Pasar al contenido principal

INTEGRACION DE LA TOMA DE DECISIONES DE LOS NIVELES TACTICO-OPERATIVO PARA LA MEJORA DE LA EFICIENCIA DEL SISTEMA DE PRODUCTIVO EN ENTORNOS INDUSTRIA 4.0

RTI2018-102020-B-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2018
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POLITÈCNICA DE VALÈNCIA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 6
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Mathematical programming-based methodology for the evaluation of supply chain collaborative planning scenarios

  • Pérez Perales, David|||0000-0001-5149-3835
  • Boza, Andres|||0000-0002-5429-0416
  • Alarcón Valero, Faustino|||0000-0002-0783-3932
  • Gómez-Gasquet, Pedro|||0000-0002-9184-6735
[EN] Nowadays, supply chain (SC) decentralised decision making is the most usual situation in SC operations planning. In this context, different companies can collaboratively plan to achieve a certain level of individual and SC performance. However in many cases, there is reluctance to collaborate because it is not known a priori which benefits will be reported. This paper aims to develop a mathematical programming-based methodology for the evaluation of different supply chain collaborative planning scenarios (MPM-SC-CP). It is assumed that different SC decision centres (DCs) make decisions based on mixed and integer linear programming models. Two main inputs feed the proposed MPM-SC-CP, a framework and associated methodology that support the integrated conceptual and analytical modeling of the SC-CP process in which several DCs make decisions according to spatio-temporal integration. Finally, an application to a real ceramic SC was conducted., This research has been funded by the European Regional Development Fund (FEDER) / Spanish Ministry of Science and Innovation (MCI)-State Research Agency (AEI), within the framework of the project entitled "Decision Making Integration of the Tactical-Operative Levels for Improving the Efficiency of the Productive System in Industry 4.0 Environments (NIOTOME)" (Ref. RTI2018-102020-B-I00).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Human resource allocation problem in the Industry 4.0: A reference framework

  • Grillo, H.
  • Caldwell, E.
  • Alemany Díaz, María Del Mar|||0000-0002-0992-8441
[EN] The Human Resource Allocation Problem (HRAP) is a well-known mathematical modeling type where a set of tasks should be assigned to a group of operators. As the smart production system brought by Industry 4.0 (I4.0) requires aligning new technologies with the human perspective, existing HRAP models should be revised and adapted to this new context. Therefore, this paper aims to design a complete proposal to support the modeling, implementation, and dynamic use of the HRAP in I4.0 called HRAP-4.0. To do so, first, the I4.0 factors that affect the HRAP are identified to revise to what extent existing models in the literature address them. To bridge gaps, this paper proposes contributions in two areas: mathematical models and methodological aspects. First, new mathematical formulations of optimization strategies (objectives) and constraints are modeled to include the I4.0 factors in a modular and reusable way, generating HRAP-4.0 model building block categories. Then a reference framework to support the formulation of HRAP-4.0 adapted to specific I4.0 situations based on the categories above is presented. Last, an implementation methodology is proposed to integrate the framework into a real I4.0 context and use the resulting HRAP-4.0 models in a dynamic environment. The reference framework comprises two decision trees to support selecting the most suitable optimization strategies (objectives) and constraints categories for the HRAP-4.0 under study. It collects the existing model categories in the literature, plus the new ones related to I4.0 herein developed. They are all essential within the cyber-physical systems (CPS) frame, which is the base of I4.0. The proposed HRAP-4.0, thus, becomes the new original tool for assigning tasks to people in the modern production system., This work has been partly supported by the project B9033 "Flexible Workforce Architecture" of the Industrial Engineering School, University of Costa Rica (UCR), and by the I+D+i project 'Integracion de la Toma de Decisiones de los Niveles Ta.ctico-Operativo para la Mejora de la Eficiencia del Sistema de Productivo en Entornos Industria 4.0 (NIOTOME)' (Ref. RTI2018-102020-B-I00) funded by MCIN/ AEI/ 10.13039/501100011033/ ERDF A way of making Europe.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

A Deep Reinforcement Learning Approach for Smart Coordination Between Production Planning and Scheduling

  • Gómez-Gasquet, Pedro|||0000-0002-9184-6735
  • Boza, Andres|||0000-0002-5429-0416
  • Pérez Perales, David|||0000-0001-5149-3835
  • Esteso, Ana|||0000-0003-0379-8786
[EN] The hierarchical approach of the production planning and control system proposes to divide decisions into various levels. Some data used in the planning level are based on predictions that anticipate the behavior of the workshop; nevertheless, these predictions can be adjusted at the schedule level. Feedback between both levels would allow better coordination; however, this feedback is not implemented due to interoperability problems and the complexity of the problem. This paper proposes an agent-based system that implements deep reinforcement learning to generate solutions based on artificial intelligence., Grant NIOTOME Ref. RTI2018-102020-B-I00 funded by MCIN/AEI/10.13039/50110 0011033 and ERDF A way of making Europe.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Reinforcement learning applied to production planning and control

