论文部分内容阅读
储层分类是油气勘探开发研究的重要内容之一,目前致密砂岩储层在低孔低渗储层占有很大比例,因此研究致密砂岩储层分类具有重要意义。本文结合四川川西新场地区须家河组致密砂岩储层的特点,综合考虑多种参数,选用孔隙度、渗透率、流动带指数aFZI、泥质含量作为储层特征参数,采用K-means聚类方法将储层分为5大类,并在此基础上,通过对比判别分析和决策树判别准确率,采用决策树方法建立储层分类的定量评价模式。实际资料证明,决策树具有更好的效果,提高了储层分类评价的效果。
Reservoir classification is one of the important contents of oil and gas exploration and development. At present, tight sandstone reservoirs occupy a large proportion of low-porosity and low-permeability reservoirs, so it is of great significance to study the classification of tight sandstone reservoirs. Based on the characteristics of tight sandstone reservoirs in Xujiahe Formation in Xinchang area, Sichuan Province, considering various parameters, porosity, permeability, flow index aFZI and shale content are selected as reservoir characteristics parameters and K-means poly According to the method, the reservoir is divided into five major categories. On the basis of this, a quantitative evaluation model of reservoir classification is established by comparing the discriminant analysis and decision tree discrimination accuracy. The actual data prove that the decision tree has better effect and improves the effect of reservoir classification and evaluation.