【摘要】 目前计算地层破裂压力的理论模型或公式虽较多,但缺乏能直观反映地层破裂压力随测井岩石力学参数变化的统计模型。基于地层破裂压力与岩石力学参数的关系,优选出了对地层破裂压力影响较大的杨氏模量、体积弹性模量、泊松比和深度等4个参数作为建立统计模型的输入变量。同时利用BP神经网络和多元回归分析法对碳酸盐岩地层实测破裂压力数据进行统计建模和预测研究。多元回归模型形式简单直观,易于使用,但精度不高;而BP神经网络模型复杂,建模较难,但预测的地层破裂压力误差小,精度高。两种统计模型都不失为预测地层破裂压力的可行方法。更多还原

【Abstract】 At present, a lot of the theoretical models or equations of calculating formation fracture pressure are presented and used, but there are few statistical models that can obviously reflect the formation fracture pressure and the logging rock mechanics parameter variety. In this paper, based the relation of formation fracture pressure and rock mechanics parameter, the four parameters which have a close connection to formation fracture pressure and are regarded as independent variable (input parameter), such as Young’s modulus, bulk modulus, poison’s ratio and depth etc. are selected. And by the BP neural network and multi-regress analysis technique, some reasonable statistical models of formation fracture pressure are established by making full use of formation fracture pressure data of carbonate formation, and the prediction study is developed. All research shows, the form of multi-regress analysis is simple and visual, and easy to use, but the error is not lesser. The BP neural network model is complex, and it’s model is difficult to set up, but the estimate’s formation fracture the pressure error is little, the precision is high. The two kinds of statistical model are still practical and feasible approaches to calculate formation fracture pressure.更多还原