Machine learning algorithms for damage detection under operational and environmental variability

TLDR

The study aims to detect structural damage amid operational and environmental variations by directly comparing four vibration‑based machine‑learning algorithms—auto‑associative neural networks, factor analysis, Mahalanobis distance, and singular value decomposition—to distinguish damage from benign changes. The authors applied these four algorithms to data from a laboratory‑tested, base‑excited three‑story frame equipped with accelerometers, varying stiffness and mass to emulate environmental effects, and introduced damage via a bumper‑induced impact nonlinearity that mimics crack opening and loose connections.

Abstract

The goal of this article is to detect structural damage in the presence of operational and environmental variations using vibration-based damage identification procedures. For this purpose, four machine learning algorithms are applied based on the auto-associative neural network, factor analysis, Mahalanobis distance, and singular value decomposition. A base-excited three-story frame structure was tested in laboratory environment to obtain time-series data from an array of accelerometers under several structural state conditions. Tests were performed with varying stiffness and mass conditions with the assumption that these sources of variability are representative of changing operational and environmental conditions. Damage is simulated through nonlinear effects introduced by a bumper mechanism that induces a repetitive, impact-type nonlinearity. This mechanism intends to simulate the cracks that open and close under dynamic loads or loose connections that rattle. The unique contribution of this study is a direct comparison of the four proposed machine learning algorithms that have been reported as reliable approaches to separate structural conditions with changes resulting from damage from changes caused by operational and environmental variations.