A similarity based methodology for machine prognostics by using kernel two sample test. (August 2020)

• Record Type: Journal Article
• Authors: Cai, Haoshu; Jia, Xiaodong; Feng, Jianshe; Li, Wenzhe; Pahren, Laura; Lee, Jay
• Is Part Of: ISA transactions. Volume 103(2020)
• Page Start: 112
• Page End: 121
• Publication Date: 2020-08
• Subjects: Remaining useful life -- Prognostics and health management -- Maximum mean discrepancy -- Kernel two sample test -- Weibull distribution -- NASA C-MAPSS dataset; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2020.03.007
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: This paper proposes a novel similarity-based algorithm for Remaining Useful Life (RUL) prediction and a methodology for machine prognostics. In the proposed RUL prediction algorithm, a Similarity Matching Procedure including the Kernel Two Sample Test (KTST) is developed to query similar run-to-failure (R2F) profiles from historical data library. Next, the preliminary predictions of RUL are obtained as remaining time-to-failure from the similar R2F records. In the last step, Weibull analysis is performed to fuse the preliminary predictions and to obtain the probability distribution of RUL. Moreover, a methodology for machine prognostics is developed based on the RUL prediction algorithm. Compared with existing similarity-based methods for RUL prediction, the proposed method holds several advantages: 1) the similarities between sensor readings or feature matrices are directly measured without extra health assessment procedure; 2) the proposed method presents good probabilistic interpretations of the prediction uncertainties; 3) the estimated RUL distribution is statistically sound by applying KTST to prescreening the historical R2F records. The effectiveness and the superiority of the proposed method are justified based on the public aero-engine dataset. Highlights: A similarity-based method is proposed for remaining useful life prediction. The method combines kernel two sample test and maximum mean discrepancy. The method improves accuracy and presents prediction uncertainties. The result is validated on public aero-engine data for prognostics.