Fault diagnosis of rolling bearings using least square support vector regression based on glowworm swarm optimization algorithm

被引：0

作者：

Xu, Qiang ^{[1
]}

Liu, Yong-Qian ^{[1
]}

Tian, De ^{[1
]}

Zhang, Jin-Hua ^{[1
]}

Long, Quan ^{[2
]}

机构：

[1] State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University

[2] Test and Research Institute, China Datang Corporation Renewable Power Co., Ltd.

来源：

Zhendong yu Chongji/Journal of Vibration and Shock | 2014年 / 33卷 / 10期

关键词：

Fault diagnosis; Glowworm swarm optimization algorithm; Least square support vector regression (LSSVR); Rolling bearings;

D O I：

10.13465/j.cnki.jvs.2014.10.002

中图分类号：

学科分类号：

摘要：

Fault diagnosis of rolling bearings is the key to improve equipment availability and reduce operation and maintenance cost. Least square support vector regression (LSSVR) is an effective method for fault diagnosis. Here, the glowworm swarm optimization (GSO) algorithm was applied to search the optimal combination of penalty and kernel parameters often restricted by subjective experience in LSSVR. A rolling bearing fault diagnosis method using LSSVR based on GSO was proposed. Tests showed that the presented method can be used to precisely diagnose both fault location and fault severity of rolling bearings, it has a higher accuracy compared with the normal LSSVR and BP neural network, so the reliability of the proposed method is verified.

引用

页码：8 / 12

页数：4

共 15 条

[1] pp. 1-16, (2007)
[2] Cortes C., Vapnik V., Support-vector networks, Machine Learning, 20, 3, pp. 273-297, (1995)
[3] Tang B.-P., Li F., Chen R.-X., Fault diagnosis based on Littlewood-Paley wavelet support vector machine, Journal of Vibration and Shock, 30, 1, pp. 128-131, (2011)
[4] Jiang W.-L., Niu H.-F., Liu S.-Y., Composite fault diagnosis method and its verification experiments, Journal of Vibration and Shock, 30, 6, pp. 176-180, (2011)
[5] Dong S.-J., Tang B.-P., Zhang Y., Bearing running state recognition based on non-extensive wavelet feature scale entropy and support vector machine, Journal of Vibration and Shock, 31, 15, pp. 50-54, (2012)
[6] Suykens J.A.K., Lukas L., Vandewalle J., Least squares support vector machines, Singapore: World Scientific, 2, pp. 757-760, (2002)
[7] Cui W.-Z., Zhu C.-C., Bao W.-X., Et al., Prediction of the chaotic time series using support vector machines, Acta Physica Sinica, 53, 10, pp. 3303-3310, (2005)
[8] Xu Z.-M., Wen X.-Q., Sun Y.-Y., Et al., State prediction of slagging-support vector machine for regression, Proceedings of the CSEE, 29, 17, pp. 8-13, (2009)
[9] Wei H.-Q., Niu Z.-M., Jiang W.-H., Et al., Application of LSSVR optimized by adaptive genetic algorithm at modeling igniting temperature of pulverized-coal, Journal of Combustion Science and Technology, 17, 3, pp. 191-195, (2011)
[10] Liu S.-Y., Xu L.-Q., Li D.-L., Et al., Dissolved oxygen prediction model of eriocheir sinensis culture based on least squares support vector regression optimized by ant colony algorithm, Transactions of the Chinese Society of Agriculture Engineering, 28, 23, pp. 167-175, (2012)

← 1 2 →