Degradation trend prediction of rolling bearing based on Weibull distribution and least squares support vector machine

PDF(1441 KB)

Journal of Vibration and Shock ›› 2014, Vol. 33 ›› Issue (20) : 52-56.

论文

Degradation trend prediction of rolling bearing based on Weibull distribution and least squares support vector machine

CHEN Chang，TANG Bao-ping，Lü Zhong-liang

Author information +

History +

Abstract

A new prediction method is proposed based on Weibull distribution and least squares support vector machine to describe the rolling bearing degradation trend. The shape parameter of Weibull distribution is used as bearing recession performance indicators. The indicators act as the input of the least squares support vector machine and then a prediction model is constructed. Due to the model parameters of least square support vector machine has an important influence on the predictive ability of the model, the proposed method choose particle swarm(PSO) algorithm to optimize the model parameters. The rolling bearing run-to-failure tests are carried out to inspect the prediction model, and the results demonstrate the effectiveness and accurateness of the proposed method.

Key words

degradation trend prediction / Weibull distribution / degradation assessment / least squares support vector machine (LS-SVM)

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

CHEN Chang;TANG Bao-ping;Lü Zhong-liang. Degradation trend prediction of rolling bearing based on Weibull distribution and least squares support vector machine[J]. Journal of Vibration and Shock, 2014, 33(20): 52-56