Fault Feature Extraction of Rolling Bearing with Sparse Representation Auto-Encoder Driven by Impact Response Mechanism

doi:10.3901/JME.2023.13.175

Abstract

Abstract: Due to the interference of slipping, signal loss in non-bearing area, noise and other factors, it is hard to accurately extract the fault feature of rolling bearings. Additionally, the abstract features extracted by intelligent diagnosis methods are not interpretable. Firstly, combined the impact response mechanism and sparse representation theory, an interpretable sparse representation sparse representation Auto-Encoder network is designed, which regards the coding and decoding layer of Auto-Encoder as the solution of sparse vector and the learning of over complete dictionary respectively. Secondly, an adaptively optimization algorithm is designed based on the loss function characteristics of impact response parameters, which effectively realizing the fast global optimization of characteristic parameters. Combined with the designed sparse representation Auto-Encoder network and the rolling bearing signal features, a two-layer neural network is built to perform high-precision feature reconstruction of bearing fault signals. Finally, simulation analysis shows that the proposed method can extract impact fault feature parameters with clear physical meaning, which has high feature extraction accuracy and good anti-noise performance. Moreover, experimental signals further verify the effectiveness of the proposed method.

Key words: rolling bearing, feature extraction, Auto-Encoder, sparse representation

CLC Number:

TN911

ZHENG Chen, DING Kang, HE Guolin, LIN Huibin, JIANG Fei. Fault Feature Extraction of Rolling Bearing with Sparse Representation Auto-Encoder Driven by Impact Response Mechanism[J]. Journal of Mechanical Engineering, 2023, 59(13): 175-183.

References

[1] CHEN Zhuyun,LI Weihua. Multisensor feature fusion for fearing fault diagnosis using sparse autoencoder and deep belief network[J]. IEEE Transactions on Instrumentation and Measurement,2017,66(7):1693-1702.
[2] CHEN Zhuyun,KONSTANTINOS G,LI Weihua. Mechanical fault diagnosis using convolutional neural networks and extreme learning machine[J]. Mechanical Systems and Signal Processing,2019,133(11):1-21.
[3] 杨蕊,李宏坤,王朝阁,等. 利用FCKT以及深度自编码神经网络的滚动轴承故障智能诊断[J]. 机械工程学报,2019,55(7):65-72. YANG Rui,LI Hongkun,WANG Chaoge,et al. Intelligent fault detection for rolling element bearing based on FCKT and deep Auto-coding neural network[J]. Journal of Mechanical Engineering,2019,55(7):65-72.
[4] YANG Fangfang,LI Weihua,LI Chuan,et al. State-of-charge estimation of lithium-ion batteries based on gated recurrent neural network[J]. Energy,2019,175(5):66-75.
[5] SHAO Haidong,JIANG Hongkai,ZHAO Ke,et al. A novel tracking deep wavelet auto-encoder method for intelligent fault diagnosis of electric locomotive bearings[J]. Mechanical Systems and Signal Processing,2018,110(9):193-209.
[6] YANG Liu,CHEN Haixin. Fault diagnosis of gearbox based on RBF-PF and particle swarm optimization wavelet neural network[J]. Neural Computing and Applications,2019,31(5):4463-4478.
[7] QU Yongzhi,ZHANG Yue,HE Miao,et al. Gear pitting fault diagnosis using disentangled features from unsupervised deep learning[J]. Journal of Risk and Reliability,2019,233(5):719-730.
[8] LI Tianfu,ZHAO Zhibin,SUN Chuang,et al. Wavelet kernel net:an interpretable deep neural network for industrial intelligent diagnosis[J]. IEEE Transactions on Systems,Man,and Cybernetics:Systems, 2021,51(1):1-11.
[9] 王华庆,任帮月,宋浏阳,等. 基于终止准则改进K-SVD字典学习的稀疏表示特征增强方法[J]. 机械工程学报,2019,55(7):35-43. WANG Huaqing,REN Bangyue,SONG Liuyang,et al. Sparse representation method based on termination criteria improved K-SVD dictionary learning for feature enhancement[J]. Journal of Mechanical Engineering,2019,55(7):35-43.
[10] 吴淑明,胡海峰,赵志斌,等. 增强稀疏分解及其在叶片振动参数识别中的应用[J]. 机械工程学报,2019,55(19):19-27. WU Shuming,HU Haifeng,ZHAO Zhibin,et al. Enhancing sparse decomposition based blade vibration parameter identification[J]. Journal of Mechanical Engineering,2019,55(19):19-27.
[11] YANG Honggang,LIN Huibin,DING Kang. Sliding window denoising K-Singular value decomposition and its application on rolling bearing impact fault diagnosis[J]. Journal of Sound and Vibration,2018,421(5):205-219.
[12] KHADERSAB A,SHIVAKUMAR S. Vibration analysis techniques for rotating machinery and its effect on bearing faults[J]. Procedia Manufacturing,2018,20(2):247-252.
[13] LIN Huibin,WU Fangtan,HE Guolin. Rolling bearing fault diagnosis using impulse feature enhancement and nonconvex regularization[J]. Mechanical Systems and Signal Processing,2020,142(8):1-17.
[14] 曹宏瑞,景新,苏帅鸣,等. 中介轴承故障动力学建模与振动特征分析[J]. 机械工程学报,2020,56(21):89-99. CAO Hongrui,JING Xin,SU Shuaiming,et al. Dynamic modeling and vibration analysis for inter-shaft bearing fault[J]. Journal of Mechanical Engineering,2020,56(21):89-99.
[15] ZHANG Shen,WANG Bingnan,KANEMURA M,et al. Model-Based analysis and quantification of bearing faults in induction machines[J]. IEEE Transactions on Industry Applications,2020,56(3):2158-2170.
[16] DING Chuancang,ZHAO Ming,LIN Jing. Sparse feature extraction based on periodical convolutional sparse representation for fault detection of rotating machinery[J]. Measurement Science and Technology,2020,32(1):8-15.
[17] WANG Huaqing,REN Bangyue,SONG Liuyang,et al. A novel weighted sparse representation classification strategy based on dictionary learning for rotating machinery[J]. IEEE Transactions on Instrumentation and Measurement,2020,69(3):712-720.
[18] WANG Cong,GAN Meng,ZHU Changan. Fault feature extraction of rolling element bearings based on wavelet packet transform and sparse representation theory[J]. Journal of Intelligent Manufacturing,2018,29(4):937-951.
[19] ZHAO Zhibin,WANG Shibin,SUN Chuang,et al. Sparse multiperiod group lasso for bearing multifault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement,2020,69(2):419-431.
[20] HE Guolin,DING Kang,LIN Hhuibin. Fault feature extraction of rolling element bearings using sparse representation[J]. Journal of Sound and Vibration,2016,366(3):514-527.