基于小波消噪和希尔伯特黄变换的损伤检测技术研究

Research on Structural Damage Detection Based on Wavelet De-Noising and Hilbert-Huang Transform

针对经验模式分解(EMD)易受噪声影响的缺点,提出采用小波消噪结合Hilbert-Huang变换的结构损伤检测方法。首先对含噪声振动信号进行小波消噪预处理实现信噪分离,再进行EMD分解得到若干固有模态函数(IMF),利用希尔伯特(Hilbert)变换得到其瞬时频率。提出了一个基于低阶瞬时频率变化率的损伤判定指标,利用此指标可以判断损伤是否发生。数值研究结果表明小波消噪结合HHT的方法是进行损伤检测比较有效的方法。

In view of the shortcoming of the empirical mode decomposition（EMD）whose precision is subject to noise effect,Hilbert-Huang transformation combined with the wavelet de-noising for structural damage detection is proposed.First,the theoretical background of the wavelet-based de-noising method and the Hilbert-Huang transform is presented.In the first step,the noisy vibration signal is pre-processed with wavelet transform to separate the signal from noise.In step two,Empirical Mode Decomposition（EMD）is carried out to obtain the Intrinsic Mode Functions（IMFs）.In the third and final stage,Hilbert transform is applied to the interested IMFs to get the instantaneous frequencies.A new damage indicator based on the instantaneous frequencies is proposed to determine whether the damage had occurred.The damage detection index,defined as the sum of the first three frequency change rate（FCR）,can be used for damage detection.The wavelet based de-noising and Hilbert-Huang transform are firstly verified by using a simulated signal with three dominant frequencies.Then a three-story shear building model is used for the damage detection.Numerical results of the study showed that the proposed method is effective for structural damage detection.