Simulation research on FLS_SVM in sensor fault diagnosis

The conception of fuzzy membership is introduced into the least square support vector machines (LS_SVMs), which overcomes the disadvantage that LS_SVMs are so sensitive to outliers in training samples and SVMs are time-consuming to solve quadratic programming problems. A sensor fault diagnosis system is designed by building the fuzzy least square vector machine (FLS_SVM) model. FLS_SVM is trained out of line, and used online. After being trained, FLS_SVM is used to simulate system dynamic characteristic. The simulation result is compared with actual output, and then fault error is drawn. Taking yaw angular rate sensor fault diagnosis for example has been simulated. The simulation result shows that, FLS_SVM can simulate the system more accurately, thus fault message of sensor is diagnosed in time. Experiments demonstrate the effectiveness of the method.