Fault diagnosis method of point machine based on vibration signal

Tongrui Yan; Jiazhen Zhang; Yongkui Sun

doi:10.1117/12.2689779

7 September 2023 Fault diagnosis method of point machine based on vibration signal

Tongrui Yan, Jiazhen Zhang, Yongkui Sun

Proceedings Volume 12790, Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023); 127901M (2023) https://doi.org/10.1117/12.2689779
Event: 8th International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023), 2023, Hangzhou, China

Abstract

Railway point machine is the key equipment to control the train path and change the operation direction. Considering the anti-interference characteristics of vibration signals, this paper innovatively proposes a fault diagnosis method for point machine based on vibration signal, which provides a new fault diagnosis method for point machine. Firstly, the vibration data of the point machine are preprocessed by using variational mode decomposition (VMD). Secondly, a hybrid feature extraction method is developed by combining various methods such as wavelet transform and frequency-domain feature extraction method, which can characterize the fault features more comprehensively. Finally, support vector machine (SVM) algorithm is used to judge fault conditions. The diagnosis accuracies of localization and inverse switching processes reach 100% and 98.9%, respectively. Comparative experiments indicate the superiority of the proposed method.

Citation Download Citation

Tongrui Yan, Jiazhen Zhang, and Yongkui Sun "Fault diagnosis method of point machine based on vibration signal", Proc. SPIE 12790, Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023), 127901M (7 September 2023); https://doi.org/10.1117/12.2689779

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