特征系统实现算法中的噪声问题研究

Noise Handling of the Eigensystem Realization Algorithm

研究特征系统实现算法在模态识别过程中的噪声处理问题。特征系统实现算法为目前土木工程领域应用较为广泛的一种模态识别法。在处理实测数据时,特征系统实现算法将实测数据分解为结构真实信号和噪声信号,从而将噪声消除。分块Hankel矩阵的维数对信噪分离过程影响很大。提出当分块Hankel矩阵的分块行与分块列数接近时,真实和噪声信号可以最好的分离。通过在实测信号里添加噪声(产生噪声-噪声信号),将实测信号和噪声-噪声信号识别的结果进行比较,提出了1种验证识别模态参数是否为结构真实模态的检验方法。本文应用导管架平台实例来验证提出方法的适用性。结果表明,当分块Hankel矩阵的分块行与分块列数接近时,真实和噪声信号能够有效地分离,此时添加的噪声主要影响噪声信号部分。由实测信号和噪声-噪声信号识别的模态参数非常吻合。

In dealing with noisy measurement data,the Eigensystem Realization Algorithm（ERA） partitions the realized model into signal and noise portions so that the noise portion can be disregarded.A critical issue is the determination of the dimensions of the block Hankel matrix.We show that the signal and noise matrices can be better separated when the number of block-rows and number of block-columns of the corresponding block Hankel matrix are chosen to be close to each other.We propose a verification procedure to justify that the estimated modal parameters are noise insensitive and thus indeed associated with the true system.The procedure involves artificially injecting random noise into the measured signals to create noisy-noisy signals,then comparing the identification results obtained respectively from the measured and noisy-noisy signals.Using experimental data collected from a jacket-type platform,we demonstrate that signal and noise portions can be properly separated while the number of the block-rows and number of block-columns are close.