Porosity is an important attribute for evaluating the petrophysical properties of reservoirs, and has guiding significance for the exploration and development of oil and gas. The seismic inversion is a key method for ...Porosity is an important attribute for evaluating the petrophysical properties of reservoirs, and has guiding significance for the exploration and development of oil and gas. The seismic inversion is a key method for comprehensively obtaining the porosity. Deep learning methods provide an intelligent approach to suppress the ambiguity of the conventional inversion method. However, under the trace-bytrace inversion strategy, there is a lack of constraints from geological structural information, resulting in poor lateral continuity of prediction results. In addition, the heterogeneity and the sedimentary variability of subsurface media also lead to uncertainty in intelligent prediction. To achieve fine prediction of porosity, we consider the lateral continuity and variability and propose an improved structural modeling deep learning porosity prediction method. First, we combine well data, waveform attributes, and structural information as constraints to model geophysical parameters, constructing a high-quality training dataset with sedimentary facies-controlled significance. Subsequently, we introduce a gated axial attention mechanism to enhance the features of dataset and design a bidirectional closed-loop network system constrained by inversion and forward processes. The constraint coefficient is adaptively adjusted by the petrophysical information contained between the porosity and impedance in the study area. We demonstrate the effectiveness of the adaptive coefficient through numerical experiments.Finally, we compare the performance differences between the proposed method and conventional deep learning methods using data from two study areas. The proposed method achieves better consistency with the logging porosity, demonstrating the superiority of the proposed method.展开更多
A reliable and effective model for reservoir physical property prediction is a key to reservoir characterization and management.At present,using well logging data to estimate reservoir physical parameters is an import...A reliable and effective model for reservoir physical property prediction is a key to reservoir characterization and management.At present,using well logging data to estimate reservoir physical parameters is an important means for reservoir evaluation.Based on the characteristics of large quantity and complexity of estimating process,we have attempted to design a nonlinear back propagation neural network model optimized by genetic algorithm(BPNNGA)for reservoir porosity prediction.This model is with the advantages of self-learning and self-adaption of back propagation neural network(BPNN),structural parameters optimizing and global searching optimal solution of genetic algorithm(GA).The model is applied to the Chang 8 oil group tight sandstone of Yanchang Formation in southwestern Ordos Basin.According to the correlations between well logging data and measured core porosity data,5 well logging curves(gamma ray,deep induction,density,acoustic,and compensated neutron)are selected as the input neurons while the measured core porosity is selected as the output neurons.The number of hidden layer neurons is defined as 20 by the method of multiple calibrating optimizations.Modeling results demonstrate that the average relative error of the model output is 10.77%,indicating the excellent predicting effect of the model.The predicting results of the model are compared with the predicting results of conventional multivariate stepwise regression algorithm,and BPNN model.The average relative errors of the above models are 12.83%,12.9%,and 13.47%,respectively.Results show that the predicting results of the BPNNGA model are more accurate than that of the other two,and BPNNGA is a more applicable method to estimate the reservoir porosity parameters in the study area.展开更多
Controllable D-D neutron sources have a long service life,low cost,and non-radioactivity.There are favorable prospects for its application in geophysical well logging,since traditional chemical radioactive sources use...Controllable D-D neutron sources have a long service life,low cost,and non-radioactivity.There are favorable prospects for its application in geophysical well logging,since traditional chemical radioactive sources used for well logging pose potential threats to the safety of the human body and environment.This paper presents an improved method to measure formation density that employs a D-D neutron source.In addition,the lithological effect on the measured density was removed to better estimate the formation porosity.First,we investigated the spatial distribution of capture gamma rays through Monte Carlo simulations as well as the relationship between the ratio of capture gamma ray counts and formation density to establish theoretical support for the design of density logging tools and their corresponding data processing methods.Second,we obtained the far to near detector counts of captured gamma rays for an optimized tool structure and then established its correlation with the density and porosity of three typical formations with pure quartz,calcite,and dolomite minerals.Third,we determined the values for correcting the densities of sandstone and dolomite with the same porosity using limestone data as the reference and established the equations for calculating the correction values,which lays a solid foundation for accurately calculating formation porosity.We observed that the capture gamma ray counts first increased then decreased and varied in different formations;this was especially observed in high-porosity formations.Under the same lithologic conditions(rock matrix),as the porosity increases,the peak value of gamma ray counts moves toward the neutron source.At different detector-source distances,the ratio of the capture gamma ray counts was well correlated with the formation density.An equation of the formation density conversion was established based on the ratio of capture gamma ray counts at the detector-source distances of 30 cm and 65 cm,and the calculated values were consistent with the true values.After correction,the formation density was highly consistent with the true value of the limestone density,and the mean absolute error was 0.013 g/cm3.The calculated porosity values were very close to the true values,and the mean relative error was 2.33%,highlighting the accuracy of the proposed method.These findings provide a new method for developing D-D neutron source logging tools and their well-log data processing methods.展开更多
