Logging data intelligent processing method

Abstract

The invention relates to the technical field of data, and discloses a logging data intelligent processing method. The method comprises the following steps: acquiring data through a multi-source logging device and preprocessing the data to form a result set; identifying and classifying stratum features according to the result set; analyzing oil and gas parameters based on the stratigraphic map and the result set; identifying risks by using the oil-gas evaluation table and the result set and establishing an early warning mechanism; the reservoir physical property is evaluated according to the oil and gas evaluation table and the early warning mechanism; and integrating the stratigraphic map, the oil and gas evaluation table and the reservoir report to reconstruct the geological structure prediction enrichment area. According to the method, full-process intelligent processing from acquisition and preprocessing of multi-source heterogeneous logging data to stratum identification, oil and gas evaluation, drilling risk early warning, reservoir assessment and oil and gas reservoir description is realized, and the problems of data space-time mismatching, parameter isolated analysis, high evaluation subjectivity, early warning lag and the like in a traditional method are solved; and the efficiency, accuracy and systematicness of logging data processing are improved.

Description

Technical Field

[0001] The present application relates to the field of data technology, and in particular to a method for intelligent processing of logging data. Background Art

[0002] In the process of oil and gas resource exploration and development, logging data, as an important information carrier that directly reflects underground geological characteristics and oil and gas status, plays an irreplaceable role in the discovery, evaluation and development of oil and gas reservoirs. Traditional logging data processing methods mainly rely on manual experience and judgment, and simple analysis is performed through basic logging parameters such as drilling fluid gas components, drill cuttings fluorescence, and lithology description to form stratigraphic division and preliminary evaluation of oil and gas layers. With the development of technology, computer-aided processing systems have gradually been introduced into the field of logging, such as gas logging instrument data processing systems and logging comprehensive analysis software. These technical means have improved data processing efficiency and accuracy, and realized the basic digitization and visualization of logging data. In recent years, with the widespread application of multi-parameter logging instruments, logging technology has developed from traditional gas logging to multi-parameter comprehensive logging such as gas logging, drill cuttings fluorescence, gamma, and acoustic waves. The data type and acquisition frequency have increased significantly, providing a data basis for a more comprehensive and accurate evaluation of formations and oil and gas status.

[0003] However, the existing logging data processing technology still has many shortcomings: first, in the face of heterogeneous data generated by multi-source logging equipment, there is a lack of effective timestamp alignment and depth correction methods, resulting in time and space mismatches between data from different sources; second, the ability to handle noise and outliers in the data processing process is limited, and the data quality is unstable; third, formation identification and oil and gas evaluation mainly rely on a single parameter or simple threshold judgment, lack of a multi-parameter comprehensive verification mechanism, and the evaluation results are highly subjective; fourth, the identification of drilling anomalies is delayed, and real-time risk warning cannot be achieved; fifth, the evaluation of reservoir physical parameters mostly relies on empirical formulas, and does not fully consider the differences in regional geological characteristics and reservoir heterogeneity; the description of oil and gas reservoirs lacks systematicity and integrity, and it is difficult to achieve accurate characterization and prediction from single well data to regional oil and gas reservoirs. These problems seriously restrict the full use of the value of logging data and affect the efficiency and success rate of oil and gas resource exploration and development. Summary of the invention

[0004] The present application provides a method for intelligent processing of logging data, which is used to realize the full-process intelligent processing from the collection and preprocessing of multi-source heterogeneous logging data to formation identification, oil and gas evaluation, drilling risk warning, reservoir assessment and oil and gas reservoir description, overcome the problems of data time and space mismatch, isolated parameter analysis, strong evaluation subjectivity, and delayed warning in traditional methods, and improve the efficiency, accuracy and systematicness of logging data processing.

[0005] The present application provides a method for intelligent processing of logging data, which comprises: collecting and preprocessing drilling process data through multi-source logging equipment to form a logging data preprocessing result set; identifying and classifying formation characteristics according to the logging data preprocessing result set to generate a formation stratification classification map; based on the stratum stratification classification map and the logging data preprocessing result set, comprehensively analyzing oil and gas parameters to form an oil and gas layer evaluation result table; using the oil and gas layer evaluation result table and the logging data preprocessing result set, identifying drilling abnormalities and classifying risk levels, and establishing a drilling risk early warning mechanism; based on the oil and gas layer evaluation result table and the drilling risk early warning mechanism, intelligently converting and evaluating reservoir physical property parameters to form a comprehensive reservoir evaluation report; integrating the stratum stratification classification map, the oil and gas layer evaluation result table and the comprehensive reservoir evaluation report to reconstruct geological structures and predict oil and gas enrichment areas, and generate oil and gas reservoir description results.

[0006] In the technical solution provided by the present application, the drilling process data is collected and preprocessed by multi-source logging equipment to form a logging data preprocessing result set, which realizes the time-depth coordination and unification of different logging data sources, solves the time-space mismatch problem in traditional logging data processing, and effectively improves the data quality and reliability of subsequent analysis; according to the logging data preprocessing result set, the formation characteristics are identified and classified, and a formation stratification classification map is generated. The Poisson change point detection algorithm is used to realize the accurate identification of the formation interface, which overcomes the defect of the traditional method of inaccurate identification of formation boundary points; based on the formation stratification classification map and the logging data preprocessing result set, the oil and gas parameters are comprehensively analyzed to form an oil and gas layer evaluation results table, and the normalized oil and gas display index and the auxiliary oil and gas identification feature data are weighted and fused through the multi-parameter interactive verification method, which avoids the one-sidedness of single parameter evaluation and improves the accuracy of oil and gas layer identification; using the oil and gas layer evaluation The results table and logging data preprocessing result set are used to identify drilling anomalies and classify risk levels, establish a drilling risk warning mechanism, and apply machine learning algorithms to the identification of drilling anomaly patterns, which significantly improves the foresight and accuracy of risk warnings, and can provide early warnings and prevent drilling accidents; according to the oil and gas layer evaluation results table and the drilling risk warning mechanism, the reservoir physical property parameters are intelligently converted and evaluated to form a comprehensive reservoir evaluation report, and the regional conversion function is used to calculate the reservoir physical property parameter set. The parameters are corrected in combination with the assessment of the degree of reservoir damage during the drilling process, and an accurate quantitative assessment of the reservoir physical property parameters is achieved; the stratigraphic stratification classification map, oil and gas layer evaluation results table and comprehensive reservoir evaluation report are integrated to reconstruct the geological structure and predict the oil and gas enrichment area, generate oil and gas reservoir description results, and apply the spatial interpolation algorithm to horizontally extend the geological information of a single well, realizing the transition from a one-dimensional wellbore model to a three-dimensional oil and gas reservoir description. The application of artificial intelligence algorithms in this scheme, such as the application of Poisson change point detection algorithm in formation interface identification, the application of multi-parameter interactive verification method in comprehensive analysis of oil and gas parameters, the application of machine learning algorithm in drilling anomaly identification and the application of spatial interpolation algorithm in three-dimensional geological modeling, has enabled the entire logging data processing process to break away from the limitations of traditional empirical judgment and realize the intelligent, automated and precise data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0008] Figure 1 A schematic diagram of an embodiment of the method for intelligently processing mud logging data in an embodiment of the present application; Figure 2 This is a schematic diagram of the process of collecting and preprocessing drilling process data through multi-source logging equipment in an embodiment of the present application. DETAILED DESCRIPTION

