论文部分内容阅读
针对目前大庆油田一类油层聚驱区块分析中,由于油层物性、原油性质、水驱开发阶段、聚合物溶液性质等指标相近,造成应用常规聚类分析进行区块归类评价困难,并且收敛速度慢的问题,利用墨西哥草帽函数对常规FCM算法进行改进.该(IFKN)方法在保证较高寻优概率基础上,对邻域调整进行侧抑制作用,加快了收敛速度,节省了计算时间12%以上.目前,通过大庆油田20个已完成注聚的工业化区块计算显示,结果可靠、快速,为下步二类、三类聚驱油层进行效果评价奠定了基础.
According to the analysis of the poly-flooding block of the first oil layer in Daqing Oilfield, due to the properties of the oil layer, the nature of the crude oil, the development stage of the water flooding and the nature of the polymer solution, the block clustering evaluation using conventional clustering analysis is difficult, (IFKN) based on the Mexican straw hat function to improve the performance of the traditional FCM based on the side of the adjustment to the side of the inhibition, speed up the convergence rate and save time 12 % .At present, through the calculation of 20 industrial blocks in Daqing Oilfield, which have already been completed, the results show that the results are reliable and fast, which lays the foundation for the next two types and three types of polymer flooding reservoirs to evaluate the effect.