Principal Components Analysis based Fault Detection and Isolation for Electronic Throttle Control system

In this paper, a Principal Component Analysis (PCA) based Fault Detection and Isolation (FDI) method for nonlinear Electronic Throttle Control (ETC) system is presented. The proposed method introduces a novel configuration of PCA bases by computing the absolute value of weights. The fault can be detected if the Sum Square Error (SSE) distance exceeds its pre-defined threshold and the isolation of the detected fault is done under the minimum of the SSE distance. The PCA model is used to detect (offline and/or online) failure in the ETC from the old Normal Operation Condition (NOC) as well as to diagnose the cause of the failure. A set of faults with armature resistance, armature inductance are evaluated to demonstrate the performance and effectiveness of the proposed method.