Research On PMSM Neural Network Sliding Mode Control And Multi Motor Speed Synchronization

With the continuous development of industrial automation technology,due to the limit of single motor power and the requirements of automatic continuous production,multi motor synchronous control is widely used in production.The control performance of single motor has a great influence on the synchronization performance of multiple motors.Therefore,it is of great significance to study the speed tracking performance of single motor and the synchronization structure of multiple motors,so as to reduce the synchronization error between multiple motors and improve the synchronization performance of multiple motors,both in theoretical research and in actual production.In this paper,permanent magnet synchronous motor is taken as the controlled object.Firstly,the mathematical model and vector control strategy of permanent magnet synchronous motor are introduced,and the vector control method of surface mounted permanent magnet synchronous motor is selected,which provides a theoretical basis for the study of speed algorithm and multi motor synchronous control.Secondly,aiming at the chattering problem in sliding mode control,a sliding mode control strategy based on improved exponential reaching law is proposed.The stability of the improved algorithm is proved by Lyapunov function.The simulation software verifies that the proposed algorithm can increase the reaching speed of sliding mode and reduce the chattering of sliding mode.Taking PMSM as the controlled object,a hardware in the loop simulation platform is built to verify the applicability of the improved algorithm.Thirdly,in order to further improve the control performance of sliding mode for PMSM speed,a sliding mode strategy based on radial basis function neural network is proposed.By using the characteristic that radial basis function neural network can approach any curve,the switching gain in sliding mode control is adjusted in real time to reduce chattering and enhance robustness.Taking the running curve of the motor in the elevator as the set speed,the tracking effect is verified by simulation.In the hardware in the loop simulation platform,taking a single motor as the controlled object,the neural network sliding mode algorithm is verified.The results show that the improved algorithm is effective and can effectively reduce the chattering of sliding mode control.Finally,the structure analysis and simulation verification of several synchronization strategies of multi motor are carried out.Aiming at the shortcomings of traditional deviation coupling structure,the speed compensator in deviation coupling is improved.The simulation analysis is carried out in Matlab / SIMLINK simulation platform to verify the correctness of the improved deviation coupling structure.At the same time,the neural network sliding mode algorithm is used in the motor speed controller,and the deviation coupling control is used in the synchronization structure to simulate the multi motor synchronization,and the synchronization effect of the improved algorithm is analyzed.The revised paper has 56 pictures,7 tables,and 70 references...