In recent years, nuclear magnetic resonance （NMR） has been increasingly used for fluid- typing in well-logging because of the improved generations of NMR logging tools. This paper first discusses the applicable cond...In recent years, nuclear magnetic resonance （NMR） has been increasingly used for fluid- typing in well-logging because of the improved generations of NMR logging tools. This paper first discusses the applicable conditions of two one-dimensional NMR methods： the dual TW method and dual TE method. Then, the two-dimensional （T2, D） and （T2, T1） NMR methods are introduced. These different typing methods for hydrocarbon are compared and analyzed by numerical simulation. The results show that the dual TW method is not suitable for identifying a macroporous water layer. The dual TE method is not suitable for typing gas and irreducible water. （T2, T1） method is more effective in typing a gas layer. In an oil-bearing layer of movable water containing big pores, （T2, T1） method can solve the misinterpretation problem in the dual TWmethod between a water layer with big pores and an oil layer. The （T2, T1） method can distinguish irreducible water from oil of a medium viscosity, and the viscosity range of oil becomes wide in contrast with that of the dual TW method. The （T2, D） method is more effective in typing oil and water layers. In a gas layer, when the SNR is higher than a threshold, the （T2, D） method can resolve the overlapping T2 signals of irreducible water and gas that occurs due to the use of the dual TE method. Twodimensional NMR for fluid-typing is an important development of well logging technology.展开更多
This paper presents an overview of petrophysical research and exploration achievements of low resistivity pay （LRP） zone by well logs in China. It includes geological characteristics and characteristics of well log ...This paper presents an overview of petrophysical research and exploration achievements of low resistivity pay （LRP） zone by well logs in China. It includes geological characteristics and characteristics of well log response of the low resistivity pay zones discovered and evaluated in recent years, as well as the problems in recognizing and evaluating low resistivity pay zones by well logs. The research areas mainly include the Neogene formations in the Bohai Bay Basin, the Triassic formations in the northern Tarim Basin and the Cretaceous formations in the Junggar Basin, The petrophysical research concerning recognition and evaluation of the low resistivity pays, based on their genetic types, is introduced in this paper.展开更多
To promote adaptation of logging evaluation technologies to the development trend of unconventional oil and gas exploration and development era in China,the current situation and challenges of logging evaluation techn...To promote adaptation of logging evaluation technologies to the development trend of unconventional oil and gas exploration and development era in China,the current situation and challenges of logging evaluation technologies in China are analyzed systematically.Based on the concept of that demand drives technology development,and referring to the international leading technologies,development strategy of logging evaluation technology in China has been put forward.(1)Deepen petrophysics study:mobile 2 D NMR laboratory analysis technology for full diameter core should be developed,characteristic charts and evaluation standards of different fluid properties,different pore structures and different core exposure times should be established based on longitudinal and traverse relaxation spectra;in-depth digital rock experiment and mathematical and physical simulation research should be carried out to create innovative logging evaluation methods;acoustic and electrical anisotropy experimental analysis technology should be developed,and corresponding logging evaluation methods be innovated.(2)Strengthen target processing of logging data:precise inversion processing technology and sensitive information extraction technology of 2 D NMR logging should be developed to finely describe the micro-pore distribution in tight reservoir and accurately distinguish movable oil,bound oil,and bound water etc.The processing method of 3 D ultra-distance detection acoustic logging should be researched.(3)Develop special logging interpretation and evaluation methods:first,mathematical model for quantitatively describing the saturation distribution law of unconventional oil and gas near source and in source should be created;second,evaluation methods and standards of shale oil and deep shale gas"sweet-spots"with mobile oil content and gas content as key parameter separately should be researched vigorously;third,calculation methods of pore pressure under two high-pressure genetic mechanisms,under-compaction and hydrocarbon charging,should be improved;fourth,evaluation method of formation fracability considering the reservoir geologic and engineering quality,and optimization method of horizontal well fracturing stage and cluster based on comprehensive evaluation of stress barrier and lithologic barrier should be worked out.展开更多