[0009] The embodiment of the present application provides a method for intelligent processing of logging data. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0010] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 , an embodiment of the method for intelligent processing of logging data in the embodiment of the present application includes: Step S101, collecting and preprocessing the drilling process data through multi-source logging equipment to form a logging data preprocessing result set; Step S102: Identify and classify formation features according to the logging data preprocessing result set, and generate a formation stratification classification map; Step S103, based on the stratigraphic classification atlas and the logging data preprocessing result set, comprehensively analyze the oil and gas parameters to form an oil and gas layer evaluation result table; Step S104: using the oil and gas layer evaluation results table and the logging data preprocessing result set, identify drilling abnormalities and classify risk levels, and establish a drilling risk early warning mechanism; Step S105: intelligently convert and evaluate reservoir physical property parameters according to the oil and gas layer evaluation results table and the drilling risk early warning mechanism to form a comprehensive reservoir evaluation report; Step S106, integrating the stratigraphic classification atlas, the oil and gas layer evaluation results table and the comprehensive reservoir evaluation report, reconstructing the geological structure and predicting the oil and gas enrichment areas, and generating oil and gas reservoir description results.

[0011] It is understandable that the execution subject of the present application may be a logging data intelligent processing system, or a terminal or a server, which is not limited here. The present application embodiment is described by taking a server as the execution subject as an example.

[0012] Specifically, the drilling process data is collected and preprocessed through multi-source logging equipment to form a logging data preprocessing result set. The specific implementation process is: the original logging parameters are collected through the gas detector, drill cuttings fluorescence detector and gamma ray detector to obtain the drilling fluid gas composition, drill cuttings fluorescence value and natural gamma value data, which constitute the original logging data stream. At the same time, engineering parameters such as drilling pressure, drilling speed, torque and pump pressure are obtained from the drilling engineering monitoring system, and combined with the lithology description data in the geological coring analysis to form an auxiliary logging parameter set. The original logging data stream is timestamped and depth corrected to eliminate the lag effect and depth deviation, and to construct time-depth consistency logging data. In a certain exploratory well example, the methane content data collected by the gas detector has a lag deviation of about 15 meters from the drilling depth. Through timestamp analysis and comparison, the data points are remapped to the correct depth, realizing the time-depth synchronization of the data. Then, the time-depth consistent logging data and auxiliary logging parameter set are resampled using the segmented cubic spline interpolation method to solve the problem of inconsistent sampling frequencies of data from different sources and generate a unified frequency data set. Then, the wavelet transform filtering technology is used to suppress noise and remove abnormal points in the unified frequency data set to improve the data signal-to-noise ratio and form high-quality logging basic data. Wavelet transform filtering technology decomposes the data at multiple scales, identifies and removes high-frequency noise components, and retains valid data information. For missing segments in high-quality logging basic data, the data is repaired and filled through the associated parameter mapping method, and a time-depth dual index system is established to form a logging data preprocessing result set.

[0013] According to the logging data preprocessing result set, the formation characteristics are identified and classified to generate a stratigraphic classification map, wherein: by calculating the coefficient of variation and the first-order derivative of the natural gamma curve in the logging data preprocessing result set, the curve mutation points are identified to form a set of candidate stratigraphic boundary points. The coefficient of variation is the ratio of the standard deviation to the mean value, which can reflect the degree of data fluctuation, and the first-order derivative reflects the curve change rate. Then, combined with the mutation characteristics of the drilling rate curve, the set of candidate stratigraphic boundary points is screened and verified, the preliminary stratigraphic boundary depth points are determined, and the preliminary stratigraphic boundary point set is constructed. Then, the preliminary stratigraphic boundary point set is optimized by the Poisson change point detection algorithm, non-geological boundary points are excluded, and an accurate stratigraphic boundary point set is generated. The Poisson change point detection algorithm identifies abnormal change points in the data sequence through statistical principles, and can effectively distinguish geological and non-geological changes. The gas logging component ratio, drill cuttings fluorescence characteristics and natural gamma values ​​in each stratigraphic section are extracted from the logging data preprocessing result set to construct a stratigraphic feature vector set. Based on the similarity calculation results of the stratigraphic feature vector set and the regional standard stratigraphic data, the geological age of each stratigraphic segment is determined to form a stratigraphic classification result. According to the morphological characteristics of the drill cuttings, mineral composition and gas logging hydrocarbon component ratio, the lithology of each stratigraphic segment in the stratigraphic classification result is subdivided and integrated to form a stratigraphic stratification classification map.

[0014] Based on the stratigraphic classification atlas and the logging data preprocessing result set, the oil and gas parameters are comprehensively analyzed to form an oil and gas layer evaluation results table. The specific implementation process is as follows: the total hydrocarbon value, methane / ethane ratio, abnormal gas component content and cuttings fluorescence intensity parameters are extracted from the logging data preprocessing result set to construct the basic oil and gas display index set. Then, according to the lithology classification results in the stratigraphic classification atlas, different evaluation standard thresholds are selected for the oil and gas display basic index set for standardization to generate a lithology-matched normalized oil and gas display index. The standardization process takes into account the background value differences of different lithologies, such as sandstone and mudstone corresponding to different total hydrocarbon background value thresholds. Then, the drilling speed mutation, drilling pressure change and mud density anomaly information are extracted from the engineering parameters in the logging data preprocessing result set, and combined with the acoustic time difference data to form auxiliary oil and gas identification feature data. The normalized oil and gas display index and the auxiliary oil and gas identification feature data are weighted and fused by the multi-parameter interactive verification method to calculate the comprehensive evaluation index value of the oil and gas layer and establish the comprehensive evaluation index curve of the oil and gas layer. The multi-parameter interactive verification method is a data fusion technology based on mutual verification of parameters, which can improve the recognition accuracy. According to the comprehensive evaluation index curve of the oil and gas layer combined with the lithology and sedimentary environment information in the stratigraphic classification map, the potential oil and gas layer segments are identified and graded to form the preliminary division results of the oil and gas layer. The index integral value and effective thickness of each oil and gas layer segment in the preliminary division results of the oil and gas layer are calculated, and the production capacity potential is predicted in combination with the regional production capacity data to form the oil and gas layer evaluation results table.

