Abstract:Aiming at the shortcomings of traditional fault diagnosis methods requiring manual feature extraction and the problems of adaptive feature extraction and intelligent diagnosis of rolling bearing fault vibration signals under big data, an end-to-end fault diagnosis method was proposed based on multi-path fusion of dilated convolutional neural network(DCNN), attention mechanism, and gated recurrent unit(GRU) by taking advantage of the ability of DCNN that could take into account spatial features at different scales without increasing computational effort and the ability of GRU to learn temporal correlations from dynamically changing sequence data. First, DCNN was used to automatically extract timing signal features from the original data. Then the GRU channel of the attention mechanism and the DCNN channel were fused, and finally the extracted features were fused and sent to the classification layer for classification. Experimental results show that the diagnosis accuracy of the proposed method is 98.75% on average, which is higher than the comparison methods and more suitable for rolling bearing fault diagnosis.
葛超, 杨奇睿, 刘佳伟, 臧理萌, 陈亮, 孙瑞琪. 基于空洞卷积神经网络与注意力机制GRU的滚动轴承故障诊断[J]. 中国冶金, 2022, 32(4): 99-105.
GE Chao, YANG Qi-rui, LIU Jia-wei, ZANG Li-meng, CHEN Liang, SUN Rui-qi. Fault diagnosis of rolling bearing based on DCNN and attention GRU algorithm[J]. China Metallurgy, 2022, 32(4): 99-105.
LI H,LIAN X,GUO C,et al. Investigation on early fault classification for rolling element bearing based on the optimal frequency band determination[J]. Journal of Intelligent Manufacturing,2015,26(1):189.
[2]
Garcia-Perez A,Romero-Troncoso R J,Cabal-Yepez E,et al. The application of high-resolution spectral analysis for identifying multiple combined faults in induction motors[J]. IEEE Transactions on Industrial Electronics,2011,58(5):2002.
[3]
Rai A,Upadhyay S H. A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings[J]. Tribology International,2016:289.
YE T,JIAN M,CHEN L,et al. Rolling bearing fault diagnosis under variable conditions using LMD-SVD and extreme learning machine[J]. Mechanism and Machine Theory,2015,90:175.
Yu F,Koltun V. Multi-scale context aggregation by dilated convolutions[EB/OL]. [2021-11-01]. https://arxiv.org/pdf/1511.07122.pdf.
[17]
Graves A,Mohamed A R,Hinton G. Speech recognition with deep recurrent neural networks[C]//2013 IEEE International Conference on Acoustics, Speech and Signal Processing. Vancouver,Canada:IEEE,2013:6645.
[18]
Hochreiter S,Schmidhuber J. Long short-term memory[J]. Neural Computation,1997,9(8):1735.
[19]
Cho K,Merrienboer B V,Gulcehre C,et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[J]. Computer Science,2014(9):1.
Luong M T,Pham H,Manning C D. Effective approaches to attention-based neural machine translation[EB/OL].[2021-11-01]. https://arxiv.org/pdf/1508.04025v3.pdf
[22]
Weik M. (2000) Wiener filtering[M]//Computer Science and Communications Dictionary. Boston:Springer,2000.