UNSUPERVISED STREAMING ANOMALY DETECTION FOR INSTRUMENTED INFRASTRUCTURE

• 成果类型: Article
• 署名作者: Hoeltgebaum, Henrique; Adams, Niall; Lau, F. Din-Houn
• 署名单位: Imperial College London
• 刊物名称: ANNALS OF APPLIED STATISTICS
• ISSN/ISSBN: 1932-6157
• DOI: 10.1214/20-AOAS1424
• 发表日期: 2021
• 页码: 1101-1125
• 关键词: fiber-optic sensors; principal components; LARGEST EIGENVALUE; PCA

摘要

Structural health monitoring (SHM) often involves instrumenting structures with distributed sensor networks. These networks typically provide high frequency data describing the spatiotemporal behaviour of the assets. A main objective of SHM is to reason about changes in structures' behaviour using sensor data. We construct a streaming anomaly detection method for data from a railway bridge instrumented with a fibre-optic sensor network. The data exhibits trend over time, which may be partially attributable to environmental factors, calling for temporally adaptive estimation. Exploiting a latent structure present in the data motivates a quantity of interest for anomaly detection. This quantity is estimated, sequentially and adaptively, using a new formulation of streaming principal component analysis. Anomaly detection for this quantity is then provided using conformal prediction. Like all streaming methods, the proposed method has free control parameters which are set using simulations based on bridge data. Experiments demonstrate that this method can operate at the sampling frequency of the data while providing accurate tracking of the target quantity. Further, the anomaly detection is able to detect train passage events. Finally, the method reveals a previously unreported cyclic structure present in the data.