Adaptive fault detection based on GRNN observer for hydraulic actuator system

In view of that the technology detecting the fault of the hydraulic actuator systems using observer is still limited, an adaptive failure detection method based on the general regression neural network(GRNN)observer for the hydraulic actuator system is presented here. The faster learning speed of the GRNN neural network makes training much more efficient. Because of the influence of environmental noise and random interference, the adaptive threshold is introduced to reduce the false alarm rate of detection. The data of the hydraulic actuator system in normal operation is used to train the neural network, then the trained neural network for the diagnosis of the collected data is used to judge whether the hydraulic actuator system fails. The three typical types of faults of the hydraulic actuator system are used to verify the effectiveness of this method. The experimental analysis results show that the proposed method can detect the fault condition of the hydraulic actuator system effectively.