Research On Control System Of Multi-motor Based On BP Neural Network With PID Algorithm

In recent years,with the continuous improvement of industrial automation,the transmission system also puts forward more stringent requirements.The transmission control system is widely used in industrial and agricultural production,which makes the study of multi-motor control important particularly.The improvement of the precision of multi-motor synchronous control will directly promote the efficiency of industrial and agricultural production,and then bring great economic benefits,so the research of multi-motor is getting more and more attention.In this thesis mainly analyzes the multi-motor control strategy and the multi-motor synchronous control mode.Firstly,the single motor is required to have a good speed tracking characteristics in the multi motor synchronous control system,so control effect of singer motor will directly restrict the precision of multi-motor synchronous control system.In industrial and agricultural production,the traditional PID controller is used to improve the response speed of the controller.The traditional PID controller is simple and easy to implement,but it is difficult to adjustment the PID parameters,so it is very difficult for the multi-motor synchronous control system with a multivariable,non-linear and strong coupling control object.This thesis adopts BP neural network PID controller to replace the traditional PID controller,but in the process of further research,it is found that the traditional BP neural network algorithm has a slow convergence and easy to fall into the local minimum.This thesis puts forward four improvement strategies which are the introduction of the inertia term,introduction of the momentum item,improving the search direction and improving the learning rate,and redesign PID controller based on improved BP neural network to improve the performance of BP neural network PID controller.Secondly,in the multi-motor synchronous control system,the multi-motor synchronous control mode is also closely related to the precision of multi-motor synchronous control of multi-motor.In this thesis,the parallel control,master-slave control,cross-coupling control and deviation coupling control are compared which proves deviation coupling control can solve the problem of multi-motor synchronous control better.However the traditional deviation coupling control speed compensator is not fast enough and not sensitive enough for the synchronous error correction of each motor.Therefore,this thesis puts forward three strategies to improve the speed compensator which are the introduction of speed signal compensation gain,introduction of error factor and add BP neural network PID controller.The deviation coupling control speed compensator is redesigned to improve the performance of speed compensator.Finally,the simulation control platform of multi-motor synchronous control system is built in Matlab / Simulink environment,and the simulation experiment is analyzed.It can be seen from the experimental results that the research in this thesis obviously improves the precision of multi-motor synchronous control.