基于机器学习方法的原油地层体积系数可靠性预测

xinmeng

基于机器学习方法的原油地层体积系数可靠性预测

Advances in Geo-Energy Research, 2019, 3(3): 225-241

原文网址: https://www.yandy-ager.com/index.php/ager/article/view/124

        神经网络，机器学习算法是一种有效的预测工具，但是在很多应用中就像黑匣子一样，这是因为其不能提供与预测相关的准确计算和基础输入变量（可能是独立变量也可能是非独立变量）之间的关系。透明开放盒箱式（TOB）学习网络算法通过提供预测中的准确计算来达到可接受和可审计的预测精度水平，从而克服了这个限制。基于最优数据匹配算法的TOB网络可以应用于电子制表或全编码的配置中。这种算法在许多复杂的和难以测量的非线性系统分析和预测有显著的优势。

       为了验证其预测性能，英国DWA能源有限公司David A.Wood与伊朗阿瓦兹石油工业大学Abouzar Choubineh将该算法应用于含四个变量（储层温度、油气比、油比重和相对气体比重）的166、203和237个数据记录的泡点原油地层体积系数预测，其中两个数据集显示了不均匀和不规则的数据覆盖。对于分布较均匀的数据集，TOB网络具有较高的预测精度(均方根误差(RMSE)~0.03；R2>；0.95)。TOB的性能很容易表示出过度拟合这些数据集的风险。TOB学习网络以其高度的透明性和对过度拟合的限制，为应用于预测复杂非线性系统的机器学习提供了一种更好的方法。其结果补充和基准了神经网络和经验关系式的预测贡献，由此为基础数据提供了进一步认识。

Reliable predictions of oil formation volume factor based on transparent and auditable machine learning approaches

David A. Wood, Abouzar Choubineh

(Published: 2019-05-02)

CorrespondingAuthor and Email:

David A.Wood, dw@dwasolutions.com;

ORCID: https://orcid.org/0000-0003-3202-4069

---

Citation: Wood, D.A., Choubineh, A. Reliable predictions of oil formation volume factor based on transparent and auditable machine learning approaches. Advances in Geo-Energy Research, 2019, 3(3): 225-241, doi: 10.26804/ager.2019.03.01.

---

ArticleType: Original article

---

Abstract：

    Neural-network, machine-learning algorithms are effective prediction tools but can behave as black boxes in many applications by not easily providing the exact calculations and relationships among the underlying input variables (which may or may not be independent of each other) involved each of their predictions. The transparent open box (TOB) learning network algorithm overcomes this limitation by providing the exact calculations involved in all its predictions and achieving acceptable and auditable levels of prediction accuracy. The TOB network, based on an optimized data-matching algorithm, can be applied in spreadsheet or fully-coded configurations. This algorithm offers significant benefits to analysis and prediction of many complex and difficult to measure non-linear systems. To demonstrate its prediction performance, the algorithm is applied to the prediction of crude oil formation volume factor at bubble point using published datasets of 166, 203 and 237 data records involving 4 variables (reservoir temperature, gas-oil ratio, oil gravity and gas specific gravity). Two of these datasets display uneven and irregular data coverage. The TOB network demonstrates high prediction accuracy (Root Mean Square Error (RMSE) ~ 0.03; R2 > 0.95) for the more evenly distributed dataset. The performance of the TOB readily reveals the risk of overfitting such datasets. With its high levels of transparency and inhibitions to being overfitted, the TOB learning network offers an insightful approach to machine learning applied to predicting complex non-linear systems. Its results complement and benchmark the prediction contributions of neural networks and empirical correlations. In doing so it provides further insight to the underlying data.

Keywords: Machine learning transparency, non-correlation-based machine learning, oil formation volume factor prediction, sparse data impacts, avoidance of overfitting.