基于稀疏自动编码深度神经网络的感应电动机故障诊断

doi:10.3901/JME.2016.09.065

摘要/Abstract

摘要： 针对目前感应电动机故障诊断大多采用监督学习提取故障特征的现状,提出一种将去噪编码融入稀疏自动编码器的深度神经网络,实现非监督学习的特征提取并用于感应电动机的故障诊断。稀疏自动编码器通过自动学习复杂数据的内在特征来提取简明的数据特征表达。为提高特征表达的鲁棒性,在稀疏编码器的基础上融入去噪编码,提取更有效的特征表达用来训练神经网络分类器进而完成整个深度神经网络的构建,并结合反向传播算法对深度神经网络进行整体微调,提升故障分类的准确度。整个训练过程引入“dropout”训练技巧,减少因过拟合带来的预测误差。试验结果表明,相比传统反向传播(Back propagation,BP)神经网络,提出的深度神经网络能更有效地实现感应电动机故障诊断。

关键词: dropout, 故障诊断, 去噪编码, 深度神经网络, 稀疏自动编码器

Abstract: To overcome the drawback of using supervised learning to extract fault features for classification in most of current induction motor fault diagnosis approaches, a deep neural network algorithm is presented, which is realized by the sparse auto-encoder combined with the denoising auto-encoder, to achieve unsupervised feature learning for fault diagnosis of induction motors. Sparse auto-encoder can learn the inherent features and extract the succinct expressions from complex data automatically. In addition, the method of denoising auto-encoder can increase the robustness of feature expression, thus improving the performance of the sparse auto-encoder. The extracted features can then be used to train a neural network classifier and complete the deep neural network construction. The back-propagation algorithm is used for fine-tuning the deep neural network with the purpose of improving the accuracy of fault classification. The “dropout” technique is also introduced into to the entire training process to reduce the prediction error caused by “overfitting”. Experimental results have shown that, compared with the traditional back propagation (BP) neural network, the presented deep neural network can realize induction motor fault diagnosis more effectively.

Key words: deep neural network, denoising, dropout, fault diagnosis, sparse auto-encoder

中图分类号:

TM346

孙文珺, 邵思羽, 严如强. 基于稀疏自动编码深度神经网络的感应电动机故障诊断[J]. 机械工程学报, 2016, 52(9): 65-71.

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.

