Design and Simulation of Adaptive Neuro-Fuzzy Inference System Inverse Controller for a Coupled Tank System

Abstract

Level control of coupled tank systems is an important issue in the industry's process in the presence of nonlinearity. This paper presented an inverse control method based on Adaptive Neuro-Fuzzy Inference System (ANFIS). The ANFIS is utilized to design and implement the nonlinear controller, which has the inverse transfer function of the system. There is no conventional direct feedback in the control loop just that in the enhancement period. The system output is used by an adaptive algorithm to adjust the parameters of the controller. The ANFIS inverse controller has been tested on a simulated coupled tank system and for the sake of results comparison, the output response of the simulated system has been compared using the ANFIS inverse controller and the classical PID controller under the same conditions. The simulation of the coupled tank system and ANFIS controller software has been designed and implemented using the LabVIEW software and MathScript facility.