Single Neuron PID Model Reference Adaptive Control for Filling Machine Based on DRNN Neural Network On-Line Identification

Abstract

In view of the controlled plant complexity of the horizontal position synchronization system in automatic filling machine, a novel approach of single neuron PID model reference adaptive control for AC permanent magnet synchronous motor (PMSM) servo control based on diagonal recurrent neural network (DRNN) on-line identification is proposed owing to the disadvantage of traditional PID controller. The DRNN is used to identify the system on-line for the single neuron PID controller to adjust its weights and PID parameters by self-learning and self-adaptability based on the desired output from a reference model. Computer simulation results show that the control system has fine dynamic and steady state performance and high position synchronization tracking precision and good robustness as well as simple structure and high adaptability. The proposed control method can also be used in the flying shear system.