[0015] Using the oil and gas layer evaluation results table and the logging data preprocessing result set, the drilling abnormalities are identified and risk levels are divided, and a drilling risk early warning mechanism is established. Specifically: by statistically calculating the gas measurement parameters, drilling engineering parameters and mud performance parameters in the logging data preprocessing result set, the parameter fluctuation range under normal drilling conditions is determined, and a drilling parameter benchmark file is established. The latest drilling parameters are extracted from the logging data preprocessing result set, compared and analyzed with the drilling parameter benchmark file, the parameter deviation value is calculated, and the abnormality index matrix is ​​generated. Then, according to the characteristic patterns of key abnormal types such as well kick, well leakage, pipe sticking and formation pressure mutation, a drilling abnormality feature library is constructed, and the abnormality index matrix is ​​matched and compared with the drilling abnormality feature library to identify the potential drilling risk point location. Combined with the oil and gas layer information in the oil and gas layer evaluation results table, the drilling risk points are correlated and analyzed, the abnormal development trend and severity are evaluated, the drilling risks are graded, and a graded risk signal is formed. By analyzing historical drilling anomaly handling cases, targeted treatment suggestions are generated for graded risk signals, combined with the current drilling environment and oil and gas layer characteristics. The graded risk signals and treatment suggestions are integrated into the drilling decision push system, which automatically triggers the early warning process, accurately pushes early warning information to drilling site engineers, and establishes a drilling risk early warning mechanism.

[0016] According to the oil and gas layer evaluation results table and the drilling risk warning mechanism, the reservoir physical property parameters are intelligently converted and evaluated to form a comprehensive reservoir evaluation report. The specific implementation process is: extract the acoustic time difference, cuttings pore characteristics and gas logging hydrocarbon component ratio data related to the reservoir physical properties from the logging data preprocessing result set, and combine the oil and gas display information in the oil and gas layer evaluation results table to construct a reservoir physical property parameter set. Then, the reservoir physical property parameter set is calculated and processed through the regional conversion function, and the logging physical property indicators are converted into reservoir porosity, permeability and oil and gas saturation values ​​to generate the initial results of quantitative reservoir evaluation. The regional conversion function is a mathematical model established based on regional geological characteristics, which can convert logging parameters into reservoir physical property parameters. Combined with the abnormal identification information in the drilling risk warning mechanism, the degree of damage to the reservoir during the drilling process is evaluated, and the initial results of the quantitative reservoir evaluation are corrected to form a reservoir physical property correction table. According to the oil and gas layer segments and reservoir physical property correction table in the oil and gas layer evaluation results table, the reservoir heterogeneity factors are analyzed, the dominant seepage channels and fluid barrier layer positions are identified, and the reservoir seepage characteristic diagram is constructed. Based on the reservoir seepage characteristic diagram, the vertical continuity and lateral distribution range of the reservoir are calculated and evaluated, the effective reservoir thickness and distribution range are determined, and the reservoir geometry data is generated. The reservoir physical property correction table, reservoir seepage characteristic diagram and reservoir geometry data are integrated to conduct a comprehensive rating of the reservoir quality, and a comprehensive reservoir evaluation report is compiled according to the reservoir depth, thickness, physical properties, heterogeneity characteristics and quality grade.

[0017] The geological structure reconstruction and oil and gas enrichment area prediction are carried out by integrating the stratigraphic classification map, the oil and gas layer evaluation results table and the comprehensive reservoir evaluation report, and the oil and gas reservoir description results are generated. The specific implementation process is as follows: Based on the stratigraphic classification map, the oil and gas layer evaluation results table and the key information of the strata and reservoir in the comprehensive reservoir evaluation report, a one-dimensional geological profile model of the wellbore is constructed to display the vertical distribution characteristics of the strata. Then, according to the one-dimensional geological profile model of the wellbore combined with the regional structural background data, the single well geological information is horizontally extended through the spatial interpolation algorithm to form a three-dimensional geological skeleton. The spatial interpolation algorithm generates a continuous spatial distribution data field by spatially analyzing and predicting the known point data. The reservoir structure in the three-dimensional geological skeleton is finely characterized by using the reservoir physical property distribution and heterogeneity characteristic data in the comprehensive reservoir evaluation report to generate a reservoir fine structure map. By analyzing the oil and gas display information and pressure data in the oil and gas layer evaluation results table, the oil and gas-water interface position is determined, the fluid distribution boundary is calibrated in the reservoir fine structure map, and the fluid distribution map is established. Based on the reservoir physical properties and connectivity data in the oil and gas layer evaluation results table and the comprehensive reservoir evaluation report, the oil and gas migration channels and enrichment areas are predicted and calculated to generate an oil and gas enrichment distribution map. The three-dimensional geological skeleton, reservoir fine structure map, fluid distribution map and oil and gas enrichment distribution map are integrated to comprehensively evaluate the resource potential and production capacity expectations of the target area to form oil and gas reservoir description results.

