Fault Diagnosis for Planetary Gearbox by Dynamically Weighted Densely Connected Convolutional Networks

doi:10.3901/JME.2019.07.052

Abstract

Abstract: Aiming at applying deep learning in fault diagnosis of the planetary gearbox, a fault diagnosis method based on dynamically weighted densely connected convolutional networks is proposed. The wavelet packet coefficient matrix of the planetary gearbox vibration signal is taken as the initial feature map for densely connected convolutional networks. Dynamically weighted layers are designed in cross-layer of densely connected convolutional networks to form dynamically weighted densely connected convolutional networks to enhance information flow in deep network layers. The fault features are extracted by dynamically weighted network layers adaptively to perform the planetary gearbox fault diagnosis. The experiment indicates that the dynamically weighted densely connected convolutional networks can realize fault diagnosis of planetary gearbox under varying speed condition more effectively.

Key words: densely connected convolutional networks, fault diagnosis, feature learning, planetary gearbox, wavelet packet transform

CLC Number:

TH17

XIONG Peng, TANG Baoping, DENG Lei, ZHAO Minghang. Fault Diagnosis for Planetary Gearbox by Dynamically Weighted Densely Connected Convolutional Networks[J]. Journal of Mechanical Engineering, 2019, 55(7): 52-57.

References

[1] 雷亚国,何正嘉,林京,等. 行星齿轮箱故障诊技术的研究进展[J]. 机械工程学报, 2011, 47(19):59-67. LEI Yaguo, HE Zhengjia, LIN Jing, et al. Research advances of fault diagnosis technique for planetary gearboxes[J]. Journal of Mechanical Engineering, 2011, 47(19):59-67.
[2] LEI Yaguo, LIN Jing, ZUO M J, et al. Condition monitoring and fault diagnosis of planetary gearboxes:A review[J]. Measurement, 2014, 48(1):292-305.
[3] 何国林,丁康,林慧斌. 基于匹配追踪的齿轮箱耦合调制振动信号分离方法研究[J]. 机械工程学报, 2016, 52(1):102-108. HE Guolin, DING Kang, LIN Huibin. Matching pursuit method for coupling modulation signal separation of gearbox vibration[J]. Journal of Mechanical Engineering, 2016, 51(1):102-108.
[4] YU Jun, HE Yongjun. Planetary gearbox fault diagnosis based on data-driven valued characteristic multigranulation model with incomplete diagnostic information[J]. Journal of Sound and Vibration, 2018, 429:63-77.
[5] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553):436.
[6] JIA Feng, LEI Yaguo, LIN Jing, et al. Deep neural networks:A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data[J]. Mechanical Systems & Signal Processing, 2016, 72-73:303-315.
[7] HE Miao, HE D. Deep Learning based approach for bearing fault diagnosis[J]. IEEE Transactions on Industry Applications, 2017, 53(3):3057-3065.
[8] WANG Lihua, ZHAO Xiaoping, WU Jiaxin, et al. Motor fault diagnosis based on short-time fourier transform and convolutional neural network[J]. Chinese Journal of Mechanical Engineering, 2017, 30(6):1-12.
[9] SRIVASTAVA R K, GREFF K, SCHMIDHUBER J. Training very deep networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems(NIPS), December 7-12, 2015, Montreal, Canada. Cambridge, MA, USA:MIT Press, 2015:2377-2385.
[10] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 26-July 1, 2016, Las Vegas, Nevada, United States, 2016:770-778.
[11] ZHAO Minghang, KANG M, TANG Baoping, et al. Deep residual networks with dynamically weighted wavelet coefficients for fault diagnosis of planetary gearboxes[J]. IEEE Transactions on Industrial Electronics, 2018, 65(5):4290-4300.
[12] HUANG Gao, LIU Zhuang, WEINBERGER K Q, et al. Densely connected convolutional networks[C]//30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, USA 2017:2261-2269.
[13] WALNUT D. F. An introduction to wavelet analysis[M]. Boston, MA, USA:Birkhäuser, 2004.
[14] YAN Ruqiang, GAO R X, CHEN Xuefeng. Wavelets for fault diagnosis of rotary machines:A review with applications[J]. Signal Processing, 2014, 96(5):1-15.
[15] WANG Yi, XU Guanghua, LIANG Lin, et al. Detection of weak transient signals based on wavelet packet transform and manifold learning for rolling element bearing fault diagnosis[J]. Mechanical Systems & Signal Processing, 2015, 54-55:259-276.
[16] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Delving deep into rectifiers:Surpassing human-level performance on ImageNet classification[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Dec.13-16, 2015, Vis, Santiago, Chile, Washington, DC, USA:IEEE Computer Society, 2015:1026-1034.
[17] GOODFELLOW I, BENGIO Y, COURVILLE A, et al. Deep learning[M]. Cambridge:MIT Press, 2016.