Convolutional Discriminative Feature Learning for Induction Motor Fault Diagnosis

被引:257
作者
Sun, Wenjun [1 ]
Zhao, Rui [2 ]
Yan, Ruqiang [1 ]
Shao, Siyu [1 ]
Chen, Xuefeng [3 ]
机构
[1] Southeast Univ, Sch Instrument Sci & Engn, Nanjing 210096, Jiangsu, Peoples R China
[2] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore 639798, Singapore
[3] Xi An Jiao Tong Univ, Xian 710049, Peoples R China
基金
中国国家自然科学基金;
关键词
Convolutional pooling architecture; discriminative learning; fault diagnosis; support vector machine (SVM); FEATURE-EXTRACTION; WAVELET TRANSFORM; NEURAL-NETWORKS; PATTERN; CLASSIFICATION; ALGORITHM;
D O I
10.1109/TII.2017.2672988
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A convolutional discriminative feature learning method is presented for induction motor fault diagnosis. The approach firstly utilizes back-propagation (BP)-based neural network to learn local filters capturing discriminative information. Then, a feed-forward convolutional pooling architecture is built to extract final features through these local filters. Due to the discriminative learning of BP-based neural network, the learned local filters can discover potential discriminative patterns. Also, the convolutional pooling architecture is able to derive invariant and robust features. Therefore, the proposed method can learn robust and discriminative representation from the raw sensory data of induction motors in an efficient and automatic way. Finally, the learned representations are fed into support vector machine classifier to identify six different fault conditions. Experiments performed on a machine fault simulator indicate that compared with the current state-of-the-art methods, the proposed method shows significant performance gains, and it is effective and efficient for induction motor fault diagnosis.
引用
收藏
页码:1350 / 1359
页数:10
相关论文
共 44 条
[11]   AI techniques in induction machines diagnosis including the speed ripple effect [J].
Filippetti, F ;
Franceschini, G ;
Tassoni, C ;
Vas, P .
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 1998, 34 (01) :98-108
[13]  
Gan Z, 2015, JMLR WORKSH CONF PRO, V38, P268
[14]   THE MEANING AND USE OF THE AREA UNDER A RECEIVER OPERATING CHARACTERISTIC (ROC) CURVE [J].
HANLEY, JA ;
MCNEIL, BJ .
RADIOLOGY, 1982, 143 (01) :29-36
[15]   Online diagnosis of induction motors using MCSA [J].
Jung, Jee-Hoon ;
Lee, Jong-Jae ;
Kwon, Bong-Hwan .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2006, 53 (06) :1842-1852
[16]   An efficient k-means clustering algorithm:: Analysis and implementation [J].
Kanungo, T ;
Mount, DM ;
Netanyahu, NS ;
Piatko, CD ;
Silverman, R ;
Wu, AY .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (07) :881-892
[17]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90
[18]  
LeCun Y, 1995, The handbook of brain theory and neural networks, V3361, P1995, DOI [DOI 10.5555/303568.303704, 10.5555/303568.303704]
[19]   An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data [J].
Lei, Yaguo ;
Jia, Feng ;
Lin, Jing ;
Xing, Saibo ;
Ding, Steven X. .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2016, 63 (05) :3137-3147
[20]   A review on empirical mode decomposition in fault diagnosis of rotating machinery [J].
Lei, Yaguo ;
Lin, Jing ;
He, Zhengjia ;
Zuo, Ming J. .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2013, 35 (1-2) :108-126