[设备健康管理]基于深度学习多样性特征提取与信息融合的行星齿轮箱故障诊断方法

摘要/Abstract

摘要： 针对行星齿轮箱振动信号噪声干扰大、单一分类器泛化能力不强的问题，提出了一种基于深度学习多样性特征提取与信息融合的行星齿轮箱故障诊断方法。利用多目标优化算法优化多个堆栈去噪自动编码器(SDAE)以获得多个性能优异的SDAE，并提取多样性的故障特征；采用多响应线性回归模型集成多样性故障特征实现信息融合，得到多目标集成堆栈去噪自动编码器(MO-ESDAE)，最后将其应用于行星齿轮箱故障诊断。实验结果表明：该方法能有效提高故障诊断精度与稳定性，具有较强的泛化能力。

关键词: 行星齿轮箱故障诊断, 深度神经网络, 多样性特征提取, 多目标进化算法

Abstract: According to the heavy noises of vibration signals and the difficulty of incipient fault diagnosis for planetary gearboxes using single classifier,a method of planetary gearbox fault diagnosis was proposed based on multiple feature extraction and information fusion combined with deep learning.The multiple excellent stacked denoising autoencoders(SDAEs) were acquired based on multi-objective evolutionary algorithm.Then,multi-response linear regression model was employed to integrate multiple SDAEs for building multi-obiective ensemble stacked denoising autoencoders (MO-ESDAEs),which was used to diagnose faults of planetary gearboxes.The experimental results show that the proposed method may enhance the fault diagnosis accuracy and stability.

Key words: planetary gearbox fault diagnosis, deep neural network, multiple feature extraction, multi-objective evolutionary algorithm

中图分类号:

TH17

金棋, 王友仁, 王俊. [设备健康管理]基于深度学习多样性特征提取与信息融合的行星齿轮箱故障诊断方法[J]. 中国机械工程.

JIN Qi, WANG Youren, WANG Jun. Planetary Gearbox Fault Diagnosis Based on Multiple Feature Extraction and Information Fusion Combined with Deep Learning[J]. China Mechanical Engineering.

