A combination of fuzzy logic and neural network can generate a fuzzy neural
controller which in association with a neural network emulator can improve the output
response of the controlled system. This combination uses the neural network training
ability to adjust the membership functions of a PID like fuzzy neural controller. Such
controller can be used to adaptively control nonlinear MIMO systems.
The goal of the controller is to force the controlled system to follow a reference
model with required transient specifications of minimum overshoot, minimum rise time
and minimum steady state error. The fuzzy membership functions were tuned using the
propagated error between the plant outputs and the desired ones.
To propagate the error from the plant outputs to the controller, a neural network
is used as a channel to the error. This neural network uses the back propagation
algorithm as a learning technique.
The controller was tested using two inputs / two outputs nonlinear time invariant
model. 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.