RBF整定PID在永磁同步电机控制中的应用研究

Application Research on RBF Tuning PID in Permanent Magnet Synchronous Motor Control

电动汽车驱动电机具有非线性、时变性和耦合性等特性。为解决常规比例积分微分(PID)控制在电动汽车上下坡或负载发生变化等情况下控制效果不理想的问题,对电动汽车中永磁同步电机的驱动控制系统进行了研究。基于径向基函数(RBF)神经网络在电机控制领域的应用现状,利用RBF神经网络在线整定PID控制参数的方法,改善控制器对电动汽车驱动电机的控制效果。分析了永磁同步电机在电动汽车中的应用特性,建立了电动汽车中永磁同步电机的离散数学模型。通过Matlab仿真,验证了RBF神经网络在永磁同步电机等非线性系统中应用的可行性,并分别在RBF在线整定PID控制和常规PID控制两种情况下进行电机的调速控制仿真试验。试验结果表明,相比常规PID控制,RBF在线整定PID控制具有更好的实时性、抗干扰能力以及自适应能力,能够有效提高电动汽车行驶的稳定性。

The drive motor of electric vehicle has the characteristics of nonlinearity,time variation,coupling and etc.In order to solve the problem that the control effect of conventional proportion integral derivative(PID)control is not ideal when the electric vehicle is running uphill and downhill or under the load changes,the driving control system of permanent magnet synchronous motor(PMSM)in electric vehicle is studied.Based on the application of radical basis function(RBF)neural network in the field of motor control,the method of on-line tuning PID control parameters by RBF neural network is used to improve the control effect of the controller of drive motor.The application characteristics of permanent magnet synchronous motor in electric vehicle are analyzed.The discrete mathematical model of permanent magnet synchronous motor in electric vehicle is established.The feasibility of applying RBF neural network to permanent magnet synchronous motor and other non-linear systems is verified by the simulation test in Matlab.The RBF on-line tuning PID control and conventional PID control are respectively used.Simulation tests of motor speed control are carried out under different conditions.The experimental results show that the RBF on-line tuning PID control has better real-time performance,anti-interference ability and adaptive ability than those of the conventional PID control,and can effectively improve the driving stability of electric vehicles.