Pasar al contenido principal

DESARROLLO DE SISTEMAS DE FABRICACION COLABORATIVOS EN PLATAFORMAS DE INTERNET INDUSTRIALES

PID2019-108277GB-C21

•
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 de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2019
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE LEÓN

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

Optimized Network for Detecting Burr-Breakage in Images of Milling Workpieces

  • Riego Del Castillo, Virginia
  • Sánchez González, Lidia
  • Strisciuglio, Nicola
[EN] Quality standards fulfilment is an essential task in manufacturing processes that involves high costs. One target is to avoid the presence of burrs in the edge of machine workpieces, which reduce the quality of the products. Furthermore, they are not easily removed since the part can even be damaged. In this paper, we propose an optimized Convolutional Neural Network, to detect the presence of burrs in images of milling parts. Its design is focused on the optimization of classification (accuracy) and performance metrics (training time and number of trainable parameters). The proposed architecture identifies burrs with a 91.16\% accuracy in the test set, outperforming existing models as EfficientNetB0. It also reduces the number of trainable parameters from other models as AlexNet by 1.5 million. The prediction process just takes 48.39 milliseconds per image. Finally, in order to check if the model gets a high activation in the region of interest, a visual explanation of the model is also carried out by using Gradient-weighted Class Activation Mapping., SI
BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

Towards industry 5.0 through metaverse

  • Martínez Gutiérrez, Alberto
  • Díez González, Javier
  • Pérez García, Hilde
  • Araujo, Magdalena
[EN] The digital transformation of the industry allows the optimization of resources through enabling technology that virtualizes the behavior of Cyber-Physical Systems (CPS) along the entire value chain. However, these virtual environments characterized by machine-to-machine interactions lacked the presence of humans who are at the center of the next defined industrial revolution, Industry 5.0. The goal is for humans to be actively integrated into these virtual environments called metaverses where interactions with environmental digital assets are possible. To achieve this human-centered industrial metaverse perspective, it is necessary to provide humans with technologies that allow them to reach a more immersive and realistic conception of the production processes. For this purpose, we present in this paper, a framework based on hyperconnectivity where several enabling technologies (e.g., Digital Twins, Virtual Reality, Industrial Internet of Things (IIoT)) are integrated in order to converge towards the industrial human-centered metaverse. To validate our framework, a demonstrator has been developed enabling the evaluation of the behavior of humans in virtual environments when facing collaborative tasks that require human-to-human interaction. Within the evaluation of this demonstrator, an experiment based on an assembly that requires interaction with an autonomous vehicle has been carried out both in reality and in the virtual world. The results obtained indicate that the avatars’ metaverse performance is closer to reality when individuals have previous experience with VR goggles, even proving, in this case, the effectiveness of metaverse for industrial operators’ training. In addition, the performance of the application has been evaluated with technical parameters and the perception of the users has been analyzed by conducting a survey receiving very positive feedback and results. Therefore, the industrial metaverse, blending cutting-edge tech with a human-centric approach for Industry 5.0, is now a reality., SI, Publicación en abierto financiada por el Consorcio de Bibliotecas Universitarias de Castilla y León (BUCLE), con cargo al Programa Operativo 2014ES16RFOP009 FEDER 2014-2020 DE CASTILLA Y LEÓN, Actuación:20007-CL - Apoyo Consorcio BUCLE
BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

Optimal COVID-19 Adapted Table Disposition in Hostelry for Guaranteeing the Social Distance through Memetic Algorithms

  • Ferrero Guillén, Rubén
  • Díez González, Javier
  • Martínez Gutiérrez, Alberto
  • Álvarez, Rubén
[EN] The COVID-19 pandemic has challenged all physical interactions. Social distancing, face masks and other rules have reshaped our way of living during the last year. The impact of these measures for indoor establishments, such as education or hostelry businesses, resulted in a considerable organisation problem. Achieving a table distribution inside these indoor spaces that fulfilled the distancing requirements while trying to allocate the maximum number of tables for enduring the pandemic has proved to be a considerable task for multiple establishments. This problem, defined as the Table Location Problem (TLP), is categorised as NP-Hard, thus a metaheuristic resolution is recommended. In our previous works, a Genetic Algorithm (GA) optimisation was proposed for optimising the table distribution in real classrooms. However, the proposed algorithm performed poorly for high obstacle density scenarios, especially when allocating a considerable number of tables due to the existing dependency between adjacent tables in the distance distribution. Therefore, in this paper, we introduce for the first time, to the authors’ best knowledge, a Memetic Algorithm (MA) optimisation that improves the previously designed GA through the introduction of a Gradient Based Local Search. Multiple configurations have been analysed for a real hostelryrelated scenario and a comparison between methodologies has been performed. Results show that the proposed MA optimisation obtained adequate solutions that the GA was unable to reach, demonstrating a superior convergence performance and an overall greater flexibility. The MA performance denoted its value not only from a COVID-19 distancing perspective but also as a flexible managing algorithm for daily table arrangement, thus fulfilling the main objectives of this paper., SI, Ministerio de Ciencia, Innovación y Universidades
BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

