Regular Paper
International Journal of Control, Automation and Systems 2022; 20(9): 2892-2901
Published online August 17, 2022
https://doi.org/10.1007/s12555-021-0276-9
© The International Journal of Control, Automation, and Systems
Time-series Independent Component Analysis-aided Fault Detection for Running Gear Systems
By dealing with the non-Gaussian measurement and slow-change faults in running gear systems, this paper presents a fault detection (FD) scheme named time-series independent component analysis (TsICA), where the time-series characteristic is taken into account. Time-series algorithms can extract slow-change information in the data. The advantages of the proposed method are: 1) it can improve the FD power; 2) it considers the information in the data 3) it is suitable for non-Gaussian systems; 4) it is sensitive to slow-change faults; 5) it can effectively shorten the first time of fault detection. The feasibility of the proposed scheme is verified through a case study on running gear systems.
Keywords Fault detection (FD), non-Gaussian, running gear systems, time-series independent component analysis (TsICA).
PDF
Standard view
Export citation
Share Article
Regular Paper
International Journal of Control, Automation and Systems 2022; 20(9): 2892-2901
Published online September 1, 2022 https://doi.org/10.1007/s12555-021-0276-9
Copyright © The International Journal of Control, Automation, and Systems.
Time-series Independent Component Analysis-aided Fault Detection for Running Gear Systems
Chao Cheng*, Sheng Yang, Yu Song, and Gang Liu
Changchun University of Technology
Abstract
By dealing with the non-Gaussian measurement and slow-change faults in running gear systems, this paper presents a fault detection (FD) scheme named time-series independent component analysis (TsICA), where the time-series characteristic is taken into account. Time-series algorithms can extract slow-change information in the data. The advantages of the proposed method are: 1) it can improve the FD power; 2) it considers the information in the data 3) it is suitable for non-Gaussian systems; 4) it is sensitive to slow-change faults; 5) it can effectively shorten the first time of fault detection. The feasibility of the proposed scheme is verified through a case study on running gear systems.
Keywords: Fault detection (FD), non-Gaussian, running gear systems, time-series independent component analysis (TsICA).
Vol. 23, No. 3, pp. 683~972
Stats or Metrics
Share this article on
Related articles in IJCAS
-
Dynamic Weighted Slow Feature Analysis-based Fault Detection for Running Gear Systems of High-speed Trains
Chao Cheng, Xin Wang, Shuiqing Xu, Ke Feng, and Hongtian Chen*
International Journal of Control, Automation, and Systems 2024; 22(6): 1924-1934 -
Algorithm of Gaussian Sum Filter Based on SGQF for Nonlinear Non-Gaussian Models
Chen Qian, Chengying Song, Sheng Li*, Qingwei Chen, and Jian Guo
International Journal of Control, Automation and Systems 2021; 19(8): 2830-2841
