A FSTCN-Based Leak Detection Method for Large-Scale Pipeline Transportation Systems
As one of the five major transportation systems, pipeline plays an important role in the energy transportation systems. In large-scale pipeline transportation systems, security issues such as leaks and explosions are prevalent, thus early detection of leaks is important to reduce security hazards in...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10815955/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841542577116938240 |
|---|---|
| author | Du Zhang Chang-Su Kim Chul-Hyun Hwang Tae-Jun Lee Hoe-Kyung Jung |
| author_facet | Du Zhang Chang-Su Kim Chul-Hyun Hwang Tae-Jun Lee Hoe-Kyung Jung |
| author_sort | Du Zhang |
| collection | DOAJ |
| description | As one of the five major transportation systems, pipeline plays an important role in the energy transportation systems. In large-scale pipeline transportation systems, security issues such as leaks and explosions are prevalent, thus early detection of leaks is important to reduce security hazards in pipeline systems. Time series-based studies are widely used for leak detection in large-scale pipeline transportation systems, but single time-domain information, which ignores the spatial distribution of pressure sensors and does not consider periodic features, may not be sufficient for the detection accuracy of complex systems. To address it, a leak detection method based on frequency spatial-temporal convolution network (FSTCN) is proposed in this paper. Next, a spatial-encoder module for leak detection is proposed, which considers the spatial correlation of pressure sensors in pipeline systems. Second, a frequency-enhanced attention layer is proposed, which enables the feature extraction module to capture the periodic features of the pressure data. Meanwhile, a network self-updating mechanism is proposed which considers the changes in detection accuracy and data distribution to adapt to the continuously changing conditions of the pipeline systems. Finally, experiments are used to validate the proposed method, and nine time series classification models are chosen for comparison. The comprehensive results demonstrate that the effectiveness and superiority of the proposed leak detection method for large-scale pipeline systems. |
| format | Article |
| id | doaj-art-b5f5c0d1966c4d57abe4ef8940d39931 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-b5f5c0d1966c4d57abe4ef8940d399312025-01-14T00:01:35ZengIEEEIEEE Access2169-35362025-01-01132101211110.1109/ACCESS.2024.352230310815955A FSTCN-Based Leak Detection Method for Large-Scale Pipeline Transportation SystemsDu Zhang0https://orcid.org/0009-0007-8111-5641Chang-Su Kim1https://orcid.org/0000-0002-2020-3142Chul-Hyun Hwang2https://orcid.org/0000-0002-6265-1314Tae-Jun Lee3https://orcid.org/0009-0006-5143-8397Hoe-Kyung Jung4https://orcid.org/0000-0002-7607-1126Department of Computer Science and Engineering, Pai Chai University, Daejeon, Republic of KoreaDepartment of Computer Science and Engineering, Pai Chai University, Daejeon, Republic of KoreaDepartment of Big Data, Hanyang Women’s University, Seoul, Republic of KoreaDepartment of Computer Science and Engineering, Pai Chai University, Daejeon, Republic of KoreaDepartment of Computer Science and Engineering, Pai Chai University, Daejeon, Republic of KoreaAs one of the five major transportation systems, pipeline plays an important role in the energy transportation systems. In large-scale pipeline transportation systems, security issues such as leaks and explosions are prevalent, thus early detection of leaks is important to reduce security hazards in pipeline systems. Time series-based studies are widely used for leak detection in large-scale pipeline transportation systems, but single time-domain information, which ignores the spatial distribution of pressure sensors and does not consider periodic features, may not be sufficient for the detection accuracy of complex systems. To address it, a leak detection method based on frequency spatial-temporal convolution network (FSTCN) is proposed in this paper. Next, a spatial-encoder module for leak detection is proposed, which considers the spatial correlation of pressure sensors in pipeline systems. Second, a frequency-enhanced attention layer is proposed, which enables the feature extraction module to capture the periodic features of the pressure data. Meanwhile, a network self-updating mechanism is proposed which considers the changes in detection accuracy and data distribution to adapt to the continuously changing conditions of the pipeline systems. Finally, experiments are used to validate the proposed method, and nine time series classification models are chosen for comparison. The comprehensive results demonstrate that the effectiveness and superiority of the proposed leak detection method for large-scale pipeline systems.https://ieeexplore.ieee.org/document/10815955/Pipeline transportation systemsleak detectiondata drivenspatial-temporal featurefrequency enhanced attention |
| spellingShingle | Du Zhang Chang-Su Kim Chul-Hyun Hwang Tae-Jun Lee Hoe-Kyung Jung A FSTCN-Based Leak Detection Method for Large-Scale Pipeline Transportation Systems IEEE Access Pipeline transportation systems leak detection data driven spatial-temporal feature frequency enhanced attention |
| title | A FSTCN-Based Leak Detection Method for Large-Scale Pipeline Transportation Systems |
| title_full | A FSTCN-Based Leak Detection Method for Large-Scale Pipeline Transportation Systems |
| title_fullStr | A FSTCN-Based Leak Detection Method for Large-Scale Pipeline Transportation Systems |
| title_full_unstemmed | A FSTCN-Based Leak Detection Method for Large-Scale Pipeline Transportation Systems |
| title_short | A FSTCN-Based Leak Detection Method for Large-Scale Pipeline Transportation Systems |
| title_sort | fstcn based leak detection method for large scale pipeline transportation systems |
| topic | Pipeline transportation systems leak detection data driven spatial-temporal feature frequency enhanced attention |
| url | https://ieeexplore.ieee.org/document/10815955/ |
| work_keys_str_mv | AT duzhang afstcnbasedleakdetectionmethodforlargescalepipelinetransportationsystems AT changsukim afstcnbasedleakdetectionmethodforlargescalepipelinetransportationsystems AT chulhyunhwang afstcnbasedleakdetectionmethodforlargescalepipelinetransportationsystems AT taejunlee afstcnbasedleakdetectionmethodforlargescalepipelinetransportationsystems AT hoekyungjung afstcnbasedleakdetectionmethodforlargescalepipelinetransportationsystems AT duzhang fstcnbasedleakdetectionmethodforlargescalepipelinetransportationsystems AT changsukim fstcnbasedleakdetectionmethodforlargescalepipelinetransportationsystems AT chulhyunhwang fstcnbasedleakdetectionmethodforlargescalepipelinetransportationsystems AT taejunlee fstcnbasedleakdetectionmethodforlargescalepipelinetransportationsystems AT hoekyungjung fstcnbasedleakdetectionmethodforlargescalepipelinetransportationsystems |