Quantifying uncertainty in structural condition with Bayesian deep learning : A study on the Z-24 bridge benchmark

A machine learning approach to damage detection is presented for a bridge structural health monitoring system, validated on the renowned Z-24 bridge benchmark dataset where a sensor instrumented, threespan bridge was realistically damaged in stages. A Bayesian autoencoder neural network is trained t...

Full description

Bibliographic Details
Main Author: Asgrimsson, David Steinar
Format: Others
Language:English
Published: KTH, Skolan för elektroteknik och datavetenskap (EECS) 2019
Subjects:
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-251451
id ndltd-UPSALLA1-oai-DiVA.org-kth-251451
record_format oai_dc
spelling ndltd-UPSALLA1-oai-DiVA.org-kth-2514512019-05-25T04:29:02ZQuantifying uncertainty in structural condition with Bayesian deep learning : A study on the Z-24 bridge benchmarkengKvantifiering av osäkerhet i strukturella tillstånd med Bayesiansk djupinlärningAsgrimsson, David SteinarKTH, Skolan för elektroteknik och datavetenskap (EECS)2019Bayesian Deep LearningAutoencodersBridge Structural Health MonitoringBridge Damage DetectionComputer and Information SciencesData- och informationsvetenskapA machine learning approach to damage detection is presented for a bridge structural health monitoring system, validated on the renowned Z-24 bridge benchmark dataset where a sensor instrumented, threespan bridge was realistically damaged in stages. A Bayesian autoencoder neural network is trained to reconstruct raw sensor data sequences, with uncertainty bounds in prediction. The reconstruction error is then compared with a healthy-state error distribution and the sequence determined to come from a healthy state or not. Several realistic damage stages were successfully detected, making this a viable approach in a data-based monitoring system of an operational bridge. This is a fully operational, machine learning based bridge damage detection system, that is learned directly from raw sensor data. En maskininlärningsmetod för strukturell skadedetektering av broar presenteras. Metoden valideras på det kända referensdataset Z-24, där en sensor-instrumenterad trespannsbro stegvist skadats. Ett Bayesianskt neuralt nätverk med autoenkoders tränas till att rekonstruera råa sensordatasekvenser, med osäkerhetsgränser i förutsägningen. Rekonstrueringsavvikelsen jämförs med avvikelsesfördelningen i oskadat tillstånd och sekvensen bedöms att komma från ett skadad eller icke skadat tillstånd. Flera realistiska stegvisa skadetillstånd upptäcktes, vilket gör metoden användbar i ett databaserat skadedetektionssystem för en bro i full storlek. Detta är ett lovande steg mot ett helt operativt databaserat skadedetektionssystem. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-251451TRITA-EECS-EX ; 101application/pdfinfo:eu-repo/semantics/openAccess
collection NDLTD
language English
format Others
sources NDLTD
topic Bayesian Deep Learning
Autoencoders
Bridge Structural Health Monitoring
Bridge Damage Detection
Computer and Information Sciences
Data- och informationsvetenskap
spellingShingle Bayesian Deep Learning
Autoencoders
Bridge Structural Health Monitoring
Bridge Damage Detection
Computer and Information Sciences
Data- och informationsvetenskap
Asgrimsson, David Steinar
Quantifying uncertainty in structural condition with Bayesian deep learning : A study on the Z-24 bridge benchmark
description A machine learning approach to damage detection is presented for a bridge structural health monitoring system, validated on the renowned Z-24 bridge benchmark dataset where a sensor instrumented, threespan bridge was realistically damaged in stages. A Bayesian autoencoder neural network is trained to reconstruct raw sensor data sequences, with uncertainty bounds in prediction. The reconstruction error is then compared with a healthy-state error distribution and the sequence determined to come from a healthy state or not. Several realistic damage stages were successfully detected, making this a viable approach in a data-based monitoring system of an operational bridge. This is a fully operational, machine learning based bridge damage detection system, that is learned directly from raw sensor data. === En maskininlärningsmetod för strukturell skadedetektering av broar presenteras. Metoden valideras på det kända referensdataset Z-24, där en sensor-instrumenterad trespannsbro stegvist skadats. Ett Bayesianskt neuralt nätverk med autoenkoders tränas till att rekonstruera råa sensordatasekvenser, med osäkerhetsgränser i förutsägningen. Rekonstrueringsavvikelsen jämförs med avvikelsesfördelningen i oskadat tillstånd och sekvensen bedöms att komma från ett skadad eller icke skadat tillstånd. Flera realistiska stegvisa skadetillstånd upptäcktes, vilket gör metoden användbar i ett databaserat skadedetektionssystem för en bro i full storlek. Detta är ett lovande steg mot ett helt operativt databaserat skadedetektionssystem.
author Asgrimsson, David Steinar
author_facet Asgrimsson, David Steinar
author_sort Asgrimsson, David Steinar
title Quantifying uncertainty in structural condition with Bayesian deep learning : A study on the Z-24 bridge benchmark
title_short Quantifying uncertainty in structural condition with Bayesian deep learning : A study on the Z-24 bridge benchmark
title_full Quantifying uncertainty in structural condition with Bayesian deep learning : A study on the Z-24 bridge benchmark
title_fullStr Quantifying uncertainty in structural condition with Bayesian deep learning : A study on the Z-24 bridge benchmark
title_full_unstemmed Quantifying uncertainty in structural condition with Bayesian deep learning : A study on the Z-24 bridge benchmark
title_sort quantifying uncertainty in structural condition with bayesian deep learning : a study on the z-24 bridge benchmark
publisher KTH, Skolan för elektroteknik och datavetenskap (EECS)
publishDate 2019
url http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-251451
work_keys_str_mv AT asgrimssondavidsteinar quantifyinguncertaintyinstructuralconditionwithbayesiandeeplearningastudyonthez24bridgebenchmark
AT asgrimssondavidsteinar kvantifieringavosakerhetistrukturellatillstandmedbayesianskdjupinlarning
_version_ 1719192462536212480