Application of Hopfield neural network in self-tuning control

An indirect self-tuning controller (STC) based on pole placement is designed with the application of a Hopfield neural network to the estimation of plant parameters and the design of the controller, the Hopfield neural network model is completely examined as to the uniqueness of the model output solution, and its application in parameter estimation and controller design is also described. The control characteristics of a plant are evaluated by means of simulation for the second-order linear time invariant plant of a typical permanent-magnet DC motor model. The results obtained are compared with those of the exponentially weighted recursive least squares method in parameter estimation and the Gaussian elimination method in solving the Diophantine equation in order to highlight the effectiveness of the proposed control strategy using the Hopfield neural network