Abstract
To achieve intelligent and effective fault diagnosis of motor bearings, a machine-learning-based approach is proposed in the paper. 1D-CNNs are adopted to extract the features and a softmax classifier is used to distinguish the faults. However, given that there are many kinds of faults in the complex system, and there is coupling between fault signals, the reliability of fault diagnosis based on single-dimension data is limited, therefore we take the current signals and vibration signals of the motor as the input simultaneously. What’s more, to achieve further improvement in fault diagnosis accuracy fault diagnosis and reduce computational effort, a self-attention layer is introduced after feature extraction to selectively strengthen the valid information of the features. Subsequently, the performance of the approach is demonstrated on the bearing dataset of KAt-DataCenter. Finally, the effectiveness of multi-dimension input and the superiority of the self-attention mechanism are verified through comparative experiments.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yang, G., Zong, M., Dengyun, S., et al.: 2MNet: Multi-sensor and multi-scale model toward accurate fault diagnosis of rolling bearing. Reliabil. Eng. Syst. Safety 216, 108017 (2021)
Lau, E.C.C., Ngan, H.W.: Detection of motor bearing outer raceway defect by wavelet packet transformed motor current signature analysis. IEEE Trans. Instrument. Measure. 59(10), 2683–2690 (2010)
He, M., He, D.: A deep learning based approach for bearing fault diagnosis. IEEE Trans. Ind. Appl. 53(3), 3057–3065 (2017)
Samanta, B., Nataraj, C.: Use of particle swarm optimization for machinery fault detection. Eng. Appl. Artific. Intell. 22(2), 308–316 (2009)
Bin, G.F.: Early fault diagnosis of rotating machinery based on wavelet packets—empirical mode decomposition feature extraction and neural network. Mech. Syst. Sign. Process. 16 (2012)
Li, B.: Feature extraction for rolling element bearing fault diagnosis utilizing generalized S transform and two-dimensional non-negative matrix factorization. J. Sound Vibrat. 12 (2011)
Zhou, F., Zhang, Z., Chen, D.: Bearing fault diagnosis based on DNN using multi-scale feature fusion. In: 2020 35th Youth Academic Annual Conference of Chinese Association of Automation (YAC), pp. 150–155. Zhanjiang, China (2020)
Zhang, X., Han, P., Xu, L., et al.: Research on bearing fault diagnosis of wind turbine gearbox based on 1DCNN-PSO-SVM. IEEE Access 8, 192248–192258 (2020)
Wen, L., Li, X., Gao, L., et al.: A new convolutional neural network-based data-driven fault diagnosis method. IEEE Trans. Indust. Electron. 65(7), 5990–5998 (2018)
Zhang, Z.: Enhanced sparse filtering with strong noise adaptability and its application on rotating machinery fault diagnosis. Neurocomputing 398, 31–44 (2020)
Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention Is All You Need. In: arXiv: 1706.03762 [cs.CL] (2017)
Wang, H., Xu, J., Yan, R., et al.: Intelligent bearing fault diagnosis using multi-head attention-based CNN. Procedia Manufac. 49, 112–118 (2020)
Kim, E., Cho, S., Lee, B., et al.: Fault detection and diagnosis using self-attentive convolutional neural networks for variable-length sensor data in semiconductor manufacturing. IEEE Trans. Semiconduct. Manufac. 32(3), 302–309 (2019)
Ding, Y., Jia, M., Miao, Q., et al.: A novel time–frequency Transformer based on self–attention mechanism and its application in fault diagnosis of rolling bearings. Mech. Syst. Signal Process. 168, 112–118 (2022)
Christian, L., James, K., Zimmer, et al.: Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: a benchmark data set for data-driven classification. In: European Conference of The Prognostics and Health Management Society, Bilbao, Spain (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Beijing Paike Culture Commu. Co., Ltd.
About this paper
Cite this paper
Fang, L., Liu, Z., Jiang, D., Qu, R. (2023). Bearing Fault Diagnosis Using 1D-CNN Combined with Multi-Dimensional Input and Self-Attention Mechanism. In: Dong, X., Yang, Q., Ma, W. (eds) The proceedings of the 10th Frontier Academic Forum of Electrical Engineering (FAFEE2022). FAFEE 2022. Lecture Notes in Electrical Engineering, vol 1054. Springer, Singapore. https://doi.org/10.1007/978-981-99-3408-9_73
Download citation
DOI: https://doi.org/10.1007/978-981-99-3408-9_73
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-3407-2
Online ISBN: 978-981-99-3408-9
eBook Packages: EnergyEnergy (R0)