Inverse learning control using neuro-fuzzy approach for a process mini-plant

This paper is concerned with a development of an inverse learning control method designed using adaptive neuro-fuzzy controller and its real-time implementation for controlling a process mini-plant. The adaptive neuro-fuzzy approach is implemented to model the dynamic inverse of the plant where, during the learning phase, an off-line and on-line technique will be performed, while in the design of the neuro-fuzzy controller, an adaptive network will be employed as a building block. A hybrid learning rule is also used to minimize the difference between the actual and a given desired trajectory. Experimental results of real-time control of a laboratory-scaled process mini-plant show that the designed on-line inverse learning control technique performs well to the changing dynamics of the plant and tracks the given desired set-points. Performance comparison was also made between the designed and PI controller.