Multichannel Information Fusion and Deep Transfer Learning for Rotating Machinery Fault Diagnosis

doi:10.3969/j.issn.1004-132X.2023.08.011

Abstract

Abstract: To address the problems of inadequate information on the characteristics of single channel signals， a rotating machinery fault diagnosis method of multichannel information fusion and deep transfer learning approach was proposed. Firstly， the one-dimensional signals collected by multi-sensors were used to generate separate time-frequency maps by wavelet transforms. Then， the information of the maps was fused into multi-channel images. Finally， the pre-trained deep residual network， as a transfer model， was used for fault diagnosis of the rotating machinery. The identification accuracy of the tests on the cylindrical roller bearing， locomotive bearing， and gearbox datasets of a bureau of locomotive section is as 99.23%， 99.78%， and 99.50% respectively； and the identification accuracy of the cross-service transfer tests on the Case Western Reserve University bearing dataset is as 93.12%， which indicates the superiority and scalability of the proposed method.

Key words: fault diagnosis, rotating machinery, multichannel information fusion, deep transfer learning

摘要： 针对单通道信号特征信息不充分的问题，提出了一种多通道信息融合与深度迁移学习的旋转机械故障诊断方法。首先使用小波变换将多传感器采集的一维信号生成多幅时频图，然后将时频图信息融合为多通道图像，最后将预训练的深度残差网络作为迁移模型对旋转机械进行故障诊断。圆柱滚子轴承、某局机务段机车轴承和齿轮箱数据集的识别准确率分别为99.23%、99.78%和99.50%，凯斯西储大学轴承数据集的跨工况迁移试验识别准确率达93.12%，这表明所提方法具有一定的优越性和可扩展性。

关键词: 故障诊断, 旋转机械, 多通道信息融合, 深度迁移学习

CLC Number:

TH13
TH17

ZHANG Long, HU Yanqing, ZHAO Lijuan, ZHANG Hao. Multichannel Information Fusion and Deep Transfer Learning for Rotating Machinery Fault Diagnosis[J]. China Mechanical Engineering, 2023, 34(08): 966-975.

张龙, 胡燕青, 赵丽娟, 张号. 多通道信息融合与深度迁移学习的旋转机械故障诊断[J]. 中国机械工程, 2023, 34(08): 966-975.