[0018] In the embodiment of the present application, the drilling process data is collected and preprocessed by multi-source logging equipment to form a logging data preprocessing result set, which realizes the time-depth coordination and unification of different logging data sources, solves the time-space mismatch problem in traditional logging data processing, and effectively improves the data quality and reliability of subsequent analysis; according to the logging data preprocessing result set, the formation characteristics are identified and classified, and a formation stratification classification map is generated. The Poisson change point detection algorithm is applied to realize the accurate identification of the formation interface, which overcomes the defect of the traditional method of inaccurate identification of formation boundary points; based on the formation stratification classification map and the logging data preprocessing result set, the oil and gas parameters are comprehensively analyzed to form an oil and gas layer evaluation result table, and the normalized oil and gas display index and the auxiliary oil and gas identification feature data are weighted and fused through the multi-parameter interactive verification method, which avoids the one-sidedness of single parameter evaluation and improves the accuracy of oil and gas layer identification; the oil and gas layer evaluation result table and the logging data preprocessing result are used to analyze the oil and gas layer evaluation result table. The results are collected to identify drilling anomalies and classify their risk levels, a drilling risk warning mechanism is established, and machine learning algorithms are applied to the recognition of drilling anomaly patterns, which significantly improves the foresight and accuracy of risk warnings, and can provide early warnings and prevent drilling accidents; according to the oil and gas layer evaluation results table and the drilling risk warning mechanism, the reservoir physical property parameters are intelligently converted and evaluated to form a comprehensive reservoir evaluation report, and the reservoir physical property parameter set is calculated and processed using the regional conversion function. The parameters are corrected in combination with the assessment of the degree of reservoir damage during the drilling process, and an accurate quantitative assessment of the reservoir physical property parameters is achieved; the stratigraphic stratification classification map, the oil and gas layer evaluation results table, and the comprehensive reservoir evaluation report are integrated to reconstruct the geological structure and predict the oil and gas enrichment area, generate oil and gas reservoir description results, and apply the spatial interpolation algorithm to horizontally extend the geological information of a single well, realizing the transition from a one-dimensional wellbore model to a three-dimensional oil and gas reservoir description, providing a systematic technical basis for oil and gas resource development decision-making. The application of artificial intelligence algorithms in this scheme, such as the application of Poisson change point detection algorithm in formation interface identification, the application of multi-parameter interactive verification method in comprehensive analysis of oil and gas parameters, the application of machine learning algorithm in drilling anomaly identification and the application of spatial interpolation algorithm in three-dimensional geological modeling, has enabled the entire logging data processing process to break away from the limitations of traditional empirical judgment and realize the intelligent, automated and precise data processing.

[0019] In a specific embodiment, the process of executing step S101 may specifically include the following steps: The original logging parameters are collected through gas detectors, drill cuttings fluorescence detectors and gamma ray detectors to obtain the gas composition of drilling fluid, drill cuttings fluorescence value and natural gamma value, and generate the original logging data stream; the drilling pressure, drilling speed, torque and pump pressure parameters are obtained from the drilling engineering monitoring system, and combined with the lithology description data in the geological core analysis to form an auxiliary logging parameter set; the original logging data stream is timestamp aligned and depth corrected to eliminate the lag effect and depth deviation, and construct time-depth consistent logging data; the time-depth consistent logging data and auxiliary logging parameter set are resampled by the segmented cubic spline interpolation method to solve the problem of inconsistent sampling frequencies of data from different sources and generate a unified frequency data set; the unified frequency data set is noise suppressed and abnormal points are eliminated by wavelet transform filtering technology to improve the data signal-to-noise ratio and form high-quality logging basic data; for the missing segments in the high-quality logging basic data, the data is repaired and filled by the associated parameter mapping method, and a time-depth dual index system is established to form a logging data preprocessing result set.

[0020] Specifically, Figure 2 As shown, it is a schematic diagram of the process of collecting and preprocessing drilling process data through multi-source logging equipment in the embodiment of the present application, and the equipment is deployed at the drilling site. The gas detector is mainly installed near the vibrating screen, and is used to continuously monitor and collect the content data of hydrocarbon gas components such as methane, ethane, propane, etc. in the drilling fluid. The sampling frequency is usually once every 30 seconds; the cuttings fluorescence detector is set at the outlet of the vibrating screen, and the cuttings samples returned from the bottom of the well are irradiated with ultraviolet light to measure the fluorescence intensity value. The fluorescence intensity reflects the content of hydrocarbon substances in the rock. The sampling frequency is once every 5 minutes; the gamma ray detector obtains natural gamma value data by detecting the natural radioactivity of the formation, and the sampling frequency is once every 1 minute. The data collected by these devices are integrated through the on-site acquisition terminal to form the original logging data stream. Each data point in the data stream contains three key information elements: parameter value, acquisition timestamp and preliminary estimated depth. At the same time, the process of obtaining drilling pressure, drilling speed, torque and pump pressure parameters from the drilling engineering monitoring system is to obtain the drilling rig operation parameters in real time through the drilling parameter acquisition system. The drilling pressure indicates the axial pressure on the drill bit, in kN; the drilling speed indicates the drilling rate of the drill bit, in m / h; the torque indicates the torque required for the drill string to rotate, in kN·m; the pump pressure indicates the outlet pressure of the drilling fluid circulation pump, in MPa. The sampling frequency of these engineering parameters is usually once every 5 seconds, which is significantly higher than the sampling frequency of geological parameters. Then, combined with the lithology description data in the geological core analysis, including rock type, color, structure, mineral composition and other information, these engineering parameters and lithology data are integrated to form an auxiliary logging parameter set to provide support information for subsequent analysis.

[0021] Since it takes a certain amount of time for gas samples to return to the ground from the bottom of the well, there is an obvious time lag effect in the gas logging data, and the lag time is related to the well depth and the drilling fluid circulation speed. The depth correction process establishes a time-depth mapping relationship, and obtains the lag time correction value by calculating the relationship between the drilling fluid circulation time and the well depth. Then, each gas logging data point is compensated for the lag time, associated with the correct well depth, and the depth deviation is eliminated to construct time-depth consistent logging data. For example, when the well depth is 2,500 meters and the drilling fluid return speed is 20 meters / minute, the calculated lag time is 125 minutes, which means that the gas components detected by the ground gas logger actually come from the formation position where the drill bit was located 125 minutes ago.

[0022] The time-depth consistent logging data and auxiliary logging parameter set are resampled by the piecewise cubic spline interpolation method to solve the problem of inconsistent sampling frequency of data from different sources. The piecewise cubic spline interpolation method is a method to construct a smooth curve between data points. It uses cubic polynomials to interpolate between adjacent data points and ensures that the curve and its first-order and second-order derivatives are continuous at the data points. The specific operation is to divide all parameters into several intervals according to depth, construct a cubic spline function in each interval, and then resample at a unified depth interval (usually 0.1 meters or 0.25 meters), unify data from different sources and different sampling frequencies to the same depth point, and generate a unified frequency data set. The process of using wavelet transform filtering technology to suppress noise and remove outliers in a unified frequency data set involves frequency domain analysis and processing of data. Wavelet transform filtering decomposes time series data into different frequency components, separates the trend, periodic changes and noise components in the data, and then retains the low-frequency and medium-frequency components (containing the main geological information) and removes the high-frequency components (mainly noise). The specific processing steps include: selecting appropriate wavelet basis functions (such as Daubechies wavelet), multi-scale decomposition of data sequences, setting thresholds to process high-frequency coefficients, and reconstructing signals to obtain noise-reduced data. Outlier removal uses statistical analysis to identify data points that exceed a reasonable range, such as using the 3-times standard deviation criterion (data points that deviate from the mean by more than 3 times the standard deviation are considered outliers) to mark and replace them with reasonable values, thereby improving the data signal-to-noise ratio and forming high-quality logging basic data.

