A PID Neural Network Control for Position Servo System with Gear Box at Variable Load

Abstract

This paper investigates an application of PID neural network (PIDNN) control for a position servo system. The position servo system consists of a permanent magnet synchronous motor (PMSM), an inverter, a gear box and a variable load. First, both the analytical model of PMSM and the model of variable load are introduced for the servo system. PIDNN controller with on-line learning, rapid adjustment, anti-jam capability is presented. A simulation with the PIDNN controller is implemented in the commercial software Portunus and compared with the results of the of conventional PID controller. The simulation results manifest that the PIDNN methodology yields an excellent performance for both rapid adjustment and anti-disturbance in the position servo system.