We propose an integrated method of data-driven and mechanism models for well logging formation evaluation,explicitly focusing on predicting reservoir parameters,such as porosity and water saturation.Accurately interpr...We propose an integrated method of data-driven and mechanism models for well logging formation evaluation,explicitly focusing on predicting reservoir parameters,such as porosity and water saturation.Accurately interpreting these parameters is crucial for effectively exploring and developing oil and gas.However,with the increasing complexity of geological conditions in this industry,there is a growing demand for improved accuracy in reservoir parameter prediction,leading to higher costs associated with manual interpretation.The conventional logging interpretation methods rely on empirical relationships between logging data and reservoir parameters,which suffer from low interpretation efficiency,intense subjectivity,and suitability for ideal conditions.The application of artificial intelligence in the interpretation of logging data provides a new solution to the problems existing in traditional methods.It is expected to improve the accuracy and efficiency of the interpretation.If large and high-quality datasets exist,data-driven models can reveal relationships of arbitrary complexity.Nevertheless,constructing sufficiently large logging datasets with reliable labels remains challenging,making it difficult to apply data-driven models effectively in logging data interpretation.Furthermore,data-driven models often act as“black boxes”without explaining their predictions or ensuring compliance with primary physical constraints.This paper proposes a machine learning method with strong physical constraints by integrating mechanism and data-driven models.Prior knowledge of logging data interpretation is embedded into machine learning regarding network structure,loss function,and optimization algorithm.We employ the Physically Informed Auto-Encoder(PIAE)to predict porosity and water saturation,which can be trained without labeled reservoir parameters using self-supervised learning techniques.This approach effectively achieves automated interpretation and facilitates generalization across diverse datasets.展开更多
The Ordos basin is a stable craton whose late Paleozoic undergoes two sedimentary stages: from the middle- late Carboniferous offshore plain to the Permian continental river and lake delta. Sandstones in delta plain c...The Ordos basin is a stable craton whose late Paleozoic undergoes two sedimentary stages: from the middle- late Carboniferous offshore plain to the Permian continental river and lake delta. Sandstones in delta plain channels, delta-front river mouth bars and tidal channels are well developed. The sandstones are distributed on or between the genetic source rocks, forming good gas source conditions with widespread subtle lithologic gas pools of low porosity, low permeability, low pressure and low abundance. In recent years, a series of experiments has been done, aimed at overcoming difficulties in the exploration of lithologic gas pools. A set of exploration techniques, focusing on geological appraisal, seismic exploration, accurate logging evaluation and interpretation, well testing fracturing, has been developed to guide the exploration into the upper Paleozoic in the basin, leading to the discoveries of four large gas fields: Sulige, Yulin, Wushenqi and Mizhi.展开更多
The wheel-rail force measurement is of great importance to the condition monitoring and safety evaluation of railway vehicles. In this paper, an improved indirect method for wheel-rail force measurement is proposed to...The wheel-rail force measurement is of great importance to the condition monitoring and safety evaluation of railway vehicles. In this paper, an improved indirect method for wheel-rail force measurement is proposed to evaluate the running safety of railway vehicles. In this method, the equilibrium equations of a suspended wheelset are derived and the wheel-rail forces are then be obtained from measured suspension and inertia forces. This indirect method avoids structural modifications to the wheelset and is applicable to the long-term operation of railway vehicles. As the wheel-rail lateral forces at two sides of the wheelset are difficult to separate, a new derailment criterion by combined use of wheelset derailment coefficient and wheel unloading ratio is proposed. To illustrate its effectiveness, the indirect method is applied to safety evaluation of rail- way vehicles in different scenarios, such as the cross wind safety of a high-speed train and the safety of a metro vehicle with hunting motions. Then, the feasibility of using this method to identify wheel-rail forces for low-floor light rail vehicles with resilient wheels is discussed. The values identified by this method is compared with that by Simpack simulation for the same low-floor vehicle, which shows a good coincidence between them in the time domain of the wheelset lateral force and the wheel-rail vertical force. In addition, use of the method to determine the high-frequency wheel-rail interaction forces reveals that it is possible to identify the high-frequency wheel-rail forces through the accelerations on the axle box.展开更多