References

［1］张龙，甄灿壮，易剑昱，等. 双通道特征融合CNN-GRU齿轮箱故障诊断［J］. 振动与冲击， 2021， 40（19）：239-245.
ZHANG Long， ZHEN Canzhuang， YI Jianyu， et al. Dual-channel Feature Fusion CNN-GRU Gearbox Fault Diagnosis［J］. Journal of Vibration and Shock， 2021， 40（19）：239-245.
［2］周奇才，刘星辰，赵炯，等. 旋转机械一维深度卷积神经网络故障诊断研究［J］. 振动与冲击， 2018， 37（23）：31-37.
ZHOU Qicai， LIU Xingchen， ZHAO Jiong， et al. Fault Diagnosis for Rotating Machinery Based on 1D Depth Convolutional Neural Network［J］. Journal of Vibration and Shock， 2018， 37（23）：39-45.
［2］CHEN S， GE H， LI H， et al. Hierarchical Deep Convolution Neural Networks Based on Transfer Learning for Transformer Rectifier Unit Fault Diagnosis［J］. Measurement， 2021， 167：108257.
［4］LI F， TANG T， TANG B， et al. Deep Convolution Domain-adversarial Transfer Learning for Fault Diagnosis of Rolling Bearings［J］. Measurement， 2021， 169：108339.
［5］QIAN C， ZHU J， SHEN Y， et al. Deep Transfer Learning in Mechanical Intelligent Fault Diagnosis：Application and Challenge［J］. Neural Processing Letters， 2022， 54（3）：2509-2531.
［6］SEGEV N， HAREL M， MANNOR S， et al. Learn on Source， Refine on Target：a Model Transfer Learning Framework with Random Forests［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2016， 39（9）：1811-1824.
［7］ZHANG R， TAO H， WU L， et al. Transfer Learning with Neural Networks for Bearing Fault Diagnosis in Changing Working Conditions［J］. IEEE Access， 2017， 5：14347-14357.
［8］陈仁祥，杨星，胡小林，等. 深度置信网络迁移学习的行星齿轮箱故障诊断方法［J］. 振动与冲击， 2021， 40（1）：127-133.
CHEN Renxiang， YANG Xing， HU Xiaolin， et al. Planetary Gearbox Fault Diagnosis Method Based on Deep Belief Network Transfer Learning［J］. Journal of Vibration and Shock， 2021， 40（1）：127-133.
［9］SHAO S， MCALEER S， YAN R， et al. Highly Accurate Machine Fault Diagnosis Using Deep Transfer Learning［J］. IEEE Transactions on Industrial Informatics， 2019， 15（4）：2446-2455.
［10］刘飞，陈仁文，邢凯玲，等. 基于迁移学习与深度残差网络的滚动轴承快速故障诊断算法［J］. 振动与冲击， 2022， 41（3）：154-164.
LIU Fei， CHEN Renwen， XING Kailing， et al. Fast Fault Diagnosis Algorithm for Rolling Bearing Based on Transfer Learning and Deep Residual Network［J］. Journal of Vibration and Shock， 2022， 41（3）：154-164.
［11］SHE D， JIA M. Wear Indicator Construction of Rolling Bearings Based on Multi-channel Deep Convolutional Neural Network with Exponentially Decaying Learning Rate［J］. Measurement， 2019， 135：368-375.
［12］CHE C， WANG H， NI X， et al. Domain Adaptive Deep Belief Network for Rolling Bearing Fault Diagnosis［J］. Computers & Industrial Engineering， 2020， 143：106427.
［13］SOUZA R M， NASCIMENTO E G S， MIRANDA U A， et al. Deep Learning for Diagnosis and Classification of Faults in Industrial Rotating Machinery［J］. Computers & Industrial Engineering， 2021， 153：107060.
［14］PAN S J， YANG Q. A Survey on Transfer Learning［J］. IEEE Transactions on Knowledge and Data Engineering， 2009， 22（10）：1345-1359.
［15］GE W， YU Y. Borrowing Treasures from the Wealthy：Deep Transfer Learning through Selective Joint Fine-tuning［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2018， 40（8）：1924-1937
［16］KUMAR A， ZHOU Y， GANDHI C P， et al. Bearing Defect Size Assessment Using Wavelet Transform Based Deep Convolutional Neural Network（DCNN）［J］. Alexandria Engineering Journal， 2020， 59（2）：999-1012.
［17］张龙，甄灿壮，熊国良，等. 基于深度时频特征的机车轴承故障诊断［J］. 交通运输工程学报， 2021， 21（6）：247-258.
ZHANG Long， ZHEN Canzhuang， XIONG Guoliang， et al. Locomotive Bearing Fault Diagnosis Based on Deep Time-frequency Features［J］. Journal of Traffic and Transportation Engineering， 2021， 21（6）：247-258.
［18］HE J， YANG S， PAPATHEOU E， et al. Investigation of a Multi-sensor Data Fusion Technique for the Fault Diagnosis of Gearboxes［J］. Proceedings of the Institution of Mechanical Engineers， Part C：Journal of Mechanical Engineering Science， 2019， 233（13）：4764-4775.
［19］徐敬领，霍家庆，宋连腾，等. 基于测井数据的米氏旋回分析及浮动天文年代标尺的建立［J］. 地球物理学报， 2022， 65（7）：2766-2778.
XU Jingling， HUO Jiaqing， SONG Lianteng， et al. Analysis of Milankovitch Cycles and Establishment of Floating Astronomical Date Scale Based on Well-logging Data［J］. Chinese Journal of Geophysics， 2022， 65（7）：2766-2778.
［20］唐云冰，高德平，罗贵火. 滚动轴承非线性轴承力及其对轴承系统振动特性的影响［J］. 航空动力学报， 2006， 21（2）：366-373.
TANG Yunbing， GAO Deping， LUO Guihuo. Nonlinear Bearing Force of the Rolling Ball Bearing and Its Influence on Vibration of Bearing System［J］. Journal of Aerospace Power， 2006， 21（2）：366-373.
［21］刘畅. 非稳态条件下滚动轴承故障诊断及退化识别技术研究［D］. 徐州：中国矿业大学， 2021.
LIU Chang. Study on Fault Diagnosis and Degradation Identification Technology of Rolling Bearing under Unsteady Condition［D］. Xuzhou：China University of Mining and Technology， 2021.

