川东沙坪场气田石炭系储集层特征及预测

沙坪场气田石炭系黄龙组主要储集空间为孔隙和裂缝,属于低孔低渗型储层,裂缝发育程度决定着低渗储层的渗流和产出能力,裂缝在改善储层渗透率方面发挥着重要的作用。以测井信息为基础,利用神经网络算法对该区未取芯井储层的孔隙度、渗透率、含水饱和度参数及裂缝发育程度进行了预测。使用误差统计法对储层参数预测模型效果进行评价,其预测效果满足本区所需储层参数计算的精度要求。证明了神经网络算法是在测井信息较少的情况下预测储层物性的有效手段,也为其他地区储层预测研究提供了参考。

Pores and fractures are main reservoir spaces in Huanglong Formation of Carboniferous in Shapingchang Gas Field,which belongs to low-pore space and permeability reservoir.The permeability and yield of reservoir is mainly dependent on the degree of fracture development,and the fractures play an important role in improving the reservoir permeability.Based on the information of logging,the porosity,permeability,aqueous saturation and the degree of fractures growth in the study area had been forecasted by using neural network algorithm.The effect of the prediction model of the reservoir parameters had been evaluated by the way of statistical error results,which meet the precision request that reservoir parameters should be calculated.It has proved that the neural network algorithm is an effect Reservoir forecasting reservoir when the logging information is less.The successful application of these fracture models provides a reference to fracture identification and prediction in other areas.