Research on Fault Diagnosis of Electric Control Valve Based on WPT-TWSVM

When the electric control valve fails, the flow signal will change slightly, and it will be mixed with a lot of environmental and system noise information. In order to improve the accuracy and reliability of the flow signal and reduce the noise, based on the energy decomposition of the wavelet packet, threshold processing and reconstruction are performed to achieve noise reduction. At the same time, the twin support vector machine method is used to classify minor faults. Finally, a simulation experiment was carried out on a semi-physical test bench for actuator failure simulation to verify the method proposed in this paper. The WPT optimized TWSVM model can diagnose the fault of the electric regulating valve more efficiently and quickly. This method breaks the wavelet threshold noise reduction processing. The limitations of traditional support vector machine classification have improved the accuracy and speed of recognition, improved the shortcomings of large signal noise and slow classification processing speed. It has certain promotion and application value in various industrial actuator fault monitoring and regulating valve, control valve minor fault classification, etc.