Acoustic emission-based damage localization using wavelet-assisted deep learning
Abstract Acoustic Emission (AE) has emerged as a popular damage detection and localization tool due to its high performance in identifying minor damage or crack. Due to the high sampling rate, AE sensors result in massive data during long-term monitoring of large-scale civil structures. Analyzing su...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-04-01
|
| Series: | Journal of Infrastructure Preservation and Resilience |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s43065-022-00051-8 |
| _version_ | 1819209984698744832 |
|---|---|
| author | Mohamed Barbosh Kyle Dunphy Ayan Sadhu |
| author_facet | Mohamed Barbosh Kyle Dunphy Ayan Sadhu |
| author_sort | Mohamed Barbosh |
| collection | DOAJ |
| description | Abstract Acoustic Emission (AE) has emerged as a popular damage detection and localization tool due to its high performance in identifying minor damage or crack. Due to the high sampling rate, AE sensors result in massive data during long-term monitoring of large-scale civil structures. Analyzing such big data and associated AE parameters (e.g., rise time, amplitude, counts, etc.) becomes time-consuming using traditional feature extraction methods. This paper proposes a 2D convolutional neural network (2D CNN)-based Artificial Intelligence (AI) algorithm combined with time–frequency decomposition techniques to extract the damage information from the measured AE data without using standalone AE parameters. In this paper, Empirical Mode Decomposition (EMD) is employed to extract the intrinsic mode functions (IMFs) from noisy raw AE measurements, where the IMFs serve as the key AE components of the data. Continuous Wavelet Transform (CWT) is then used to obtain the spectrograms of the AE components, serving as the “artificial images” to an AI network. These spectrograms are fed into 2D CNN algorithm to detect and identify the potential location of the damage. The proposed approach is validated using a suite of numerical and experimental studies. |
| first_indexed | 2024-12-23T06:03:58Z |
| format | Article |
| id | doaj.art-40d4d4c2ae4b43c88a2d6c2f7990bc76 |
| institution | Directory Open Access Journal |
| issn | 2662-2521 |
| language | English |
| last_indexed | 2024-12-23T06:03:58Z |
| publishDate | 2022-04-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Infrastructure Preservation and Resilience |
| spelling | doaj.art-40d4d4c2ae4b43c88a2d6c2f7990bc762022-12-21T17:57:37ZengSpringerOpenJournal of Infrastructure Preservation and Resilience2662-25212022-04-013112410.1186/s43065-022-00051-8Acoustic emission-based damage localization using wavelet-assisted deep learningMohamed Barbosh0Kyle Dunphy1Ayan Sadhu2Department of Civil and Environmental Engineering, Western UniversityDepartment of Civil and Environmental Engineering, Western UniversityDepartment of Civil and Environmental Engineering, Western UniversityAbstract Acoustic Emission (AE) has emerged as a popular damage detection and localization tool due to its high performance in identifying minor damage or crack. Due to the high sampling rate, AE sensors result in massive data during long-term monitoring of large-scale civil structures. Analyzing such big data and associated AE parameters (e.g., rise time, amplitude, counts, etc.) becomes time-consuming using traditional feature extraction methods. This paper proposes a 2D convolutional neural network (2D CNN)-based Artificial Intelligence (AI) algorithm combined with time–frequency decomposition techniques to extract the damage information from the measured AE data without using standalone AE parameters. In this paper, Empirical Mode Decomposition (EMD) is employed to extract the intrinsic mode functions (IMFs) from noisy raw AE measurements, where the IMFs serve as the key AE components of the data. Continuous Wavelet Transform (CWT) is then used to obtain the spectrograms of the AE components, serving as the “artificial images” to an AI network. These spectrograms are fed into 2D CNN algorithm to detect and identify the potential location of the damage. The proposed approach is validated using a suite of numerical and experimental studies.https://doi.org/10.1186/s43065-022-00051-8NDTDamage detection and localizationAEEMDWTCNN |
| spellingShingle | Mohamed Barbosh Kyle Dunphy Ayan Sadhu Acoustic emission-based damage localization using wavelet-assisted deep learning Journal of Infrastructure Preservation and Resilience NDT Damage detection and localization AE EMD WT CNN |
| title | Acoustic emission-based damage localization using wavelet-assisted deep learning |
| title_full | Acoustic emission-based damage localization using wavelet-assisted deep learning |
| title_fullStr | Acoustic emission-based damage localization using wavelet-assisted deep learning |
| title_full_unstemmed | Acoustic emission-based damage localization using wavelet-assisted deep learning |
| title_short | Acoustic emission-based damage localization using wavelet-assisted deep learning |
| title_sort | acoustic emission based damage localization using wavelet assisted deep learning |
| topic | NDT Damage detection and localization AE EMD WT CNN |
| url | https://doi.org/10.1186/s43065-022-00051-8 |
| work_keys_str_mv | AT mohamedbarbosh acousticemissionbaseddamagelocalizationusingwaveletassisteddeeplearning AT kyledunphy acousticemissionbaseddamagelocalizationusingwaveletassisteddeeplearning AT ayansadhu acousticemissionbaseddamagelocalizationusingwaveletassisteddeeplearning |