The primary emphasis of this project is on the use of artificial neural networks (ANNs) for identification and control of unknown nonlinear dynamic systems. However, generally much is known about the plant. This research involves the use of a "gray layer" which facilitates the integration of known characteristics of the otherwise unknown plant into an ANN. The convergence characteristics using this novel technique are of several orders of magnitude better than the conventional schemes. Both state of the art intelligent control and adaptive control technologies are used, and their application is demonstrated in the context of electrically commutated machines.*** //
