Application of Convolutional Neural Networks for Motor Fault Diagnosis: An Overview

XVII International Conference on Systems, Automatic Control and Measurements, SAUM 2024 (pp. 157-160)

АУТОР(И) / AUTHOR(S): Anđela Đorđević , Saša S. Nikolić , Miodrag Spasić , Jelena Dimitrijević

САЖЕТАК / ABSTRACT:

Maintenance of electric motors presents a task of high importance in industrial systems, as the motors are their vital components. With the demands of high system autonomy in Industry 4.0 and along with the rapid development of artificial intelligence, intelligent maintenance starts playing a crucial role in the industrial environment. Deep learning methods have especially proved to be effective tools in executing fault diagnosis tasks. In the last five years, the deep learning structures that have predominantly been applied in electric motor maintenance are convolutional neural networks (CNNs). In this paper an overview of CNN models used for electric motor fault detection in the last five years is given.

КЉУЧНЕ РЕЧИ / KEYWORDS:

convolutional neural networks, electric motor, fault detection, fault diagnosis, predictive maintenance

ПРОЈЕКАТ / ACKNOWLEDGEMENT:

This work was supported by the Ministry of Science, Technological Development and Innovation of the Republic of Serbia [grant number 451-03-66/2024-03/200102]

ЛИТЕРАТУРА / REFERENCE

Qiu, C. Xiaopeng, P. Zuowei, S. Nanliang, L. Zhong, B. Xianqiang, and X. Xinghua, „Deep Learning Techniques in Intelligent Fault Diagnosis and Prognosis for Industrial Systems: A Review“, Sensors, vol. 23, no. 3: 1305, 2023, doi: 10.3390/s23031305
Perić, N. Vukić, D. Antić, M. Milojković, and A. Đorđević, Application of Convolutional Neural Networks for Road Type Classification”, Facta Universitatis, Series: Automatic Control and Robotics, vol. 22, no. 1, pp. 001-013, 2023, doi: 10.22190/FUACR230123001P
Kim, J. H. Jung, J. U. Ko, H. B. Kong, J. Lee, and B. D. Youn, “Direct Connection-Based Convolutional Neural Network (DC-CNN) for Fault Diagnosis of Rotor Systems”, IEEE Access, vol. 8, pp. 172043-172056, 2020, doi: 10.1109/ACCESS.2020.3024544
Djordjevic, M. Milovanovic, M. Milojkovic, J. Petrovic, and S. Nikolic, “Endocrine CNN-Based Fault Detection for DC Motors”, Elektronika Ir Elektrotechnika, vol 30, no. 3, pp. 4-14, 2024, doi: 10.5755/j02.eie.36747
Ince, S. Kiranyaz, L. Eren, M. Askar and M. Gabbouj, „Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks,“ IEEE Transactions on Industrial Electronics, vol. 63, no. 11, pp. 7067-7075, Nov. 2016, doi: 10.1109/TIE.2016.2582729
Gu, Y. Zhang, M. Yang, and C. Li, “Motor On-Line Fault Diagnosis Method Research Based on 1D-CNN and Multi-Sensor Information,” Applied Sciences, vol. 13, no. 7: 4192, 2023, doi: 10.3390/app13074192
F. R, Junior, I. A. dos Santos Areias, M. M. Campos, C. E. Teixeira, L. E. B. da Silva, and G. F. Gomes, “Fault Detection and Diagnosis in Electric Motors Using 1d Convolutional Neural Networks with Multi-Channel Vibration Signals,” Measurement, vol. 190, 110759, 2022, doi: 10.1016/j.measurement.2022.110759
Quian, B. Li, and L. Chen, “CNN-Based Feature Fusion Motor Fault Diagnosis,” Electronics, vol. 11, no. 17, 2746, 2022, doi: 10.3390/electronics11172746
Mey, W. Neudeck, A. Schneider and O. Enge-Rosenblatt, „Machine Learning-Based Unbalance Detection of a Rotating Shaft Using Vibration Data,“ 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Vienna, Austria, 2020, pp. 1610-1617, doi: 10.1109/ETFA46521.2020.9212000
Skowron, T. Orlowska-Kowalska, M. Wolkiewicz, and C.T. Kowalski, “Convolutional Neural Network-Based Stator Current Data-Driven Incipient Stator Fault Diagnosis of Inverter-Fed Induction Motor,” Energies, vol. 13, no. 6, 1475, 2020, doi: 10.3390/en13061475
Kerboua and R. Kelaiaia, “Fault Diagnosis in an Asynchronous Motor Using Three-Dimensional Convolutional Neural Network,” Arabian Journal for Science and Engineering, vol. 49, no. 3, pp. 3467-3485, 2024, doi: 10.1007/s13369-023-08025-y