[1]	LUO Ji-Sai, XU De-Ge, SHI Mei-Li. Gearbox Fault Diagnosis with Rotating Speed Fluctuation Based on SVD and Chirplet Path Pursuit Algorithm [J]. J4, 201016, 21(16): 1947-1951.
[2]	ZHANG Xi-Ning, DIAO Meng, WEN An-Rui. A Multi-objective Optimization Method for Holo-balancing Weights of Rotor Set [J]. J4, 201016, 21(16): 1974-1977.
[3]	QIN Guohao, ZHANG Kai, DING Kun, HUANG Fengfei, ZHENG Qing, DING Guofu, . Dynamic Wide Convolutional Residual Network for Bearing Fault Diagnosis Method [J]. China Mechanical Engineering, 2023, 34(18): 2212-2221.
[4]	LI Xin, CHENG Junsheng, WU Xiaowei, WANG Jian, YANG Yu, . Early Weak Fault Detection Method of Gear Rotating Machinery by Combining SPCA and OCHD [J]. China Mechanical Engineering, 2023, 34(15): 1805-1812.
[5]	DONG Shaojiang, ZHOU Cunfang, CHEN Lili, XU Xiangyang. Cross-domain Fault Diagnosis of Bearings Based on Discriminant Feature Extraction and Dual-domain Alignment [J]. China Mechanical Engineering, 2023, 34(15): 1856-1863.
[6]	MENG Kang, TENG Wei, PENG Dikang, XIANG Ling, LIU Yibing. Operating Mechanism and Data Driven Approach for Fault Alarm of Wind Turbine Gearbox Systems [J]. China Mechanical Engineering, 2023, 34(12): 1476-1485.
[7]	ZHENG Jinde, CHEN Yan, TONG Jinyu, PAN Haiyang. RGCMvMRDE and Its Applications in Rolling Bearing Fault Diagnosis [J]. China Mechanical Engineering, 2023, 34(11): 1315-1325.
[8]	ZHANG Long, ZHANG Hao, WANG Chaobing, WANG Xiaobo, WEN Peitian, ZHAO Lijuan. Explicit Dynamics Driving Fault Diagnosis Method for Bearing Variable Conditions [J]. China Mechanical Engineering, 2023, 34(08): 982-992.
[9]	DONG Shaojiang, ZHU Peng, ZHU Sunke, LIU Lanhui, XING Bin, HU Xiaolin. Fault Diagnosis Method of Rolling Bearings Based on Simulation Data Drive and Domain Adaptation [J]. China Mechanical Engineering, 2023, 34(06): 694-702.
[10]	LI Dongyang, YUAN Dongfeng, ZHANG Haixia, ZHENG Anzhu, DI Zijun, LIANG Daojun, . Research on Intelligent Tool Fault Diagnosis System of Machine Tools with Cloud-Edge-Device Collaboration [J]. China Mechanical Engineering, 2023, 34(05): 584-594.
[11]	ZHAO Jing, YANG Shaopu, LI Qiang, LIU Yongqiang, . A New Transfer Learning Method with Residual Attention and Its Applications on Rolling Bearing Fault Diagnosis [J]. China Mechanical Engineering, 2023, 34(03): 332-343.
[12]	ZHAO Yike, WANG Jiaxu, ZHANG Xin, WU Lei, LIU Zhiwen. Aero-engine Fault Diagnosis Based on an Enhanced Minimum Entropy Deconvolution [J]. China Mechanical Engineering, 2023, 34(02): 193-200.
[13]	LI Ke, , YAN Han, GU Jiefei, , SU Lei, SU Wensheng, XUE Zhigang. Research on Multi-source Transfer Learning Bearing Fault Diagnosis Based on Shapelets Time Series [J]. China Mechanical Engineering, 2022, 33(24): 2990-2996,3006.
[14]	GUO Wei, XING Xiaosong. Intelligent Fault Diagnosis of Bearings with Few Samples Based on an Improved Convolutional Generative Adversarial Network [J]. China Mechanical Engineering, 2022, 33(19): 2347-2355.
[15]	WU Lei, WANG Jiaxu, ZHANG Xin, LIU Zhiwen. Blind Deconvolution Based on Reweighted-kurtosis Maximization for Wind Turbine Fault Diagnosis [J]. China Mechanical Engineering, 2022, 33(19): 2356-2363.