[0023] For the missing segments in high-quality logging basic data, data repair and filling through the association parameter mapping method is an important means to solve the problem of incomplete data. The association parameter mapping method is based on the principle of correlation between parameters and estimates the missing values ​​by establishing a mapping relationship between parameters. The correlation coefficient matrix between parameters is calculated to identify other parameters that are highly correlated with the missing parameters. Then, a regression model is established to describe the relationship between parameters, and the missing parameter values ​​are estimated using known parameter values. For example, when the acoustic time difference data is missing, the density data that is highly correlated with it can be used for estimation to achieve data repair and filling. A time-depth dual index system is established to simultaneously associate each data point with the corresponding acquisition time and well depth information to form a complete logging data preprocessing result set, providing a reliable data basis for subsequent analysis.

[0024] In a specific embodiment, the process of executing step S102 may specifically include the following steps: By calculating the coefficient of variation and the first-order derivative of the natural gamma curve in the logging data preprocessing result set, the curve mutation points are identified to form a set of candidate stratigraphic boundary points; combined with the mutation characteristics of the drilling rate curve, the set of candidate stratigraphic boundary points is screened and verified, the preliminary stratigraphic boundary depth points are determined, and a preliminary stratigraphic boundary point set is constructed; the preliminary stratigraphic boundary point set is optimized by the Poisson change point detection algorithm, non-geological boundary points are excluded, and an accurate stratigraphic boundary point set is generated; the gas logging component ratios, drill cuttings fluorescence characteristics and natural gamma values ​​in each stratigraphic segment are extracted from the logging data preprocessing result set to construct a stratigraphic feature vector set; based on the similarity calculation results between the stratigraphic feature vector set and the regional standard stratigraphic data, the geological age of each stratigraphic segment is determined to form a stratigraphic classification result; according to the drill cuttings morphological characteristics, mineral composition and gas logging hydrocarbon component ratio, the stratigraphic segments in the stratigraphic classification results are lithologically subdivided, and integrated to form a stratigraphic stratification classification map.

[0025] Specifically, the original logging parameters are collected through gas detectors, drill cuttings fluorescence detectors and gamma ray detectors. The gas detector is installed near the vibrating screen to continuously collect data on the content of hydrocarbon gas components such as methane, ethane, and propane in the drilling fluid, with a sampling frequency of once every 30 seconds; the drill cuttings fluorescence detector is located at the outlet of the vibrating screen, and measures and records the fluorescence intensity value by irradiating the returned rock cuttings samples with ultraviolet light, with a sampling frequency of once every 5 minutes; the gamma ray detector obtains the natural gamma value by measuring the natural radioactivity of the formation, with a sampling frequency of once every 1 minute. The data collected by these three devices are integrated through the data acquisition terminal to form an original logging data stream containing parameter values, acquisition timestamps and preliminary depth estimates.

[0026] At the same time, engineering parameters such as drilling pressure, drilling speed, torque and pump pressure are obtained from the drilling engineering monitoring system. The drilling pressure refers to the axial pressure on the drill bit (kN), the drilling speed refers to the drilling rate of the drill bit (m / h), the torque refers to the torque required for the rotation of the drill string (kN·m), and the pump pressure refers to the outlet pressure of the drilling fluid circulation pump (MPa). The sampling frequency of these parameters is as high as once every 5 seconds. Then, combined with the lithological description data in the geological coring analysis, such as rock type, color, structure and mineral composition, the engineering parameters and lithological data are integrated to form an auxiliary logging parameter set. Since it takes time for the drilling fluid to carry gas and cuttings from the bottom of the well back to the ground, there is a time lag between the gas logging data and the cuttings data relative to the actual drilling depth. By calculating the relationship between the drilling fluid circulation time and the well depth, a time-depth mapping model is established, and time compensation and depth correction are performed on each data point. The data collected on the ground are accurately matched to its true source depth, and time-depth consistent logging data is constructed. For example, at a well depth of 2,500 meters, if the drilling fluid return rate is 20 meters per minute, the lag time is about 125 minutes, which means that the gas data collected on the ground actually reflects the formation characteristics of the drill bit's location 125 minutes ago.

[0027] The time-depth consistent logging data and auxiliary logging parameter set are resampled by the piecewise cubic spline interpolation method to solve the problem of inconsistent sampling frequency of data from different sources. The piecewise cubic spline interpolation method is a mathematical interpolation method that uses cubic polynomials to construct a smooth curve between adjacent data points to ensure that the curve and its first-order and second-order derivatives are continuous at the data points. Specifically, the different parameter data are divided into several intervals according to depth, and a cubic spline function is established in each interval. Then, all parameters are resampled according to a uniform depth interval (usually 0.1 meters or 0.25 meters), and the sampling points of different data sources are unified to the same depth sequence to generate a uniform frequency data set. Wavelet transform filtering technology is used to suppress noise and remove outliers in the uniform frequency data set. Wavelet transform filtering is a signal processing technology that can decompose time series data into components of different frequencies and distinguish trends, periodic changes, and noise parts in the signal. In practical applications, wavelet basis functions suitable for geological data characteristics (such as Daubechies wavelet) are selected to decompose the data at multiple scales, set thresholds to process high-frequency coefficients (mainly containing noise), retain low-frequency and medium-frequency components (containing main geological information), and obtain noise-reduced data by inverse transformation and signal reconstruction. Statistical methods are used to eliminate abnormal points, such as marking points that deviate from the data mean by more than three times the standard deviation as abnormal points and replacing them with reasonable values, thereby improving the data signal-to-noise ratio and forming high-quality logging basic data.

