Noise-robust automated sudden damage detection using blind source separation enhanced by variational mode decomposition and support vector machine based on shapelet transform
Compared to parametric counterparts, non-parametric (aka, model-free) damage detection methods have no requirements of accurate models, with the potential of autonomous monitoring of various complex structures. However, noises, or low signal-to-noise ratio (SNR), are one of the main challenges. This...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/182841 |
| _version_ | 1826131809267613696 |
|---|---|
| author | Shen, Wei Fu, Yuguang Kong, Qingzhao Li, Jin-Yang |
| author2 | School of Civil and Environmental Engineering |
| author_facet | School of Civil and Environmental Engineering Shen, Wei Fu, Yuguang Kong, Qingzhao Li, Jin-Yang |
| author_sort | Shen, Wei |
| collection | NTU |
| description | Compared to parametric counterparts, non-parametric (aka, model-free) damage detection methods have no requirements of accurate models, with the potential of autonomous monitoring of various complex structures. However, noises, or low signal-to-noise ratio (SNR), are one of the main challenges. This study is aimed at improving blind source separation (BSS)-based damage detection method, one of the most advanced non-parametric methods, in both aspects of noise robustness and autonomous operation. In particular, the measured acceleration responses are processed by variational mode decomposition (VMD) and wavelet transform (WT) in sequential, acting as the input for a BSS model. The BSS is then solved by independent component analysis (ICA), which approves to be more noise-robust compared to the state-of-the-art counterparts. Furthermore, shapelet transform is applied to extract the universal shape-based spike-like feature from the BSS model for training a support vector machine (SVM) model, applicable to different structures; it finally automates the sudden damage detection process and enables online monitoring. The effectiveness of the proposed method is illustrated by a numerical example and an experimental test, and demonstrated by a real-world seismic-excited structure. The results show that both single and multiple sudden damages can be automatically detected with high accuracy. Compared with the existing BSS methods, the proposed BSS method is more capable to detect small damages at relatively low SNR. In addition, the classification accuracy of SVM is also improved when shapelet-based feature is used for training, which reduces the malfunction of automated damage detection as shown by the numerical example. Therefore, the proposed strategy has the potential for rapid condition assessment of structures during rare/extreme events, before engineers are sent for further post-event inspection. |
| first_indexed | 2025-03-09T15:43:24Z |
| format | Journal Article |
| id | ntu-10356/182841 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-03-09T15:43:24Z |
| publishDate | 2025 |
| record_format | dspace |
| spelling | ntu-10356/1828412025-03-03T07:52:29Z Noise-robust automated sudden damage detection using blind source separation enhanced by variational mode decomposition and support vector machine based on shapelet transform Shen, Wei Fu, Yuguang Kong, Qingzhao Li, Jin-Yang School of Civil and Environmental Engineering Engineering Sudden damage detection Autonomous monitoring Compared to parametric counterparts, non-parametric (aka, model-free) damage detection methods have no requirements of accurate models, with the potential of autonomous monitoring of various complex structures. However, noises, or low signal-to-noise ratio (SNR), are one of the main challenges. This study is aimed at improving blind source separation (BSS)-based damage detection method, one of the most advanced non-parametric methods, in both aspects of noise robustness and autonomous operation. In particular, the measured acceleration responses are processed by variational mode decomposition (VMD) and wavelet transform (WT) in sequential, acting as the input for a BSS model. The BSS is then solved by independent component analysis (ICA), which approves to be more noise-robust compared to the state-of-the-art counterparts. Furthermore, shapelet transform is applied to extract the universal shape-based spike-like feature from the BSS model for training a support vector machine (SVM) model, applicable to different structures; it finally automates the sudden damage detection process and enables online monitoring. The effectiveness of the proposed method is illustrated by a numerical example and an experimental test, and demonstrated by a real-world seismic-excited structure. The results show that both single and multiple sudden damages can be automatically detected with high accuracy. Compared with the existing BSS methods, the proposed BSS method is more capable to detect small damages at relatively low SNR. In addition, the classification accuracy of SVM is also improved when shapelet-based feature is used for training, which reduces the malfunction of automated damage detection as shown by the numerical example. Therefore, the proposed strategy has the potential for rapid condition assessment of structures during rare/extreme events, before engineers are sent for further post-event inspection. Ministry of Education (MOE) Nanyang Technological University National Research Foundation (NRF) This research/project was supported by the National Research Foundation, Singapore under its AI Singapore Programme (AISG Award No: AISG2-TC-2021-001), and The Ministry of Education Tier 1 Grants, Singapore (No. RG121/21 and No. RS04/21), and the start-up grant at Nanyang Technological University, Singapore (03INS001210C120). 2025-03-03T07:52:29Z 2025-03-03T07:52:29Z 2025 Journal Article Shen, W., Fu, Y., Kong, Q. & Li, J. (2025). Noise-robust automated sudden damage detection using blind source separation enhanced by variational mode decomposition and support vector machine based on shapelet transform. Journal of Sound and Vibration, 595, 118783-. https://dx.doi.org/10.1016/j.jsv.2024.118783 0022-460X https://hdl.handle.net/10356/182841 10.1016/j.jsv.2024.118783 2-s2.0-85207878363 595 118783 en AISG2-TC-2021-001 RG121/21 RS04/21 03INS001210C120 Journal of Sound and Vibration © 2024 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies. |
| spellingShingle | Engineering Sudden damage detection Autonomous monitoring Shen, Wei Fu, Yuguang Kong, Qingzhao Li, Jin-Yang Noise-robust automated sudden damage detection using blind source separation enhanced by variational mode decomposition and support vector machine based on shapelet transform |
| title | Noise-robust automated sudden damage detection using blind source separation enhanced by variational mode decomposition and support vector machine based on shapelet transform |
| title_full | Noise-robust automated sudden damage detection using blind source separation enhanced by variational mode decomposition and support vector machine based on shapelet transform |
| title_fullStr | Noise-robust automated sudden damage detection using blind source separation enhanced by variational mode decomposition and support vector machine based on shapelet transform |
| title_full_unstemmed | Noise-robust automated sudden damage detection using blind source separation enhanced by variational mode decomposition and support vector machine based on shapelet transform |
| title_short | Noise-robust automated sudden damage detection using blind source separation enhanced by variational mode decomposition and support vector machine based on shapelet transform |
| title_sort | noise robust automated sudden damage detection using blind source separation enhanced by variational mode decomposition and support vector machine based on shapelet transform |
| topic | Engineering Sudden damage detection Autonomous monitoring |
| url | https://hdl.handle.net/10356/182841 |
| work_keys_str_mv | AT shenwei noiserobustautomatedsuddendamagedetectionusingblindsourceseparationenhancedbyvariationalmodedecompositionandsupportvectormachinebasedonshapelettransform AT fuyuguang noiserobustautomatedsuddendamagedetectionusingblindsourceseparationenhancedbyvariationalmodedecompositionandsupportvectormachinebasedonshapelettransform AT kongqingzhao noiserobustautomatedsuddendamagedetectionusingblindsourceseparationenhancedbyvariationalmodedecompositionandsupportvectormachinebasedonshapelettransform AT lijinyang noiserobustautomatedsuddendamagedetectionusingblindsourceseparationenhancedbyvariationalmodedecompositionandsupportvectormachinebasedonshapelettransform |