Real time neuro-fuzzy control of a nonlinear dynamic system

The real time control of a nonlinear dynamic system using intelligent control techniques is considered. The focus is to investigate the current neuro fuzzy approaches from literature and adapt them to a specific application. The nonlinear dynamic system considered here is an unstable balance beam system that contains two fluid tanks, one at each end, and the balance is achieved by pumping the fluid back and forth from the tanks. The proposed controller which is a six layer network called Generalized Network based Fuzzy Inferencing Systems (GeNFIS) is developed based on the popular approach, called ANFIS (Adaptive Networks based Fuzzy Inference Systems). GeNFIS is tested on the balance beam system, both in a real time actual experiment and the simulation, and is found to be successful under supervised learning. Results of testing different versions of GeNFIS on the balance beam system are presented