Bibliographic Details
| Title: |
基于 Newton-GNN 的天然气管道系统 稳态仿真方法. |
| Alternate Title: |
A steady-state simulation method for natural gas pipeline systems based on Newton-GNN. |
| Authors: |
杨毅1 yangyi@pipechina.com.cn, 刁洪涛1, 陈洁1, 侯本权1, 贾文龙2, 林友志2, 李长俊2 |
| Source: |
Chemical Engineering of Oil & Gas / Shi You Yu Tian Ran Qi Hua Gong. Jun2026, Vol. 55 Issue 3, p164-174. 11p. |
| Subject Terms: |
*Graph neural networks, *Newton-Raphson method, *Generalization, *Natural gas pipelines, *Pipeline maintenance & repair, *Computer simulation |
| Abstract (English): |
Objective Simulation constitutes a core technology for intelligent pipeline network dispatching. Data-driven approaches leverage large-scale datasets and pre-trained models to significantly reduce real-time simulation latency. Method This study introduces a steady-state simulation framework based on graph neural networks (GNN). First, a graph representation of the pipeline system was constructed using cross-sections and adjacency matrices. Subsequently, inspired by the Newton-Raphson method widely employed in mechanistic simulations, the original GNN was reconstructed by designing a linear incremental update function, leading to the development of the Newton-GNN model. Finally, pipeline system simulation was achieved by mimicking the inverse Jacobian matrix and linear iteration steps through learned approximations. Result Validation demonstrates that: First, across 6 000 diverse cases, the proposed model enhances accuracy by 72.3% compared to the baseline GNN, with a relative deviation as low as 0.06%. Second, in generalization tests, the model adapts effectively to various scenarios with parameter variations. Third, in two case studies, including the XYX and FR-SH sections, the proposed model yields relative deviations of 2.17% and 1.70% for mainline pressure predictions, respectively. Conclusion The Newton-GNN model exhibits high accuracy and strong generalization ability, making it promising for large-scale natural gas pipeline network simulations. [ABSTRACT FROM AUTHOR] |
| Abstract (Chinese): |
目的 仿真是管网智能调度的核心技术, 数据驱动方法利用海量数据和前置训练, 可以显著缩短实时仿真时间。 方法 提出基于图神经网络 (graph neural network, GNN) 的稳态仿真方法。首先, 利用管道截面和邻接矩阵构建图结构; 其次, 受机理仿真的牛顿迭代法启发, 重构原始 GNN, 设计了线性增量更新函数, 提出了 Newton-GNN 模型; 最后, 通过模型学习 并比拟雅可比矩阵求逆与线性迭代过程, 实现管道系统仿真。结果 ①在 6000 组案例中, 模型较原始 GNN 精度提升了 72.3% (相对偏差 0.06% );②泛化性分析中, 模型可以适应多种参数变化; ③在 XYX 和 FR-SH 段两个实例验证中, 主干线压 力相对偏差为 2.17% 和 1.70%。结论 该模型具有较高精度和优异的泛化性, 可应用于大规模天然气管网系统仿真。 [ABSTRACT FROM AUTHOR] |
| Database: |
Energy & Power Source |
