Fault Diagnosis of Electro-hydraulic Position Servo Closed-loop System Based on Support Vector Regression

A fault diagnosis method is proposed for electro-hydraulic position closed-loop system based on support vector regression (SVR), a new class of kernel based techniques introduced within statistical learning theory and structural risk minimization. This new fault diagnosis approach leads to solving convex optimization problems and also the model complexity follows from this solution. By using the measurable parameters, the total fault diagnosis model and the partial fault diagnosis model of SVR for electro-hydraulic position closed-loop system are established. The simulation results show that this method can effectively detect the fault of electro-hydraulic position closed-loop system.