Pasar al contenido principal

DIGITALIZATION OF POWER ELECTRONIC APPLICATIONS WITHIN KEY TECHNOLOGY VALUE CHAINS

PCI2022-135021-2

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Afrontar las Prioridades de Nuestro Entorno
Subprograma Subprograma Estatal de Internacionalización
Convocatoria Proyectos Programación Conjunta Internacional
Año convocatoria 2022
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE OVIEDO

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

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

Proposed Solution for Improving Efficiency in Fuel Cell Power Systems Based on Short-Circuit Energy Recovering

  • Carrascal Garcia, Jorge
  • Toro Matamoros, Raúl Mario del
  • González, Leandro
  • Haber Guerra , Rodolfo
  • Rubio González, Miguel Angel
This work presents a design solution for energy recovery in fuel cell power systems, validated through simulation tools to improve energy efficiency. The work is specifically applied to low-temperature proton exchange membrane fuel cell (LTPEMFC) systems that employ short-circuit (SC) activation techniques to enhance catalytic activity during operation. The design addresses the energy supply discontinuity problem to the load during SC time intervals, allowing energy normally dissipated through an electronic switch to be supplied to the balance of plant (BOP), thereby minimizing energy losses and increasing system efficiency. A model-based design approach using numerical simulation tools was applied to validate the feasibility of the proposed system for a 1 kW fuel cell. Results show greater energy recovery at lower operating power (50 W), reaching 4.27% and 2.38% for theoretical and simulation validation, with the following supplier parameters: 9.00 V SC voltage, 100 ms SC pulse duration, and 10 s SC interval. Previous sensitivity studies reveal that the optimal parameter combination integrates 100 ms SC pulse duration, 0.5 s SC interval, that combined with 9.00 V SC voltage, yields 34% energy recovery at 50 W. ESR aging in energy storage supercapacitors affects SC effectiveness more than capacity degradation over 5000 h of LTPEMFC stack operation. The proposed method enables LTPEMFC operation expansion to lower power conditions, compensating for damage in idle and start-stop cycling modes. Future challenges involve physical implementation and experimental validation., This work was supported in part by the Digitalization of Power Electronic Applications within Key Technology Value Chains (PowerizeD) under Grant 101096387; in part by the Ministerio de Ciencia, Innovación y Universidades (MICIU)/Agencia Estatal de Investigación (AEI)/10.13039/501100011033 under Grant PCI2022-135004-2; in part by European Union NextGenerationEU/Plan de Recuperación, Transformación y Resiliencia (PRTR); and in part by the INVECPRO: Industrial and Transversal Research for a New Generation of Professional Vehículo Eléctrico Conectado (VEC) with High Added Value, funded by Spanish Ministry of Industry, Trade and Tourism (MINCOTUR) under Grant VEC-010000-2022-10., Peer reviewed