[0028] For the missing segments in the high-quality logging basic data, the data is repaired and filled by the associated parameter mapping method. The associated parameter mapping method is based on the correlation principle between parameters, calculates the correlation coefficient matrix between the parameters, identifies other parameters that are highly correlated with the missing parameters, and then establishes a regression model to describe the quantitative relationship between the parameters, and estimates the missing parameter values ​​using known parameters. A time-depth dual index system is established to simultaneously associate each data point with the corresponding acquisition time and well depth information to form a complete logging data preprocessing result set.

[0029] In the process of identifying the curve mutation point by calculating the coefficient of variation and the first-order derivative of the natural gamma curve in the logging data preprocessing result set, the following formula is involved:

[0030] in, represents the coefficient of variation of the natural gamma curve, represents the standard deviation of the natural gamma value, It indicates the average value of natural gamma. The coefficient of variation can reflect the relative fluctuation of data and help to identify the variation characteristics between different strata.

[0031]

[0032] in, represents the first derivative of the natural gamma curve, Indicates depth The gamma value at represents the gamma value at depth h+Δh, Indicates depth interval. The first-order derivative reflects the rate of change of the gamma value. When the derivative value becomes significantly larger, it indicates that there may be a stratum interface.

[0033] In the process of determining the geological age attribution of each stratigraphic section based on the similarity calculation results between the stratigraphic feature vector set and the regional standard stratigraphic data, the following similarity calculation formula is used:

[0034] in, represents the characteristic vector of the i-th stratigraphic segment and the standard stratigraphic characteristic vector of the jth region The cosine similarity of represents the dot product of two vectors, and Represents the Euclidean norm of two vectors. The cosine similarity ranges from -1 to 1. The closer the value is to 1, the more similar the two formation characteristics are.

[0035]

[0036] in, represents the characteristic vector of the i-th stratigraphic segment and the standard stratigraphic characteristic vector of the jth region The Euclidean distance of Represents the feature vector The kth component value of Represents the feature vector The kth component value of n represents the dimension of the feature vector. The smaller the Euclidean distance, the more similar the two formation characteristics are.

[0037] Morphological characteristics information is extracted from drill cuttings samples collected at the logging site. The morphological characteristics of drill cuttings refer to the appearance, size, shape and surface structure of the cuttings, which are obtained by naked eye observation and microscopic analysis. Morphological characteristics include particle size (coarse sand, fine sand, silt, etc.), particle shape (angular, sub-angular, sub-round, round, etc.), surface structure (smooth, rough, porous, etc.) and color (gray, brown, black, etc.). These morphological characteristics directly reflect the basic genetic type and sedimentary environment characteristics of the rock. The mineral composition of the drill cuttings is analyzed, and the main mineral composition of the rocks in each stratigraphic section is determined by methods such as rock cutting thin section identification, X-ray diffraction analysis or mineral fluorescence feature identification. Mineral composition analysis includes the content and distribution characteristics of the main rock-forming minerals (such as quartz, feldspar, clay minerals, carbonate minerals, etc.), as well as the types and contents of accessory minerals (such as mica, heavy minerals, etc.). Different lithology types have characteristic mineral combinations, such as sandstone is mainly composed of quartz and feldspar, mudstone is rich in clay minerals, and limestone is mainly composed of calcite. At the same time, a comprehensive analysis is conducted in combination with the gas logging hydrocarbon component ratio data. The gas logging hydrocarbon component ratio refers to the ratio of the content of hydrocarbon gases with different carbon numbers, such as methane, ethane, and propane. These ratios are closely related to the lithology and organic matter characteristics. Commonly used ratios include methane / ethane ratio, methane / total hydrocarbon ratio, and wet gas ratio. These ratios show certain regular differences in different lithology types and can be used as auxiliary criteria for lithology subdivision. Based on the above three types of data, multi-feature comprehensive identification is used to subdivide the lithology of each stratigraphic section. A regional lithology feature standard library is established, which contains typical feature combinations of morphological characteristics, mineral composition, and gas logging ratios of different lithology types; then the drill cuttings features obtained during the actual drilling process are pattern matched with the standard library to identify the most similar lithology type; for situations where multiple features are crossed or inconsistent, a weighted decision algorithm is used to assign weights according to the reliability and indicative significance of each feature, and comprehensively judge the lithology attribution. Through this multi-feature comprehensive identification method, the preliminary stratigraphic classification results are subdivided into more detailed lithological units, such as the rough "sandstone section" is subdivided into "quartz sandstone", "feldspar sandstone", "lithic sandstone", etc.; the "carbonate rock section" is subdivided into "limestone", "dolomite", "marlstone", etc. This subdivision not only takes into account the rock type, but also includes characteristic information such as sedimentary structure and genetic type. The lithological subdivision results are integrated with the previous stratigraphic boundary point set and geological age attribution information to form a complete stratigraphic stratification classification map. The map uses depth as the vertical axis, and simultaneously displays the stratigraphic boundary depth, geological age, lithology type and lithology change characteristics, intuitively showing the vertical distribution and change law of the wellbore through the stratum, providing a basic geological framework for subsequent oil and gas evaluation, reservoir analysis and geological structure reconstruction.

[0038] In a specific embodiment, the process of executing step S103 may specifically include the following steps: The total hydrocarbon value, methane / ethane ratio, abnormal gas component content and cuttings fluorescence intensity parameters were extracted from the logging data preprocessing result set to construct the basic oil and gas display index set; according to the lithology classification results in the stratigraphic stratification classification atlas, different evaluation standard thresholds were selected for the basic oil and gas display index set for standardization processing to generate the lithology matching normalized oil and gas display index; the drilling speed mutation, drilling pressure change and mud density abnormality information were extracted from the engineering parameters in the logging data preprocessing result set, and the auxiliary oil and gas identification feature data were combined with the acoustic wave time difference data to form the auxiliary oil and gas identification feature data; the normalized oil and gas display index and the auxiliary oil and gas identification feature data were weighted and fused by the multi-parameter interactive verification method to calculate the comprehensive evaluation index value of the oil and gas layer and establish the comprehensive evaluation index curve of the oil and gas layer; according to the comprehensive evaluation index curve of the oil and gas layer combined with the lithology and sedimentary environment information in the stratigraphic stratification classification atlas, the potential oil and gas layer segments were identified and graded to form the preliminary division results of the oil and gas layer; the index integral value and effective thickness of each oil and gas layer segment in the preliminary division results of the oil and gas layer were calculated, and the production capacity potential was predicted in combination with the regional production capacity data to form the oil and gas layer evaluation results table.

