Delineation of bed boundaries based on resistivity logging curves is important prior information for the inversion and interpretation of resistivity logging data.Traditionally,the layering algorithm mainly use the der...Delineation of bed boundaries based on resistivity logging curves is important prior information for the inversion and interpretation of resistivity logging data.Traditionally,the layering algorithm mainly use the derivatives of resistivity curves or other logging methods as reference.However,measurement error or resolution mismatch may lead to misjudgment of the boundary.In view of the shortcomings of traditional methods,this paper presents an automatic layering algorithm of array induction logging curves based on deep learning.In this algorithm,a locally connected convolution neural network is used,and the generalization ability of the network is improved by enlarging the training set,optimizing the window length and threshold,and strengthening the layering effect.Simulation and field data show the eff ectiveness of the proposed algorithm.展开更多
With the help of the modified geometrical factor theory, the Marquardt method was used to calculate the true electrical parameters of the formation from array induction logs. The inversion results derived from the ass...With the help of the modified geometrical factor theory, the Marquardt method was used to calculate the true electrical parameters of the formation from array induction logs. The inversion results derived from the assumed model and some practical cases show that the rebuilt formation profile determined by 2-ft resolution array induction logs is reasonable when the formation thickness is greater than 1 m, which thus indicates that the inversion method is reliable and can provide quantitative information for the discrimination of oil/gas or water zone.展开更多
Based on the structural characteristic of metal drill collar for induction logging while drilling, we have given the analytical formulae of lengthways fields Ez and Hz when the tool is located in a fan-ring shaped slo...Based on the structural characteristic of metal drill collar for induction logging while drilling, we have given the analytical formulae of lengthways fields Ez and Hz when the tool is located in a fan-ring shaped slot of drill collar by the boundary conditions of electromagnetic field, and derived the other components of electromagnetic field in and out the fan-ring slot from Ez and Hz. In the other intervals of formation, where the drill collar is a solid cylinder, the analytical formulae of field are educed through the method of variable coefficient. The total analytical solutions of field in whole space have been obtained. With the help of the analytical formulae, we have also given numerical examples and analyzed the distributive characteristic of electromagnetic field. From the computational results we find that the secondary scattering field Hz is in a linear relation with the conductivity of stratum. The characteristic of field is very useful for induction logging while drilling, which can be used to measure and analyze the logging responses of the stratum conductivity. This paper sets up a theoretical foundation for us to study the distrbutions of field and to direct the design of logging instruments.展开更多
This paper investigates the relation between the induced electromotive force measured by induction logging tool and the apparent conductivity, and the relation between the apparent conductivity and the formation true ...This paper investigates the relation between the induced electromotive force measured by induction logging tool and the apparent conductivity, and the relation between the apparent conductivity and the formation true conductivity. Assuming the conductivity in Green's function to be the function of the field point coordinate, the apparent conductivity expression of electric-field intensity is derived using Green's formula, and the integral equation has been established representing the relationship of the apparent conductivity with the true conductivity under this condition. The integral equation is analyzed and then leads to the conclusion that the equivalent conductivity is the apparent conductivity and the values of the apparent conductivity function contain the true conductivity, and the method derived the true conductivity from the apparent conductivity around the well axis is put forward. The validity of the approach given in this paper is verified through numerical calculation. On the basis of above means, the transmitter coil produces an electric-field distribution in formation at every point where the induction logging tool moves along a wellbore, and a number of the receiving coils obtain an apparent conductivity distribution; this is what induction electric-field logging is.展开更多
After Doll presented the well-known geometrical factor theory, Moran et al. fully discussed the propagation effect of electromagnetic waves in formation media and derived the rigorous solution based on the Maxwell equ...After Doll presented the well-known geometrical factor theory, Moran et al. fully discussed the propagation effect of electromagnetic waves in formation media and derived the rigorous solution based on the Maxwell equations. For a two-coil system model shown in Fig. 1, Moran et al. based their induction theory on the following point of view, i. e. the alternating current I_T in the transmitter coil T radiates electromagnetic waves in the sur-展开更多
为研究感应测井数据质量,采用长短期记忆(Long Short Term Memory,LSTM)网络作为感应测井数据预测模型。首先建立阵列感应测井数据库,进行统一标准格式化并建立3层模拟地层环境模型;其次建立LSTM神经网络预测模型预测阵列感应测井原始...为研究感应测井数据质量,采用长短期记忆(Long Short Term Memory,LSTM)网络作为感应测井数据预测模型。首先建立阵列感应测井数据库,进行统一标准格式化并建立3层模拟地层环境模型;其次建立LSTM神经网络预测模型预测阵列感应测井原始阵列数据,并通过图表可视化输出预测结果;最后使用预测指标评价预测结果。结果表明基于LSTM神经网络的预测模型预测阵列感应测井原始阵列数据较为准确,且比传统方法更快速、简便。展开更多
基金the National Nature Science Foundation of China(No.41604123)。
文摘Delineation of bed boundaries based on resistivity logging curves is important prior information for the inversion and interpretation of resistivity logging data.Traditionally,the layering algorithm mainly use the derivatives of resistivity curves or other logging methods as reference.However,measurement error or resolution mismatch may lead to misjudgment of the boundary.In view of the shortcomings of traditional methods,this paper presents an automatic layering algorithm of array induction logging curves based on deep learning.In this algorithm,a locally connected convolution neural network is used,and the generalization ability of the network is improved by enlarging the training set,optimizing the window length and threshold,and strengthening the layering effect.Simulation and field data show the eff ectiveness of the proposed algorithm.
