Real-time operation of an autonomous fuzzy controller
D. Gardner, C.-H. Chen, Kaveh Ashenayi, Sujeet Shenoi · 2002
The authors are developing a practical autonomous fuzzy logic controller. The controller is provided with basic knowledge which enables it to continuously observe plant performance while performing its control actions and to use the outcomes of its actions in shaping its control policy in real time. The controller remains dormant when the plant is operating satisfactorily, but it rapidly and autonomously initiates adaptation in real time when adverse performance is observed. The controller can effectively deal with individual variations in plant characteristics, compensate for component wear and tear, and handle dynamic interactions with the environment. The main features of the autonomous control algorithm, which has been thoroughly tested on a variety of simulated and real systems, are highlighted. The hardware implementation employs an Intel MCS-51 series microcontroller board incorporating an inexpensive 8-b Intel 8031 processor.>