Rolling bearing fault diagnosis using an optimization deep belief network

被引:801
作者
Shao, Haidong [1 ]
Jiang, Hongkai [1 ]
Zhang, Xun [1 ]
Niu, Maogui [1 ]
机构
[1] Northwestern Polytech Univ, Sch Aeronaut, Xian 710072, Shaanxi, Peoples R China
基金
中国国家自然科学基金;
关键词
optimization DBN; rolling bearing; fault diagnosis; stochastic gradient descent; particle swarm;
D O I
10.1088/0957-0233/26/11/115002
中图分类号
T [工业技术];
学科分类号
120111 [工业工程];
摘要
The vibration signals measured from a rolling bearing are usually affected by the variable operating conditions and background noise which lead to the diversity and complexity of the vibration signal characteristics, and it is a challenge to effectively identify the rolling bearing faults from such vibration signals with no further fault information. In this paper, a novel optimization deep belief network (DBN) is proposed for rolling bearing fault diagnosis. Stochastic gradient descent is used to efficiently fine-tune all the connection weights after the pre-training of restricted Boltzmann machines (RBMs) based on the energy functions, and the classification accuracy of the DBN is improved. Particle swarm is further used to decide the optimal structure of the trained DBN, and the optimization DBN is designed. The proposed method is applied to analyze the simulation signal and experimental signal of a rolling bearing. The results confirm that the proposed method is more accurate and robust than other intelligent methods.
引用
收藏
页数:17
相关论文
共 34 条
[1]
Bagging schemes on the presence of class noise in classification [J].
Abellan, Joaquin ;
Masegosa, Andres R. .
EXPERT SYSTEMS WITH APPLICATIONS, 2012, 39 (08) :6827-6837
[2]
Unsupervised Clustering for Fault Diagnosis in Nuclear Power Plant Components [J].
Baraldi, Piero ;
Di Maio, Francesco ;
Zio, Enrico .
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2013, 6 (04) :764-777
[3]
Bengio Yoshua, 2006, Advances in Neural Information Processing Systems 19, V19, P153
[4]
[5]
A demodulating approach based on local mean decomposition and its applications in mechanical fault diagnosis [J].
Chen, Baojia ;
He, Zhengjia ;
Chen, Xuefeng ;
Cao, Hongrui ;
Cai, Gaigai ;
Zi, Yanyang .
MEASUREMENT SCIENCE AND TECHNOLOGY, 2011, 22 (05)
[6]
Application and comparison of an ANN-based feature selection method and the genetic algorithm in gearbox fault diagnosis [J].
Hajnayeb, A. ;
Ghasemloonia, A. ;
Khadem, S. E. ;
Moradi, M. H. .
EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (08) :10205-10209
[7]
Application of support vector machine based on pattern spectrum entropy in fault diagnostics of rolling element bearings [J].
Hao, Rujiang ;
Peng, Zhike ;
Feng, Zhipeng ;
Chu, Fulei .
MEASUREMENT SCIENCE AND TECHNOLOGY, 2011, 22 (04)
[8]
Hinton G., 2010, Neural Networks: Tricks of the Trade, V9, P926, DOI [10.1007/978-3-642-35289-8_32, DOI 10.1007/978-3-642-35289-8_32]
[9]
Reducing the dimensionality of data with neural networks [J].
Hinton, G. E. ;
Salakhutdinov, R. R. .
SCIENCE, 2006, 313 (5786) :504-507
[10]
Training products of experts by minimizing contrastive divergence [J].
Hinton, GE .
NEURAL COMPUTATION, 2002, 14 (08) :1771-1800