Health Monitoring of Large-Scale Civil Structures: An Approach Based on Data Partitioning and Classical Multidimensional Scaling

Abstract

A major challenge in structural health monitoring (SHM) is the efficient handling of big data, namely of high-dimensional datasets, when damage detection under environmental variability is being assessed. To address this issue, a novel data-driven approach to early damage detection is proposed here. The approach is based on an efficient partitioning of the dataset, gathering the sensor recordings, and on classical multidimensional scaling (CMDS). The partitioning procedure aims at moving towards a low-dimensional feature space; the CMDS algorithm is instead exploited to set the coordinates in the mentioned low-dimensional space, and define damage indices through norms of the said coordinates. The proposed approach is shown to efficiently and robustly address the challenges linked to high-dimensional datasets and environmental variability. Results related to two large-scale test cases are reported: the ASCE structure, and the Z24 bridge. A high sensitivity to damage and a limited (if any) number of false alarms and false detections are reported, testifying the efficacy of the proposed data-driven approach.

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

“…Hence, according to Kramar's recommendation [47], the bottleneck layer should have smaller neurons than the other hidden layers. The great advantage of the auto-associative neural network is its unsupervised learning aspect and ability to remove the noise, outliers, and any variability condition in data (features) [47][48][49].…”

A Novel Wireless Low-Cost Inclinometer Made from Combining the Measurements of Multiple MEMS Gyroscopes and Accelerometers

“…SHM measurements can be used to determine structural parameters with structural system identification techniques [ 11 , 12 ]. Structural system identification targets identifying the computer-based model’s parameters (such as axial or flexural stiffness) to estimate the structural response of the structure [ 13 ]. Based on the nature of the structural response and the features of the external excitation, structural system identification methods can be classified as static or dynamic [ 12 , 14 ].…”

Damage Detection in Largely Unobserved Structures under Varying Environmental Conditions: An AutoRegressive Spectrum and Multi-Level Machine Learning Methodology

“…To this aim, the most relevant techniques are statistical distance measures, which may depend upon the type of damage-sensitive features to handle. Some of the useful univariate and multivariate distance techniques to mention include the Mahalanobis distance [ 20 , 21 , 22 ] and Kullback–Leibler divergence [ 15 , 23 , 24 ], dynamic time warping [ 25 ], and other damage indices based on relative errors [ 26 , 27 ], classical and robust multidimensional scaling algorithms [ 28 , 29 ], etc.…”