用人工神经网络方法分析油藏压裂效果——以靖安油田塞A井区长2油藏为例

通过已有的少数井的试井资料分析得出压裂裂缝参数,以现有的参数为样本建立人工神经网络系统.以影响压裂结果的地层厚度、孔隙度、泥质含量、压裂施工参数、工作压力加砂排量为输入参数,以裂缝导流能力和裂缝半长为输出参数,用BP神经网络训练,推断出所有井的压裂裂缝参数,从而得到整个油藏的压裂裂缝分布特征,对压裂措施的效果有了直观的评价.

ANALYSIS ON THE FRACTURING RESULT OF RESERVOIR BY ARTIFICIAL NEURAL NETWORK:A case study of the C2 reservior in SA wellblock,Jingan oilfeld

The fracture parameters are obtained through the well test data from a small number of wells.With the existing parameters as samples,the artificial neural network system is set up.The input parameters that influence the outcome of fracturing,such as the formation thickness,porosity,clay content,working stress and sand displacement,are selected.The ability to fracture conductivity and fracture half-length are the output parameters.With training by BP neural networks,the fracturing parameters of the whole wel...