Gearbox Fault Diagnosis Research Based on Morphological Hat Product Convolutional Autoencoder

doi:10.3901/JME.2023.23.132

Abstract

Abstract: In the early stage of equipment fault, the fault signal is mixed with various noises and invalid information, and it is difficult to extract weak fault signal characteristics. In order to solve this problem, a Morphological Hat Product-Convolutional Auto Encoder (MHP-CAE) model is proposed for fault feature information extraction and recognition of mechanical equipment. Firstly, the morphological filter hat product operation is embedded in the convolutional autoencoder as one of the network layers to extract and identify the fault characteristics of the gearbox. In order to overcome the defects of incomplete and inaccurate signal processing using single-scale morphological analysis, multi-scale morphological cap product operation is adopted, in which morphological cap product is mainly used to extract pulse characteristics in fault signals. The kurtosis-based method is used to fuse the pulse components contained in the features extracted by morphological operators of different scales. Then the residual learning is further used to connect the encoder and decoder to obtain good fault feature learning performance. The effectiveness of the method is verified by a gearbox fault diagnosis example. The gearbox fault diagnosis experiments in single and multiple working conditions show that MHP-CAE can perform noise reduction and feature learning of vibration signals in an unsupervised learning manner. The model has good denoising and feature learning performance. Its feature extraction effect is better than some of the latest deep neural networks.

Key words: gearbox, fault diagnosis, morphological cap product operation, convolutional autoencoder, residual learning

CLC Number:

TH132

HUANG Jiahuan, YU Jianbo. Gearbox Fault Diagnosis Research Based on Morphological Hat Product Convolutional Autoencoder[J]. Journal of Mechanical Engineering, 2023, 59(23): 132-145.

