A HYBRID NEURAL-NETWORK-BASED SELF-ORGANIZING CONTROLLER

This paper presents a novel and systematic approach to constructing a self-organizing and self-learning multivariable controller. The proposed controller is built on a hybrid neural network consisting of a variable-structure competitive network and a standard back-propagation neural network (BNN). We develop the corresponding self-organizing and learning algorithms. The controller shares certain features with traditional fuzzy controllers in terms of using error-based input forms and emphasizing the rule-based paradigms. However, knowledge representation and reasoning are here carried out by the network structure and computing, instead of logical inference. On the other hand, compared with ordinary BNN-based control paradigms the proposed controller possesses a distinctive characteristic; that is, while having the advantages of computational efficiency and trainable capability of the network paradigm, it maintains the clarity of the rule-based paradigm by self-organizing a rule-base, thereby providing an explicit explanation facility for the BNN network. In addition, the on-line extracted rule-base may be used as a basis for algorithm-based fuzzy controllers. Extensive simulation studies on the problem of multivariable blood pressure control not only demonstrates the feasibility and efficiency of the proposed system, but also offers same insights into better understanding of many aspects of the system, particularly in those aspects such as the adaptive ability and learning convergence property with respect to a wide range of situations subject to different net parameters and controlled environments.