文摘With the help of the modified geometrical factor theory, the Marquardt method was used to calculate the true electrical parameters of the formation from array induction logs. The inversion results derived from the assumed model and some practical cases show that the rebuilt formation profile determined by 2-ft resolution array induction logs is reasonable when the formation thickness is greater than 1 m, which thus indicates that the inversion method is reliable and can provide quantitative information for the discrimination of oil/gas or water zone.
基金Supported by the National Natural Science Foundation of China(Grant No.10705049)the Beijing Natural Science Foundation(Grant No.1083011)Fund-ing Project for Academic Human Resources Development in Institutions of Higher Learning[PHR(IHLB)]
文摘Based on the structural characteristic of metal drill collar for induction logging while drilling, we have given the analytical formulae of lengthways fields Ez and Hz when the tool is located in a fan-ring shaped slot of drill collar by the boundary conditions of electromagnetic field, and derived the other components of electromagnetic field in and out the fan-ring slot from Ez and Hz. In the other intervals of formation, where the drill collar is a solid cylinder, the analytical formulae of field are educed through the method of variable coefficient. The total analytical solutions of field in whole space have been obtained. With the help of the analytical formulae, we have also given numerical examples and analyzed the distributive characteristic of electromagnetic field. From the computational results we find that the secondary scattering field Hz is in a linear relation with the conductivity of stratum. The characteristic of field is very useful for induction logging while drilling, which can be used to measure and analyze the logging responses of the stratum conductivity. This paper sets up a theoretical foundation for us to study the distrbutions of field and to direct the design of logging instruments.
基金supported by the National Science and Technology Major Project (Grant No. 2011ZX05020)
文摘This paper investigates the relation between the induced electromotive force measured by induction logging tool and the apparent conductivity, and the relation between the apparent conductivity and the formation true conductivity. Assuming the conductivity in Green's function to be the function of the field point coordinate, the apparent conductivity expression of electric-field intensity is derived using Green's formula, and the integral equation has been established representing the relationship of the apparent conductivity with the true conductivity under this condition. The integral equation is analyzed and then leads to the conclusion that the equivalent conductivity is the apparent conductivity and the values of the apparent conductivity function contain the true conductivity, and the method derived the true conductivity from the apparent conductivity around the well axis is put forward. The validity of the approach given in this paper is verified through numerical calculation. On the basis of above means, the transmitter coil produces an electric-field distribution in formation at every point where the induction logging tool moves along a wellbore, and a number of the receiving coils obtain an apparent conductivity distribution; this is what induction electric-field logging is.
文摘After Doll presented the well-known geometrical factor theory, Moran et al. fully discussed the propagation effect of electromagnetic waves in formation media and derived the rigorous solution based on the Maxwell equations. For a two-coil system model shown in Fig. 1, Moran et al. based their induction theory on the following point of view, i. e. the alternating current I_T in the transmitter coil T radiates electromagnetic waves in the sur-
文摘为研究感应测井数据质量,采用长短期记忆(Long Short Term Memory,LSTM)网络作为感应测井数据预测模型。首先建立阵列感应测井数据库,进行统一标准格式化并建立3层模拟地层环境模型;其次建立LSTM神经网络预测模型预测阵列感应测井原始阵列数据,并通过图表可视化输出预测结果;最后使用预测指标评价预测结果。结果表明基于LSTM神经网络的预测模型预测阵列感应测井原始阵列数据较为准确,且比传统方法更快速、简便。