Fault Detection for Electro Hydraulic Position Servo System Based on Kernel Regression Interval Model

Considering that the problems of traditional fault detection methods used for electro-hydraulic position servo system in which is incapable of obtaining adaptive threshold and improving the generalization performance of model structure, a fault detection method based on kernel regression interval model is proposed in this paper. The method make full use of the measurable input-output data to construct interval model, where those data is capable of reflecting the uncertainties of electro-hydraulic position servo system in the absence of failure and accuracy and structure complexity of the constructed interval model can be trade-off. Then, interval model is used to judge whether the actual output of the electro hydraulic position servo system exceeds the interval output to realize fault detection. Because this method considers the dynamic threshold based on interval for fault detection, it can eliminate the false alarm of fixed threshold and is capable of improving the adaptability in detecting fault. Finally, The experimental examples are investigated to demonstrate the effectiveness of the proposed fault detection methodwhich can be applied for the real-time fault detection of the electro-hydraulic position servo system.