Real-Time Localization Method of Large Pressure Vessel Leaks Based on Improved CNN and STCA of Elastic Wavefield
In this paper, a real-time leak source localization method based on convolutional neural network (CNN) of elastic wavefield images and spatio-temporal correlation analysis (STCA) is developed for the pressure vessel leakage. This method uses a single sensor array coupled to the wall to collect the e...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10268946/ |
| _version_ | 1797661498729824256 |
|---|---|
| author | Bian Xu Huang Xinjing |
| author_facet | Bian Xu Huang Xinjing |
| author_sort | Bian Xu |
| collection | DOAJ |
| description | In this paper, a real-time leak source localization method based on convolutional neural network (CNN) of elastic wavefield images and spatio-temporal correlation analysis (STCA) is developed for the pressure vessel leakage. This method uses a single sensor array coupled to the wall to collect the elastic wave data excited by the leak source. Besides, the distance <inline-formula> <tex-math notation="LaTeX">$R$ </tex-math></inline-formula> and the direction <inline-formula> <tex-math notation="LaTeX">$\theta $ </tex-math></inline-formula> between the leak source and the sensor array are calculated based on CNN and STCA respectively, to finally obtain the location (<inline-formula> <tex-math notation="LaTeX">$R$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$\theta$ </tex-math></inline-formula>) of the leak source. In this paper, the digital twin model of the experimental platform is established, the training set is obtained by the finite element simulation, and the CNN model applied to the elastic wavefield images is studied and constructed. The experimental results show that the maximum locating error is 1.46 cm and the average locating error is about 0.56 cm within the range of a 1 m2 experimental plate based on the method proposed in this paper. |
| first_indexed | 2024-03-11T18:45:26Z |
| format | Article |
| id | doaj.art-2c58f9ea7ab346a89fdc3684bcb6f61c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T18:45:26Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2c58f9ea7ab346a89fdc3684bcb6f61c2023-10-11T23:00:18ZengIEEEIEEE Access2169-35362023-01-011110892610893710.1109/ACCESS.2023.332154510268946Real-Time Localization Method of Large Pressure Vessel Leaks Based on Improved CNN and STCA of Elastic WavefieldBian Xu0https://orcid.org/0000-0001-5503-5567Huang Xinjing1https://orcid.org/0000-0002-8964-8502Tianjin Ren’ai College, Tianjin, ChinaState Key Laboratory of Precision Measurement Technology and Instruments, Tianjin University, Tianjin, ChinaIn this paper, a real-time leak source localization method based on convolutional neural network (CNN) of elastic wavefield images and spatio-temporal correlation analysis (STCA) is developed for the pressure vessel leakage. This method uses a single sensor array coupled to the wall to collect the elastic wave data excited by the leak source. Besides, the distance <inline-formula> <tex-math notation="LaTeX">$R$ </tex-math></inline-formula> and the direction <inline-formula> <tex-math notation="LaTeX">$\theta $ </tex-math></inline-formula> between the leak source and the sensor array are calculated based on CNN and STCA respectively, to finally obtain the location (<inline-formula> <tex-math notation="LaTeX">$R$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$\theta$ </tex-math></inline-formula>) of the leak source. In this paper, the digital twin model of the experimental platform is established, the training set is obtained by the finite element simulation, and the CNN model applied to the elastic wavefield images is studied and constructed. The experimental results show that the maximum locating error is 1.46 cm and the average locating error is about 0.56 cm within the range of a 1 m2 experimental plate based on the method proposed in this paper.https://ieeexplore.ieee.org/document/10268946/Elastic waveleakagelocationsensor arraydeep learning |
| spellingShingle | Bian Xu Huang Xinjing Real-Time Localization Method of Large Pressure Vessel Leaks Based on Improved CNN and STCA of Elastic Wavefield IEEE Access Elastic wave leakage location sensor array deep learning |
| title | Real-Time Localization Method of Large Pressure Vessel Leaks Based on Improved CNN and STCA of Elastic Wavefield |
| title_full | Real-Time Localization Method of Large Pressure Vessel Leaks Based on Improved CNN and STCA of Elastic Wavefield |
| title_fullStr | Real-Time Localization Method of Large Pressure Vessel Leaks Based on Improved CNN and STCA of Elastic Wavefield |
| title_full_unstemmed | Real-Time Localization Method of Large Pressure Vessel Leaks Based on Improved CNN and STCA of Elastic Wavefield |
| title_short | Real-Time Localization Method of Large Pressure Vessel Leaks Based on Improved CNN and STCA of Elastic Wavefield |
| title_sort | real time localization method of large pressure vessel leaks based on improved cnn and stca of elastic wavefield |
| topic | Elastic wave leakage location sensor array deep learning |
| url | https://ieeexplore.ieee.org/document/10268946/ |
| work_keys_str_mv | AT bianxu realtimelocalizationmethodoflargepressurevesselleaksbasedonimprovedcnnandstcaofelasticwavefield AT huangxinjing realtimelocalizationmethodoflargepressurevesselleaksbasedonimprovedcnnandstcaofelasticwavefield |