DESIGN OF ADAPTIVE FUZZY-NEURAL PID-LIKE CONTROLLER FOR NONLINEAR MIMO SYSTEMS

Abstract

Abstract:A combination of fuzzy logic and neural network can generate a fuzzy neuralcontroller which in association with a neural network emulator can improve the outputresponse of the controlled system. This combination uses the neural network trainingability to adjust the membership functions of a PID like fuzzy neural controller. Suchcontroller can be used to adaptively control nonlinear MIMO systems.The goal of the controller is to force the controlled system to follow a referencemodel with required transient specifications of minimum overshoot, minimum rise timeand minimum steady state error. The fuzzy membership functions were tuned using thepropagated error between the plant outputs and the desired ones.To propagate the error from the plant outputs to the controller, a neural networkis used as a channel to the error. This neural network uses the back propagationalgorithm as a learning technique.The controller was tested using two inputs / two outputs nonlinear time invariantmodel. Different reference (set-point) inputs were applied to the closed loop system.Also, different values of loads and disturbances were applied to the closed loop system.Simulation results show that the controller achieves the design requirements.