| MODEL-BASED SENSOR FAULT DIAGNOSIS OF VEHICLE
SUSPENSIONS WITH A SUPPORT VECTOR MACHINE |
| Kicheol Jeong, Seibum Choi |
| KAIST |
|
|
|
|
|
|
|
| ABSTRACT |
|
In this paper, a means of generating residuals based on a quarter-car model and evaluating them using a support
vector machine (SVM) is proposed. The proposed model-based residual generator shows very robust performance regardless
of unknown road surface conditions. In addition, an SVM classifier without empirically set thresholds is used to evaluate the
residuals. The proposed method is expected to reduce the effort required to design fault diagnosis algorithms. While an
unknown input observer is used to generate the residual, the relative velocity of the vehicle suspension is obtained additionally.
The proposed algorithm is verified using commercial vehicle simulator Carsim with Matlab & Simulink. As a result, the fault
diagnosis algorithm proposed in this paper can detect sensor faults that cannot be detected by a limit checking method and can
reduce the effort required when designing algorithms. |
| Key Words:
Fault diagnosis, Support vector machine, Vehicle suspension, Unknown input observer |
|
Corresponding Author.
Seibum Choi , Email. 
Preview 
Full text via DOI 
Download Citation
Print
