数据驱动与物理驱动融合的双驱动渗流代理模型构建

A data-driven flow surrogate model based on a data-driven and physics-driven method

渗流代理模型的构建是油气藏模拟技术研究的前沿方向,而目前广泛使用的纯数据驱动渗流代理模型无理论支撑,对数据数量和质量的要求较高,很大程度上限制了渗流代理模型的发展。为此提出了数据驱动与物理驱动相融合的双驱动渗流代理模型,其在纯数据驱动渗流代理模型的基础上,融合油气渗流理论,模拟预测油气渗流过程。结果表明:相较于纯数据驱动渗流代理模型,即使训练数据极度稀疏,双驱动渗流代理模型仍具有较高的预测精度;通过在训练数据中加入不同等级的干扰噪声,验证了双驱动渗流代理模型的鲁棒性优于纯数据驱动渗流代理模型;通过迁移学习,将训练好的双驱动渗流代理模型应用到新的渗流场,实现了快速收敛并节省了计算资源。

The building of flow surrogate models is the frontier of simulation technology research for oil and gas reservoirs.However,the currently widely used pure data-driven flow surogate models have no theoretical support and require a high data volume and data quality,which greatly limits the development of flow surrogate models.Therefore,this paper propos-es a flow surrogate model based on a data-driven and physics-driven method.On the basis of the pure data-driven flow sur-rogate model,it takes advantage of the flow theory to simulate and predict oil and gas flow processes.Firstly,the dual-driv-en flow surrogate model is compared with the pure data-driven model.The results show that the proposed model can still maintain high prediction accuracy even if the training data is extrermely sparse.Secondly,the robustness of the dual driven model is explored by adding different levels of noise interference to the training data,and it is verified that the proposed model outperforms the pure data driven flow surrogate model.Finally,the trained dual driven flow surrogate model is ap-plied to a new flow field through transfer leamning.The model can achieve rapid convergence and save computing resources.