Dynamic Parameter Identification for Intelligent PID Control

Abstract

In this paper, an intelligent PID control structure using dynamic parameter is designed to solve the problem that the parameters of the aircraft model change, which results in controller performance degradation in real physical systems. The system dynamics parameters are identified by the deep neural network, and the parameters of the PID controller are adaptively scheduled based on the parameter identification results, so that the control system has the best matching with the system dynamics and the control performance is the best.