PID Control Based Neural Network and Genetic Algorithm for Inverted Pendulum System

摘要

The inverted pendulum is a non-linear system and it is a single-input and double-outputs system. This paper here provides an analysis of the system, which can be the basis for designing different kinds of controllers. Then, the paper uses the fuzzy control to stabilize the inverted pendulum on the vertical line from the stable point at the horizon. Based on the fuzzy control result, this paper controls the pendulum by PID controller and the PID parameters are trained by using neural network and genetic algorithm(GA). The excellent experiment result of the rapidness and the good anti-disturbance ability of the inverted pendulum testify the feasibility of the proposed method.