PSI - Issue 64

Available online at www.sciencedirect.com Available online at www.sciencedirect.com ScienceDirect Structural Integrity Procedia 00 (2023) 000–000

www.elsevier.com/locate/procedia

ScienceDirect

Procedia Structural Integrity 64 (2024) 1369–1375

SMAR 2024 – 7th International Conference on Smart Monitoring, Assessment and Rehabilitation of Civil Structures A convolutional autoencoder for damage assessment of FRP strengthened RC beams Ricardo Perera a, * Javier Montes a , Marta Baena b , Cristina Barris b a Department of Mechanical Engineering, Technical University of Madrid, 28006 Madrid, Spain b Analysis and Advanced Materials for Structural Design (AMADE), Polytechnic School, University of Girona, 17003 Girona, Spain Abstract The use of fibre reinforced polymer (FRP) in civil construction applications has gained considerable popularity worldwide as suitable method for strengthening existing concrete structures. However, there is very little experience in the implementation of methods able to give a reliable prediction about the health of this type of structures even although sudden and brittle failure modes are likely to happen. Electromechanical impedance (EMI) method formulated from measurements obtained from PZT patches gives the ability for monitoring the performance and changes experienced by these strengthened beams at a local level, which is a key aspect considering their possible premature debonding failure modes. In this work, a deep learning approach using convolutional variational auto-encoders for exploiting the raw impedance signatures is implemented to automatically detect anomalies in an unsupervised manner for this type of structures. To validate the effectiveness of the method, an experimental test campaign was performed. A concrete specimen strengthened with FRP and instrumented with PZT transducers in different location was subjected to different loading stages which provided different levels of damage. The results showed the potential of the method for EMI data-driven minor damage identification for real-life concrete infrastructures. © 2024 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of SMAR 2024 Organizers Keywords: Convolutional autoencoder; Unsupervised methods; FRP strengthening; EMI method © 2024 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of SMAR 2024 Organizers

* Corresponding author. Tel.: 34-910677242. E-mail address: ricardo.perera@upm.es

2452-3216 © 2024 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of SMAR 2024 Organizers

2452-3216 © 2024 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of SMAR 2024 Organizers 10.1016/j.prostr.2024.09.373