In oil and gas exploration,elucidating the complex interdependencies among geological variables is paramount.Our study introduces the application of sophisticated regression analysis method at the forefront,aiming not...In oil and gas exploration,elucidating the complex interdependencies among geological variables is paramount.Our study introduces the application of sophisticated regression analysis method at the forefront,aiming not just at predicting geophysical logging curve values but also innovatively mitigate hydrocarbon depletion observed in geochemical logging.Through a rigorous assessment,we explore the efficacy of eight regression models,bifurcated into linear and nonlinear groups,to accommodate the multifaceted nature of geological datasets.Our linear model suite encompasses the Standard Equation,Ridge Regression,Least Absolute Shrinkage and Selection Operator,and Elastic Net,each presenting distinct advantages.The Standard Equation serves as a foundational benchmark,whereas Ridge Regression implements penalty terms to counteract overfitting,thus bolstering model robustness in the presence of multicollinearity.The Least Absolute Shrinkage and Selection Operator for variable selection functions to streamline models,enhancing their interpretability,while Elastic Net amalgamates the merits of Ridge Regression and Least Absolute Shrinkage and Selection Operator,offering a harmonized solution to model complexity and comprehensibility.On the nonlinear front,Gradient Descent,Kernel Ridge Regression,Support Vector Regression,and Piecewise Function-Fitting methods introduce innovative approaches.Gradient Descent assures computational efficiency in optimizing solutions,Kernel Ridge Regression leverages the kernel trick to navigate nonlinear patterns,and Support Vector Regression is proficient in forecasting extremities,pivotal for exploration risk assessment.The Piecewise Function-Fitting approach,tailored for geological data,facilitates adaptable modeling of variable interrelations,accommodating abrupt data trend shifts.Our analysis identifies Ridge Regression,particularly when augmented by Piecewise Function-Fitting,as superior in recouping hydrocarbon losses,and underscoring its utility in resource quantification refinement.Meanwhile,Kernel Ridge Regression emerges as a noteworthy strategy in ameliorating porosity-logging curve prediction for well A,evidencing its aptness for intricate geological structures.This research attests to the scientific ascendancy and broad-spectrum relevance of these regression techniques over conventional methods while heralding new horizons for their deployment in the oil and gas sector.The insights garnered from these advanced modeling strategies are set to transform geological and engineering practices in hydrocarbon prediction,evaluation,and recovery.展开更多
Pore formation is a significant challenges in the advancement of laser additive manufacturing(LAM)technologies.To address this issue,image data-driven pore detection techniques have become a research focus.However,exi...Pore formation is a significant challenges in the advancement of laser additive manufacturing(LAM)technologies.To address this issue,image data-driven pore detection techniques have become a research focus.However,existing methods are constrained by reliance on a single detection environment(e.g.,consistent brightness)and fixed input image sizes,limiting their predictive accuracy and application scope.This paper introduces an in-novative a pore detection method based on a deep learning model for laser-directed energy deposition(L-DED).The proposed method leverages the deep learning model’s ability to extract feature information from melt pool images captured by a high-speed camera,enabling efficient pore detection under varying brightness conditions and diverse image sizes.The detection results demonstrate that,under varying brightness levels,the proposed model achieves a pore detection accuracy of approximately 93.5% and a root mean square error(RMSE)of 0.42 for local porosity prediction.Additionally,even with changes in input image size,the model maintains robust performance,achieving a detection accuracy of 96% for pore status detection and an RMSE value of 0.09 for local porosity prediction.This study not only addresses the limitations of traditional detection techniques but also broadens the scope of online detection technologies.It highlights the potential of deep learning in complex industrial settings and provides valuable insights for advancing defect detection research in related fields.展开更多
基金the support of Research Program of Fine Exploration and Surrounding Rock Classification Technology for Deep Buried Long Tunnels Driven by Horizontal Directional Drilling and Magnetotelluric Methods Based on Deep Learning under Grant E202408010the Sichuan Science and Technology Program under Grant 2024NSFSC1984 and Grant 2024NSFSC1990。