有机碳含量是评价烃源岩潜力的主要参数,常用的总有机碳含量(TOC)测井反演模型难以深度剖析测井曲线之间的复杂共线性关系,制约了多维测井信息的综合评价效果。利用玛湖凹陷三叠系白碱滩组泥岩的热解实验结果和常规测井曲线资料,建立了...有机碳含量是评价烃源岩潜力的主要参数,常用的总有机碳含量(TOC)测井反演模型难以深度剖析测井曲线之间的复杂共线性关系,制约了多维测井信息的综合评价效果。利用玛湖凹陷三叠系白碱滩组泥岩的热解实验结果和常规测井曲线资料,建立了一种基于PCA-BP(Principal Component Analysis and Back Propagation)神经网络的有机碳含量智能预测方法。该方法以敏感测井曲线的加权平均值和TOC测试结果为原始数据集,首先利用方差膨胀因子检测测井曲线之间共线性,然后采用主成分分析PCA(Principal Component Analysis)技术对原始数据集进行去共线性和降维处理,确定出2个主成分,最后结合中子、自然伽马、密度、声波时差曲线值,建立出6个输入节点的3层BP(Back Propagation)神经网络预测模型,对研究区三叠系白碱滩组烃源岩潜力进行精细评价。3口取心井累积410m井段的预测结果表明,模型的决定系数高达0.879,预测结果平均绝对误差和均方误差分别为0.220和0.107,平均相对误差为16.1%。研究结果为准噶尔盆地勘探领域优选提供了可靠参考。展开更多
基金support from PetroChina Company Limited Innovation Foundation(Grant No.07-06D-01-04-01-07)State Key Laboratory of Petroleum Resource and Prospecting,China University of Petroleum(Beijing)(Grant No.PRPDX2008-02)
文摘In recent years, nuclear magnetic resonance （NMR） has been increasingly used for fluid- typing in well-logging because of the improved generations of NMR logging tools. This paper first discusses the applicable conditions of two one-dimensional NMR methods： the dual TW method and dual TE method. Then, the two-dimensional （T2, D） and （T2, T1） NMR methods are introduced. These different typing methods for hydrocarbon are compared and analyzed by numerical simulation. The results show that the dual TW method is not suitable for identifying a macroporous water layer. The dual TE method is not suitable for typing gas and irreducible water. （T2, T1） method is more effective in typing a gas layer. In an oil-bearing layer of movable water containing big pores, （T2, T1） method can solve the misinterpretation problem in the dual TWmethod between a water layer with big pores and an oil layer. The （T2, T1） method can distinguish irreducible water from oil of a medium viscosity, and the viscosity range of oil becomes wide in contrast with that of the dual TW method. The （T2, D） method is more effective in typing oil and water layers. In a gas layer, when the SNR is higher than a threshold, the （T2, D） method can resolve the overlapping T2 signals of irreducible water and gas that occurs due to the use of the dual TE method. Twodimensional NMR for fluid-typing is an important development of well logging technology.
基金Supported by CNPC Innovation Foundation,Research Projects of PetroChina,Xinjiang and Tarim Oil Companies
文摘This paper presents an overview of petrophysical research and exploration achievements of low resistivity pay （LRP） zone by well logs in China. It includes geological characteristics and characteristics of well log response of the low resistivity pay zones discovered and evaluated in recent years, as well as the problems in recognizing and evaluating low resistivity pay zones by well logs. The research areas mainly include the Neogene formations in the Bohai Bay Basin, the Triassic formations in the northern Tarim Basin and the Cretaceous formations in the Junggar Basin, The petrophysical research concerning recognition and evaluation of the low resistivity pays, based on their genetic types, is introduced in this paper.
文摘To promote adaptation of logging evaluation technologies to the development trend of unconventional oil and gas exploration and development era in China,the current situation and challenges of logging evaluation technologies in China are analyzed systematically.Based on the concept of that demand drives technology development,and referring to the international leading technologies,development strategy of logging evaluation technology in China has been put forward.(1)Deepen petrophysics study:mobile 2 D NMR laboratory analysis technology for full diameter core should be developed,characteristic charts and evaluation standards of different fluid properties,different pore structures and different core exposure times should be established based on longitudinal and traverse relaxation spectra;in-depth digital rock experiment and mathematical and physical simulation research should be carried out to create innovative logging evaluation methods;acoustic and electrical anisotropy experimental analysis technology should be developed,and corresponding logging evaluation methods be innovated.(2)Strengthen target processing of logging data:precise inversion processing technology and sensitive information extraction technology of 2 D NMR logging should be developed to finely describe the micro-pore distribution in tight reservoir and accurately distinguish movable oil,bound oil,and bound water etc.The processing method of 3 D ultra-distance detection acoustic logging should be researched.(3)Develop special logging interpretation and evaluation methods:first,mathematical model for quantitatively describing the saturation distribution law of unconventional oil and gas near source and in source should be created;second,evaluation methods and standards of shale oil and deep shale gas"sweet-spots"with mobile oil content and gas content as key parameter separately should be researched vigorously;third,calculation methods of pore pressure under two high-pressure genetic mechanisms,under-compaction and hydrocarbon charging,should be improved;fourth,evaluation method of formation fracability considering the reservoir geologic and engineering quality,and optimization method of horizontal well fracturing stage and cluster based on comprehensive evaluation of stress barrier and lithologic barrier should be worked out.
