Data-driven approach for detection of structural changes using train-induced dynamic responses

• Type: Article in International Conference Proceedings Book
• Date: 2021

Authors

Meixedo, A (Author) Other; Santos, J (Author) Other; Ribeiro, D (Author) Other; Rui Calçada (Author) FEUP; Todd, M (Author) Other

Conference proceedings International

Title: International Conference on Structural Health Monitoring of Intelligent Infrastructure: Transferring Research into Practice, SHMII

Pages: 441-448

10th International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2021

30 June 2021 through 2 July 2021

Indexing

Scopus

Other information

Authenticus ID: P-00W-N63

Abstract (EN): This work considers the detection of structural changes in railway bridge vibration response induced by train traffic using structural health monitoring systems. To achieve this goal, an innovative data-driven unsupervised methodology is proposed, consisting of a combination of time series analysis and advanced multivariate statistical techniques such as autoregressive models, multiple linear regression, and outlier analysis. The efficiency of the proposed methodology is verified on a complex bowstring-arch railway bridge. A digital twin of the bridge is used to simulate baseline and damage conditions by performing finite element time-history analysis using as input measurements of real temperatures, noise effects, and train speeds, and loads. The methodology proven to be highly robust to false detections and sensitive to early damage by automatically detecting small stiffness reductions in the concrete slab, diaphragms, and arches, as well as friction increase in the bearing devices. © 2021 International Conference on Structural Health Monitoring of Intelligent Infrastructure: Transferring Research into Practice, SHMII. All rights reserved.

Language: English

Type (Professor's evaluation): Scientific