Quantum k-Nearest Neighbors for Accelerated and Robust Damage Detection in Railway Bridge Structural Health Monitoring: A Case Study on KW51 bridge
e-Journal of Nondestructive Testing · 2026-07 · 31 (7)
DOI: 10.58286/32912 ↗Kurz gefasst
Fachartikel in der Zeitschrift e-Journal of Nondestructive Testing, 2026-07. Verfasst von Haniye Ghafouri Rouzbahani und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Structural health monitoring (SHM) is essential for ensuring the safety and longevity of critical infrastructure, such as bridges, which represent vital components in transportation systems requiring accurate and timely assessment of their structural integrity. This study investigates the effectiveness of quantum-enhanced machine learning, specifically the quantum k-nearest neighbors (q-KNN) algorithm, for damage detection in bridge infrastructures. Conventional K-nearest neighbor (KNN) algorithms have demonstrated robustness in bridge SHM tasks; however, their accuracy and computational efficiency can be limited by large, complex, or imbalanced damage datasets. The q-KNN approach leverages quantum computational features, including quantum parallelism and superior optimization landscapes, to address these limitations. Comparative experimental data obtained from railway bridge KW51 reveal that q-KNN achieves faster convergence rates and enhanced computational efficiency during the training and inference phases, owing to its capacity for simultaneous multi-state processing. Furthermore, q-KNN outperforms classical KNN in accuracy, particularly for challenging damage scenarios where traditional algorithms may become trapped in local minima or struggle with noisy sensor inputs. The results highlight that integrating quantum machine learning into SHM workflows can significantly enhance both accuracy and speed of damage identification, facilitating timely, data-efficient, and robust decision-making for civil infrastructure maintenance.
Zitieren
APA
Rouzbahani, H. G., Mamaghani, M. O., & Pospischil, F. (2026). Quantum k-Nearest Neighbors for Accelerated and Robust Damage Detection in Railway Bridge Structural Health Monitoring: A Case Study on KW51 bridge. e-Journal of Nondestructive Testing, 31(7). https://doi.org/10.58286/32912
Vancouver
Rouzbahani HG, Mamaghani MO, Pospischil F. Quantum k-Nearest Neighbors for Accelerated and Robust Damage Detection in Railway Bridge Structural Health Monitoring: A Case Study on KW51 bridge. e-Journal of Nondestructive Testing. 2026;31(7). doi:10.58286/32912
BibTeX
@article{Rouzbahani2026,
author = {Rouzbahani, Haniye Ghafouri and Mamaghani, Mohammad Omidi and Pospischil, Ferdinand},
title = {Quantum k-Nearest Neighbors for Accelerated and Robust Damage Detection in Railway Bridge Structural Health Monitoring: A Case Study on KW51 bridge},
journal = {e-Journal of Nondestructive Testing},
year = {2026},
volume = {31},
number = {7},
doi = {10.58286/32912}
}
EUVIMED