Control Experiment of the Inverted Pendulum Using Adaptive Neural-Fuzzy Controller
Yang Xiaohui, Liu Hesheng, Liu Guo-ping, Xiao Gen-fu · 2010
In this brief, it presents the implementation of control of an inverted pendulum system by using the Adaptive Neural- Fuzzy. The inverted pendulum system has been built in the educational kit whose purpose is to educate control engineers in the college students. The inverted pendulum system is known as a nonlinear system whose goal is to maintain the balance of the pendulum while tracking a desired position of the cart. ANFIS (Adaptive Neural-Fuzzy Inference System) is used to control the system. It based on expert experiences optimizes the parameters of fuzzy controller by training and learning sample data. This controller is to control the inverted pendulum. ANFIS is compared with LQR (Linear Quadratic Regulator) and the traditional PID Control. Experimental results show that successful control performances of both balancing and tracking the position for the inverted pendulum system.