EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Vibration-Based Machine Learning Model Training for Railway Bridge Health Monitoring

Rocco Alaggio iD, Muhammad Asad iD, Riccardo Cirella iD, Stefania Costantini iD, Giovanni De Gasperis iD

Sensors · 2026

DOI: 10.3390/s26134323 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Rocco Alaggio und 4 weiteren Autor:innen. Beteiligte Einrichtung: Dipartimento di Ingegneria Civile, Edile-Architettura e Ambientale, Università degli Studi dell'Aquila, 67100 L'Aquila, Italy. Hauptthemen laut MEDLINE: Machine Learning, Vibration, Railroads. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union - NextGenerationEU italy, Italian Ministry of University and Research (MUR) National Innovation Ecosystem.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bridge health monitoring and machine learning are increasingly intertwined for civil engineers and artificial intelligence experts. Bridges’ poor health can result in severe outcomes if not addressed in time. Therefore, continuous monitoring is required to detect any anomaly or damage. Sensors, such as accelerometers, inclinometers, thermistors, etc., can help actively monitor these bridges. The signals from these sensors help record physiological activities. Such activities are helpful for anomaly detection, damage localization, and bridge health predictions with the help of machine learning algorithms. The proposed method extracts features from the dynamic response of a bridge to ambient excitation. It focuses on processing the signal received from different accelerometers installed on a steel railway bridge to determine the location of the damage and the level of the damage predictions. Initially, features are extracted from time-series data; then, they are fed to a deep neural network after some pre-processing. Normal and augmented data are used with different parameter tuning for results. Original data is also subdivided, and the effect of data slicing on the predictions is investigated. The results show that one-fourth of the slicing of the original data gives the best results for training and testing accuracy with a deep neural network. The results show that the reduced matrix representation, particularly the 40 × 40 feature slicing, improved the classification performance for the predefined bridge scenario classes under the considered experimental settings. For bridge scenario classification, the best reported accuracy was 93.54%, while for damage intensity classification the best reported accuracy was 98.21%. In the DNN-based optimizer comparison, the Adam optimizer achieved higher and more stable performance than Stochastic Gradient Descent (SGD), with test accuracies of 92.3% and 93.7% compared with 75.2% and 86.4%, respectively. It is also observed that the Adam optimizer outperformed Stochastic Gradient Descent (SGD) in terms of both damage localization and damage intensity estimation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningVibrationRailroadsNeural Networks, ComputerAlgorithmsHumansAccelerometryMonitoring, PhysiologicPredictive Learning Models

Stichwörter der Autor:innen

accelerometeranomaly detectionmachine learning (ML)neural networksteel bridgesstructural health monitoring

Autor:innen und Institutionen

  • Dipartimento di Ingegneria Civile, Edile-Architettura e Ambientale, Università degli Studi dell'Aquila, 67100 L'Aquila, Italy.
  • Dipartimento di Ingegneria e Scienze dell'Informazione e Matematica, Università degli Studi dell'Aquila, 67100 L'Aquila, Italy.
  • School of Computer and Information Technology, Beaconhouse National University, Lahore 53700, Pakistan.

ORCID-Profile: Rocco Alaggio, Muhammad Asad, Riccardo Cirella, Stefania Costantini, Giovanni De Gasperis

Förderung

  • European Union - NextGenerationEU italy
  • Italian Ministry of University and Research (MUR) National Innovation Ecosystem

Zitieren

APA

Alaggio, R., Asad, M., Cirella, R., Costantini, S., & De Gasperis, G. (2026). Vibration-Based Machine Learning Model Training for Railway Bridge Health Monitoring. Sensors. https://doi.org/10.3390/s26134323

Vancouver

Alaggio R, Asad M, Cirella R, Costantini S, De Gasperis G. Vibration-Based Machine Learning Model Training for Railway Bridge Health Monitoring. Sensors. 2026. doi:10.3390/s26134323

BibTeX
@article{Alaggio2026,
  author = {Alaggio, Rocco and Asad, Muhammad and Cirella, Riccardo and Costantini, Stefania and De Gasperis, Giovanni},
  title = {Vibration-Based Machine Learning Model Training for Railway Bridge Health Monitoring},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26134323}
}
Kostenlos starten →