Anomaly detection in long-term tunnel deformation monitoring. (1st January 2022)

• Record Type: Journal Article
• Authors: Maes, Kristof; Salens, Wim; Feremans, Gerrit; Segher, Koen; François, Stijn
• Is Part Of: Engineering structures. Volume 250(2022)
• Publication Date: 2022-01-01
• Subjects: Tunnel monitoring -- Novelty detection -- Pattern recognition -- Black-box modeling; Structural engineering -- Periodicals; Structural analysis (Engineering) -- Periodicals; Construction, Technique de la -- Périodiques; Génie parasismique -- Périodiques; Pression du vent -- Périodiques; Earthquake engineering; Structural engineering; Wind-pressure; Periodicals; 624.105
• DOI: 10.1016/j.engstruct.2021.113383
• Languages: English
• ISSNs: 0141-0296

Abstract

Abstract: Tunnels are critical infrastructure that require a careful monitoring of their structural health. This paper explores the use of novelty detection algorithms for long-term tunnel monitoring projects. The algorithms are applied to the monitoring of the Waasland tunnel in Antwerp, where the deformations and temperatures have been monitored over a period of one year. The case demonstrates that novelty detection by means of principal component analysis enables the identification of minor changes in the tunnel response, and can therefore be embedded in an early detection warning system. An additional numerical analysis based on simulation data further demonstrates that this approach requires a sufficiently long training period, in order to enable distinguishing between regular deviations in the tunnel response and anomalies. Highlights: A case study of anomaly detection in tunnel deformation monitoring is presented. Data are obtained from in situ tunnel measurements over a period of 1 year. Numerical simulations are added to gain insight in the problem physics. Detection by means of principal component analysis (PCA) enables early novelty warning.