Bridge damage identification under varying environmental and operational conditions combining Deep Learning and numerical simulations

Simple item page
dc.contributor.authorFernandez-Navamuel, Ana
dc.contributor.authorPardo, David
dc.contributor.authorMagalhães, Filipe
dc.contributor.authorZamora-Sánchez, Diego
dc.contributor.authorOmella, Ángel J.
dc.contributor.authorGarcia-Sanchez, David
dc.contributor.institutionE&I SEGURAS Y RESILIENTES
dc.date.issued2023-10-01
dc.descriptionPublisher Copyright: © 2023 The Authors
dc.description.abstractThis work proposes a novel supervised learning approach to identify damage in operating bridge structures. We propose a method to introduce the effect of environmental and operational conditions into the synthetic damage scenarios employed for training a Deep Neural Network, which is applicable to large-scale complex structures. We apply a clustering technique based on Gaussian Mixtures to effectively select Q representative measurements from a long-term monitoring dataset. We employ these measurements as the target response to solve various Finite Element Model Updating problems before generating different damage scenarios. The synthetic and experimental measurements feed two Deep Neural Networks that assess the structural health condition in terms of damage severity and location. We demonstrate the applicability of the proposed method with a real full-scale case study: the Infante Dom Henrique bridge in Porto. A comparative study reveals that neglecting different environmental and operational conditions during training detracts the damage identification task. By contrast, our method provides successful results during a synthetic validation.en
dc.description.sponsorshipDavid Pardo has received funding from: the Spanish Ministry of Science and Innovation projects with references TED2021-132783B-I00 , PID2019-108111RB-I00 (FEDER/AEI) and PDC2021-121093-I00 (MCIN/AEI/10.13039/501100011033/Next Generation EU), the “ BCAM Severo Ochoa ” accreditation of excellence CEX2021-001142-S/MICIN/AEI/10.13039/501100011033 ; the Spanish Ministry of Economic and Digital Transformation with Misiones Project IA4TES ( MIA.2021.M04.008 /NextGenerationEU PRTR); and the Basque Government through the BERC 2022-2025 program , the Elkartek project SIGZE ( KK-2021/00095 ), and the Consolidated Research Group MATHMODE ( IT1456-22 ) given by the Department of Education. This work was financially supported by: Base Funding — UIDB/04708/2020 of the CONSTRUCT - Instituto de I&D em Estruturas e Construções — funded by national funds through the FCT/MCTES (PIDDAC). Authors would like to acknowledge the Basque Government funding within the ELKARTEK programme (SIGZE project ( KK-2021/00095 )), the European Horizon (HE) with LIASON project ( GA 101103698 ), and FUTURAL project .
dc.description.statusPeer reviewed
dc.identifier.citationFernandez-Navamuel , A , Pardo , D , Magalhães , F , Zamora-Sánchez , D , Omella , Á J & Garcia-Sanchez , D 2023 , ' Bridge damage identification under varying environmental and operational conditions combining Deep Learning and numerical simulations ' , Mechanical Systems and Signal Processing , vol. 200 , 110471 . https://doi.org/10.1016/j.ymssp.2023.110471
dc.identifier.doi10.1016/j.ymssp.2023.110471
dc.identifier.issn0888-3270
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85162134275&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofMechanical Systems and Signal Processing
dc.relation.projectIDBERC, IT1456-22-2022-2025
dc.relation.projectIDEuropean Horizon, GA 101103698
dc.relation.projectIDSpanish Ministry of Economic and Digital Transformation
dc.relation.projectIDU.S. Department of Education, ED
dc.relation.projectIDFederación Española de Enfermedades Raras, FEDER, PDC2021-121093-I00-CEX2021-001142-S/MICIN/AEI/10.13039/501100011033
dc.relation.projectIDEusko Jaurlaritza, KK-2021/00095
dc.relation.projectIDMinisterio de Ciencia e Innovación, MICINN, PID2019-108111RB-I00-TED2021-132783B-I00
dc.relation.projectIDMinistério da Ciência, Tecnologia e Ensino Superior, MCTES
dc.relation.projectIDFundació Catalana de Trasplantament, FCT
dc.relation.projectIDInstitute of Research and Development in Structures and Construction
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subject.keywordsDamage identification
dc.subject.keywordsDeep Learning
dc.subject.keywordsStructural Health Monitoring
dc.subject.keywordsVarying environmental and operational conditions
dc.subject.keywordsControl and Systems Engineering
dc.subject.keywordsSignal Processing
dc.subject.keywordsCivil and Structural Engineering
dc.subject.keywordsAerospace Engineering
dc.subject.keywordsMechanical Engineering
dc.subject.keywordsComputer Science Applications
dc.titleBridge damage identification under varying environmental and operational conditions combining Deep Learning and numerical simulationsen
dc.typejournal article
Files