Vibration-based damage detection for bridges by deep convolutional denoising autoencoder

Abstract

One of the main challenges for structural damage detection using monitoring data is to acquire features that are sensitive to damages but insensitive to noise (e.g. sensor measurement noise) as well as environmental and operational effects (e.g. temperature effect). Inspired by the capabilities of deep learning methods in representation learning, various deep neural networks have been developed to obtain effective damage features from raw vibration data. However, most of the available deep neural networks are supervised, resulting in practical difficulties owing to the lack of damage labels. This article proposes a damage detection strategy based on an unsupervised deep neural network, referred to as deep convolutional denoising autoencoder, which accepts multi-dimensional cross-correlation functions as input. The strategy aims to extract damage features from field measurements of undamaged structures under the influence of noise and temperature uncertainties. In the proposed strategy, cross-correlation functions of vibration data are first calculated as basic features; then deep convolutional denoising autoencoder is developed to reconstruct cross-correlation functions from their noise-corrupted versions to extract desired features; exponentially weighted moving average control charts are finally established for these features to identify minor structural damages. The strategy is evaluated through a numerical simply supported beam model and an experimental continuous beam model. The mechanism of deep convolutional denoising autoencoder to extract damage features is interpreted by visualizing feature maps of convolutional layers in the encoder. It is found that these layers perform rough estimations of modal properties and preserve the damage information as the general trend of these properties in multiple extra frequency bands. The results show that the proposed strategy is competent for structural damage detection under the exposed environment and worth further exploring its capabilities in applications of real bridges.

An Unsupervised Learning Approach for Early Damage Detection by Time Series Analysis and Deep Neural Network to Deal with Output-Only (Big) Data

“…As well as the input and output layers, a deep autoencoder includes several hidden layers. The central hidden layer is called the bottleneck, as it has the minimum number of neurons among all the hidden layers; this layer plays a crucial role in the problem of dimensionality reduction [23]. In this study, a deep autoencoder with seven hidden layers has been designed, to extract the outputs of the bottleneck layer as the low-dimensional system features.…”

A decentralized unsupervised structural condition diagnosis approach using deep auto‐encoders

“…Deep learning algorithms can be divided into supervised and unsupervised learning. Recently, the supervised deep learning algorithms have been applied to structural surface crack detection and damage classification, especially the convolutional neural networks (CNN) (Bang, Park, Kim, & Kim, 2019;Cha, Choi, & Büyüköztürk, 2017;Li, Zhao, & Zhou, 2019;Lin et al, 2017;Pathirage et al, 2018;Y. Zhang, Miyamori, Mikami, & Saito, 2019).…”

“…Recently, unsupervised deep learning algorithms (Gu, Gul, & Wu, 2017;Lei, Jia, Lin, Xing, & Ding, 2016;Ozdagli & Koutsoukos, 2019;Rafiei & Adeli, 2018;Y. Zhang et al, 2019;Zhou & Wahab, 2017;H.…”

Lost data reconstruction for structural health monitoring using deep convolutional generative adversarial networks

“…The encoder-decoder networks are unsupervised learning architectures in which it compresses the input to a small set of data and then reconstructs the input from them. 26 This feature is quite suitable for time-series data compression and reconstruction. Autoencoder is a popular encoderdecoder structure, which transforms the inputs into a smaller latent space vector and produces the outputs to the same size as the inputs.…”