摘要
以BP网络模型为基础,以地层渗透率、孔隙度、油层厚度、压裂砂量、砂比、施工排量和工作压力等影响压裂效果的主要参数作为输入参数,对某油藏实际的投产压裂井的数据进行训练学习,并由训练计算得到的权重系数,对油藏的压裂施工参数进行计算,得出用砂量和压后产量的关系曲线,以此为依据优化压裂用砂量。
Based on the model of BP network, the reservoir permeability, porosity, reservoir thickness, amount of sand in fracturing, sand ratio, operational displacement and working pressure, which are major parameters influencing the fracture effect, are used as imput parameters, the parameters of production-fracturing wells of a reservoir is trained and learnt. The fracturing parameters of the reservoir are calculated by using the weighted factors obtained from calculation in training, and a correlation curve between sand producing rate and post fracturing production is derived, which is used as a basis for optimizing sand usage in fracturing.
出处
《石油天然气学报》
CAS
CSCD
北大核心
2005年第2期214-215,共2页
Journal of Oil and Gas Technology
基金
中国石油天然气集团公司中青年创新基金资助项目(04E707)。
关键词
人工神经网络
压裂
压裂用砂量
优化
artificial neural network
amount of sand in fracturing
optimization
