A temperature-driven MPCA method for structural anomaly detection
| Autor: | Irwanda Laory, Yiqing Ni, Yanjie Zhu, Hui Jin, Daniele Inaudi |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry Anomaly (natural sciences) 0211 other engineering and technologies 020101 civil engineering Pattern recognition 02 engineering and technology Maximization Blind signal separation Independent component analysis 0201 civil engineering 021105 building & construction Principal component analysis Anomaly detection Structural health monitoring Artificial intelligence Reduction (mathematics) business Civil and Structural Engineering |
| Zdroj: | Engineering Structures. 190:447-458 |
| ISSN: | 0141-0296 |
| DOI: | 10.1016/j.engstruct.2019.04.004 |
| Popis: | An important issue in structural health monitoring (SHM) is to develop appropriate algorithms that can explicitly extract meaningful changes in measurements due to structural anomalies, especially damage. However, the effects due to environmental factors, especially temperature variations may produce significant misinterpretations. Consequently, developing solutions to identify the structural anomaly, accounting for temperature influence, from measurements, is crucial and highly anticipated. This paper presents a Temperature-driven Moving Principal Component Analysis method, designated as Td-MPCA, for anomaly detection. The Td-MPCA introduces the idea of blind source separation (BSS) for thermal identification with intent to enhance the performance of Moving Principal Component Analysis (MPCA) for anomaly detection. To achieve this target, temperature-induced strain variations are first investigated and revealed by employing Independent Component Analysis based on maximization non-Gaussianity, also known as Fast ICA. Afterwards, the MPCA is adopted for anomaly detection on the separated temperature-related response. Three case studies are provided in this paper to evaluate the proposed method. The first one is a numerical truss bridge with a simulated 5% stiffness reduction. The results confirm that Td-MPCA is more sensitive than MPCA in detecting anomalies, where the simulated stiffness loss fails to be detected by MPCA. The second case study is on an experimental truss bridge where two damage scenarios are introduced and interpreted. The detection results show that Td-MPCA outperforms MPCA since the damage is identified at the expected time by Td-MPCA but not by MPCA. The third case study is an in-situ curved viaduct in Switzerland. Data acquired during both construction period and normal service period has been used for interpretation. Results demonstrate that Td-MPCA is able to identify the date of change in construction process without any delay when compared with the application of MPCA only. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect