A Vehicle simulation model is built by AMESim software. During the Electronic Stability Program (ESP) running on, the cases of varieties about system variables are investigated based on the automobile dynamic model. Fault modes of actuators and sensors in ESP are built up. And data-fault is acquired. Support Vector Machine (SVM) based on classification is applied for fault diagnosis of the ESP system. The basic idea is to identify the information and classify new fault samples by using the trained SVM model. Finally, simulation examples are performed to verify the effectiveness of the proposed design.