时间序列与主成分分析的结构损伤识别

提出一种基于AR模型均方根误差主成分分析的结构损伤识别方法.首先利用检测数据建立AR模型,求得模型的均方根误差,然后,采用主成分分析的方法获得主成分载荷矩阵,将此矩阵经过数据标准化处理得到结构损伤特征指标.通过比较结构不同状态下传感器获得的损伤特性指标,进行损伤定位.最后,基于美国Los Alamos实验室三层框架结构模型的损伤实验数据,利用本文方法和基于AR模型系数损伤定位的方法对该结构各种损伤状况进行识别.2种方法的对比研究表明采用本文的方法,通过主成分分析排除外界干扰因素,减少运算量,具有更高的损伤识别精度.

Structural Damage Identification Based on Time Series and Principal Component Analysis

Structural damage identification based on the principal component analysis method for the root mean squared error （RMSE） of auto regressive （AR） model is proposed in this paper. Firstly, the AR model is estab-lished by using dynamic responding data, and the RMSE of AR model is calculated. The loading matrix is obtained from principal component analysis, and the damage characteristic index is obtained through standardized processing of the loading matrix. The damag sors placed in different positions frame structure model of the Los e is located by comparing with the of a structure. Finally, based on Alamos National Laboratory, the damage characteristic index resulted from sen-a series of experimental data of a three-story damage states are detected with two methods, namely the presented method and the AR model coefficient method. A comparison shows that the present method can lead to less amount of computing time, high suitability and identification accuracy, because the principal com-ponent analysis eliminates external interference.