Physically-based simulation for oil leakage and diffusion on river using heterogeneous graph attention network
Once the oil pipeline leakage accident occurs on the river, the simulation of the leakage diffusion range is of great significance for the designation of emergency rescue plans. The existing methods cannot show the precise leakage diffusion process consistent with the physical law for crude oil on t...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-02-01
|
Series: | Heliyon |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024012180 |
_version_ | 1797304513833467904 |
---|---|
author | Yuanfeng Lian Hanzhao Gao Lianen Ji Shaohua Dong |
author_facet | Yuanfeng Lian Hanzhao Gao Lianen Ji Shaohua Dong |
author_sort | Yuanfeng Lian |
collection | DOAJ |
description | Once the oil pipeline leakage accident occurs on the river, the simulation of the leakage diffusion range is of great significance for the designation of emergency rescue plans. The existing methods cannot show the precise leakage diffusion process consistent with the physical law for crude oil on the river and the simulation suffers high run-time complexity. This paper proposed a two-phase leakage simulation for oil and water combined with the physical process of smoothed particle hydrodynamics (SPH) and graph attention network. A new and efficient method—Mixture Tension Divergence-Free SPH (MTDF-SPH)—that the mixture model and the surface tension model are introduced to the divergence-free smoothed particle hydrodynamics (DFSPH) for simulating the mixing and decomposition effects of immiscible phases. To further accelerate the leakage diffusion process, we design a physics-aware heterogeneous graph attention network (PAGATNet), based on Attention Graph Network Block (AGNB) and Feature-Response Knowledge Distillation (FRKD) to enhance the network's ability for extracting the particle features of physical properties. The experimental results on different test cases show the accuracy, robustness and effectiveness of our method than those of the state-of-the-art in two-phase leakage simulation of crude oil on the river. |
first_indexed | 2024-03-08T00:11:37Z |
format | Article |
id | doaj.art-e675e3a2400d43dab4b6596e4d8b9517 |
institution | Directory Open Access Journal |
issn | 2405-8440 |
language | English |
last_indexed | 2024-03-08T00:11:37Z |
publishDate | 2024-02-01 |
publisher | Elsevier |
record_format | Article |
series | Heliyon |
spelling | doaj.art-e675e3a2400d43dab4b6596e4d8b95172024-02-17T06:39:57ZengElsevierHeliyon2405-84402024-02-01103e25187Physically-based simulation for oil leakage and diffusion on river using heterogeneous graph attention networkYuanfeng Lian0Hanzhao Gao1Lianen Ji2Shaohua Dong3Department of Computer Science and Technology, China University of Petroleum, Beijing, 102249, China; Beijing Key Laboratory of Petroleum Data Mining, Beijing, 102249, China; Corresponding author at: Department of Computer Science and Technology, China University of Petroleum, Beijing, 102249, China.Department of Computer Science and Technology, China University of Petroleum, Beijing, 102249, ChinaDepartment of Computer Science and Technology, China University of Petroleum, Beijing, 102249, China; Beijing Key Laboratory of Petroleum Data Mining, Beijing, 102249, ChinaNational Engineering Laboratory for Pipeline Safety, China University of Petroleum, Beijing, 102249, ChinaOnce the oil pipeline leakage accident occurs on the river, the simulation of the leakage diffusion range is of great significance for the designation of emergency rescue plans. The existing methods cannot show the precise leakage diffusion process consistent with the physical law for crude oil on the river and the simulation suffers high run-time complexity. This paper proposed a two-phase leakage simulation for oil and water combined with the physical process of smoothed particle hydrodynamics (SPH) and graph attention network. A new and efficient method—Mixture Tension Divergence-Free SPH (MTDF-SPH)—that the mixture model and the surface tension model are introduced to the divergence-free smoothed particle hydrodynamics (DFSPH) for simulating the mixing and decomposition effects of immiscible phases. To further accelerate the leakage diffusion process, we design a physics-aware heterogeneous graph attention network (PAGATNet), based on Attention Graph Network Block (AGNB) and Feature-Response Knowledge Distillation (FRKD) to enhance the network's ability for extracting the particle features of physical properties. The experimental results on different test cases show the accuracy, robustness and effectiveness of our method than those of the state-of-the-art in two-phase leakage simulation of crude oil on the river.http://www.sciencedirect.com/science/article/pii/S2405844024012180Heterogeneous graph attention networkFluid simulationMultiphase flowSmoothed particle hydrodynamicsMixture model |
spellingShingle | Yuanfeng Lian Hanzhao Gao Lianen Ji Shaohua Dong Physically-based simulation for oil leakage and diffusion on river using heterogeneous graph attention network Heliyon Heterogeneous graph attention network Fluid simulation Multiphase flow Smoothed particle hydrodynamics Mixture model |
title | Physically-based simulation for oil leakage and diffusion on river using heterogeneous graph attention network |
title_full | Physically-based simulation for oil leakage and diffusion on river using heterogeneous graph attention network |
title_fullStr | Physically-based simulation for oil leakage and diffusion on river using heterogeneous graph attention network |
title_full_unstemmed | Physically-based simulation for oil leakage and diffusion on river using heterogeneous graph attention network |
title_short | Physically-based simulation for oil leakage and diffusion on river using heterogeneous graph attention network |
title_sort | physically based simulation for oil leakage and diffusion on river using heterogeneous graph attention network |
topic | Heterogeneous graph attention network Fluid simulation Multiphase flow Smoothed particle hydrodynamics Mixture model |
url | http://www.sciencedirect.com/science/article/pii/S2405844024012180 |
work_keys_str_mv | AT yuanfenglian physicallybasedsimulationforoilleakageanddiffusiononriverusingheterogeneousgraphattentionnetwork AT hanzhaogao physicallybasedsimulationforoilleakageanddiffusiononriverusingheterogeneousgraphattentionnetwork AT lianenji physicallybasedsimulationforoilleakageanddiffusiononriverusingheterogeneousgraphattentionnetwork AT shaohuadong physicallybasedsimulationforoilleakageanddiffusiononriverusingheterogeneousgraphattentionnetwork |