A PCA-BASED ALGORITHM FOR STRUCTURAL HEALTH MONITORING USING FREQUENCY RESPONSE FUNCTIONS
ZHU Junhua1,2; YU Ling1,2
1. Department of Mechanics and Civil Engineering, Jinan University, Guangzhou, 510632, China;2. Key Lab of Disaster Forecast and Control in Engineering of Ministry of Education of China,Jinan University, Guangzhou, 510632, China
Abstract:Abstract: Based on measured Frequency Response Functions (FRFs), an easier and more efficient method for structural health monitoring is proposed by using Principle Component Analysis (PCA) in this paper. The FRFs of the healthy and damaged structure are used as initial data. The method uses a PCA transform technique to obtain the features of intact structure, also called the Principle Components (PCs), in which an orthogonal transformation matrix packed by the first few eigenvectors of covariance matrix can be found. Further, the orthogonal transformation matrix is applied to the FRFs of damage structures so as to find the features of the corresponding damage state of structures. Both structural damage detection and structural health monitoring can be achieved by comparing the two dimensional PCs distribution charts respectively corresponding to the damaged and to the healthy state of structures. Two numerical simulation examples show that the proposed method is correct, effective and feasible. Because it is based purely on the analysis of the vibration responses of structures, which makes it quite easy to perform and demonstrates its adaptability to structural health monitoring in field.
朱军华;;余岭;. 基于频响函数的结构健康监测主成分分析法 [J]. , 2011, 30(5): 111-115.
ZHU Junhua;YU Ling;. A PCA-BASED ALGORITHM FOR STRUCTURAL HEALTH MONITORING USING FREQUENCY RESPONSE FUNCTIONS. , 2011, 30(5): 111-115.