Knowledge-based control

Two types of expert control are distinguished. The first, direct expert control, uses the knowledge-based system directly to generate the control signal. The second approach, supervisory expert control, influences the process in an indirect way. A real-time expert system shell is described that uses the progressive reasoning principle. The direct expert control approach has been investigated by using the phase plane and has proved to be useful for different processes. The system has been extended by introducing a supervisory level to realize a desired dynamic behavior and zero steady-state error. Several experiments were carried out using heuristic adaptation and pattern recognition. An expert control approach to supervise adaptive control algorithms as well as parameter estimation algorithms is presented.<<ETX>>