A Multi-periodicity and Multi-scale Network for Motor Fault Diagnosis



Published Sep 4, 2023
Pengcheng Xia Kaiwen Zhang Yixiang Huang Chengliang Liu


Intelligent fault diagnosis of motor is of tremendous significance to ensuring reliable industrial production, and deep learning methods have gained notable achievements recently. Most researches automatically extracted fault information from raw monitoring signals with deep models, whereas the strong periodic temporal information containing in the signals were ignored. To tackle this limitation, a multi-periodicity and multi-scale network is proposed in this paper. 1D monitoring signals are transformed into 2D space with multiple various periods, allowing for the straightforward reflection and modeling of variations both within and between different periods. Multi-scale learning is introduced to extract temporal information from the multi-periodicity representations with multiple scales in a parameter-efficient way. Experiments carried out on a motor fault dataset verified the effectiveness of the proposed method. The results demonstrate that over 99% diagnosis accuracy can be achieved with onechannel vibration signals, and superior performance is obtained under diverse noise conditions compared with other methods.

Abstract 246 | PDF Downloads 233



Motor fault diagnosis, Multi-periodicity, Multi-scale, Time series modelling

Gangsar, P., & Tiwari, R. (2020). Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-theart review [Journal Article]. Mechanical Systems and Signal Processing, 144. doi: ARTN 106908 10.1016/j.ymssp.2020.106908

Hendrycks, D., & Gimpel, K. (2016). Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415.

Lang, W., Hu, Y., Gong, C., Zhang, X., Xu, H., & Deng, J. (2022). Artificial intelligence-based technique for fault detection and diagnosis of ev motors: A review [Journal Article]. IEEE Transactions on Transportation Electrification, 8(1), 384-406. doi: 10.1109/tte.2021.3110318

Shao, S., Yan, R., Lu, Y., Wang, P., & Gao, R. X. (2020). Dcnn-based multi-signal induction motor fault diagnosis [Journal Article]. IEEE Transactions on Instrumentation and Measurement, 69(6), 2658-2669. doi: 10.1109/tim.2019.2925247

Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., . . . Rabinovich, A. (2015). Going deeper with convolutions. In 2015 ieee conference on computer vision and pattern recognition (cvpr) (p. 1-9). doi: 10.1109/CVPR.2015.7298594

Tang, Y., Zhang, X., Qin, G., Long, Z., Huang, S., Song, D., & Shao, H. (2021). Graph cardinality preserved attention network for fault diagnosis of induction motor under varying speed and load condition [Journal Article]. IEEE Transactions on Industrial Informatics, 1-1. doi: 10.1109/tii.2021.3112696

Tao, Z., Xia, P., Huang, Y., Xiao, D., Wuang, Y., Zhong, Z., & Liu, C. (2021). Induction motor fault diagnosis based on multi-sensor fusion under high noise and sensor failure condition [Conference Proceedings]. In 2021 global reliability and prognostics and health management (phm-nanjing) (p. 1-8). doi: 10.1109/PHMNanjing52125.2021.9612787

Wang, F., Liu, R. N., Hu, Q. H., & Chen, X. F. (2021). Cascade convolutional neural network with progressive optimization for motor fault diagnosis under nonstationary conditions [Journal Article]. IEEE Transactions on Industrial Informatics, 17(4), 2511-2521. doi: 10.1109/Tii.2020.3003353

Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., & Long, M. (2023). Timesnet: Temporal 2d-variation modeling for general time series analysis. In The eleventh international conference on learning representations.

Xia, P., Huang, Y., Tao, Z., Liu, C., & Liu, J. (2023). A digital twin-enhanced semi-supervised framework for motor fault diagnosis based on phase-contrastive current dot pattern [Journal Article]. Reliability Engineering & System Safety, 235, 109256. doi: 10.1016/j.ress.2023.109256

Xia, P., Huang, Y., Wang, Y., Zhong, Z., & Liu, C. (2022). Selective kernel prototypical network for few-shot motor fault diagnosis with unseen faults [Conference Proceedings]. In 2022 global reliability and prognostics and health management (phm-yantai) (p. 1-7). doi: 10.1109/PHM-Yantai55411.2022.9942130

Xiao, D., Huang, Y., Zhang, X., Shi, H., Liu, C., & Li, Y. (2018). Fault diagnosis of asynchronous motors based on lstm neural network. In 2018 prognostics and system health management conference (phm-chongqing) (p. 540-545). doi: 10.1109/PHMChongqing.2018.00098
Regular Session Papers