Hyperconnectivity Proposal for Smart Manufacturing

  • Martínez Gutiérrez, Alberto
  • Díez González, Javier
  • Verde García, Paula
  • Ferrero Guillén, Rubén
  • Pérez García, Hilde
[EN] Smart Manufacturing is characterized by the digitization and massive communication of Cyber-Physical Systems under the Industrial Internet of Things paradigm. However, the heterogeneity of communication protocols hinders connectivity among assets due to lack of interoperability. Moreover, the decomposition of the classical production hierarchy towards decentralized self-organization makes the implementation of interoperability in industrial environments key to help decision-making. In this sense, the interoperability of heterogeneous assets (e.g., external, internal, and human) has been defined as hyperconnectivity and supposes a technological challenge in the scientific literature. To prove this novel hyperconnectivity definition, the authors propose and develop a novel hyperconnected demonstrator where all types of assets are interconnected in a case study consisting of the automation of an inspection process. For this purpose, an industrial internet platform has been used for connecting industrial equipment creating a collaborative environment through the use of interoperability. In this regard, it has been possible to communicate assets among the cloud, humans, and CPS with a processing time of less than 10 ms, which demonstrates that the technological challenge of implementing the hyperconnectivity concept of this paper has been successfully addressed., SI, This research has been developed and funded by the Spanish Ministry of Science and Innovation project grant number PID2019-108277GB-C21/AEI/10.13039/501100011033 and by the Universidad de León., Ministerio de Ciencia, Innovación y Universidades
BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

Digital Twin for Automatic Transportation in Industry 4.0

  • Martínez Gutiérrez, Alberto
  • Díez González, Javier
  • Ferrero Guillén, Rubén
  • Verde García, Paula
  • Álvarez, Rubén
  • Pérez García, Hilde
[EN] Industry 4.0 is the fourth industrial revolution consisting of the digitalization of processes facilitating an incremental value chain. Smart Manufacturing (SM) is one of the branches of the Industry 4.0 regarding logistics, visual inspection of pieces, optimal organization of processes, machine sensorization, real-time data adquisition and treatment and virtualization of industrial activities. Among these tecniques, Digital Twin (DT) is attracting the research interest of the scientific community in the last few years due to the cost reduction through the simulation of the dynamic behaviour of the industrial plant predicting potential problems in the SM paradigm. In this paper, we propose a new DT design concept based on external service for the transportation of the Automatic Guided Vehicles (AGVs) which are being recently introduced for the Material Requirement Planning satisfaction in the collaborative industrial plant. We have performed real experimentation in two different scenarios through the definition of an Industrial Ethernet platform for the real validation of the DT results obtained. Results show the correlation between the virtual and real experiments carried out in the two scenarios defined in this paper with an accuracy of 97.95% and 98.82% in the total time of the missions analysed in the DT. Therefore, these results validate the model created for the AGV navigation, thus fulfilling the objectives of this paper., SI, Ministerio de Ciencia, Innovación y Universidades
BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

Table Organization Optimization in Schools for Preserving the Social Distance during the COVID-19 Pandemic

  • Ferrero Guillén, Rubén
  • Díez González, Javier
  • Verde García, Paula
  • Álvarez, Rubén
  • Pérez García, Hilde
[EN] The COVID-19 pandemic has supposed a challenge for education. The school closures during the initial coronavirus outbreak for reducing the infections have promoted negative effects on children, such as the interruption of their normal social relationships or their necessary physical activity. Thus, most of the countries worldwide have considered as a priority the reopening of schools but imposing some rules for keeping safe places for the school lessons such as social distancing, wearing facemasks, hydroalcoholic gels or reducing the capacity in the indoor rooms. In Spain, the government has fixed a minimum distance of 1.5 m among the students’ desks for preserving the social distancing and schools have followed orthogonal and triangular mesh patterns for achieving valid table dispositions that meet the requirements. However, these patterns may not attain the best results for maximizing the distances among the tables. Therefore, in this paper, we introduce for the first time in the authors’ best knowledge a Genetic Algorithm (GA) for optimizing the disposition of the tables at schools during the coronavirus pandemic. We apply this GA in two real-application scenarios in which we find table dispositions that increase the distances among the tables by 19.33% and 10%, respectively, with regards to regular government patterns in these classrooms, thus fulfilling the main objectives of the paper., SI, Ministerio de Ciencia, Innovación y Universidades
BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

Convergence of Virtual Reality and Digital Twin technologies to enhance digital operators’ training in industry 4.0

  • Martínez Gutiérrez, Alberto
  • Díez González, Javier
  • Verde García, Paula
  • Pérez García, Hilde
[EN] Industry 4.0 technologies enable the generation of added value throughout the production process. Among them, Digital Twins (DT) allow the modelization of cyber–physical systems in the virtual world and Virtual Reality (VR) allows an immersive perspective of the behavior of industrial equipment in a digitized environment. The combination of DT and VR can generate a digital platform for operators’ training where the industrial operator can perceive a more realistic environment for digital learning. In this paper, we introduce the convergence of DT and VR to enhance the digital learning process of driving an industrial mobile robot. To validate this proposal, an experimental methodology looking for measuring the transfer of skills from digital training into the real world has been set. This experiment consists of handling a mobile robot in a predefined course looking for committing the lowest number of failures in the minimum possible time. The experiment has been carried out by defining three different training methods: training with real equipment as the control group and two different experimental groups following digital training (VR and computer application-supported techniques). The abilities of their subjects have been measured in the initial and final stages of the experiment showing an improvement of 47% through real training, 38% through VR and 28% through the computer application. Results demonstrate the utility of using DT to attain significant digital learning and validate the initial hypothesis demonstrating the enhancement of digital learning through VR-supported training., SI, Ministerio de Ciencia e Innovación