复杂裂缝内支撑剂铺置规律及有效支撑面积

Proppant Placement Rule and Effective Supporting Area in Complex Fractures

复杂裂缝内支撑剂的铺置规律比较复杂,目前大多数研究都是基于数值模拟方法,存在耗时费力的情况,为了实现支撑面积的快速预测,利用数值模拟方法,在研究注入速度、流体黏度、砂比、粒径及密度等因素对铺置效果影响的基础上,运用神经网络、实验数据,建立了裂缝内支撑剂有效支撑面积神经网络预测模型。结果表明:不同因素都有合理的取值范围,取值超过该范围都会导致铺置效果变差,各级裂缝随影响因素的变化规律不相同,且主次缝的支撑剂铺置是相互影响的,分支前主缝砂堤高度超过一定高度后,砂堤高度越高,次级缝的砂堤面积越小,主次缝最大砂堤面积不会同时出现;基于反向传播(back propagation,BP)神经网络的裂缝内有效支撑面积预测模型,模型预测结果与数值计算结果误差在3.42%~6.46%,该模型能够准确、快速的预测支撑剂在裂缝中运移后形成的砂堤面积。研究结果可以为非常规资源的压裂开发提供理论帮助。

The proppant placement rule in complex fractures is relatively complex.At present,most of the research are based on numerical simulation methods,which are time-consuming and laborious.The numerical simulation method was used to study the influence of injection rate,fluid viscosity,sand ratio,particle size and density on the placement effect.And on this basis,the neural network prediction model of effective proppant support area in fractures was established by using neural network and experimental data.The results show that there are different reasonable ranges in these factors,and exceeding this range can lead to poor laying effect.The variation laws in different levels of cracks are different,and the proppant laying of the main and secondary joints are mutually affected.After the height of the sand embankment of the main joint before branching exceeds a certain height,the higher the sand embankment height,the smaller the sand embankment area of the secondary joint is,and the maximum sand embankment area of the main and secondary joints appear at different times.There is 3.42%~6.46% error between the numerical calculation result and the model prediction result which is obtained from the prediction model of effective support area in cracks based on back propagation(BP) neural network.The area of sand dike formed after proppant migration in the fractures is predicted accurately and quickly.The research is of great significance to the fracturing development of unconventional resources.