A design neurofuzzy controller for level process control

Abstract

This paper presents the design and implementation of a self-organizing neurofuzzy controller for tuning the fuzzy logic parameter using back-propagation neural network. The controller is implemented by software on a microcomputer to control the unknown transfer function system of a real plant for testing the learning efficiency of self-organization and proper parameter tuning where the scaling factor (g/sub 0/, g/sub 1/) is set from an experiment corresponding with process characterization and the designer experience. The results show that the performance of this controller is improved in terms of the set point compared with the PID standard controller.