Tuning PID Controller by Neural Network for Robot Manipulator Trajectory Tracking

Abstract

Ziegler and Nichols proposed the well-known Ziegler-Nichols method to tune the coefficients of PID controller. This tuning method is simple and gives fixed values for the coefficients which make PID controller have weak adaptabilities for the model parameters variation and changing in operating conditions. In order to achieve adaptive controller, the Neural Network (NN) self-tuning PID control is proposed in this paper which combines conventional PID controller and Neural Network learning capabilities. The proportional, integral and derivative (KP, KI, KD) gains are self tuned on-line by the NN output which is obtained due to the error value on the desired output of the system under control. The conventional PID controller in the robot manipulator is replaced by NN self tuning PID controller so as to achieve trajectory tracking with minimum steady-state error and improving the dynamic behavior (overshoot). The simulation results showed that the proposed controller has strong self-adaptability over the conventional PID controller.