Online Hybrid Learning Methods for Real-Time Structural Health Monitoring Using Remote Sensing and Small Displacement Data

Abstract

Structural health monitoring (SHM) by using remote sensing and synthetic aperture radar (SAR) images is a promising approach to assessing the safety and the integrity of civil structures. Apart from this issue, artificial intelligence and machine learning have brought great opportunities to SHM by learning an automated computational model for damage detection. Accordingly, this article proposes online hybrid learning methods to firstly deal with some major challenges in data-driven SHM and secondly detect damage via small displacement data from SAR images in a real-time manner. The proposed methods contain three main parts: (i) data augmentation by Hamiltonian Monte Carlo and slice sampling for addressing the problem of small displacement data, (ii) data normalization by an online deep transfer learning algorithm for removing the effects of environmental and/or operational variability from augmented data, and (iii) feature classification via a scalar novelty score. The major contributions of this research include proposing two online hybrid unsupervised learning methods and providing effective frameworks for online damage detection. A small set of displacement samples extracted from SAR images of TerraSar-X regarding a long-term monitoring scheme of the Tadcaster Bridge in United Kingdom is applied to validate the proposed methods.

Elimination of Thermal Effects from Limited Structural Displacements Based on Remote Sensing by Machine Learning Techniques

“…Sarmadi [36] exploited this neural network to aid in non-parametric anomaly detection methods to address the negative effects of the environmental and/operational variability from time-series and modal features. Entezami et al [18] developed an online hybrid learning method for real-time SHM with small displacements from SAR images using a novel data normalization algorithm based on the AANN. The reconstruction-based data normalization can be developed from some advanced machine learning algorithms.…”

“…The significant variability in conditions in SHM are mainly caused by environmental and operational changes. In most cases, variations in temperature, humidity, wind characteristics, and live loads (e.g., traffic) are the major reasons for changes in the measured data or features extracted from such data (e.g., modal parameters [17], displacements extracted from SAR images [18,19]).…”

Multi-Antenna Global Navigation Satellite System/Inertial Measurement Unit Tight Integration for Measuring Displacement and Vibration in Structural Health Monitoring

“…On this basis, an SHM strategy first intends to measure responses such as displacements over time, and then obtain insightful information about the current or unknown condition of a civil structure by computational techniques either in time domain or in frequency domain [3,4]. Various types of sensor devices such as linear variable differential transformers, optical fiber sensors, smartphones, vision cameras, and radars are used in SHM to measure the displacement responses, but dynamic deformation monitoring widely adopts GNSS and accelerometers for SHM non-stop or with high periodicity but not requiring gluing/embedding sensors into the structure [5][6][7][8]. The RTK-GNSS can achieve a subcentimeter-level measurement accuracy, and it is often selected for structural displacement estimation of large-scale structures such as long-span bridges and high-rise buildings, which usually have at least centimeter-level displacements [9][10][11].…”

A Parsimonious Yet Robust Regression Model for Predicting Limited Structural Responses of Remote Sensing

“…The choice of an appropriate sensing technology and of the measurement of the structural response to different natural or man-made excitation sources is critical to provide data sensitive to the structural state. The process of data analytics is often conducted through data cleaning, compression, fusion [10], data augmentation [11], data prediction [12], data normalization [13], and feature extraction [14]. Different machine learning algorithms within the realms of unsupervised learning [15][16][17][18] and supervised learning [19] can be adopted for decision-making about whether the bridge has suffered damage or can still operate normally.…”