Yi Li, Yuheng Yu, Xinyu Hu, and Xianguo Liu
Permanent magnet synchronous linear motor, BP neural network,least squares, dynamic response performance
The permanent magnet synchronous linear motor has the character- istics of nonlinearity, coupling, load disturbance and time-varying parameters, which lead to low precision of speed tracking control of the linear motor. To solve this problem, this paper proposes a vector control method for tuning proportional integral derivative (PID) parameters of the improved back propagation (BP) neural network. This method optimizes the traditional BP neural network by the least squares method and optimizes the network structure and initial value selection. The simulation was performed using the Matlab/Simulink tool and compared with the traditional PID algorithm. The simulation results show that the control structure proposed in this paper has better dynamic response performance than the traditional PID control structure when the specified speed is 1 m/s, and the load is 100 N. It can effectively suppress the thrust fluctuation and has a better anti-interference ability. The experimental results also prove the effectiveness of the method.
Important Links:
Go Back
