, 101057294 AIDEAS), and the Generalitat Valenciana (PROMETEO/2021/065)., Peer Reviewed
O2, repositorio institucional de la UOC
Publication Artículo científico (JournalArticle)

Simulation of heuristics for automated guided vehicle task sequencing with resource sharing and dynamic queues

  • Fuentes Leon, Jonas
  • Peyman, Mohammad
  • Martin Solano, Xabier Andoni
  • Juan, Angel A.
Automated guided vehicles (AGVs) stand out as a paradigmatic application of Industry 4.0, requiring the seamless integration of new concepts and technologies to enhance productivity while reducing labor costs, energy consumption, and emissions. In this context, specific industrial use cases can present a significant technological and scientific challenge. This study was inspired by a real industrial application for which the existing AGV literature did not contain an already well-studied solution. The problem is related to the sequencing of assigned tasks, where the queue formation dynamics and the resource sharing define the scheduling. The combinatorial nature of the problem requires the use of advanced mathematical tools such as heuristics, simulations, or a combination of both. A heuristic procedure was developed that generates candidate task sequences, which are, in turn, evaluated in a discrete-event simulation model developed in Simul8. This combined approach allows high-quality solutions to be generated and realistically evaluated, even graphically, by stakeholders and decision makers. A number of computational experiments were developed to validate the proposed method, which opens up some future lines of research, especially when considering stochastic settings.
O2, repositorio institucional de la UOC
Publication Artículo científico (JournalArticle)

Optimization challenges in vehicle-to-grid (V2G) systems and artificial intelligence solving methods

  • Escoto Gomar, Marc
  • Guerrero Portolés, Antoni
  • Ghorbani, Elnaz
  • Juan, Angel A.
Vehicle-to-grid (V2G) systems play a key role in the integration of electric vehicles (EVs) into smart grids by enabling bidirectional energy flows between EVs and the grid. Optimizing V2G operations poses significant challenges due to the dynamic nature of energy demand, grid constraints, and user preferences. This paper addresses the optimization challenges in V2G systems and explores the use of artificial intelligence (AI) methods to tackle these challenges. The paper provides a comprehensive analysis of existing work on optimization in V2G systems and identifies gaps where AI-driven algorithms, machine learning, metaheuristic extensions, and agile optimization concepts can be applied. Case studies and examples demonstrate the efficacy of AI-driven algorithms in optimizing V2G operations, leading to improved grid stability, cost optimization, and user satisfaction. Furthermore, agile optimization concepts are introduced to enhance flexibility and responsiveness in V2G optimization. The paper concludes with a discussion on the challenges and future directions for integrating AI-driven methods into V2G systems, highlighting the potential for these intelligent algorithms and methods.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Dynamic reactive assignment of tasks in real-time automated guided vehicle environments with potential interruptions

  • Martin Solano, Xabier Andoni
  • Hatami, Sara
  • Calvet Liñán, Laura
  • Peyman, Mohammad
  • Juan Pérez, Ángel Alejandro
An efficient management of production plants has to consider several external and internal factors, such as potential interruptions of the ongoing processes. Automated guided vehicles (AGVs) are becoming a widespread technology that offers many advantages. These AGVs can perform complex tasks in an autonomous way. However, an inefficient schedule of the tasks assigned to an AGV can suffer from unwanted interruptions and idle times, which in turn will affect the total time required by the AGV to complete its assigned tasks. In order to avoid these issues, this paper proposes a heuristic-based approach that: (i) makes use of a delay matrix to estimate circuit delays for different daily times; (ii) employs these estimates to define an initial itinerary of tasks for an AGV; and (iii) dynamically adjusts the initial agenda as new information on actual delays is obtained by the system. The objective is to minimize the total time required for the AGV to complete all the assigned tasks, taking into account situations that generate unexpected disruptions along the circuits that the AGV follows. In order to test and validate the proposed approach, a series of computational experiments utilizing real-life data are carried out. These experiments allow us to measure the improvement gap with respect to the former policy used by the system managers., This work has been partially supported by the Spanish Ministry of Industry, Commerce and Tourism (AEI-010500-2021b-54), the EU Comission (HORIZON-CL4-2021-TWIN-TRANSITION-01-07, 101057294 AIDEAS), and the Generalitat Valenciana (PROMETEO/2021/065)., Peer Reviewed, Postprint (published version)
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Dynamic Reactive Assignment of Tasks in Real-Time Automated Guided Vehicle Environments with Potential Interruptions