References

[1] LUO Yingchao，CUI Lingli，MA Jianfeng. An improved phenomenological model of the planetary gearbox based on meshing vibration characteristics[J]. IEEE Access，2020，99:103462-103475.
[2] 万书亭，彭勃，王晓龙. 基于双时域变换和稀疏编码收缩的滚动轴承早期故障诊断方法[J]. 中国机械工程，2020，31(23):2829-2836. WAN Shuting，PENG Bo，WANG Xiaolong. Early fault diagnosis method of rolling bearing based on dual time domain transformation and sparse coding shrinkage [J]. Mechanical Engineering，2020，31(23):2829-2836.
[3] LI Yongbo，LI Guoyan，WEI Yu，et al. Health condition identification of planetary gearboxes based on variational mode decomposition and generalized composite multi-scale symbolic dynamic entropy[J]. ISA Transactions，2018，81:329-341.
[4] ZHAO Rui，YAN Ruqiang，CHEN Zhenghua， et al. Deep learning and its applications to machine health monitoring[J]. Mechanical Systems and Signal Processing，2019，115:213-237.
[5] LEI Yaguo. 4-Clustering algorithm-based fault diagnosis[J]. Intelligent Fault Diagnosis & Remaining Useful Life Prediction of Rotating Machinery，2017:175-229.
[6] EBERSBACH S，PENG Z. Expert system development for vibration analysis in machine condition monitoring[J]. Expert Systems with Applications，2008，34(1):291-299.
[7] PRAVEEN K T，SAIMURUGAN M，KRISHNAKUMAR P，et al. Fault diagnosis of automobile gearbox based on machine learning techniques[J]. Procedia Engineering，2014，97:2092-2098.
[8] CHEN Zhiqiang，DENG Shengcai，CHEN Xudong，et al. Deep neural networks-based rolling bearing fault diagnosis[J]. Microelectronics Reliability，2017，75:327-333.
[9] WU Chunzhi，JIANG Pengcheng，DING Chuang，et al. Intelligent fault diagnosis of rotating machinery based on one-dimensional convolutional neural network[J]. Computers in Industry，2019108:53-61.
[10] ABDELJABER O，AVCI O，KIRANYAZ S，et al. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks[J]. Journal of Sound and Vibration，2017，388:154-170.
[11] PLAKIAS S，BOUTALIS Y S. Fault detection and identification of rolling element bearings with attentive dense CNN[J]. Neurocomputing，2020，405:208-217.
[12] QIN Na，LIANG Kaiwe，HUANG Deqing，et al. Multiple convolutional recurrent neural networks for fault identification and performance degradation evaluation of high-speed train bogie[J]. IEEE Transactions on Neural Networks and Learning Systems，2020，31(12):5363-5376.
[13] HE Kaiming，ZHANG Xiangyu，REN Shaoqing， et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition，2016，770-778.
[14] LI Xueyi，LI Jialin，ZHAO Chenyang，et al. Gear pitting fault diagnosis with mixed operating conditions based on adaptive 1D separable convolution with residual connection[J]. Mechanical Systems and Signal Processing，2020，142:106740.
[15] WANG Huaqing， LI Shisong， SONG Liuyang， et al. A novel convolutional neural network-based fault recognition method via image fusion of multi-vibration-signal[J]. Computers in Industry，2019，105:182-190.
[16] WU Chunzhi，JIANG Pengcheng，DING Chuang，et al. Intelligent fault diagnosis of rotating machinery based on one-dimensional convolutional neural network[J]. Computers in Industry. 2019，108:53-61.
[17] MA Sai，CHU Fulei，HAN Qinkai. Deep residual learning with demodulated time-frequency features for fault diagnosis of planetary gearbox under nonstationary running conditions[J]. Mechanical Systems and Signal Processing，2019，127:190-201.
[18] QIAN Quan，QIN Yi，WANG Yi，et al. A new deep transfer learning network based on convolutional auto-encoder for mechanical fault diagnosis[J]. Measurement，2021，178:109352.
[19] MAO Wentao，FENG Wushi，LIU Yamin，et al. A new deep auto-encoder method with fusing discriminant information for bearing fault diagnosis[J]. Mechanical Systems and Signal Processing，2021，150:107233.
[20] YU Jianbo，ZHOU Xingkang. One-dimensional residual convolutional autoencoder based feature learning for gearbox fault diagnosis[J]. IEEE Transactions on Industrial Informatics， 2020，16(10):6347-6358.
[21] 陈超宇，陈磊，张旺，等. 全矢深度学习在轴承故障诊断中的应用[J]. 机械传动，2019，43(1):150-155. CHEN Chaoyu，CHEN Lei，ZHANG Wang，et al. Application of full vector deep learning in bearing fault diagnosis [J]. Mechanical transmission，2019，43(1):150-155.
[22] 巩晓赟. 基于全矢谱的非平稳故障诊断关键技术研究[D]. 郑州:郑州大学， 2013. GONG Xiaoyun. Research on key techniques of non-stationary fault diagnosis based on full vector spectrum [D]. Zhengzhou:Zhengzhou University，2013.
[23] LV Feiya， WEN Chenglin，BAO Zejing， et al. Fault diagnosis based on deep learning [C]//American Control Conference. IEEE, 2016.
[24] YU Jianbo， HUANG Jiahuan， LIU Changhui， et al. Fault feature of gearbox vibration signals based on morphological filter dynamic convolution autoencoder[J]. IEEE Sensors Journal，2022，22(23):22931-22942.
[25] GONG Tingkai，YUAN Xiaohui，LEI Xiaohui， et al. Fault detection for rolling element bearing based on repeated single-scale morphology and simplified sensitive factor algorithm[J]. Measurement，2018，127:348-355.
[26] YE Zhuang，YU Jianbo. Deep morphological convolutional network for feature learning of vibration signals and its applications to gearbox fault diagnosis[J]. Mechanical Systems and Signal Processing，2021， 161(5):107984.
[27] WANG Bing，HU Xiong，LI Hongru. Rolling bearing performance degradation condition recognition based on mathematical morphological fractal dimension and fuzzy C-means[J]. Measurement，2017，109:1-8.
[28] 章立军，杨德斌，徐金梧，等. 基于数学形态滤波的齿轮故障特征提取方法[J]. 机械工程学报，2007，43(2):71-75. ZHANG Lijun，YANG Debin，XU Jinwu，et al. Gear fault feature extraction method based on mathematical morphological filtering[J]. Journal of Mechanical Engineering，2007，43(2):71-75.
[29] 苗宝权，陈长征，罗园庆，等. 基于自适应增强差分积形态滤波器的滚动轴承故障特征提取方法[J]. 机械工程学报，2021，57(9):78-88. MIAO Baoquan，CHEN Changzheng，LUO Yuanqing，et al. An adaptive augmented differential product morphology filter-based rolling bearing fault feature extraction method[J]. Journal of Mechanical Engineering， 2021，57(09):78-88.
[30] NIKOLAOU N G，ANTONIADIS I A. Application of morphological operators as envelope extractors for impulsive-type period signals[J]. Mechanical Systems and Signal Processing，2003，17(6):1147-1162.
[31] 袁非牛，章琳，史劲亭，等. 自编码神经网络理论及应用综述[J]. 计算机学报，2019，42(1):28. YUAN Feiniu，ZHANG Lin，SHI Jinting，et al. Overview of theory and application of self-encoding neural networks[J]. Journal of Computer Science，2019，42(1):28.
[32] YAN Xiaoan，JIA Minping. Fault detection for rolling element bearing using an enhanced morphological-hat product filtering method[C]. IOP Conference Series:Materials Science and Engineering， 2018， 394(3):032066.
[33] 周兴康，余建波. 基于深度一维残差卷积自编码网络的齿轮箱故障诊断[J]. 机械工程学报，2020，56(7):96-108. ZHOU Xingkang，YU Jianbo. Gearbox fault diagnosis based on deep one-dimensional residual convolutional autoencoder network[J]. Journal of Mechanical Engineering，2020，56(7):96-108.
[34] LI Xueyi，LI Jialin，ZHAO Chengying，et al. Gear pitting fault diagnosis with mixed operating conditions based on adaptive 1D separable convolution with residual connection[J]. Mechanical Systems and Signal Processing，2020，142:106740.