Semi-supervised detection of structural damage using Variational Autoencoder and a One-Class Support Vector Machine

TL;DR

This paper introduces a semi-supervised approach combining Variational Autoencoders and One-Class SVMs to automatically detect structural damage from sensor data, improving upon manual decision rules in SHM systems.

Contribution

It presents a novel semi-supervised method integrating VAE and OC-SVM for automatic damage detection in structures, optimized with hyperparameter tuning.

Findings

Effective damage detection across nine damage scenarios

Automated anomaly identification without manual thresholds

Enhanced detection accuracy using data-driven features

Abstract

In recent years, Artificial Neural Networks (ANNs) have been introduced in Structural Health Monitoring (SHM) systems. A semi-supervised method with a data-driven approach allows the ANN training on data acquired from an undamaged structural condition to detect structural damages. In standard approaches, after the training stage, a decision rule is manually defined to detect anomalous data. However, this process could be made automatic using machine learning methods, whom performances are maximised using hyperparameter optimization techniques. The paper proposes a semi-supervised method with a data-driven approach to detect structural anomalies. The methodology consists of: (i) a Variational Autoencoder (VAE) to approximate undamaged data distribution and (ii) a One-Class Support Vector Machine (OC-SVM) to discriminate different health conditions using damage sensitive features extracted from VAE's signal reconstruction. The method is applied to a scale steel structure that was tested in nine damage's scenarios by IASC-ASCE Structural Health Monitoring Task Group.