RT Conference Proceedings
T1 Combined model-based and machine learning approach for damage identification in bridge type structures
A1 Fernández-Navamuel, Ana
A1 Zamora-Sánchez, Diego
A1 Armijo-Prieto, Alberto
A1 Varona-Poncela, Tomás
A1 García-Sánchez, David
A1 García-Villena, Francisco
A1 Ruiz-Cuenca, Francisco
AB In this work, we propose a combined approach of model-based and machine learning techniques for damage identification in bridge structures. First, a finite element model is calibrated with real data from experimental vibration modes for the undamaged or baseline state. Second, generic synthetic damage scenarios based on modal parameters are automatically generated with the model to train machine learning algorithms for damage classification (Support Vector Machine, SVM) and damage location and quantification (Neural Network, NN). For an initial validation of the method we use a lab scale truss bridge model, proving that specific damage scenarios can be assessed by the Supervised Machine Learning algorithms trained with generic damage scenarios including a certain variability. The NN provides an assessment in terms of damage location and quantification, whereas the SVM provides a damage severity classification with graphical indication of the damage location and quantification through a reduced dimension plot.
SN 2564-3738
YR 2021
FD 2021
LK https://hdl.handle.net/11556/2941
UL https://hdl.handle.net/11556/2941
LA eng
NO Fernández-Navamuel , A , Zamora-Sánchez , D , Armijo-Prieto , A , Varona-Poncela , T , García-Sánchez , D , García-Villena , F & Ruiz-Cuenca , F 2021 , ' Combined model-based and machine learning approach for damage identification in bridge type structures ' , International Conference on Structural Health Monitoring of Intelligent Infrastructure: Transferring Research into Practice, SHMII , vol. 2021-June , pp. 727-732 .
NO Publisher Copyright: © 2021 International Conference on Structural Health Monitoring of Intelligent Infrastructure: Transferring Research into Practice, SHMII. All rights reserved.
NO This work has been supported by the Spanish Ministry of Economy and Competitiveness (MINECO) through “RESILTRACK: Resilience of railway infrastructures against Climate Change” project funded by CIEN-CDTI programme. CEMOSA, TECNALIA and MAGTEL collaborated in obtaining the results presented in this paper.
DS TECNALIA Publications
RD 28 jul 2024