  • Martin, Xabier A.|||0000-0003-4182-0120
  • Hatami, Sara|||0000-0002-8000-4989
  • Calvet, Laura|||0000-0001-8425-1381
  • Peyman, Mohammad|||0000-0003-4734-2414
  • Juan, Ángel A.|||0000-0003-1392-1776
An efficient management of production plants has to consider several external and internal factors, such as potential interruptions of the ongoing processes. Automated guided vehicles (AGVs) are becoming a widespread technology that offers many advantages. These AGVs can perform complex tasks in an autonomous way. However, an inefficient schedule of the tasks assigned to an AGV can suffer from unwanted interruptions and idle times, which in turn will affect the total time required by the AGV to complete its assigned tasks. In order to avoid these issues, this paper proposes a heuristic-based approach that: (i) makes use of a delay matrix to estimate circuit delays for different daily times; (ii) employs these estimates to define an initial itinerary of tasks for an AGV; and (iii) dynamically adjusts the initial agenda as new information on actual delays is obtained by the system. The objective is to minimize the total time required for the AGV to complete all the assigned tasks, taking into account situations that generate unexpected disruptions along the circuits that the AGV follows. In order to test and validate the proposed approach, a series of computational experiments utilizing real-life data are carried out. These experiments allow us to measure the improvement gap with respect to the former policy used by the system managers.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Using Reinforcement Learning to Solve a Dynamic Orienteering Problem with Random Rewards Affected by the Battery Status

  • Juan, Ángel A|||0000-0003-1392-1776
  • Marugan, C.A.|||0009-0008-9076-0906
  • Ahsini, Y.|||0009-0006-5582-6725
  • Fornes, R.|||0009-0001-6956-9137
  • Panadero, Javier|||0000-0002-3793-3328
  • Martin, Xabier A|||0000-0003-4182-0120
This paper discusses an orienteering optimization problem where a vehicle using electric batteries must travel from an origin depot to a destination depot while maximizing the total reward collected along its route. The vehicle must cross several consecutive regions, with each region containing different types of charging nodes. A charging node has to be selected in each region, and the reward for visiting each node-in terms of a 'satisfactory' charging process-is a binary random variable that depends upon dynamic factors such as the type of charging node, weather conditions, congestion, battery status, etc. To learn how to efficiently operate in this dynamic environment, a hybrid methodology combining simulation with reinforcement learning is proposed. The reinforcement learning component is able to make informed decisions at each stage, while the simulation component is employed to validate the learning process. The computational experiments show how the proposed methodology is capable of design routing plans that are significantly better than non-informed decisions, thus allowing for an efficient management of the vehicle's battery under such dynamic conditions.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

A Hybrid Simulation and Reinforcement Learning Algorithm for Enhancing Efficiency in Warehouse Operations

  • Leon, Jonas F.
  • Li, Yuda|||0000-0001-8031-6555
  • Martin, Xabier A.|||0000-0003-4182-0120
  • Calvet, Laura|||0000-0001-8425-1381
  • Panadero, Javier|||0000-0002-3793-3328
  • Juan, Ángel A.|||0000-0003-1392-1776
The use of simulation and reinforcement learning can be viewed as a flexible approach to aid managerial decision-making, particularly in the face of growing complexity in manufacturing and logistic systems. Efficient supply chains heavily rely on steamlined warehouse operations, and therefore, having a well-informed storage location assignment policy is crucial for their improvement. The traditional methods found in the literature for tackling the storage location assignment problem have certain drawbacks, including the omission of stochastic process variability or the neglect of interaction between various warehouse workers. In this context, we explore the possibilities of combining simulation with reinforcement learning to develop effective mechanisms that allow for the quick acquisition of information about a complex environment, the processing of that information, and then the decision-making about the best storage location assignment. In order to test these concepts, we will make use of the FlexSim commercial simulator.