Leak Detection and Location Based on ISLMD and CNN in a Pipeline
The key to leak detection and location in water supply pipelines is signal denoising and feature extraction. First, in this paper, an improved spline-local mean decomposition (ISLMD) is proposed to eliminate noise interference. Based on the ISLMD decomposition of a signal, the cross-correlation func...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8657927/ |
| _version_ | 1818415912430075904 |
|---|---|
| author | Mengfei Zhou Zheng Pan Yunwen Liu Qiang Zhang Yijun Cai Haitian Pan |
| author_facet | Mengfei Zhou Zheng Pan Yunwen Liu Qiang Zhang Yijun Cai Haitian Pan |
| author_sort | Mengfei Zhou |
| collection | DOAJ |
| description | The key to leak detection and location in water supply pipelines is signal denoising and feature extraction. First, in this paper, an improved spline-local mean decomposition (ISLMD) is proposed to eliminate noise interference. Based on the ISLMD decomposition of a signal, the cross-correlation function between the reference signal and the product functions component can be obtained. And then the PF component containing the leak information can be extracted reasonably. Compared with improved local mean decomposition, the ISLMD has higher accuracy in leak location. Second, an image recognition method using a convolutional neural network for leak detection is proposed, which can better address the problem that the features of different leak apertures or locations are highly similar to each other. The images from the conversion of the reconstructed signals are used as the input of the AlexNet model, which is capable of adaptive extraction of leak signal features. The trained AlexNet model can effectively detect different leak apertures. Finally, the signal time-delay between the upstream and downstream pressure transmitters caused by the leak and propagation of negative pressure wave is determined according to generalized cross-correlation analysis, and thereby, the leak location is obtained. The experimental results show that the proposed method is effective for leak detection and location. |
| first_indexed | 2024-12-14T11:42:32Z |
| format | Article |
| id | doaj.art-f2dc2ff9c2b249a49d77a8efdfa38a2b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T11:42:32Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f2dc2ff9c2b249a49d77a8efdfa38a2b2022-12-21T23:02:46ZengIEEEIEEE Access2169-35362019-01-017304573046410.1109/ACCESS.2019.29027118657927Leak Detection and Location Based on ISLMD and CNN in a PipelineMengfei Zhou0https://orcid.org/0000-0003-0385-8558Zheng Pan1Yunwen Liu2Qiang Zhang3Yijun Cai4Haitian Pan5College of Chemical Engineering, Zhejiang University of Technology, Hangzhou, ChinaCollege of Chemical Engineering, Zhejiang University of Technology, Hangzhou, ChinaCollege of Chemical Engineering, Zhejiang University of Technology, Hangzhou, ChinaCollege of Chemical Engineering, Zhejiang University of Technology, Hangzhou, ChinaCollege of Chemical Engineering, Zhejiang University of Technology, Hangzhou, ChinaCollege of Chemical Engineering, Zhejiang University of Technology, Hangzhou, ChinaThe key to leak detection and location in water supply pipelines is signal denoising and feature extraction. First, in this paper, an improved spline-local mean decomposition (ISLMD) is proposed to eliminate noise interference. Based on the ISLMD decomposition of a signal, the cross-correlation function between the reference signal and the product functions component can be obtained. And then the PF component containing the leak information can be extracted reasonably. Compared with improved local mean decomposition, the ISLMD has higher accuracy in leak location. Second, an image recognition method using a convolutional neural network for leak detection is proposed, which can better address the problem that the features of different leak apertures or locations are highly similar to each other. The images from the conversion of the reconstructed signals are used as the input of the AlexNet model, which is capable of adaptive extraction of leak signal features. The trained AlexNet model can effectively detect different leak apertures. Finally, the signal time-delay between the upstream and downstream pressure transmitters caused by the leak and propagation of negative pressure wave is determined according to generalized cross-correlation analysis, and thereby, the leak location is obtained. The experimental results show that the proposed method is effective for leak detection and location.https://ieeexplore.ieee.org/document/8657927/Local mean decompositionconvolutional neural networkgeneralized cross-correlationleak detection and locationfault detection |
| spellingShingle | Mengfei Zhou Zheng Pan Yunwen Liu Qiang Zhang Yijun Cai Haitian Pan Leak Detection and Location Based on ISLMD and CNN in a Pipeline IEEE Access Local mean decomposition convolutional neural network generalized cross-correlation leak detection and location fault detection |
| title | Leak Detection and Location Based on ISLMD and CNN in a Pipeline |
| title_full | Leak Detection and Location Based on ISLMD and CNN in a Pipeline |
| title_fullStr | Leak Detection and Location Based on ISLMD and CNN in a Pipeline |
| title_full_unstemmed | Leak Detection and Location Based on ISLMD and CNN in a Pipeline |
| title_short | Leak Detection and Location Based on ISLMD and CNN in a Pipeline |
| title_sort | leak detection and location based on islmd and cnn in a pipeline |
| topic | Local mean decomposition convolutional neural network generalized cross-correlation leak detection and location fault detection |
| url | https://ieeexplore.ieee.org/document/8657927/ |
| work_keys_str_mv | AT mengfeizhou leakdetectionandlocationbasedonislmdandcnninapipeline AT zhengpan leakdetectionandlocationbasedonislmdandcnninapipeline AT yunwenliu leakdetectionandlocationbasedonislmdandcnninapipeline AT qiangzhang leakdetectionandlocationbasedonislmdandcnninapipeline AT yijuncai leakdetectionandlocationbasedonislmdandcnninapipeline AT haitianpan leakdetectionandlocationbasedonislmdandcnninapipeline |