Research On Electro-hydraulic Servo System Based On Least Squares Support Vector Machine And Adaptive Control Algorithm

In today's automated control range,electro-hydraulic servo systems play an increasingly important role.In some precision occasions where the precision of control is extremely high,more and more researchers choose valve-controlled cylinder electro-hydraulic servo systems.As a control system,it is widely used in the aerospace field,for example,a load simulator that can accurately simulate the trajectory of an air rudder,control the flight speed and route of the aircraft,and the like.The electro-hydraulic servo system can be applied as a force,speed,position servo control system,but the most frequently used position servo system is the position servo system.Even in some force and speed control systems,position servo systems are often embedded in it.Therefore,it is necessary to improve the displacement control accuracy of the position servo system.However,the electro-hydraulic position system is not a static system.As the running time increases,the whole system is time-varying due to the existence of some time-varying parameters.Furthermore,due to the existence of nonlinear components such as hydraulic valves,It is decided that the whole system is nonlinear.Finally,due to the existence of a large number of nonlinear components,the system model is difficult to establish.Based on the above shortcomings,it is difficult for an ordinary controller to achieve the desired control requirements.Therefore,a controller with an extremely adaptable capability for designing an electro-hydraulic servo has high engineering application value.In this paper,the electro-hydraulic servo position system is firstly analyzed theoretically.On the basis of knowing its working principle,the hydraulic components are analyzed to obtain the open-loop transfer function.By consulting a large amount of literature and combining with the existing hydraulic components of the laboratory.The parameter list of the whole system is obtained,and the theoretical model is substituted.The system is in a stable state are obtained through Matlab/Simulink software.Secondly,an adaptive PID controller based on PSO-LSSVM model is designed.The related statistical basic knowledge and regression principle of SVM and LSSVM are introduced in detail.It can be known that LSSVM can approximate any nonlinear function,so it is used for system identification modeling and identification based on the model structure.Model parameters,The system identification modeling is carried out,so that the accurate model which accurately describes the dynamic behavior of the system can be obtained.The correlation parameters of LSSVM are optimized by particle swarm optimization algorithm.Based on LSSVM and particle swarm optimization algorithm,the experimental data of electro-hydraulic servo system is collected and designed.The related identification test is carried out,and a more accurate PSO-LSSVM model is trained.Based on the PSO-LSSVM model,an adaptive PID controller is designed.In order to verify the control effect,the ordinary PID control and ANN-PID are also given.Control as a comparison,and finally based on the simulation results of each signal,the superiority of the LSSVM adaptive PID controller control effect is confirmed.Finally,a closed-loop control experiment was carried out on the electro-hydraulic servo control platform.The test results show that the control effect of LSSVM adaptive PID controller is better than PID controller and ANN-PID controller in practical engineering applications.The experiment verified the feasibility and superiority of the proposed LSSVM adaptive PID controller.