人工神经网络在CO2驱采收率预测中的应用

CO2驱是三次采油中最具潜力的提高采收率方法之一,准确评价和预测CO2驱的采收率成为一项非常重要的工作。由于影响采收率的因素较多,且影响因素与采收率之间是一种非线性、不确定的复杂关系,致使常规预测方法效率及精度不高。针对此问题编写BP神经网络程序,引入影响采收率的5个无因次变量对于这种非线性、不确定的多变量系统进行预测,结果表明,人工神经网络方法具有更好的自适应性,能较好地反映影响CO2驱的各种参数与采收率的内在联系,而且预测精度较高。应用BP神经网络方法预测CO2驱采收率是可行而有效的。

Application of artificial neural network in recovery factor forecast of carbon dioxide flooding

CO2 flooding is one of the most potential EOR methods.It is very important to accurately forecast the recovery factor of CO2 flooding.There are many influential factors on the recovery factor,and there is a nonlinear,uncertain,complex relationship between the influential factors and recovery factor,thus resulting in low accuracy with conventional forecast methods.Accordingly,a program of BP neural network has been developed,five dimensionless variables affecting recovery factor are introduced to forecast su...