Symmetric NARMA-U Model and Its Neural Network Self-Tuning Controller
NARMA-L2 model with prediction error compensation was approached by NARMA mod-el's first-order Taylor expansion at adaptive filtering dynamic working point.By second order Taylor expansion approaching at the adaptive filtering dynamic working point,a symmetric NARMA-U mod-el was obtained.By using BP neural net work identifying symmetrical NARMA-U model parameters,a generalized object function was developed.Based on the nonlinear system neural net work self-tun-ing controller of symmetrical NARMA-U model developed,on-line learning of BP neural net connec-tion weight value was conducted by using adaptive optimization algorithm for direct minimization of index function.Simulation results indicate that the model shows excellent response.
neural net work self-tuning controllernonlinear systemsymmetric NARMA-U modeladaptive optimization algorithm for direct minimization of index function
万方数据
维普
