一种基于Volterra模型的非线性系统具有全解耦结构的递阶式自适应辨识方法

研究了在输入输出观测数据均含有噪声时如何对基于Volterra级数描述的非线性系统进行解耦自适应辨识的问题. 按照Volterra级数模型的伪线性组合结构, 采用总体最小二乘辨识技术的原理, 导出了一种总体全解耦辨识的思想. 从而建立了一种具有全解耦结构的递阶式自适应辨识算法, 给出了该算法的结构图. 相比于部分解耦辨识算法, 该算法的优点在于它能够在全噪声数据环境下得到更高的收敛速度和精度. 仿真研究的结果证明了本文方法的有效性.

A Staged Adaptive Identification Method with Fully Decoupled Structure for Nonlinear System Based on Volterra Model

The decoupled adaptive identification problem for nonlinear system based on Volterra series is discussed in allusion to the corrupted input and output observation data. According to the pseudo linear combination structure of Volterra series model, by applying the principle of the total least squares identification, a total fully decoupled identification idea is revealed. And then a staged adaptive identification algorithm with fully decoupled structure is built, and its framework diagram is shown. The advantage of the presented algorithm is that it possesses higher convergence speed and precision than the partly decoupled identification algorithm under a complete noise data environment. Finally simulation results indicate that the presented algorithm in this paper is efficient.