DocumentCode
3217378
Title
Fault diagnosis of rail vehicle suspension system based on distributed DPCA
Author
Xiukun Wei ; Ying Guo
Author_Institution
State Key Lab. of Rail Way Traffic Control & Safety, Beijing Jiaotong Univ., Beijing, China
fYear
2015
fDate
23-25 May 2015
Firstpage
2758
Lastpage
2763
Abstract
The suspension system plays a crucial role of the rail vehicles. The fault diagnosis of the suspension system is an effective way to ensure the security, stable operation of rail vehicles. In this paper, a distributed fault diagnosis method is proposed. This paper concerns the fault diagnosis issue of rail vehicle suspension systems with the extended form of dynamic principle components analysis, distributed dynamic principle components analysis (Distributed DPCA). The signal information used in the fault diagnosis is obtained from the SIMPACK and MATLAB co-simulation environment. In this paper, the typical primary spring and secondary damper faults are diagnosis successfully using Distributed DPCA. For each suspension subsystem, DPCA is applied and the detection results are co-operated mainly by the distributed relation of the subsystems. The statistical index SPE and T2 are applied to monitor the performance of suspension system and the distributed analysis are used to handle the fault isolation problem. The effectiveness of the proposed approach is demonstrated by the simulation results for several fault scenarios.
Keywords
fault diagnosis; locomotives; principal component analysis; shock absorbers; springs (mechanical); vibration control; Matlab; SIMPACK; SPE statistical index; T2 statistical index; dampers; distributed DPCA; distributed dynamic principle components analysis; distributed fault diagnosis method; fault isolation; rail vehicle suspension system; springs; Fault detection; Fault diagnosis; Monitoring; Rails; Shock absorbers; Vehicles; Distributed DPCA; Fault diagnosis; Suspension system;
fLanguage
English
Publisher
ieee
Conference_Titel
Control and Decision Conference (CCDC), 2015 27th Chinese
Conference_Location
Qingdao
Print_ISBN
978-1-4799-7016-2
Type
conf
DOI
10.1109/CCDC.2015.7162398
Filename
7162398
Link To Document