Formation pressure is the key parameter for the analysis of wellbore safety.With increasing drilling depth,how-ever,the behavior of this variable becomes increasingly complex.In this work,a 3D model of the formation p...Formation pressure is the key parameter for the analysis of wellbore safety.With increasing drilling depth,how-ever,the behavior of this variable becomes increasingly complex.In this work,a 3D model of the formation pres-sure under uncertainty is presented.Moreover a relevant algorithm is elaborated.First,the logging data of regional key drilling wells are collected and a one-dimensional formation pressure profile along the well depth is determined.Then,a 3D model of regional formation pressure of the hierarchical group layer is defined by using the Kriging interpolation algorithm relying on a support vector machine(SVM)and the formation pressure of the drilled wells.To validate the method,the formation pressure of one pre-drilled well is compared with the well logging results.The comparison reveals that the maximum relative error is less than 4.5%.The software based on this model is complemented by a computer visualization technology,which provides a relevant tool for under-standing and analyzing the 3D formation pressure.The outcomes of this study are intended to support the char-acterization of areas with missing or poor 3D seismic data and provide more accurate information for the analysis of wellbore integrity.展开更多
Sticking is the most serious cause of failure in complex drilling operations.In the present work a novel“early warning”method based on an artificial intelligence algorithm is proposed to overcome some of the known pr...Sticking is the most serious cause of failure in complex drilling operations.In the present work a novel“early warning”method based on an artificial intelligence algorithm is proposed to overcome some of the known pro-blems associated with existing sticking-identification technologies.The method is tested against a practical case study(Southern Sichuan shale gas drilling operations).It is shown that the twelve sets of sticking fault diagnostic results obtained from a simulation are all consistent with the actual downhole state;furthermore,the results from four groups of verification samples are also consistent with the actual downhole state.This shows that the pro-posed training-based model can effectively be applied to practical situations.展开更多
基金supported by Scientific Research and Technology Development Project of CNPC“Study on Exploration and Development Theory and Key Technology of Gulong Shale Oil in Daqing”(2021ZZ10-03)Scientific Research and Technology Development Project of CNPC“Development of Integrated Software(Smart Drilling)for Drilling and Completion Engineering Design and Optimization Decision”(2020B-4019)+1 种基金Scientific Research and Technology Development Project of CNPC“Integration and Experiment of Safe,Optimal and Fast Drilling and Completion Technology for Complex Ultra Deep Wells”(2020F-46)project funded by China Postdoctoral Science Foundation“Research on the Effect of Stress Distribution Difference on Acoustic Propagation Characteristics in Drill String”(2021M693508).
文摘Formation pressure is the key parameter for the analysis of wellbore safety.With increasing drilling depth,how-ever,the behavior of this variable becomes increasingly complex.In this work,a 3D model of the formation pres-sure under uncertainty is presented.Moreover a relevant algorithm is elaborated.First,the logging data of regional key drilling wells are collected and a one-dimensional formation pressure profile along the well depth is determined.Then,a 3D model of regional formation pressure of the hierarchical group layer is defined by using the Kriging interpolation algorithm relying on a support vector machine(SVM)and the formation pressure of the drilled wells.To validate the method,the formation pressure of one pre-drilled well is compared with the well logging results.The comparison reveals that the maximum relative error is less than 4.5%.The software based on this model is complemented by a computer visualization technology,which provides a relevant tool for under-standing and analyzing the 3D formation pressure.The outcomes of this study are intended to support the char-acterization of areas with missing or poor 3D seismic data and provide more accurate information for the analysis of wellbore integrity.
基金The project is supported by CNPC Key Core Technology Research Projects(2022ZG06)received by Qing Wangproject funded by China Postdoctoral Science Foundation(2021M693508)received by Qing Wang.Basic Research and Strategic Reserve Technology Research Fund Project of Institutes directly under CNPC received by Qing Wang.
文摘Sticking is the most serious cause of failure in complex drilling operations.In the present work a novel“early warning”method based on an artificial intelligence algorithm is proposed to overcome some of the known pro-blems associated with existing sticking-identification technologies.The method is tested against a practical case study(Southern Sichuan shale gas drilling operations).It is shown that the twelve sets of sticking fault diagnostic results obtained from a simulation are all consistent with the actual downhole state;furthermore,the results from four groups of verification samples are also consistent with the actual downhole state.This shows that the pro-posed training-based model can effectively be applied to practical situations.