基于最小二乘模型的Bayes参数辨识方法

Parameter Identification with Recursive Least Squares Method Based on Bayes

现实中的系统都具有一定的非线性,并且这种非线性在非线性通道补偿和非线性系统故障诊断等领域是不可忽略的。针对有白噪声干扰的输出误差非线性系统,将数学模型与基于最小二乘的Bayes算法相结合,用数学模型参数代替辨识模型信息向量中的未知项,用基于白噪声的最小二乘模型进行不可预测辨识,从而提出了基于最小二乘模型的Bayes参数辨识方法。介绍了Bayes基本原理及2种常用的方法,经过理论分析和MATLAB仿真研究证明,该方法原理简单、计算量小、速度快、抗干扰能力强,可以对较高精度非线性系统进行参数估计和在线辨识。

Practical system is a nonlinear system, and sometimes this nonlinearity which in the field of nonlinear channel compensation and fault diagnosis of nonlinear systems can not be ignored. The output error of nonlinear system with white noise interference combined the mathematical model based on least squares Bayes algorithm to instead of the unknown in the information vector of parameter identification model, and using the least squares model based on white noise for the unpredictability of identification. In order to verify the validity of the method, the paper also described a Bayesian basic principles and its two commonly used methods. The theoretical analysis and MATLAB simulation results showed that the principle of this method is simple, small amount of calculation, fast running and strong anti-interference ability, so it can be carried out on the higher accuracy nonlinear system for parameter estimation and on-line identification.