Structural health monitoring (SHM) is a hot research topic with the main purpose of damage detection in a structure and assessing its health state. The major focus of SHM studies in recent years has been on developing vibration-based damage detection algorithms and using machine learning, especially deep learning-based approaches. Most of the deep learning-based methods proposed for damage detection in civil structures are based on supervised algorithms that require data from the healthy state and different damaged states of the structure in the training phase. As it is not usually possible to collect data from damaged states of a large civil structure, using such algorithms for these structures may be impractical. This paper proposes a new unsupervised deep learning-based method for structural damage detection based on convolutional autoencoders (CAEs). The main objective of the proposed method is to identify and quantify structural damage using a CAE network that employs raw vibration signals from the structure and is trained by the signals solely acquired from the healthy state of the structure. The CAE is chosen to take advantage of high feature extraction capability of convolution layers and at the same time use the advantages of an autoencoder as an unsupervised algorithm that does not need data from damaged states in the training phase. Applications on the two numerical models of IASC-ASCE benchmark structure and a grid structure located at the University of Central Florida, as well as the full-scale Tianjin Yonghe Bridge, prove the efficiency of the proposed algorithm in assessing the global health state of the structures and quantifying the damage.
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.
In this article, a novel vibration-based damage detection approach is proposed based on selecting effective cepstral coefficients, consisting of three main stages: (1) signal processing and feature extraction, (2) damage detection by combining effective cepstral coefficients through feature selection methods, and (3) performance evaluation. First, two feature extraction techniques are used in damage identification systems, including linear prediction cepstral coefficients and mel frequency cepstral coefficients. Second, to improve the performance of damage detection, the combination of the effective cepstral coefficients is proposed as a damage index. By applying several feature selection methods, the most effective coefficients are found and then combined to create a subset that carries the most significant information about the structural damage. Finally, the support vector machine classifier is performed to evaluate the proposed approach in detecting the structural damage. The proposed technique is verified using a suite of numerical and full-scale studies. Results confirm that the proposed method achieves a significant performance with great accuracy and reduces false alarms.
In recent years, many efforts have been made to develop efficient deep-learning-based structural health monitoring (SHM) methods. Most of the proposed methods employ supervised algorithms that require data from different damaged states of a structure in order to monitor its health conditions. As such data are not usually available for real civil structures, using supervised algorithms for the health monitoring of these structures might be impracticable. This paper presents a novel two-stage technique based on generative adversarial networks (GANs) for unsupervised SHM and damage identification. In the first stage, a deep convolutional GAN (DCGAN) is used to detect and quantify structural damages; the detected damages are then localized in the second stage using a conditional GAN (CGAN). Raw acceleration signals from a monitored structure are used for this purpose, and the networks are trained by only the intact state data of the structure. The proposed method is validated through applications on the numerical model of a bridge health monitoring (BHM) benchmark structure, an experimental steel structure located at Qatar University, and the full-scale Tianjin Yonghe Bridge.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.