基于小波域数据的线性ARMAX模型参数估计

Parameter Estimation of Linear ARMAX Model Based on Data of Wavelet Domain

线性时不变系统离散ARMAX模型在随机噪声情况下影响输出精度。为此提出直接利用小波域的输入输出数据,估计出模型的参数的方法。最小二乘法是时域参数估计的主要方法,随着对小波理论的深入研究,在信号处理方面起着重要的作用。信号经过小波变换后,得到具有时频特征的小波域的信号,方便进行去噪的处理,去噪结果比时域和频域更有效。通过小波最小二乘法估计出模型的参数,与时域最小二乘法的估计参数比较,仿真表明改进方法是可行性和有效性。

For the output data of linear ARMAX model are corrupted with noises, a method of parameter estima-tion was proposed to directly estimate the parameters of the model with the input-output data of wavelet domain. The least squared （LS） method is an important method for parameter estimation in time domain, and with the wavelet transform developed, it plays an important role in signal processing. By means of wavelet transform, the signals have both characteristics of time and frequency and becam signals of wavelet domain. Then the denoising result was more effective than in time domain and in frequency domain. The parameters of the model were estimated by the wavelet least squared method, compare with the least squared method in time domain, the proposed method is feasible and ef-fective.