基于小波包分析的框架结构损伤识别

Damage Identification of Frame Structures Based on Wavelet Packet Analysis

损伤将引起结构动力特性和动力响应的变化,反过来,可以通过结构动力性能或动力响应的变化识别结构损伤,但它们对结构局部损伤并不十分敏感。而小波包分析具有优越的时-频局部化性能,可以在时—频域以任意精度进行信号分析。本文在小波包分析基础上,提出了基于小波包分析的损伤检测和识别方法:首先将结构响应信号分解为小波包组分,然后通过考察各组分小波信号的变化情况识别损伤。该方法仅利用结构响应数据识别损伤,实测方便,计算简单,并通过3层钢框架结构的模型试验成功地识别出损伤时刻和损伤位置,验证了其可行性。

Damage will cause the variations of structural dynamic property and response. Contrarily, the structural damage may be identified by the variation of dynamic property and response. But they are not much sensitive to the local damage of structure. As the wavelet packet analysis has an excellent localized performance in time-frequency domain, it may analyse a signal in an arbitrary resolution in time-frequency domain. On the basis of wavelet packet analysis, a structural damage detection method based on wavelet packet analysis is presented in this paper. Firstly, the structural response signals are decomposed into the wavelet packet components. And then, the damage is identified by observing the variation of every wavelet signal. This method uses the data of structural response only to identify damage. The field measure is convenient and the analysis is simple. At last, the presented method was applied to detect and identification the damage time and location of frame structure successfully. Its feasibility was validated.