[0039] Specifically, the total hydrocarbon value, methane / ethane ratio, abnormal gas component content and drill cuttings fluorescence intensity parameters are extracted from the logging data preprocessing result set to construct the basic indicator set for oil and gas display. The total hydrocarbon value refers to the sum of the contents of all hydrocarbons detected by the gas detector, in parts per million (ppm); the methane / ethane ratio is the ratio of the methane content to the ethane content, a dimensionless number that reflects the maturity and source of hydrocarbon gases; the abnormal gas component content refers to the content of non-hydrocarbon gases such as hydrogen, carbon dioxide, hydrogen sulfide, etc., in the same unit of ppm; the drill cuttings fluorescence intensity parameter refers to the fluorescence intensity value generated by the drill cuttings under ultraviolet light, in relative fluorescence units (RFU). These parameters are directly extracted from the corresponding data columns in the logging data preprocessing result set, and are integrated according to the depth sequence to form the basic indicator set for oil and gas display.

[0040] According to the lithology classification results in the stratigraphic classification atlas, different evaluation standard thresholds are selected for the oil and gas display basic indicator set for standardization processing to generate a normalized oil and gas display index for lithology matching. Since the background values ​​of different lithologies (such as sandstone, mudstone, carbonate rock, etc.) are very different, differentiated evaluation standards must be set for different lithologies. The standardization process adopts the interval mapping method to set specific background values ​​and abnormal value thresholds for each lithology type, map the original parameter values ​​to the 0-1 interval, and generate a dimensionless normalized oil and gas display index. For example, the total hydrocarbon background value in sandstone is 500ppm and the abnormal value is 5000ppm, while the total hydrocarbon background value in mudstone is 800ppm and the abnormal value is 8000ppm. The original total hydrocarbon value is converted into a normalized index value between 0-1 through linear mapping. The drilling speed mutation, drilling pressure change and mud density abnormality information are extracted from the engineering parameters in the logging data preprocessing result set, and combined with the acoustic time difference data to form auxiliary oil and gas identification feature data. Drilling rate mutation refers to the significant change of drilling rate in a short distance, with the unit of (m / h) / m; drilling pressure change refers to the fluctuation amplitude of drilling pressure in stable drilling, with the unit of kN / m; mud density abnormal information refers to the percentage change of mud density relative to the baseline value; acoustic wave time difference data refers to the propagation time of sound waves through the rock formation, with the unit of microseconds / foot. These parameters can reflect the reservoir physical characteristics and fluid properties from the side, and provide auxiliary basis for oil and gas layer identification.

[0041] Through the multi-parameter interactive validation method, the normalized oil and gas display index and the auxiliary oil and gas identification feature data are weighted and fused to calculate the comprehensive evaluation index value of the oil and gas layer, and the comprehensive evaluation index curve of the oil and gas layer is established. The multi-parameter interactive validation method is a data fusion technology based on mutual validation between parameters. It improves the recognition accuracy by examining the coordinated change characteristics of multiple parameters. The implementation process calculates the correlation matrix between the parameters, determines the mutual support relationship between the parameters, and then sets the initial weight according to the reliability and sensitivity of the parameters. Then, the weight is dynamically adjusted by cross-validation, so that the comprehensive evaluation index after multi-parameter fusion can reflect the characteristics of the oil and gas layer to the maximum extent. Finally, the parameters are weighted and summed according to the determined weights to obtain the comprehensive evaluation index value reflecting the oil and gas potential of each depth point, and a continuous comprehensive evaluation index curve of the oil and gas layer is constructed.

[0042] According to the comprehensive evaluation index curve of the oil and gas layer combined with the lithology and sedimentary environment information in the stratigraphic classification atlas, the potential oil and gas layer segments are identified and graded to form the preliminary oil and gas layer division results. Set the threshold of the comprehensive evaluation index, and mark the continuous sections exceeding the threshold as potential oil and gas layers; then combine the lithology conditions (such as porous sandstone, carbonate reservoir, etc.) and sedimentary environment characteristics (such as delta front, shallow sea shelf, etc.) to screen and exclude high-index sections that do not have reservoir conditions; according to the comprehensive evaluation index, the identified oil and gas layer segments are divided into four grades: excellent, good, medium, and poor, to form the preliminary oil and gas layer division results. Calculate the index integral value and effective thickness of each oil and gas layer segment in the preliminary oil and gas layer division results, combine the regional production capacity data to predict the production capacity potential, and form an oil and gas layer evaluation results table. The index integral value is a comprehensive indicator to measure the quality of oil and gas layers, and characterizes the intensity and scale of the enrichment of oil and gas layers. The calculation formula is as follows:

[0043] in, Indicates the index integral value of the oil and gas layer segment, and Represent the top and bottom depths of the oil and gas layer, represents the weight coefficient at depth z, which is related to lithology and porosity. Represents the comprehensive evaluation index value at depth z, It represents the physical property adjustment coefficient at depth z, which is related to permeability and saturation. dz represents the depth integral differential element.

[0044] The calculation of the effective thickness of the oil and gas layer takes into account the limitation of the index threshold, and the formula is as follows:

[0045] in, represents the effective thickness of the oil and gas layer, represents the thickness of the kth depth segment, is a step function, when Greater than threshold The value is 1 when , otherwise it is 0. is the effectiveness coefficient related to porosity, is the flow capacity coefficient related to water saturation, and N represents the total number of depth segments in the oil and gas layer. Then, the productivity database of developed oil and gas wells in the region is collected and sorted, including production data such as daily oil production, daily gas production, water content, etc. of each well, as well as corresponding reservoir characteristic parameters, such as effective thickness, average porosity, average permeability, oil and gas saturation, etc. These data are derived from the test data, production history records and reservoir evaluation results of existing wells in the region, forming a basic data set containing the corresponding relationship between productivity and reservoir characteristics. The data are statistically analyzed and processed to identify the correlation between productivity and various reservoir parameters. Through correlation analysis, the key parameters that have the most significant impact on productivity are determined, such as effective thickness, permeability and oil and gas saturation are usually positively correlated with productivity, while water saturation is negatively correlated with productivity. Then, statistical or machine learning methods such as multivariate regression analysis and neural networks are used to construct a productivity prediction model, which can predict the potential productivity level based on reservoir characteristic parameters. Subsequently, the characteristic parameters of each oil and gas layer segment in the preliminary oil and gas layer division results of the target well are input into the capacity prediction model to calculate the expected daily oil production, daily gas production and other capacity indicators of each oil and gas layer segment. In the prediction process, key factors such as the comprehensive evaluation index of the oil and gas layer, effective thickness, and formation pressure are considered, and calibration is performed in combination with the regional capacity distribution law to ensure the rationality and reliability of the prediction results. Uncertainty analysis is performed on the prediction results to evaluate the credible interval and risk level of the predicted value. Usually, probability statistics methods are used to calculate the capacity prediction range under different confidence levels, such as P10 (optimistic prediction), P50 (median prediction) and P90 (conservative prediction) values, so as to fully reflect the uncertainty characteristics of capacity prediction. The preliminary oil and gas layer division results are integrated with the capacity potential prediction results to compile an oil and gas layer evaluation results table. The results table includes information such as the depth range, thickness, lithology characteristics, oil and gas display intensity, comprehensive evaluation index, quality grade, predicted capacity parameters and credible interval, and development suggestions of the oil and gas layer.

