Rolling bearing fault diagnosis based on DBN algorithm improved with PSO

PDF(1540 KB)

Journal of Vibration and Shock ›› 2020, Vol. 39 ›› Issue (5) : 89-96.

LI Yibing1,2,WANG Lei1,2, JIANG Li1,2

Author information +

History +

Abstract

Aiming at the problem of debugging network layer structure being time-consuming during deep belief network (DBN) being applied in bearing fault diagnosis, the DBN algorithm improved with particle swarm optimization (PSO) and the bearing fault diagnosis model based on the DBN algorithm improved with PSO were proposed.In the proposed model, PSO algorithm was used to optimize DBN network structure, and the adaptive time instant estimation algorithm was used to finely tune the model parameters.Then, the DBN model with the optimal structure was used to extract low-dimensional fault features in the original vibration signals.The extracted fault features were input into a Soft-max classifier to identify bearing fault modes.The results using the proposed model were compared with those using SVM, BP neutral network, DBN and stacked de-noising auto-encoders, respectively.The comparison results showed that the DBN algorithm improved with PSO has higher accuracy and better robustness.

Key words

deep belief network (DBN) / particle swarm optimization (PSO) / adaptive moment estimation / rolling bearing / fault diagnosis

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LI Yibing1,2,WANG Lei1,2, JIANG Li1,2. Rolling bearing fault diagnosis based on DBN algorithm improved with PSO[J]. Journal of Vibration and Shock, 2020, 39(5): 89-96

References

[1] S. Nandi, H. A. Toliyat, X. Li. Condition Monitoring and Fault Diagnosis of Electrical Motors—a Review[J]. IEEE Transactions on Energy Conversion, 2005, 20（4）：719-729
[2] Hinton G E, Salakhutdinov R R. Reducing the Dimensionality of Data with Neural Networks.[J]. Science (New York, N.Y.), 2006, 313（5786）
[3] Geoffrey E. Hinton, Simon Osindero, Yee-Whye Teh. A Fast Learning Algorithm for Deep Belief Nets[J], 2006, 18（7）：1527-1554
[4] Su L., C. M. Yeh C., Y. Liu J.et al. A Systematic Evaluation of the Bag-of-Frames Representation for Music Information Retrieval[J]. IEEE Transactions on Multimedia, 2014, 16（5）：1188-1200
[5] Jaitly N, Nguyen P, Senior A, et al. Application of pretrained deep neural networks to large vocabulary speech recognition[C]//Thirteenth Annual Conference of the International Speech Communication Association. 2012.
[6] M. Schmidt E., E. Kim Y. Learning Emotion-Based Acoustic Features with Deep Belief Networks[M], 2011. 65-68
[7] Dongying Han, Na Zhao, Peiming Shi. A New Fault Diagnosis Method Based On Deep Belief Network and Support Vector Machine with Teager–Kaiser Energy Operator for Bearings[J], 2017, 9（12）
[8] Prasanna Tamilselvan, Pingfeng Wang. Failure Diagnosis Using Deep Belief Learning Based Health State Classification[J]. Reliability Engineering & System Safety, 2013, 115：124-135
[9] 李巍华，单外平，曾雪琼. 基于深度信念网络的轴承故障分类识别[J]. 振动工程学报，2016（02）：340-347
Li W H, Shan W P, Zeng X Q. Bearing fault identification based on deep belief network[J]. J of Vibration Engineering, 2016, 29(02): 340-347
[10] 李军亮，滕克难，夏菲. 基于深度学习的军用飞机部件状态参数预测[J]. 振动与冲击，2018（06）：61-67
Li Junliang;TENG Ke’nan;XIA Fei al. Military aircraft components state parameters prediction using the deep belief learning[J]. Journal of Vibration and Shock, 2018（06）：61-67
[11] Haidong Shao, Hongkai Jiang, Haizhou Zhanget al. Electric Locomotive Bearing Fault Diagnosis Using a Novel Convolutional Deep Belief Network[J]. IEEE Transactions on Industrial Electronics, 2018, 65（3）：2727-2736
[12] 郭亮，高宏力，张一文等. 基于深度学习理论的轴承状态识别研究[J]. 振动与冲击，2016（12）：166-170
GUO Liang，GAO Hongli，ZHANG Yiwen，et al． Research
on bearing condition monitoring based on deep learning［J］．
Journal of Vibration and Shock，2016，35( 12) : 166-170
[13] Van Tung Tran, Faisal AlThobiani, Andrew Ball. An Approach to Fault Diagnosis of Reciprocating Compressor Valves Using Teager–Kaiser Energy Operator and Deep Belief Networks[J]. Expert Systems with Applications, 2014, 41（9）：4113-4122
[14] Nair V, Hinton G E. Rectified linear units improve restricted boltzmann machines[C]//Proceedings of the 27th international conference on machine learning (ICML-10). 2010: 807-814.
[15] Yushi Chen, Zhouhan Lin, Xing Zhaoet al. Deep Learning-Based Classification of Hyperspectral Data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7（6）：2094-2107
[16] Diederik P. Kingma, Jimmy Ba. Adam: A Method for Stochastic Optimization[J]. arXiv preprint arXiv:1412.6980, 2014
[17] Ruslan Salakhutdinov, Iain Murray. On the Quantitative Analysis of Deep Belief Networks[M]. Helsinki, Finland: ACM, 2008. 872-879
[18] Mark Braverman. Poly-Logarithmic Independence Fools Bounded-Depth Boolean Circuits[J]. Commun. ACM, 2011, 54（4）：108-115
[19] Sebastian Ruder. An Overview of Gradient Descent Optimization Algorithms[J]. Ruder S. An overview of gradient descent optimization algorithms[J]. arXiv preprint arXiv:1609.04747, 2016., 2016
[20] N. Le Roux, Y. Bengio. Representational Power of Restricted Boltzmann Machines and Deep Belief Networks[J]. Neural Comput, 2008, 20（6）：1631-1649
[21] Yoshua Bengio Jérôme Louradour Hugo Larochelle. Exploring Strategies for Training Deep Neural Networks[J]. Journal of Machine Learning Research, 2009：10-11
[22] Eberhart R., Kennedy J. A New Optimizer Using Particle Swarm Theory[M], 1995. 39-43
[23] Ioan Cristian Trelea. The Particle Swarm Optimization Algorithm: Convergence Analysis and Parameter Selection[J]. Information Processing Letters, 2003, 85（6）：317-325
[24] Yuhui Shi, Russell C. Eberhart. Parameter Selection in Particle Swarm Optimization[M]. Berlin, Heidelberg: Springer Berlin Heidelberg, 1998. 591-600
[25] Loparo K. A. Bearings Vibration Data Set[Db/Ol][J]. Cleveland, Ohio:Case Western Reserve University, 2014：