arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.01391cs.LGstat.ML
收藏

贝叶斯神经网络在虚拟流量计量中的应用研究

Bayesian Neural Networks for Virtual Flow Metering: An Empirical Study

Solution Seeker AS;Norwegian University of Science and Technology(挪威科技大学);University of Oslo(奥斯陆大学)

Bjarne Grimstad, Mathilde Hotvedt, Anders T. Sandnes, Odd Kolbjørnsen, Lars S. Imsland

摘要:

最近的工作已经从机器学习(ML)的应用到石油和天然气井中的流速建模提出了有希望的结果。ML模型的令人鼓舞的结果和有利特性,例如计算成本低的评估和易于校准新数据,引发了对数据驱动的虚拟流量计(VFM)开发的乐观态度。数据驱动的VFM是在小数据范围内开发的,在小数据范围内,质疑模型的不确定性和鲁棒性是很重要的。对不确定性的建模可以帮助建立对模型的信任,这是工业应用的先决条件。本文的贡献是介绍了一种基于贝叶斯神经网络的概率VFM。在模型和测量的不确定性进行了描述,并展示了如何使用变分推理进行近似贝叶斯推理。该方法是通过对一个大型异构数据集进行建模来研究的,该数据集由五个不同石油和天然气资产的60口井组成。对历史和未来测试数据的预测性能进行了分析,其中50%最佳性能模型的平均误差分别为4-6%和8-13%。变分推理似乎提供了更强大的预测比参考方法对未来的数据。预测性能和不确定性校准进行了详细探讨,并根据四个数据的挑战进行了讨论。研究结果激励替代策略的发展,以提高数据驱动的VFM的鲁棒性。

英文摘要:

Recent works have presented promising results from the application of machine learning (ML) to the modeling of flow rates in oil and gas wells. Encouraging results and advantageous properties of ML models, such as computationally cheap evaluation and ease of calibration to new data, have sparked optimism for the development of data-driven virtual flow meters (VFMs). Data-driven VFMs are developed in the small data regime, where it is important to question the uncertainty and robustness of models. The modeling of uncertainty may help to build trust in models, which is a prerequisite for industrial applications. The contribution of this paper is the introduction of a probabilistic VFM based on Bayesian neural networks. Uncertainty in the model and measurements is described, and the paper shows how to perform approximate Bayesian inference using variational inference. The method is studied by modeling on a large and heterogeneous dataset, consisting of 60 wells across five different oil and gas assets. The predictive performance is analyzed on historical and future test data, where an average error of 4-6% and 8-13% is achieved for the 50% best performing models, respectively. Variational inference appears to provide more robust predictions than the reference approach on future data. Prediction performance and uncertainty calibration is explored in detail and discussed in light of four data challenges. The findings motivate the development of alternative strategies to improve the robustness of data-driven VFMs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