Fault Diagnosis of Hydraulic Proportional Servo Valve Based on Time-Frequency Feature Extraction and GOA-SVM

Aiming at difficulty in effective fault diagnosis in actual work, a new fault diagnosis method of the hydraulic proportional servo valve based on Grasshopper Optimized Support Vector Machine (GOA-SVM) is proposed. Firstly, the denoising method based on wavelet transform removes the random noise of spool position signal, pressure signal and current signal. Then, time-frequency feature extraction and construction of fault feature vectors are performed using time domain, frequency domain and energy entropy in time and frequency domain. Based on GOA-SVM, the valve fault pattern recognition is performed. The experimental results show that the pattern recognition accuracy of the method reaches more than 95% and can be used for the fault diagnosis of hydraulic proportional servo valves.