Fault Diagnosis of Hydraulic Actuator Based on Least Squares Support Vector Machines

According to the fault diagnosis method based on a mathematical model of the control system, a fault diagnosis method is proposed for hydraulic actuator based on least squares support vector machines (LS-SVM). This new fault diagnosis approach leads to solving a linear set of equations instead of solving a quadratic programming problem. The LS-SVM formulation also involves less tuning parameters. By using the measurable parameters, the fault diagnosis model of LS-SVM for hydraulic actuator are established. The simulation results show that this method can effectively detect every fault of servo valve, displacement sensor and servo amplifier.