参考文献

[1] EL HACHEMI BENBOUZID M. A review of induction motors signature analysis as a medium for faults detection[J]. IEEE Transactions on Industrial Electronics, 2000,47(5)：984-993.
[2] RODRIGUE P J,BELAHCEN A,ARKKIO A. Signatures of electrical faults in the force distribution and vibration pattern of induction motors[J]. IEEE Proceedings-Electric Power Applications,2006,153(4)：523-529.
[3] FILIPPETTI F,FRANCESCHINI G,TASSONI C,et al. AI techniques in induction machines diagnosis including the speed ripple effect[J]. IEEE Transactions on Industry Applications,1998,34(1)：98-108.
[4] HAJNAYEB A,GHASEMLOONIA A,KHADEM S E,et al. Application and comparison of an ANN-based feature selection method and the genetic algorithm in gearbox fault diagnosis[J]. Expert Systems with Applications,2011,38(8)：10205-10209.
[5] YOON H,PARK C,KIM J S,et al. Algorithm learning based neural network integrating feature selection and classification[J]. Expert Systems with Applications,2013, 40(1)：231-241.
[6] MALHI A,YAN R,GAO R X. Prognosis of defect propagation based on recurrent neural networks[J]. IEEE Transactions on Instrumentation and Measurement,2011, 60(3)：703-711.
[7] 袁胜发,褚福磊,何永勇. 基于网络支持向量机的涡轮泵多故障诊断[J]. 机械工程学报,2007,43(4)：152-158.
YUAN Shengfa,CHU Fulei,HE Yongyong. Multi-fault diagnosis for turbo-pump based on mesh support vector machines[J]. Chinese Journal of Mechanical Engineering,2007,43(4)：152-158.
[8] 刘贵立,张国英. 基于小波包的遗传神经网络故障诊断系统研究[J]. 机械工程学报,2000,36(9)：110-112.
LIU Guili,ZHANG Guoying. Study on genetic neural network of the fault diagnosis based on wavelet packet[J]. Chinese Journal of Mechanical Engineering,2000,36(9)：110-112.
[9] 李巍华,张盛刚. 基于改进证据理论及多神经网络融合的故障分类[J]. 机械工程学报,2010,46(9)：93-99.
LI Weihua,ZHANG Shenggang. Fault classification based on improved evidence theory and multiple neural network fusion[J]. Journal of Mechanical Engineering,2010, 46(9)：93-99.
[10] CHERIYADAT A M. Unsupervised feature learning for aerial scene classification[J]. IEEE Transactions on Geoscience & Remote Sensing,2014,52(1)：439-451.
[11] HINTON G E,SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006,313(5786)：504-507.
[12] SCHMIDHUBER J. Multi-column deep neural networks for image classification[J]. Eprint. Arxiv.,2012,157(10)： 3642-3649.
[13] KRIZHEVSKY A,SUTSKEVER I,HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems,2012,25：1106-1114.
[14] HINTON G,DENG L,YU D,et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups[J]. IEEE Signal Processing Magazine,2012,29(6)：82-97.
[15] WRIGHT J,MA Y,MAIRAL J,et al. Sparse representation for computer vision and pattern recognition [J]. Proceedings of IEEE,2010,98(6)：1031-1044.
[16] RANZATO M,BOUREAU Y L,LECUN Y. Sparse feature learning for deep belief networks[C]// Twenty-first Annual Conference on Neural Information Processing Systems, Vancouver, Canada, 2007：1185-1192.
[17] BOUREAU Y L,BACH F,LECUN Y,et al. Learning mid-level features for recognition[C]// 2010 IEEE Conference on Computer Vision and Patten Recognition, June 13-18,2010,San Francisco,CA,2010：2559-2566.
[18] SHIN H C,ORTON M R,COLLINS D J,et al. Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4D patient data[J]. IEEE Transactions on Software Engineering,2013,35(8)：1930-1943.
[19] OLSHAUSEN B A. Emergence of simple-cell receptive field properties by learning a sparse code for natural images[J]. Nature,1996,381(6583)：607-609.
[20] KULLBACK S,LEIBLER R A. On information and sufficiency[J]. Annals of Mathematical Statistics,1951,22(1)：79-86.
[21] RUMELHART D E,HINTON G E,WILLIAMS R J. Learning representations by back propagating errors[J]. Nature,1986,323(6088)：533-536.
[22] VINCENT P,LAROCHELLE H,BENGIO Y,et al. Extracting and composing robust features with denoising autoencoders[C] // Proceedings of the 25th International Conference on Machine Learning. July 5-9,2008, Helsinki,Finland, 2008：1096-1103.
[23] HINTON G E,SRIVASTAVA N,KRIZHEVSKY A,et al. Improving neural networks by preventing co-adaptation of feature detectors[J]. Research Gate,2012,3(4)：212-223.
[24] COATES A,NG A Y,LEE H. An analysis of single-layer networks in unsupervised feature learning[J]. Journal of Machine Learning Research,2011,15：215-223.
[25] JI Dou,WANG Xiangjun. Fault diagnosis of DC machine based on DS evidential theory and BP network[J]. Marine Electric & Electronic Engineering,2007,27(4)：204-206.
[26] AN Xueli,JIANG Dongxiang,LI Shaohua. Application of back propagation neural network to fault diagnosis of direct-drive wind turbine[C]// World Non-Grid-Connected Wind Power and Energy Conference,November 5-7,2010, Nanjing,China, 2010：1-5.
[27] SUN Yanjing,ZHANG Shen,MIAO Changxin, et al. Improved BP neural network for transformer fault diagnosis[J]. Journal of China University of Mining and Technology,2007,17(1)：138-142.
[28] KHASHEI M,ZEINAL H A,BIJARI M. A novel hybrid classifi-cation model of artificial neural networks and multiple linear regression models[J]. Expert Systems with Applications,2012,39(3)：2606-2620.
[29] BOUCHARD G. Clustering and classification employing softmax function including efficient bounds：US,US 8065246 B2[P]. 2011-11-22.