文摘We propose an integrated method of data-driven and mechanism models for well logging formation evaluation,explicitly focusing on predicting reservoir parameters,such as porosity and water saturation.Accurately interpreting these parameters is crucial for effectively exploring and developing oil and gas.However,with the increasing complexity of geological conditions in this industry,there is a growing demand for improved accuracy in reservoir parameter prediction,leading to higher costs associated with manual interpretation.The conventional logging interpretation methods rely on empirical relationships between logging data and reservoir parameters,which suffer from low interpretation efficiency,intense subjectivity,and suitability for ideal conditions.The application of artificial intelligence in the interpretation of logging data provides a new solution to the problems existing in traditional methods.It is expected to improve the accuracy and efficiency of the interpretation.If large and high-quality datasets exist,data-driven models can reveal relationships of arbitrary complexity.Nevertheless,constructing sufficiently large logging datasets with reliable labels remains challenging,making it difficult to apply data-driven models effectively in logging data interpretation.Furthermore,data-driven models often act as“black boxes”without explaining their predictions or ensuring compliance with primary physical constraints.This paper proposes a machine learning method with strong physical constraints by integrating mechanism and data-driven models.Prior knowledge of logging data interpretation is embedded into machine learning regarding network structure,loss function,and optimization algorithm.We employ the Physically Informed Auto-Encoder(PIAE)to predict porosity and water saturation,which can be trained without labeled reservoir parameters using self-supervised learning techniques.This approach effectively achieves automated interpretation and facilitates generalization across diverse datasets.
文摘The Ordos basin is a stable craton whose late Paleozoic undergoes two sedimentary stages: from the middle- late Carboniferous offshore plain to the Permian continental river and lake delta. Sandstones in delta plain channels, delta-front river mouth bars and tidal channels are well developed. The sandstones are distributed on or between the genetic source rocks, forming good gas source conditions with widespread subtle lithologic gas pools of low porosity, low permeability, low pressure and low abundance. In recent years, a series of experiments has been done, aimed at overcoming difficulties in the exploration of lithologic gas pools. A set of exploration techniques, focusing on geological appraisal, seismic exploration, accurate logging evaluation and interpretation, well testing fracturing, has been developed to guide the exploration into the upper Paleozoic in the basin, leading to the discoveries of four large gas fields: Sulige, Yulin, Wushenqi and Mizhi.
基金supported by the National Natural Science Foundation of China (Grant No. U1334206 and No. 51475388)Science & Technology Development Project of China Railway Corporation (Grant No. J012-C)
文摘The wheel-rail force measurement is of great importance to the condition monitoring and safety evaluation of railway vehicles. In this paper, an improved indirect method for wheel-rail force measurement is proposed to evaluate the running safety of railway vehicles. In this method, the equilibrium equations of a suspended wheelset are derived and the wheel-rail forces are then be obtained from measured suspension and inertia forces. This indirect method avoids structural modifications to the wheelset and is applicable to the long-term operation of railway vehicles. As the wheel-rail lateral forces at two sides of the wheelset are difficult to separate, a new derailment criterion by combined use of wheelset derailment coefficient and wheel unloading ratio is proposed. To illustrate its effectiveness, the indirect method is applied to safety evaluation of rail- way vehicles in different scenarios, such as the cross wind safety of a high-speed train and the safety of a metro vehicle with hunting motions. Then, the feasibility of using this method to identify wheel-rail forces for low-floor light rail vehicles with resilient wheels is discussed. The values identified by this method is compared with that by Simpack simulation for the same low-floor vehicle, which shows a good coincidence between them in the time domain of the wheelset lateral force and the wheel-rail vertical force. In addition, use of the method to determine the high-frequency wheel-rail interaction forces reveals that it is possible to identify the high-frequency wheel-rail forces through the accelerations on the axle box.
文摘有机碳含量是评价烃源岩潜力的主要参数,常用的总有机碳含量(TOC)测井反演模型难以深度剖析测井曲线之间的复杂共线性关系,制约了多维测井信息的综合评价效果。利用玛湖凹陷三叠系白碱滩组泥岩的热解实验结果和常规测井曲线资料,建立了一种基于PCA-BP(Principal Component Analysis and Back Propagation)神经网络的有机碳含量智能预测方法。该方法以敏感测井曲线的加权平均值和TOC测试结果为原始数据集,首先利用方差膨胀因子检测测井曲线之间共线性,然后采用主成分分析PCA(Principal Component Analysis)技术对原始数据集进行去共线性和降维处理,确定出2个主成分,最后结合中子、自然伽马、密度、声波时差曲线值,建立出6个输入节点的3层BP(Back Propagation)神经网络预测模型,对研究区三叠系白碱滩组烃源岩潜力进行精细评价。3口取心井累积410m井段的预测结果表明,模型的决定系数高达0.879,预测结果平均绝对误差和均方误差分别为0.220和0.107,平均相对误差为16.1%。研究结果为准噶尔盆地勘探领域优选提供了可靠参考。
