Skip to main content

DIGITALIZATION OF POWER ELECTRONIC APPLICATIONS WITHIN KEY TECHNOLOGY VALUE CHAINS

PCI2022-135004-2

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal para Afrontar las Prioridades de Nuestro Entorno
Subprogram Subprograma Estatal de Internacionalización
Call Proyectos Programación Conjunta Internacional
Call year 2022
State Plan 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre AGENCIA ESTATAL CONSEJO SUPERIOR DE INVESTIGACIONES CIENTIFICAS (CSIC)

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Extending the operational lifespan of key components in a cyberphysical system. A method and case study

  • Castaño, Fernando
  • Cruz, Yarens J.
  • Villalonga, Alberto
  • Haber Guerra, Rodolfo E.
Nowadays extending the lifespan of key electronic components in cyber-physical systems is a must from the viewpoint of efficiency and sustainability. Up-to-date, there is a fresh push to use Artificial intelligence (AI) for estimating the remaining useful life (RUL) of electronic components. This paper proposes an automated framework for predicting RUL and classifying device failures. The framework includes a library of AI-based models to perform RUL estimation and to assess the actual condition of critical electronic components, without disconnecting them in a cyber-physical system. The best model is selected using the Q-learning method, which runs in parallel with the set of models. To evaluate the framework, a case study involving electrolytic capacitors of DC/DC power converters is presented. The results corroborate the suitability of the suggested approach in real-data sets and industrial test-bed., This work was supported by the project “Digitalization of Power Electronic Applications within Key Technology Value Chains (PowerizeD)”, grant ID 101096387, funded by the European Union HORIZON FP and Chips JU, and PCI2022-135004-2 funded by MICIU/AEI/ 10.13039/501100011033 by the European Union NextGenerationEU/PRTR. This work is also supported by iGENZERO project with reference TED2021-131921A-I00, funded by MCIN/AEI/ 10.13039/501100011033 and by the European Union “NextGenerationEU”/PRTR., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Automation and Robotics Pilot Lines in the Context of Industry 5.0

  • Alonso, Rubén
  • Sánchez, Tomás F.
  • Alfaro, Diego A.
  • Cruz, Yarens J.
  • Villalonga, Alberto
  • Castaño, Fernando
Pilot lines have become a key element in modern industry. The demands for resilience, human-centricity, and sustainability in Industry 5.0, combined with technological innovations, highlight the critical role of these lines in the new industrial paradigm. Pilot lines facilitate the validation of processes and the reduction in uncertainties, making them essential tools for future industries. This article examines the current state of pilot lines and evaluates their alignment with Industry 5.0 principles. As part of this analysis, the GAMHE 5.0 pilot line is presented as a line designed with a focus on automation and robotics, meeting the requirements of the industries of the future. This article also details a series of case studies conducted on the pilot line, demonstrating its flexibility and adaptability. Finally, the advantages and disadvantages of small-scale lines are analyzed within the context of Industry 5.0, emphasizing their importance in balancing technology, human factors, and sustainability., This work was supported by the project “Digitalization of Power Electronic Applications within Key Technology Value Chains (PowerizeD)”, ID 101096387, funded by the European Union HORIZON FP and Chips JU, and PCI2022-135004-2 funded by MICIU/AEI/10.13039/501100011033 by the “European Union NextGenerationEU/PRTR”. The work is also funded by the project “Self-reconfiguration for Industrial Cyber–Physical Systems based on Digital Twins and artificial intelligence. Methods and application in Industry 4.0 pilot line”, Spain, grant ID PID2021-127763OB-100, and supported by MICIU and NextGenerationEU/PRTR. This work is also supported by iGENZERO project with reference TED2021-131921A-I00, funded by MCIN/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

A Data-Driven Approach for Predicting Remaining Useful Life of Semiconductor Devices Based on Machine Learning and Synthetic Data Generation: A Review and Case Study on SiC MOSFETs

  • Cruz,Yarens J.
  • Castaño, Fernando
  • Villalonga, Alberto
  • Mishra, Madhav
  • Haber, Rodolfo E.
Predicting the remaining useful life of electronic components is a crucial aspect for predictive maintenance and system reliability across multiple fields and applications. Data-driven approaches, particularly those methods based on machine learning, are currently being used due to their ability to model complex degradation patterns without the need for explicit physical modeling. However, several challenges remain, including the availability and quality of data, as well as the uncertainty quantification of the results. To tackle these obstacles, this work explores the use of synthetic data for augmenting datasets, as well as feature selection and the assessment of different neural network architectures, including models with recurrent layers and probabilistic output. The proposed approach was evaluated on a silicon carbide metal-oxide-semiconductor field-effect transistor dataset. The best results for modeling the remaining useful life of these devices were obtained with a model trained on an augmented dataset that included synthetic data. This model’s probabilistic output allows building a confidence interval for the predictions, which is helpful to identify outliers. This model outperformed other state-of-the-art algorithms using only 4 out of 22 features, demonstrating the effectiveness of the feature selection procedure, the data augmentation method, and the neural network architecture for this case study., Project “Digitalization of Power Electronic Applications within Key Technology Value Chains ” (Grant Number: 101096387) Ministerio de Ciencia Innovación y Universidades /Agencia Estatal de Investigación (Grant Number: (AEI)/10.13039/501100011033) European Union NextGenerationEU/Plan de Recuperación, Transformación y Resiliencia (PRTR) (Grant Number: PCI2022-135004-2) Project “Self Reconfiguration for Industrial Cyber-Physical Systems Based on Digital Twins and Artificial Intelligence. Methods and Application in Industry 4.0 Pilot Line” (Grant Number: PID2021-127763OB-100) MICIU, Spain NextGenerationEU/PRTR, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Early defect detection in thermo-insulating panels: A case study on quality inspection

