PID Parameter Tuning Based On Adaptive Dynamic Programming

Abstract

The traditional PID control algorithm requires tuning and optimization to achieve better control performance in the nonlinear time-delay system, which complicates the controller design. We proposed a new self-tuning and optimization algorithm for controller parameters based on Adaptive Dynamic Programming(ADP). The algorithm uses neural networks to approximate the performance index functions and control strategies in dynamic programming to achieve online self-tuning and optimization of control parameters. Using ADP and Genetic algorithms tuning Proportional-Integral-Derivative(PID) control parameters and comparing the results can demonstrate the feasibility and effectiveness of our proposed approach.