Intelligent control using θ-adaptive neural networks: a new approach to identification and control of nonlinear systems

Abstract

A novel use of neural networks for parameter estimation in nonlinear identification and control problems is proposed. The neural network is used to identify the relation between system variables and parameters of a dynamical system. Two different algorithms, a block estimation method and a recursive estimation method are presented. In the block estimation method, the neural network approximates the mapping between the system response and the system parameters, while in the recursive method, the parameter estimates are recursively updated by incorporating new information. Both methods are useful for parameter estimation in systems where either the structure of the nonlinearities present are unknown or when the parameters occur nonlinearly. Analytical conditions under which successful estimation can be carried out are studied. How the algorithms can be applied to control of nonlinear systems with unknown parameters and the associated stability issues are also discussed.