论文部分内容阅读
An approach is proposed to avoid model structure determination in system identification using NARMAX (nonlinear auto- regressive moving average with exogenous inputs) model. Identification procedure is formulated as an optimization procedure of a special class of Hopfield network in the proposed approach. The particular structure of these Hopfield networks can avoid the local optimum problem. Training of these Hopfield network achieves model structure determination and parameter estimation. Convergence of Hopfield networks guarantees that a NARMAX model of random initial state will approach a valid identification model with accurate state parameters. Results of two simulation examples illustrate that this approach is efficient and simple.
An approach is proposed to avoid model structure determination in system identification using NARMAX (nonlinear auto-regressive moving average with exogenous inputs) model. Identification of the particular class of Hopfield network in the proposed approach. of these Hopfield networks can avoid the local optimum problem. Training of these Hopfield networks achieves model structure determination and parameter estimation. Convergence of Hopfield networks guarantees that a NARMAX model of random initial state will approach a valid identification model with accurate state parameters. two simulation examples illustrate that this approach is efficient and simple.