In this paper a neuro-fuzzy controller (NFC) for temperature control of a water bath system is proposed. A five layer neural network is used to adjust input and output parameters of membership function in a fuzzy logic controller. The hybrid learning algorithm is used for training this network. The simulation results shows that the proposed controller has good set point tracking and disturbance rejection properties. Also it is robust against changes in the system parameters. It is also superior to the conventional PID controller.
