On optimal control scheme based on feedforward and inverse models of artificial neural network

Abstract

The mostly optimum control questions were based on precise mathematical model of the controlled object at present, and only aimed at the few parameters implementation optimization control. Because it was very difficult or imposable that established precise mathematical model of actual controlled objects.Because actual massive complex, unknown and indefinite nonlinear objects had many optimization parameters, it made conventional optimum control method no longer to be suitable to. In order to solve these problems, in the analysis optimum control principle foundation, the optimum control scheme based on the ANN's (Artificial Neural Network) feedforward / inverse model had designed. Basis on characteristics of nonlinear mapping and adaptive study of ANN's models and so on, the configuration of the ANN's feedforward and inverse models were designed. Used specialized training method of ANN models, and based on the EF(Exponential Forgetting) algorithm renewed covariance matrix, iterative training online to ANN's models were carried out, therefore obtained the ANN's models with the optimization configuration. Simulation results show that, designed optimum control structure scheme is reasonable, and ANN's controller may get good controlling effect. © 2011 Springer-Verlag.