  • Esteso, Ana|||0000-0003-0379-8786
  • Peidro Payá, David|||0000-0001-8678-6881
  • Mula, Josefa|||0000-0002-8447-3387
  • Díaz-Madroñero Boluda, Francisco Manuel|||0000-0003-1693-2876
[EN] The objective of this paper is to examine the use and applications of reinforcement learning (RL) techniques in the production planning and control (PPC) field addressing the following PPC areas: facility resource planning, capacity planning, purchase and supply management, production scheduling and inventory management. The main RL characteristics, such as method, context, states, actions, reward and highlights, were analysed. The considered number of agents, applications and RL software tools, specifically, programming language, platforms, application programming interfaces and RL frameworks, among others, were identified, and 181 articles were sreviewed. The results showed that RL was applied mainly to production scheduling problems, followed by purchase and supply management. The most revised RL algorithms were model-free and single-agent and were applied to simplified PPC environments. Nevertheless, their results seem to be promising compared to traditional mathematical programming and heuristics/metaheuristics solution methods, and even more so when they incorporate uncertainty or non-linear properties. Finally, RL value-based approaches are the most widely used, specifically Q-learning and its variants and for deep RL, deep Q-networks. In recent years however, the most widely used approach has been the actor-critic method, such as the advantage actor critic, proximal policy optimisation, deep deterministic policy gradient and trust region policy optimisation., The funding for the research work that has led to the obtained results came from the following grants: CADS4.0 (Ref. RTI2018-101344-B-I00) and NIOTOME (Ref. RTI2018102020-B-I00), financed byMCIN/AEI/10.13039/501100011033 and 'ERDF A way of making DEurope'; the EU H2020 research and innovation programme with grant numbers 825631 'Zero-Defect Manufacturing Platform (ZDMP)' and 958205 'Industrial Data Services for Quality Control in SmartManufacturing (i4Q)'; 'Industrial Production and Logistics Optimization in Industry 4.0' (i4OPT) (Ref. PROMETEO/2021/065) and 'Resilient, Sustainable and PeopleOriented Supply Chain 5.0 Optimization Using Hybrid Intelligence' (RESPECT) (Ref. CIGE/2021/159) Projects were funded by the Generalitat Valenciana (Valencian Regional Government).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Artificial Intelligence in Supply Chain Operations Planning: Collaboration and Digital Perspectives

  • Rodríguez-Sánchez, María De Los Ángeles
  • Alemany Díaz, María Del Mar|||0000-0002-0992-8441
  • Boza, Andres|||0000-0002-5429-0416
  • Cuenca, L.|||0000-0003-3589-4182
  • Ortiz Bas, Ángel|||0000-0001-5690-0807
[EN] Digital transformation provide supply chains (SCs) with extensive accurate data that should be combined with analytical techniques to improve their management. Among these techniques Artificial Intelligence (AI) has proved their suitability, memory and ability to manage uncertain and constantly changing information. Despite the fact that a number of AI literature reviews exist, no comprehensive review of reviews for the SC operations planning has yet been conducted. This paper aims to provide a comprehensive review of AI literature reviews in a structured manner to gain insights into their evolution in incorporating new ICTs and collaboration. Results show that hybrization man-machine and collaboration and ethical aspects are understudied., This research has been funded by the project entitled NIOTOME (Ref. RTI2018-102020-B-I00) (MCI/AEI/FEDER, UE). The first author was supported by the Generalitat Valenciana (Conselleria de Educación, Investigación, Cultura y Deporte) under Grant ACIF/2019/021.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A Conceptual Framework for the Operations Planning of the Textile Supply Chains: insights for Sustainable and Smart Planning in Uncertain and Dynamic Context

  • Lorente-Leyva, Leandro
  • Peluffo-Ordóñez, Diego H.
  • Alemany Díaz, María Del Mar|||0000-0002-0992-8441
[EN] Recent practices in textile supply chains (SC) show a growing concern for sustainability not only in its economic dimension, but fundamentally in its environmental and social ones. One of the key management processes that affect sustainability is the SC operations planning since its fundamental role in achieving a balance between supply and demand in a sustainable manner. Moreover, in an uncertain and dynamic environment such as the textile sector, it is necessary to provide a certain learning capability to the operations planning techniques used to increase the speed and quality of response of the textile SC to unexpected situations. In this context, mathematical programming models, heuristics and artificial intelligence techniques have proven their validity to achieve sustainable, robust and smart supply chains. Despite their potential, neither a conceptual framework (CF) nor a literature review have been detected to support the development and study of such models in the textile supply chain operations planning. In view of these gaps, this paper proposes a CF for supporting the sustainable and smart operations planning of the textile supply chains in a dynamic and uncertain context based on a set of dimensions, categories and elements that reflect the specific characteristics of the textile sector. Firstly, a tentative CF is predefined based on other generic works on SC operations planning in uncertain context and the own authors¿ knowledge. Secondly, a structured literature review based on this CF has been made resulting, at the same time, in the updating of some of its dimensions, categories and elements to reflect some textile specific characteristics. Consequently, the CF is not only predefined but also logically derived from the literature analysis. The results of the literature review show that there is a great opportunity to contribute to making textile supply chains more sustainable, smart, flexible, robust and resilient in dynamic and uncertain environments., This research was initiated in the framework of the project entitled NIOTOME (Ref. RTI2018-102020-B-I00) (MCI/AEI/FEDER, UE) now closed. Then, it was further developed in the framework of the projects entitled "Industrial Production and Logistics Optimization in Industry 4.0 (i4OPT) (PROMETEO/2021/065) " and "Autonomous And Self-Organized Artificial Intelligent Orchestrator For a Greener Industry 4.0" (TALON) (UE 101070181) . Leandro L. Lorente-Leyva and Diego H. Peluffo-Ordonez are greatly grateful by the support given by the SDAS Research Group (https://sdas-group.com /) . Funding for open access charge: CRUE-Universitat Politecnica de Valencia.