A cooperating intelligent control system based on expert systems and neural networks

How to effectively combine expert control with neurocontrol has become an interesting issue in the development of intelligent control. A framework of a cooperating intelligent control system is presented, in which these two different controllers are effectively integrated together and coordinate to gain better control quality. Knowledge transference and sharing between two different controllers is achieved by making use of a mapping between the usable-characteristic vector space and the output vector space. An online approach analogous to human debating and compromising is adopted to coordinate two controllers to overcome their respective shortcomings by learning the other's strong points via a coordinator. The simulation shows that this approach provides good control quality and high reliability, especially when the system undergoes a sudden change.<
>