Autor(es)

Ferri, Gabriel G. B. ; Tominaga, Rafael N. ; Avila, Sergio L. ; Machado, Renato M. ; Salles, Mauricio B. C. ; Carmo, Bruno S.

• Tipo de documento: Artigo Científico
• Fonte: 2025 IEEE INTERNATIONAL ELECTRIC MACHINES & DRIVES CONFERENCE, IEMDC; v. N/A, p. 3-pg., 2025-01-01.

Resumo

Given the difficulty of obtaining representative and quality industrial datasets, such as electrical currents, we propose a multi-model stacking approach. Our method combines the strengths of three distinct neural network architectures in a multi-domain approach, tuned to process data from the frequency, time, and time-frequency domains. We evaluate the proposed architecture on three datasets (CWRU, PU, and PECCE). The stacking model achieved the highest test accuracy of 99% on the PECCE dataset, which represents an 8% improvement over using just one architecture. On the noisy CWRU dataset, we achieved accuracies above 98% for noise levels up to 10 dB. On the PU dataset, we observe that the stacking generalizes effectively to different operating conditions. Therefore, the multi-domain stacking approach has proven itself, confirming its versatility and potential for applicability in diverse industrial scenarios. (AU)

• Processo FAPESP: 20/15230-5 - Centro de Pesquisa e Inovação de Gases de Efeito Estufa - RCG2I
• Beneficiário: Julio Romano Meneghini
• Modalidade de apoio: Auxílio à Pesquisa - Programa Centros de Pesquisa Aplicada