PRIMUS: um modelo CNN para manutenção Preditiva em motores indutores industriais
Resumo
A demandas por monitoramento de motores industriais está progressivamente aumentando na busca de previnir falhas, paradas não programadas e manutenções com maior efetividade. Assim, a falta de planejamento nessas máquinas pode agravar contratempos com relação a custos financeiros e estratégicos em diversos setores industriais. Este trabalho apresenta o PRIMUS, um modelo CNN para manutenção PReditIva em Motores indUtores industriaiS para fechamentos delta e estrela nos modos série e paralelo. Realizou-se gravações sonoras dos motores com variações de 1500 a 1650 rpm. Analisou-se a propriedade do motor com o modelo de gravação em formato circular tridimensional com distância constante de 15 cm relativa ao eixo principal do motor.
Palavras-chave:
aprendizado de máquina, signal processing, motor industrial
Referências
Prabhu Thirugnanam. Advances, new perspective and applications in induction motors. In Induction Motors-Recent Advances, New Perspectives and Applications. IntechOpen, 2023.
Vicente Biot-Monterde, Angela Navarro-Navarro, Israel Zamudio-Ramirez, Jose A Antonino-Daviu, and Roque A Osornio-Rios. Automatic classification of rotor faults in soft-started induction motors, based on persistence spectrum and convolutional neural network applied to stray-flux signals. Sensors, 23(1):316, 2022.
Francesco Aggogeri, Nicola Pellegrini, and Franco Luis Tagliani. Recent advances on machine learning applications in machining processes. Applied sciences, 11(18):8764, 2021.
Yuri Merizalde, Luis Hernández-Callejo, and Oscar Duque-Perez. State of the art and trends in the monitoring, detection and diagnosis of failures in electric induction motors. Energies, 10(7):1056, 2017.
Muhammad Aman Sheikh, Sheikh Tahir Bakhsh, Muhammad Irfan, Nursyarizal bin Mohd Nor, and Grzegorz Nowakowski. A review to diagnose faults related to three-phase industrial induction motors. Journal of Failure Analysis and prevention, 22(4):1546–1557, 2022.
Andressa Borré, Laio Oriel Seman, Eduardo Camponogara, Stefano Frizzo Stefenon, Viviana Cocco Mariani, and Leandro dos Santos Coelho. Machine fault detection using a hybrid cnn-lstm attention-based model. Sensors, 23(9):4512, 2023.
Linkha Hardine, Dian Budhi Santoso, and Ridwan Satrio Hadikusuma. Analysis of the influence of star delta system in reduce electric starting surge in 3 phase motors. Electrician: Jurnal Rekayasa Dan Teknologi Elektro, 16(2):208– 214, 2022.
Ali Abdo, Jamal Siam, Ahmed Abdou, Rashad Mustafa, and Hakam Shehadeh. Electrical fault detection in three-phase induction motor based on acoustics. In 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe), pages 1– 5. IEEE, 2020.
Minh-Quang Tran, Meng-Kun Liu, Quoc-Viet Tran, and Toan-Khoa Nguyen. Effective fault diagnosis based on wavelet and convolutional attention neural network for induction motors. IEEE Transactions on Instrumentation and Measurement, 71:1–13, 2021.
Olav Vaag Thorsen and Magnus Dalva. Failure identification and analysis for high-voltage induction motors in the petrochemical industry. IEEE transactions on industry applications, 35(4):810–818, 2002.
Minh-Quang Tran, Mohammed Amer, Almoataz Y Abdelaziz, Hong-Jie Dai, Meng-Kun Liu, Mahmoud Elsisi, et al. Robust fault recognition and correction scheme for induction motors using an effective iot with deep learning approach. Measurement, 207:112398, 2023.
Stephen J Chapman. Fundamentos de máquinas elétricas. AMGH editora, 2013.
Vicente Biot-Monterde, Angela Navarro-Navarro, Israel Zamudio-Ramirez, Jose A Antonino-Daviu, and Roque A Osornio-Rios. Automatic classification of rotor faults in soft-started induction motors, based on persistence spectrum and convolutional neural network applied to stray-flux signals. Sensors, 23(1):316, 2022.
Francesco Aggogeri, Nicola Pellegrini, and Franco Luis Tagliani. Recent advances on machine learning applications in machining processes. Applied sciences, 11(18):8764, 2021.
Yuri Merizalde, Luis Hernández-Callejo, and Oscar Duque-Perez. State of the art and trends in the monitoring, detection and diagnosis of failures in electric induction motors. Energies, 10(7):1056, 2017.
Muhammad Aman Sheikh, Sheikh Tahir Bakhsh, Muhammad Irfan, Nursyarizal bin Mohd Nor, and Grzegorz Nowakowski. A review to diagnose faults related to three-phase industrial induction motors. Journal of Failure Analysis and prevention, 22(4):1546–1557, 2022.
Andressa Borré, Laio Oriel Seman, Eduardo Camponogara, Stefano Frizzo Stefenon, Viviana Cocco Mariani, and Leandro dos Santos Coelho. Machine fault detection using a hybrid cnn-lstm attention-based model. Sensors, 23(9):4512, 2023.
Linkha Hardine, Dian Budhi Santoso, and Ridwan Satrio Hadikusuma. Analysis of the influence of star delta system in reduce electric starting surge in 3 phase motors. Electrician: Jurnal Rekayasa Dan Teknologi Elektro, 16(2):208– 214, 2022.
Ali Abdo, Jamal Siam, Ahmed Abdou, Rashad Mustafa, and Hakam Shehadeh. Electrical fault detection in three-phase induction motor based on acoustics. In 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe), pages 1– 5. IEEE, 2020.
Minh-Quang Tran, Meng-Kun Liu, Quoc-Viet Tran, and Toan-Khoa Nguyen. Effective fault diagnosis based on wavelet and convolutional attention neural network for induction motors. IEEE Transactions on Instrumentation and Measurement, 71:1–13, 2021.
Olav Vaag Thorsen and Magnus Dalva. Failure identification and analysis for high-voltage induction motors in the petrochemical industry. IEEE transactions on industry applications, 35(4):810–818, 2002.
Minh-Quang Tran, Mohammed Amer, Almoataz Y Abdelaziz, Hong-Jie Dai, Meng-Kun Liu, Mahmoud Elsisi, et al. Robust fault recognition and correction scheme for induction motors using an effective iot with deep learning approach. Measurement, 207:112398, 2023.
Stephen J Chapman. Fundamentos de máquinas elétricas. AMGH editora, 2013.
Publicado
15/09/2025
Como Citar
PAIXÃO, Gilmar; GOMES, Cláudo.
PRIMUS: um modelo CNN para manutenção Preditiva em motores indutores industriais. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO MUSICAL (SBCM), 19. , 2025, Campinas/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 46-49.
DOI: https://doi.org/10.5753/sbcm_estendido.2025.14985.