文摘Porosity is an important attribute for evaluating the petrophysical properties of reservoirs, and has guiding significance for the exploration and development of oil and gas. The seismic inversion is a key method for comprehensively obtaining the porosity. Deep learning methods provide an intelligent approach to suppress the ambiguity of the conventional inversion method. However, under the trace-bytrace inversion strategy, there is a lack of constraints from geological structural information, resulting in poor lateral continuity of prediction results. In addition, the heterogeneity and the sedimentary variability of subsurface media also lead to uncertainty in intelligent prediction. To achieve fine prediction of porosity, we consider the lateral continuity and variability and propose an improved structural modeling deep learning porosity prediction method. First, we combine well data, waveform attributes, and structural information as constraints to model geophysical parameters, constructing a high-quality training dataset with sedimentary facies-controlled significance. Subsequently, we introduce a gated axial attention mechanism to enhance the features of dataset and design a bidirectional closed-loop network system constrained by inversion and forward processes. The constraint coefficient is adaptively adjusted by the petrophysical information contained between the porosity and impedance in the study area. We demonstrate the effectiveness of the adaptive coefficient through numerical experiments.Finally, we compare the performance differences between the proposed method and conventional deep learning methods using data from two study areas. The proposed method achieves better consistency with the logging porosity, demonstrating the superiority of the proposed method.
基金supported by the National Natural Science Foundation of China(No.41002045)。
文摘A reliable and effective model for reservoir physical property prediction is a key to reservoir characterization and management.At present,using well logging data to estimate reservoir physical parameters is an important means for reservoir evaluation.Based on the characteristics of large quantity and complexity of estimating process,we have attempted to design a nonlinear back propagation neural network model optimized by genetic algorithm(BPNNGA)for reservoir porosity prediction.This model is with the advantages of self-learning and self-adaption of back propagation neural network(BPNN),structural parameters optimizing and global searching optimal solution of genetic algorithm(GA).The model is applied to the Chang 8 oil group tight sandstone of Yanchang Formation in southwestern Ordos Basin.According to the correlations between well logging data and measured core porosity data,5 well logging curves(gamma ray,deep induction,density,acoustic,and compensated neutron)are selected as the input neurons while the measured core porosity is selected as the output neurons.The number of hidden layer neurons is defined as 20 by the method of multiple calibrating optimizations.Modeling results demonstrate that the average relative error of the model output is 10.77%,indicating the excellent predicting effect of the model.The predicting results of the model are compared with the predicting results of conventional multivariate stepwise regression algorithm,and BPNN model.The average relative errors of the above models are 12.83%,12.9%,and 13.47%,respectively.Results show that the predicting results of the BPNNGA model are more accurate than that of the other two,and BPNNGA is a more applicable method to estimate the reservoir porosity parameters in the study area.
基金supported by the National Natural Science Foundation of China(Nos.41704113,41674129)Key R&D Projects in Shandong Province(No.2019GSF109047)+1 种基金China Postdoctoral Science Foundation Grant(No.2019M661912)Science and Technology Plan Project of Shandong Education of China(Nos.J18KA190 and J18KA128)。
文摘Controllable D-D neutron sources have a long service life,low cost,and non-radioactivity.There are favorable prospects for its application in geophysical well logging,since traditional chemical radioactive sources used for well logging pose potential threats to the safety of the human body and environment.This paper presents an improved method to measure formation density that employs a D-D neutron source.In addition,the lithological effect on the measured density was removed to better estimate the formation porosity.First,we investigated the spatial distribution of capture gamma rays through Monte Carlo simulations as well as the relationship between the ratio of capture gamma ray counts and formation density to establish theoretical support for the design of density logging tools and their corresponding data processing methods.Second,we obtained the far to near detector counts of captured gamma rays for an optimized tool structure and then established its correlation with the density and porosity of three typical formations with pure quartz,calcite,and dolomite minerals.Third,we determined the values for correcting the densities of sandstone and dolomite with the same porosity using limestone data as the reference and established the equations for calculating the correction values,which lays a solid foundation for accurately calculating formation porosity.We observed that the capture gamma ray counts first increased then decreased and varied in different formations;this was especially observed in high-porosity formations.Under the same lithologic conditions(rock matrix),as the porosity increases,the peak value of gamma ray counts moves toward the neutron source.At different detector-source distances,the ratio of the capture gamma ray counts was well correlated with the formation density.An equation of the formation density conversion was established based on the ratio of capture gamma ray counts at the detector-source distances of 30 cm and 65 cm,and the calculated values were consistent with the true values.After correction,the formation density was highly consistent with the true value of the limestone density,and the mean absolute error was 0.013 g/cm3.The calculated porosity values were very close to the true values,and the mean relative error was 2.33%,highlighting the accuracy of the proposed method.These findings provide a new method for developing D-D neutron source logging tools and their well-log data processing methods.
