Combined Probability Approach and Indirect Data-Driven Method for Bearing Degradation Prognostics

Author

Caesarendra, Wahyu ; Widodo, Achmad ; Thom, Pham Hong ; Yang, Bo-Suk ; Setiawan, Joga Dharma

Author_Institution

Sch. of Mech. Eng., Pukyong Nat. Univ., Pusan, South Korea

Volume

60

Issue

1

fYear

2011

fDate

3/1/2011 12:00:00 AM

Firstpage

14

Lastpage

20

Abstract

This study proposes an application of relevance vector machine (RVM), logistic regression (LR), and autoregressive moving average/generalized autoregressive conditional heteroscedasticity (ARMA/GARCH) models to assess failure degradation based on run-to-failure bearing simulating data. Failure degradation is calculated by using an LR model, and then regarded as the target vectors of the failure probability for training the RVM model. A multi-step-ahead method-based ARMA/GARCH is used to predict censored data, and its prediction performance is compared with one of Dempster-Shafer regression (DSR) method. Furthermore, RVM is selected as an intelligent system, and trained by run-to-failure bearing data and the target vectors of failure probability obtained from the LR model. After training, RVM is employed to predict the failure probability of individual units of bearing samples. In addition, statistical process control is used to analyze the variance of the failure probability. The result shows the novelty of the proposed method, which can be considered as a valid machine degradation prognostic model.

Keywords

autoregressive moving average processes; failure (mechanical); machine bearings; maintenance engineering; mechanical engineering computing; probability; support vector machines; ARMA/GARCH models; Dempster-Shafer regression; RVM model; autoregressive moving average; bearing degradation prognostics; failure degradation; failure probability; generalized autoregressive conditional heteroscedasticity; indirect data driven method; intelligent system; logistic regression; machine degradation prognostic model; multistep-ahead method; prediction performance; probability approach; relevance vector machine; run-to-failure bearing data; run-to-failure bearing simulating data; statistical process control; Autoregressive processes; Data models; Degradation; Predictive models; Probability; Process control; Training; Autoregressive moving average; Dempster-Shafer regression; censored data; generalized autoregressive conditional heteroscedasticity; prognostics; relevance vector machine; run-to-failure;

fLanguage

English

Journal_Title

Reliability, IEEE Transactions on

Publisher

ieee

ISSN

0018-9529

Type

jour

DOI

10.1109/TR.2011.2104716

Filename

5710447