Skip to main navigation Skip to search Skip to main content

Use of a Roving Vision Sensor Setup to Train an Autoencoder for Damage Detection of Bridge Structures

  • Darragh Lydon
  • , Myra Lydon
  • , Juliana Early
  • , Su Taylor
  • Queen's University of Belfast

Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

Abstract

This paper will demonstrate a solution for detecting damage to a bridge structure from measured displacements gathered using a roving vision sensor based approach. The measurement of displacement was accomplished using a synchronised multi-camera vision-based displacement measurement system. Displacement measurements can provide a valuable insight into the structural condition and service behaviour of bridges under live loading. Computer Vision systems have been validated as a means of displacement calculation, the research developed here is intended to form the basis of a real time damage detection system. This is done through the use of unsupervised deep learning methods for anomaly detection which could form the basis of a low cost durable alternative. The performance of the system was evaluated in a series of controlled laboratory tests. This research provides a means of detecting changes to a bridge structure through use of minimal sensor installation, reducing potential sources of error and allowing for potential live rating of bridge structures.

Original languageEnglish
Title of host publicationCivil Structural Health Monitoring - Proceedings of CSHM-8 Workshop
EditorsCarlo Rainieri, Giovanni Fabbrocino, Nicola Caterino, Francesca Ceroni, Matilde A. Notarangelo
PublisherSpringer Science and Business Media Deutschland GmbH
Pages367-372
Number of pages6
ISBN (Print)9783030742577
DOIs
Publication statusPublished - 2021
Externally publishedYes
Event8th Civil Structural Health Monitoring Workshop, CSHM-8 2021 - Virtual, Online
Duration: 31 Mar 20212 Apr 2021

Publication series

NameLecture Notes in Civil Engineering
Volume156
ISSN (Print)2366-2557
ISSN (Electronic)2366-2565

Conference

Conference8th Civil Structural Health Monitoring Workshop, CSHM-8 2021
CityVirtual, Online
Period31/03/212/04/21

Keywords

  • Anomaly Detection
  • Computer Vision
  • Deep Learning
  • Structural Health Monitoring

Fingerprint

Dive into the research topics of 'Use of a Roving Vision Sensor Setup to Train an Autoencoder for Damage Detection of Bridge Structures'. Together they form a unique fingerprint.

Cite this