石油勘探与开发2026，Vol.53Issue(3)：712-721,10.DOI:10.11698/PED.20250577
数据物理驱动的图连接元智能注采模型
An intelligent injection-production model based on graph connection element driven by data and physics
摘要
Abstract
To address the challenges of connectivity characterization,dynamic prediction efficiency,and real-time optimization in complex reservoir injection-production systems,this study proposes a physics-and deep learning-integrated intelligent injection-production modeling framework based on the graph connection element method.The method adopts the connection element method as the physical foundation and constructs a non-Euclidean graph representation to describe interwell connectivity,enabling characterization of the physical topology and dynamic interactions within the well pattern system.By incorporating an adaptive attention mechanism into a graph convolutional network and embedding time-dependent node attributes,a physics-consistent reservoir performance prediction model is developed.Furthermore,a hybrid optimization strategy integrating differential evolution and particle swarm optimization is employed to establish an intelligent optimization framework taking the economic net present value as the objective.Based on rapid prediction of injection and production behaviors,the proposed approach enables optimization of injection-production parameters and maximization of exploitation economics.Field applications demonstrate that the proposed intelligent injection-production model based on graph connection element accurately reproduces water-cut behavior of producers and provides quantitative uncertainty estimation.It achieves rapid history matching and dynamic response forecasting for complex injection-production systems,exhibiting high accuracy and stability.It enables global optimization of production strategies under economic constraints,demonstrating strong engineering applicability and scalability.关键词
非欧几里得空间/图神经网络/图连接元/物理约束/代理模型/差分进化-粒子群算法/生产优化Key words
non-Euclidean space/graph neural networks/graph connection element/physics-constrained learning/surrogate model/differential evolution-particle swarm optimization/production optimization分类
能源科技引用本文复制引用
赵辉,徐云峰,贾德利,饶翔,周玉辉,孟凡坤..数据物理驱动的图连接元智能注采模型[J].石油勘探与开发,2026,53(3):712-721,10.基金项目
国家自然科学基金青年基金A类"油气智能开发模拟与优化调控"(52525403) （52525403）
国家科技重大专项"高效智能采油采气工程关键技术及装备"(2024ZD14065) （2024ZD14065）
国家自然科学基金面上项目(52574028) （52574028）