  • Alonso, Rubén
  • Castaño, Fernando
  • Cruz, Yarens J.
  • Villalonga, Alberto
  • Haber, Rodolfo E.
This work presents a novel end-to-end approach to early defect detection in thermo-insulating panels, widely used in the construction sector. Unlike existing studies that focus on isolated aspects, our contribution combines: (i) a composable and interoperable software platform designed to support data augmentation, segmentation, and classification; (ii) a multi-technique synthetic image generation strategy that overcomes the limitations of scarce and unbalanced datasets; and (iii) a hybrid segmentation and classification pipeline that extends traditional U-Net architectures with post-segmentation polygonal analysis for robust defect identification. The proposed solution is validated on the GAMHE 5.0 Industry 5.0 pilot line, demonstrating not only improvements in detection accuracy and control time but also its feasibility in humanin-the-loop, near-production environments, a gap rarely addressed in the literature. These results confirm that the approach goes beyond a mere consolidation of existing methods, providing instead a scalable, human-centric, and sustainable framework for Zero-Defect Manufacturing., This work was supported by “Digitalization of Power Electronic Applications within Key Technology Value Chains (PowerizeD)”, ID 101096387, funded by the European Union HORIZON FP and Chips JU, and PCI2022- 135004-2 funded by MICIU/AEI/10.13039/501100011033 by the European Union NextGenerationEU/PRTR”. ii) “Self-reconfiguration for Industrial Cyber-Physical Systems based on digital twins and Artificial Intelligence. Methods and application in Industry 4.0 pilot line,” Spain, grant ID PID2021-127763OB-100, and supported by MICIU and NextGenerationEU/PRTR. iii) iGENZERO project with reference TED2021-131921A-I00, funded by MCIN/ AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR. iv) Horizon Europe project "BIO insulation materials for Enhancing the Energy performance of Buildings" (BIO4EEB), Grant agreement ID: 101091967, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Integrating AutoML and LLMs to streamline the optimisation of production processes. A case study on GAMHE 5.0 pilot line

  • Cruz, Yarens J
  • Castaño, Fernando
  • Villalonga, Alberto
  • Quiza, Ramón
  • Haber, Rodolfo E
Optimising production processes is a key challenge in modern industry, with Machine Learning and Artificial Intelligence playing an increasingly important role. Yet, current approaches often require manual intervention and expert knowledge, slowing adoption. To overcome these limitations, this work proposes a methodology that integrates Automated Machine Learning with Large Language Models to carry out process optimisation in a highly automated, end-to-end manner. LLM are employed for code generation, enabling the creation of datasets from existing sources while accounting for contextual information expressed in natural language. AutoML then builds predictive models of the production process, which serve as objective functions in an optimisation algorithm. The methodology was validated through a case study involving four setups, consistently producing optimal solutions aligned with the defined goals. A comparative evaluation of thirteen LLMs for code generation and four AutoML frameworks for modelling was conducted. The best-performing LLMs, DeepSeek DeepSeek-R1, Anthropic Claude Sonnet 4, OpenAI gpt-oss-20b, and OpenAI GPT-5, achieved a 100% functional score. For modelling, TPOT and AutoGluon produced accurate results with coefficients of determination above 0.96 for all the target variables while yielding reliable optimisation solutions., This work was supported in part by the project ‘Digitalization of Power Electronic Applications within Key Technology Value Chains (PowerizeD)’, GA 101096387, and PCI2022-135004-2 funded by MICIU/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR. The work was also funded by the project ‘Self reconfiguration for Industrial Cyber-Physical Systems based on Digital Twins and artificial intelligence. Methods and application in Industry 4.0 pilot line’, grant ID PID2021-127763OB-100, and supported by MICIU, Spain and NextGenerationEU/PRTR. This work was also partially supported by the project ‘More than Moore for Disruptive Innovation in Power Electronics (Moore4Power)’, Horizon Europe GA 101252572, funded by the Call HORIZON-JU-CHIPS-2025-IA-two-stage., Peer reviewed