基于决策树的注采连通关系判别研究

判别注采连通关系的传统方法是由人工通过对比测井曲线, 逐个层位地进行连通关系的识别和分类, 这种方式工作量大、耗费劳动力多、判别效率较低。针对大庆油田注采连通关系判别的这种现状, 从油藏开发数据中提取并构建出注采井间的相对特征, 使用CART（分类回归树）算法建立了注采连通关系自动判别的决策树模型。实验结果表明, 该方法具有操作简单、判别速度快等优点, 在提高连通关系判别效率的同时保证了有较高的精度。

Study on inferring interwell connectivity of injection-production system based on decision tree

The traditional method of identifying interwell connectivity of injection-production system is manual analysing the logging curve by every small layer, which is labor-intensive, bring out a lot of workload and keep a very low work efficiency. In order to change the status quo of inferring interwell connectivity in Daqing oilfield, this paper analysised the logging data of oilfield development to extract and establish some relative characteristics between injection wells and production wells and used CART algorithm to construct a decision tree for the automatic identification of interwell connectivity of injection wells and production wells. According to the experimental results, this method has the advantages of simple operation and fast discriminant. It improves the efficiency of discrimination and meanwhile ensured a greater accuracy.