Adaptive neuro-fuzzy control approach for a single inverted pendulum system

• Main Authors: Al-Mekhlafi, Mohammed A. A., Abdul Wahid, Herman, Abd. Aziz, Azian
• Format: Article
• Language: English
• Published: Institute of Advanced Engineering and Science 2018
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utm.my/id/eprint/84653/1/HermanAbdulWahid2018_AdaptiveNeuroFuzzyControlApproachforaSingleInverted.pdf; http://eprints.utm.my/id/eprint/84653/; http://dx.doi.org/10.11591/ijece.v8i5.pp3657-3665
• Institution: Universiti Teknologi Malaysia

The inverted pendulum is an under-actuated and nonlinear system, which is also unstable. It is a single-input double-output system, where only one output is directly actuated. This paper investigates a single intelligent control system using an adaptive neuro-fuzzy inference system (ANFIS) to stabilize the inverted pendulum system while tracking the desired position. The non-linear inverted pendulum system was modelled and built using MATLAB Simulink. An adaptive neuro-fuzzy logic controller was implemented and its performance was compared with a Sugeno-fuzzy inference system in both simulation and real experiment. The ANFIS controller could reach its desired new destination in 1.5 s and could stabilize the entire system in 2.2 s in the simulation, while in the experiment it took 1.7 s to reach stability. Results from the simulation and experiment showed that ANFIS had better performance compared to the Sugeno-fuzzy controller as it provided faster and smoother response and much less steady-state error.