| Gas turbine is a strategic equipment in the fields of national energy and defense,and is one of the key research areas that require breakthroughs in China.Among them,the pneumatic actuator is an important part of the gas turbine control system.Long-term operation is prone to stiction,which will affect the control effect of the control loop.This paper focuses on the research of stiction detection and fault diagnosis methods for pneumatic actuators in gas turbines,aiming to improve the safety and reliability of gas turbines.The main research work is as follows:(1)This provides a detailed introduction to the basic structure and working principle of the gas turbine pneumatic actuator,and analyzes the nonlinear characteristics and typical faults of the pneumatic actuator,summarizing the causes and hazards of the faults.(2)A method for detecting stiction in pneumatic actuators is proposed based on the stiction characteristic curve and residual network,which is susceptible to external interference and poor controller parameter adjustment.Firstly,the stiction simulation data is obtained by using the stiction model to draw the stiction characteristic curve.Secondly,the residual network is used for training to establish the stiction detection model.Finally,the proposed stiction detection method is simulated and tested using an actuator fault simulation platform and an international valve stiction database.The results show that this detection method can effectively detect whether there is stiction characteristic in pneumatic actuators.(3)A fault diagnosis method for the pneumatic actuator based on VMD-MSEOSELM is proposed to solve the problem of low accuracy of traditional pneumatic.Firstly,the original signal of the pneumatic actuator is decomposed using the VMD method.Then,the MSE method is applied to extract the fault features of the decomposed signal.Secondly,the OSELM algorithm is used to classify the faults of the pneumatic actuator.Finally,a fault diagnosis system for the gas turbine pneumatic actuator is designed and the proposed fault diagnosis method is tested and verified through the actuator fault simulation platform and the Shanghai Xinhua gas turbine simulation machine.The results show that the fault diagnosis method proposed in this paper has high accuracy. |