Asynchronous Motor Finite-time Dynamic Facial Neural Network Control Considering Iron Loss

Induction motors are applied in various fields and provides power for a variety of mechanical equipment because of its reliable performance,easy to manufacture,easy to operate and maintain,light weight and low price.In the drive system of electric vehicle,induction motor has become the most widely used motor because of its advantages of light weight,high efficiency,low cost,convenient maintenance and high specific power suitable for high-speed operation.In order to obtain good driving force when the electric vehicle is running at high speed,a small excitation inductance is usually used.However,this method will generate a lot of current ripple in the system,which will increase the core loss of the induction motor,cause the error of the magnetic field orientation angle,and further affect the dynamic and stable performance of the control system,so it is necessary to consider the influence of core loss on induction motor.At the same time,because the induction motor has the characteristics of high order,nonlinear and strong coupling,and it is easy to be interfered by internal and external factors during operation,which affects the dynamic and static performance and control accuracy of the system.Therefore,how to give full play to the advantages of induction motor and improve the impact of its shortcomings has become the focus of scholars.Many effective control methods,such as backstepping control,sliding mode control and Hamilton control,have been put forward by scholars after in-depth research.Based on this,this paper takes the induction motor considering the core loss as the control object,and combines the backstepping method,adaptive neural network control technology,finite time dynamic surface control and sliding mode control method.It proposes the finite time dynamic surface control method and finite time dynamic surface sliding mode control method respectively,and constructs the corresponding induction motor position tracking controller.The main research results are as follows:1.For the drive system of induction motor considering the core loss,this paper adopts the finite time dynamic surface control method to design the position tracking controller of induction motor.Based on the adaptive backstepping method,this paper combines with the neural network control method,and introduces the finite time control method and the dynamic surface control technology,and it not only solves the " computational complexity " problem in the traditional backstepping method,but also improves the asymptotic convergence of the system to the finite time convergence,and improves the control performance of the system.In addition,the consideration of input voltage saturation makes the controller more practical.2.For the drive system of induction motor considering the core loss,this paper uses the control strategy of finite time dynamic surface control and sliding mode control to design the position tracking controller of induction motor.Based on the adaptive backstepping method,the nonlinear terms in the system are approached by the neural network control method.At the same time,the finite time dynamic surface control method is combined with the sliding mode control method,which not only gives full play to the advantages of the finite time dynamic surface control method,but also enhances the anti-interference ability of the system through the sliding mode control method.3.The controller constructed in the above content is simulated with MATLAB respectively.By comparing the finite time dynamic surface control method with the dynamic surface control method,the finite time control can improve the control performance and tracking accuracy of the system.In addition,by comparing the finite time dynamic surface sliding mode control method with the finite time dynamic surface control method,it shows that the sliding mode control can improve the anti-interference ability of the system.Finally,the effectiveness of the proposed control strategy is verified by MATLAB comparative simulation experiment.