DocumentCode :
3473840
Title :
Prognostics of products using time series analysis based on degradation data
Author :
Huang, Tingting ; Wang, Li ; Jiang, Tongmin
Author_Institution :
Dept. of Syst. Eng., Beihang Univ., Beijing, China
fYear :
2010
fDate :
12-14 Jan. 2010
Firstpage :
1
Lastpage :
5
Abstract :
This paper presents a method to predict degradation path of products using time series modeling procedure based on product performance degradation data. The product performance degradation data are treated as a time series data and stochastic process are utilized to describe the degradation process for predicting long-term trend. A degradation test is processed for miniature bulbs until they failed and the degradation data are collected for prognostics. Degradation path of a miniature bulb is predicted using time series analysis based on short time period degradation data and long time period degradation data respectively. A comparison between the predicted degradation path and the real degradation path of the miniature bulb is processed and the results show that the degradation path prediction of the product using time series analysis is effective.
Keywords :
failure analysis; fault diagnosis; stochastic processes; time series; degradation path prediction; degradation process; degradation test; long-term trend; miniature bulbs; period degradation data; product performance degradation data; products prognostics; stochastic process; time series analysis; time series data; time series modeling; Data analysis; Data mining; Degradation; Failure analysis; Performance analysis; Predictive models; Stochastic processes; Testing; Time series analysis; Yttrium; degradation path; miniature bulbs; prognostics; time series analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Prognostics and Health Management Conference, 2010. PHM '10.
Conference_Location :
Macao
Print_ISBN :
978-1-4244-4756-5
Electronic_ISBN :
978-1-4244-4758-9
Type :
conf
DOI :
10.1109/PHM.2010.5413404
Filename :
5413404
Link To Document :
بازگشت