Damage detection of structures using signal processing and artificial neural networks

Abstract

This article presents a signal-based seismic structural health monitoring technique for damage detection and evaluating damage severity of a multi-story frame subjected to an earthquake event. As a case study, this article is focused on IASC–ASCE benchmark problem to provide the possibility for side-by-side comparison. First, three signal processing techniques including empirical mode decomposition, Hilbert vibration decomposition, and local mean decomposition, categorized as instantaneous time–frequency methods, have been compared to find a method with the best resolution in extracting frequency responses. Time-varying single degree of freedom and multiple degree of freedom models are used since real vibration signals are nonstationary and nonlinear in nature. Based on the results, empirical mode decomposition has proved to outperform than the others. Second, empirical mode decomposition is used to extract the acceleration response of the sensors. Next, a two-stage artificial neural network is used to classify damage patterns. The first artificial neural network identifies location and severity of damage and the second one calculates the severity of damage for the entire structure. IASC–ASCE benchmark problem is used to validate the proposed procedure. By taking advantage of signal processing and artificial intelligence techniques, damage detection of structures was successfully carried out in three levels including damage occurrence, damage severity, and the location of damage.

Sparse damage detection via the elastic net method using modal data

“…Comparing equations ( 10) and (11), the key difference between the elastic net and l 1 regularizations lies in the added term β 2 I. Through adding a small value on the diagonal items of X T X , the condition number of X T X can be reduced significantly.…”

“…[1][2][3] Doebling et al 4 and Sohn et al 5 present a comprehensive review of vibration-based damage detection methods before 1996 and between 1996 and 2001, respectively. Recently, a number of advanced methods based on signal processing techniques [6][7][8] and machine learning [9][10][11] have been proposed. Moreover, researchers have developed various techniques to consider the uncertainties and temperature effects for reliable damage detection.…”

Aplicação de técnicas de machine learning para o monitoramento de vibração e detecção de trincas em pontes

“…Técnicas de processamento de sinais de vibração podem ser utilizadas para avaliar mudanças em parâmetros estruturais de pontes. As respostas dinâmicas das estruturas são convertidas em grandezas digitais por dispositivos inteligentes capazes de captar oscilações avaliadas em ambiente computacional com a finalidade de determinar padrões, Beheshti et al (2020). Os impactos das vibrações podem ser avaliados segundo regulamentações quanto aos níveis que podem ou não apresentar danosàs estruturas, Bachmann et al (1994).…”

Deep learning based thermal crack detection on structural concrete exposed to elevated temperature

“…During the last decades, there are number of computer vision based methods developed to overcome the disadvantages of traditional investigations (Andrushia et al, 2019; Andrushia and Anand, 2020; Dai et al, 2019). These techniques use image-processing techniques to detect structural damages such as spalling, cracks and exposed aggregate (Beheshti Aval et al, 2020; Cha et al, 2016, 2017; Chen and Yu, 2020).…”