摘要
为了得到更精确的CO_2驱原油最小混相压力,考虑挥发组分(N_2+CO_2+CH_4+H_2S)含量、中间烃组分(C_(2-6))含量、重质组分(C_7^+)含量、重质组分的相对分子质量、重质组分密度以及温度的影响,建立了基于遗传算法参数寻优的支持向量回归机模型。模型优点在于使数据结构风险最小化,是基于数据精度高和回归函数复杂性适宜的条件下进行全局参数寻优得到最优模型,根据测试样本数据可以给出预测结果,得到更为准确的最小混相压力数值。该模型计算结果平均相对误差为3.44%,与文献中的实验结果、细管实验结果对比,具有较好的准确性。
In order to more precisely obtain the oil minimal miscible pressure of CO2 flooding, considering the in- fluences of the Use other people's result, study the various factors between contents of volatile (N2+CO2+CH4 + H2S) , intermediate hydrocarbon (C2.6) , heavy hydrocarbon ( C7 ) , molecular weight ( Mc7+ ) and density (ρc7+) of the heavy components and temperature, the optimized support vector regression (SVR) machine model was established on the basis of the genetic algorithm ( GA ) parameters. The advantages of this model is to make the data structure risk minimal, which is the obtained optimized model from the overall parameters under the conditions of the high-precision data and suitable complexity of the regression function, and moreover with the help of the testing sample data, the predicted results were presented, thus the more accurate minimal miscible pressure value was ob- tained. Comparing the model calculation results with the experimental ones in the references and slim-tube test, the average relative error is 3.44% i. e. much better accuracy is presented.
出处
《大庆石油地质与开发》
CAS
CSCD
北大核心
2017年第3期123-129,共7页
Petroleum Geology & Oilfield Development in Daqing
基金
中国石油天然气股份有限公司"十二五"重大科技项目"天然气开发关键技术研究"(2011B-1507)
关键词
CO2驱
最小混相压力
遗传算法
模型
支持向量回归机
carbon dioxide ( CO2 ) flooding
minimum miscible pressure
genetic algorithm ( GA )
model
sup-port vector regression ( SVR) machine