An improved TSBP scheme for RUL estimation using migratory linear regression model and Beta-KDE method

Guliang Li; Jiazhe Zhang; Yu Wei; Yongfang Mao

doi:10.1117/12.2689916

7 September 2023 An improved TSBP scheme for RUL estimation using migratory linear regression model and Beta-KDE method

Guliang Li, Jiazhe Zhang, Yu Wei, Yongfang Mao

Proceedings Volume 12790, Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023); 127901G (2023) https://doi.org/10.1117/12.2689916
Event: 8th International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023), 2023, Hangzhou, China

Abstract

The prediction of the remaining useful life (RUL) of the equipment is one of the important parts of the equipment health management and safety. We focus on trajectory similarity-based prognostic method in the data-driven scheme adopting migratory linear regression model, similarity-metric technique and Beta-KDE method based on nuclear density estimation (KDE) to predict some devices’ RUL. The training set generate the training HI library. The migratory linear regression model trained by above library transforms the test embedding into the test health indicator (HI), which are used to describe health degradation of some device. One test HI curve is compared with all the training HI curves to get the inaccurate RUL estimation. The Beta-KDE method based on KDE sifts the inaccurate value to get a valid RUL estimation, which is used to calculate the final result. This scheme was applied for turbofan engine dataset #1 and the result proved an advantage in other approaches.

Citation Download Citation

Guliang Li, Jiazhe Zhang, Yu Wei, and Yongfang Mao "An improved TSBP scheme for RUL estimation using migratory linear regression model and Beta-KDE method", Proc. SPIE 12790, Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023), 127901G (7 September 2023); https://doi.org/10.1117/12.2689916

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available