Intelligent control for self-erecting inverted pendulum via adaptive neuro-fuzzy inference system

• Main Authors: Saifizul, A.A., Zainon, Z., Abu Osman, Noor Azuan, Azlan, C.A., Ibrahim, U.F.S.U.
• Format: Article
• Language: English
• Published: 2006
• Subjects: TA Engineering (General). Civil engineering (General)
• Online Access: http://eprints.um.edu.my/4439/1/Intelligent_control_for_self-erecting_inverted_pendulum_via_adaptive_neuro-fuzzy_inference_system.pdf; http://eprints.um.edu.my/4439/; http://www.tsb-web.org.tw/isb2007/isb2007-paper/ISB/0670.pdf

A self-erecting single inverted pendulum (SESIP) is one of typical nonlinear systems. The control scheme running the SESIP consists of two main control loops. Namely, these control loops are swing-up controller and stabilization controller. A swing-up controller of an inverted pendulum system must actuate the pendulum from the stable position. While a stabilization controller must stand the pendulum in the unstable position. To deal with this system, a lot of control techniques have been used on the basis of linearized or nonlinear model. In real-time implementation, a real inverted pendulum system has state constraints and limited amplitude of input. These problems make it difficult to design a swing-up and a stabilization controller. In this paper, first, the mathematical models of cart and single inverted pendulum system are presented. Then, the Position-Velocity controller is designed to swingup the pendulum considering physical behavior. For stabilizing the inverted pendulum, a Takagi- Sugeno fuzzy controller with Adaptive Neuro-Fuzzy Inference System (ANFIS) architecture is used to guarantee stability at unstable equilibrium position. Experimental results are given to show the effectiveness of these controllers.