Novel network structure and parameter identification method for RBF-AR model

Abstract

The invention discloses a novel network structure and parameter identification method for an RBF-AR model. An RBF-AR (Radial Basis Function Network-Style Coefficients Auto Regressive) model is converted into a novel generalized RBF neural network containing two hidden layers according to the structure characteristics of the model. In view of the problem that an SNPOM (Structured Nonlinear Parameter Optimization) method is of low RBF-AR model identification accuracy at low noise-to-signal ratio, a self-organization state space model of the RBF-AR model is built and an adaptive particle filter algorithm with parameter optimal initial value and parameter driving noise statistical characteristic estimation as the core is employed to identify the parameters of the RBF-AR model. The noise-containing data modeling precision and prediction precision of the RBF-AR model can be improved effectively. Online estimation and real-time control of the RBF-AR model are realized. A novel method is provided for parameter identification of the RBF-AR model.

Description

technical field [0001] The invention relates to a novel network structure and parameter identification method of an RBF-AR model. Background technique [0002] Recently, researchers have found that combining neural networks with some simple models can result in high-performance combined models. A typical example is the RBF-AR(X) (RBF network-style coefficients autoregressive model with exogenous variable) model proposed by Peng et al., which provides an effective solution for the modeling and control of nonlinear systems. The RBF-AR model not only has the advantage of RBF network function approximation, but also has the advantage of state-dependent autoregressive model describing nonlinearity. The research results show that the RBF-AR model is superior to some other models or methods in terms of prediction accuracy; in the case of achieving similar prediction accuracy, the RBF-AR model requires much fewer centers than the RBF network alone. [0003] However, one difficulty...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiencies of the existing technology and solve the technical problem of poor accuracy and reliability of the existing RBF-AR mod...

Images