Improved application of GM(1,1) model in turnaround fault prediction

Chen Wang; Cong-Yong Cao; Meng-Jie Shao; Jin Kong; Xin Chen

doi:10.1117/12.2668486

16 February 2023 Improved application of GM(1,1) model in turnaround fault prediction

Chen Wang, Cong-Yong Cao, Meng-Jie Shao, Jin Kong, Xin Chen

Proceedings Volume 12591, Sixth International Conference on Traffic Engineering and Transportation System (ICTETS 2022); 125911S (2023) https://doi.org/10.1117/12.2668486
Event: 6th International Conference on Traffic Engineering and Transportation System (ICTETS 2022), 2022, Guangzhou, China

Abstract

Taking the S700K type rutting machine commonly used in high-speed rail as an example, a new method of turnout fault prediction based on the improved GM (1,1) model is proposed in view of the problems of "fault repair" and "timed repair" of traditional railway electricity. In order to improve the prediction accuracy of the model, the sliding average method and multi-step prediction are introduced to improve the traditional GM (1,1) model. Algorithm simulation comparison and verification of turnout action current data shows that the prediction accuracy of the improved GM (1,1) model is better. taking the 2DQJ characteristics of the field S700K turning machine as an example, the effectiveness and accuracy of the improved GM (1,1) model in the prediction of turnout fault are verified.

Citation Download Citation

Chen Wang, Cong-Yong Cao, Meng-Jie Shao, Jin Kong, and Xin Chen "Improved application of GM(1,1) model in turnaround fault prediction", Proc. SPIE 12591, Sixth International Conference on Traffic Engineering and Transportation System (ICTETS 2022), 125911S (16 February 2023); https://doi.org/10.1117/12.2668486

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