参考文献

[1]YIP L.Analysis and Modeling of Planetary Gearbox Vibration Data for Early Fault Detection [D].Toronto:University of Toronto,2011.
[2]孙灿飞，王友仁.直升机行星传动轮系故障诊断研究进展[J].航空学报,2017,38(7):106-119.
SUN Canfei,WANG Youren.Advance in the Study on Fault Diagnosis of Helicopter Planetary Gears[J].Acta Aeronautica et Astronautica Sinica,2017,38(7):106-119.
[3]LIU W Y,ZHANG W H,HAN J G,et al． A New Windturbine Fault Diagnosis Method Based on the Local Mean Decomposition[J].Renewable Energy，2012,48(6):411-415.
[4]祝文颖,冯志鹏.基于改进经验小波变换的行星齿轮箱故障诊断[J].仪器仪表学报,2016,37(10):2193-2201.
ZHU Wenying,FENG Zhipeng.Fault Diagnosis of Planetary Gearbox Based on Improved Empirical Wavelet Transform[J].Chinese Journal of Scientific Instrument,2016,37(10):2193-2201.
[5]李永龙,邵忍平,薛腾.基于小波神经网络的齿轮系统故障诊断[J].航空动力学报,2010,25(1):234-240.
LI Yonglong,SHAO Renping,XUE Teng,et al.Gear Fault Diagnosis Based on Wavelet and Neural Network[J].Journal of Aerospace Power,2010,25(1):234-240.
[6]徐玉秀,赵晓清,杨文平,等.多参数与多测点信息融合的行星轮故障诊断[J].仪器仪表学报,2014,35(8):1789-1795.
XU Yuxiu,ZHAO Xiaoqing,YANG Wenping,et al.Planetary Gear Fault Diagnosis Based on Information Fusion of Multi-parameters and Multi-points[J].Chinese Journal of Scientific Instrument,2014,35(8):1789-1795.
[7]LEI Yaguo,JIA Feng,LIN Jing,et al.An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning towards Mechanical Big Data[J].IEEE Transactions on Industrial Electronics,2016,63(5):3137-3147.
[8]雷亚国,贾峰,周昕,等.基于深度学习理论的机械装备大数据健康监测方法[J].机械工程学报,2015,51(21):49-56.
LEI Yaguo,JIA Feng,ZHOU Xin,et al.A Deep Learning-based Method for Machinery Health Monitoring with Big Data[J]．Journal of Mechanical Engineering,2015,51(21):49-56.
[9]赵光权,葛强强,刘小勇,等.基于DBN的故障特征提取及诊断方法研究[J].仪器仪表学报,2016,37(9):1946-1953.
ZHAO Guangquan,GE Qiangqiang,LIU Xiaoyong,et al.Fault Feature Extration and Diagnosis Method Based on Deep Belief Nework[J].Chinese Journal of Scientific Instrument,2016,37(9):1946-1953.
[10]SUN Wenjun,SHAO Siyu,YAN Ruqiang.Induction Motor Fault Diagnosis Based on Deep Neural Network of Sparse Auto-encoder[J].Journal of Mechanical Engineering,2016,52(9):65-71.
[11]ZHANG Chong,SUN Jiahui,TAN K C.Deep Belief Networks Ensemble with Multi-objective Optimization for Failure Diagnosis[C]//IEEE International Conference on Systems,Man,and Cybernetics.Hong Kong,2015:32-37.
[12]LI Yongbo,YANG Yuantao,LI Guoyan,et al.A Fault Diagnosis Scheme for Planetary Gearboxes Using Modified Multi-scale Symbolic Dynamic Entropy and mRMR Feature Selection[J].Mechanical Systems & Signal Processing,2017,91:295-312.
[13]LAHIRI A,ROY A G,SHEET D,et al.Deep Neural Ensemble for Retinal Vessel Segmentation in Fundus Images towards Achieving Label-free Angiography[C]// International Conference of the IEEE Engineering in Medicine and Biology Society.Lake Buena Vista,2016:1340-1343.
[14]ZHANG Chong,LIM Pin,QIN A K,et al.Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics[J].IEEE Transactions on Neural Networks & Learning Systems,2016,28(10):2306-2318.
[15]ZHANG Q,LI H.MOEA/D:a Multi-objective Evolutionary Algorithm Based on Decomposition[J].IEEE Transactions on Evolutionary Computation,2007,11(6):712-731.
[16]TING K M,WITTEN I H.Issues in Stacked Generalization[J].Journal of Artificial Intelligence Research,2011,10(1):271-289.
[17]BENGIO Y.Learning Deep Architectures for AI[J].Foundations & Trends in Machine Learning,2009,2(1):1-127.
[18]ERHAN D,BENGIO Y,COURVILLE A,et al.Why does Unsupervised Pre-training Help Deep Learning[J].Journal of Machine Learning Research,2010,11(3):625-660.
[19]VINCENT P,LAROCHELLE H,LAJOIE I,et al.Stacked Denoising Autoencoders:Learning Useful Representations in a Deep Network with a Local Denoising Criterion[J].Journal of Machine Learning Research,2010,11(12):3371-3408.
[20]LAWSON C J,HANSON R J.Solving Least Squares Problem[M].Philadephia:SIAM Publication,1995.
[21]KHAZAEE M,AHMADI H,OMID M,et al.Classifier Fusion of Vibration and Acoustic Signals for Fault Diagnosis and Classification of Planetary Gears Based on Dempster-shafer Evidence Theory[J].Journal of Process Mechanical Engineering,2014,228(1):21-32.
[22]LIU Zhiliang,QU Jian,ZUO Ming,et al.Fault Level Diagnosis for Planetary Gearboxes Using Hybrid Kernel Feature Selection and Kernel Fisher Discriminant Analysis[J].The International Journal of Advanced Manufacturing Technology,2013,67(5/8):1217-1230.