Soft computing techniques as applied to expert tuning of PID controllers

We present results obtained through the use of soft computing tools for supervising the tuning process of PID gains located within the control loop of a class of nonlinear systems. The results are compared with PID controllers implemented in either a stand alone scheme or as a part of conventional gain scheduling structure. This work is motivated by an increasing need in the industry to design highly reliable and efficient controllers for dealing with regulation and tracking capabilities of complex processes characterized by nonlinearities and possibly time varying parameters. The soft computing based controllers proposed are hybrid in nature in that, they integrate within a well defined hierarchical structure the benefits of hard algorithmic controllers with those of supervisory capabilities. The controllers have also the distinct features of learning and auto-tuning, without the need for tedious and computationally extensive online systems identification schemes