基于模糊神经网络建立室内驱油实验预测模型  

PREDICTION MODEL OF INDOOR FLOODING EXPERIMENT BASED ON FUZZY NEURAL NETWORK

作　　者：刘明[1,2] 马国伟[1,2] 何令普 孙海生 张娜 李稳宏 Liu Ming;Ma Guowei;He Lingpu;Sun Haisheng;Zhang Na;Li Wenhong(Petroleum Technology Research Institute of PetroChina Changqing Oilfield Company, Xi’an 710018, Shaanxi, China;National Engineering Laboratory for Exploration and Development of Low Permeability Oil and Gas Fields, Xi’an 710018, Shaanxi, China;The Fourth Oil Production Plant of Changqing Oilfield Branch, Yinchuan 750002, Ningxia, China;The Sixth Oil Production Plant of Changqing Oilfield Branch, Xi’an 710018, Shaanxi, China;School of Chemical Engineering, Northwest University, Xi’an 710069, Shaanxi, China)

机构地区：[1]中国石油长庆油田分公司油气工艺研究院,陕西西安710018 [2]低渗透油气田勘探开发国家工程实验室,陕西西安710018 [3]中国石油长庆油田分公司第四采油厂,宁夏银川750002 [4]中国石油长庆油田分公司第六采油厂,陕西西安710018 [5]西北大学化工学院,陕西西安710069

出　　处：《精细石油化工》2021年第6期39-45,共7页Speciality Petrochemicals

摘　　要：为提高低渗透油藏的采收率,利用室内驱油实验来研究已了CQ-Ⅲ剂的驱油效果。实验结果表明:CQ-Ⅲ剂具有良好的驱油效果,其采收率提高幅度在1.50%~10.23%,最佳注入工艺参数为:30000 mg/L低矿化度、分数0.3%、60℃及0.3 PV注入量。利用模糊神经网络建立了室内驱油实验预测模型,结果表明实验真实值与模型预测值近似相等,且两者并无显著性差异,表明该模型可以用来预测室内驱油实验。In order to improve the oil recovery of low permeability reservoirs,the oil displacement effect of the synthesized CQ-Ⅲagent was studied by indoor oil displacement experiments.The experimental results show that the CQ-Ⅲagent has a good oil displacement effect,and its oil recovery rate is increased by 1.50%10.23%.The optimal injection process parameters are:30000 mg/L low salinity,0.3%concentration,60℃and 0.3 PV injection volume.The prediction model of indoor oil displacement experiment is established by using fuzzy neural network.The results show that the real value of the experiment is approximately equal to the prediction value of the model,and there is no significant difference between the two data,indicating that the model can be used to predict indoor oil displacement experiments.

关 键 词：低渗透油藏 室内驱油实验 模糊神经网络 

分 类 号：TE348[石油与天然气工程—油气田开发工程] TE357