文摘In oil and gas exploration,elucidating the complex interdependencies among geological variables is paramount.Our study introduces the application of sophisticated regression analysis method at the forefront,aiming not just at predicting geophysical logging curve values but also innovatively mitigate hydrocarbon depletion observed in geochemical logging.Through a rigorous assessment,we explore the efficacy of eight regression models,bifurcated into linear and nonlinear groups,to accommodate the multifaceted nature of geological datasets.Our linear model suite encompasses the Standard Equation,Ridge Regression,Least Absolute Shrinkage and Selection Operator,and Elastic Net,each presenting distinct advantages.The Standard Equation serves as a foundational benchmark,whereas Ridge Regression implements penalty terms to counteract overfitting,thus bolstering model robustness in the presence of multicollinearity.The Least Absolute Shrinkage and Selection Operator for variable selection functions to streamline models,enhancing their interpretability,while Elastic Net amalgamates the merits of Ridge Regression and Least Absolute Shrinkage and Selection Operator,offering a harmonized solution to model complexity and comprehensibility.On the nonlinear front,Gradient Descent,Kernel Ridge Regression,Support Vector Regression,and Piecewise Function-Fitting methods introduce innovative approaches.Gradient Descent assures computational efficiency in optimizing solutions,Kernel Ridge Regression leverages the kernel trick to navigate nonlinear patterns,and Support Vector Regression is proficient in forecasting extremities,pivotal for exploration risk assessment.The Piecewise Function-Fitting approach,tailored for geological data,facilitates adaptable modeling of variable interrelations,accommodating abrupt data trend shifts.Our analysis identifies Ridge Regression,particularly when augmented by Piecewise Function-Fitting,as superior in recouping hydrocarbon losses,and underscoring its utility in resource quantification refinement.Meanwhile,Kernel Ridge Regression emerges as a noteworthy strategy in ameliorating porosity-logging curve prediction for well A,evidencing its aptness for intricate geological structures.This research attests to the scientific ascendancy and broad-spectrum relevance of these regression techniques over conventional methods while heralding new horizons for their deployment in the oil and gas sector.The insights garnered from these advanced modeling strategies are set to transform geological and engineering practices in hydrocarbon prediction,evaluation,and recovery.
基金supported by National Natural Science Foundation of China(Grant No.52475155)National Science Foundation for Hunan Province,China(Grant No.2023JJ30137)+2 种基金Guangdong Basic and Applied Basic Research Foundation(Grant No.2024A1515010684)Guangdong Basic and Applied Basic Research Foundation(Grant No.2023A1515240059)Program sponsored by the Foundation of Yuelushan Center for Industrial Innovation(Grant No.2023YCII0138).
文摘Pore formation is a significant challenges in the advancement of laser additive manufacturing(LAM)technologies.To address this issue,image data-driven pore detection techniques have become a research focus.However,existing methods are constrained by reliance on a single detection environment(e.g.,consistent brightness)and fixed input image sizes,limiting their predictive accuracy and application scope.This paper introduces an in-novative a pore detection method based on a deep learning model for laser-directed energy deposition(L-DED).The proposed method leverages the deep learning model’s ability to extract feature information from melt pool images captured by a high-speed camera,enabling efficient pore detection under varying brightness conditions and diverse image sizes.The detection results demonstrate that,under varying brightness levels,the proposed model achieves a pore detection accuracy of approximately 93.5% and a root mean square error(RMSE)of 0.42 for local porosity prediction.Additionally,even with changes in input image size,the model maintains robust performance,achieving a detection accuracy of 96% for pore status detection and an RMSE value of 0.09 for local porosity prediction.This study not only addresses the limitations of traditional detection techniques but also broadens the scope of online detection technologies.It highlights the potential of deep learning in complex industrial settings and provides valuable insights for advancing defect detection research in related fields.
