陕西科技大学学报（自然科学版）2018，Vol.36Issue(1)：90-95,6.
致密储层动态渗透率预测模型
Study on prediction of dynamic permeability based on improved BP neural network
摘要
Abstract
In the development of the low permeability tight reservoir ,the permeability is influ-enced by so many factors ,the common permeability model that based on single variable has trouble in accurately describing the permeability .In this paper ,the main factors affecting per-meability of the low permeability reservoir are analyzed ,including effective stress ,tempera-ture and water saturation .And then we establish a BP neural network permeability prediction model optimized by the artificial bee colony algorithm ,in w hich effective stress ,temperature and water saturation are input layer nodes ,permeability is output layer node .The permeabili-ty of different conditions is used to establish learning samples for training and predicting .Re-sult show s that the maximum absolute error of the training results is 0 .06347 × 10 -3 μm2 , the maximum relative error is 4 .382％ and the average relative error is 1 .069％ .It shows that the BP neural network model optimized by artificial bee colony algorithm ,in other words ,the hybrid neural network can accurately describe the internal relations and laws be-tween the permeability and various influence factors .Whereas ,the average relative error of the conventional BP neural network permeability model is 10 .699％ .Obviously ,the hybrid neural network is more accurate and stable than the conventional BP neural network .In one word ,the hybrid neural network has a wonderful adaptability to the permeability prediction of low permeability tight reservoirs .关键词
致密储层/人工蜂群算法/BP神经网络/混合神经网络/渗透率预测模型Key words
tight reservoir/artificial bee colony algorithm/back propagation neural network/hybrid neural network/permeability prediction model分类
能源科技引用本文复制引用
董满仓,柴汝宽,辛晶,陈映赫,黄建树..致密储层动态渗透率预测模型[J].陕西科技大学学报（自然科学版）,2018,36(1):90-95,6.基金项目
国家重大科技专项项目(2017ZX05032004-002) （2017ZX05032004-002）
