A structural damage detection algorithm based on discrete wavelet transform and ensemble pattern recognition models

Abstract

Damage detection is of great importance in reducing maintenance cost and preventing collapse of structures. Despite existing damage detection methods, the current literature lacks a comprehensive method, which: (i) is applicable to complex structures with large degrees of freedom, (ii) captures even low-level damages, and (iii) gives reasonable accuracy in the presence of uncertainty conditions such as noise and temperature. Hence, this study proposes a damage detection algorithm based on discrete wavelet transform and an ensemble of pattern recognition models, in which: (1) vibration data is decomposed through discrete wavelet transforms, (2) the decomposed data is compressed using principal component analysis, (3) individual damage models of the structure are trained through pattern recognition models of deep neural network and couple sparse coding, where the compressed decomposed vibration data as well as damage data are inputted, and (4) ultimately, the individual damage models are merged into one by majority voting to predict damage location and severity of the structure. The proposed algorithm is tested on a numerical model of a one-bay three-story steel frame, and experimental data of a large-scale bridge structure. It is found that the algorithm can precisely detect low-level damages at multiple locations, even in beam–column connections and complex structures, in the presence of uncertainty conditions such as noise and temperature.