[0046] =In a specific embodiment, the process of executing step S104 may specifically include the following steps: By statistically calculating the gas logging parameters, drilling engineering parameters and mud performance parameters in the logging data preprocessing result set, the parameter fluctuation range under normal drilling conditions is determined, and a drilling parameter benchmark file is established; the latest drilling parameters are extracted from the logging data preprocessing result set, compared and analyzed with the drilling parameter benchmark file, the parameter deviation value is calculated, and the abnormality index matrix is ​​generated; according to the characteristic patterns of key abnormal types such as well kick, well leakage, pipe sticking and formation pressure mutation, a drilling abnormality feature library is constructed, and the abnormality index matrix is ​​matched and compared with the drilling abnormality feature library to identify the location of potential drilling risk points; combined with the oil and gas layer information in the oil and gas layer evaluation result table, the drilling risk points are correlated and analyzed, the abnormal development trend and severity are evaluated, the drilling risks are graded, and a graded risk signal is formed; by analyzing historical drilling abnormality processing cases, targeted processing suggestions are generated for the graded risk signals in combination with the current drilling environment and oil and gas layer characteristics; the graded risk signals and processing suggestions are integrated into the drilling decision push system, the early warning process is automatically triggered, the early warning information is accurately pushed to the drilling site engineers, and a drilling risk early warning mechanism is established.

[0047] Specifically, by statistically calculating the gas measurement parameters, drilling engineering parameters and mud performance parameters in the logging data preprocessing result set, the parameter fluctuation range under normal drilling conditions is determined, and a drilling parameter benchmark file is established. Gas measurement parameters include the content and ratio of hydrocarbon gases such as methane, ethane, and propane; drilling engineering parameters include physical quantities such as drilling speed, drilling pressure, torque, and rotation speed that reflect the drilling state; mud performance parameters include mud density, viscosity, shear force, water loss, and other indicators that reflect the state of the circulation system. Statistical analysis is performed on the data of these parameters in the historical stable drilling stage, and the statistical quantities such as the mean value, standard deviation, and coefficient of variation of each parameter are calculated to determine the normal fluctuation range of each parameter, forming a drilling parameter benchmark file as a reference for abnormal identification. The latest drilling parameters are extracted from the logging data preprocessing result set, compared and analyzed with the drilling parameter benchmark file, and the parameter deviation value is calculated to generate an abnormality index matrix. Specifically, the real-time parameters of the current drilling status are extracted in a sliding time window (usually 10-30 minutes), and these parameters are compared with the normal range of the corresponding parameters in the benchmark file to calculate the deviation value of each parameter. The deviation value is usually calculated using a standardized method, that is, (measured value-benchmark value) / standard deviation, which indicates the degree to which the current parameter deviates from the normal range. The deviation values ​​of all parameters are organized into a matrix form, with each row representing a time point and each column representing a parameter, to form an abnormality index matrix, which intuitively reflects the change trend and abnormal state of each parameter over time.

[0048] According to the characteristic patterns of key abnormal types such as kick, lost circulation, stuck pipe and sudden change of formation pressure, a drilling abnormality feature library is constructed, and the abnormality index matrix is ​​matched and compared with the drilling abnormality feature library to identify the potential drilling risk point location. Kick refers to the uncontrolled entry of formation fluid into the wellbore, which is usually manifested by increased mud volume, decreased mud density, and increased total hydrocarbon value of gas measurement; lost circulation refers to the entry of drilling fluid into the formation, which is characterized by reduced mud return and decreased pump pressure; stuck pipe refers to the obstruction of the drill string underground, which is manifested by increased torque, fluctuation of drilling pressure, and reduced drilling speed; sudden change of formation pressure is manifested by changes in drilling speed, sudden increase of gas content and abnormal drilling pressure. For these typical abnormal types, their characteristic patterns are extracted through expert experience and machine learning methods, and a drilling abnormality feature library containing feature vectors of different abnormal types is constructed. Then, a pattern recognition algorithm (such as support vector machine, neural network, etc.) is used to calculate and match the similarity between the real-time generated abnormality index matrix and the pattern in the feature library. When the similarity exceeds the set threshold, the potential drilling risk point location is identified.

[0049] Combined with the oil and gas layer information in the oil and gas layer evaluation results table, the drilling risk points are analyzed for correlation, the abnormal development trend and severity are evaluated, the drilling risks are graded, and a graded risk signal is formed. Oil and gas layer information includes key data such as stratum, lithology, porosity and permeability characteristics, fluid type and pressure system, which are of great significance for understanding the background and causes of drilling anomalies. In the process of correlation analysis, the identified risk points are compared with the oil and gas layers encountered in the drilling to analyze the correlation between the two. At the same time, the change rate, duration and impact range of the abnormal indicators are considered to comprehensively evaluate the development trend and severity of the anomalies. According to the evaluation results, the drilling risks are divided into four levels: emergency (red), severe (orange), moderate (yellow) and slight (blue), forming a graded risk signal to provide an intuitive reference for subsequent decision-making. By analyzing historical drilling anomaly handling cases, targeted treatment suggestions are generated for the graded risk signals, combined with the current drilling environment and oil and gas layer characteristics. Historical drilling anomaly handling cases are valuable experience resources, which include the treatment methods and effect evaluations of various drilling anomalies in different regions and different formation conditions. During the implementation process, a case database is constructed to record key information such as anomaly type, severity, geological background, treatment methods and effects; then, based on similar case retrieval technology, historical cases similar to the current situation are searched from the case library; then, based on the current drilling environment (such as well depth, temperature, pressure, etc.) and oil and gas layer characteristics (such as lithology, porosity, pressure system, etc.), historical treatment methods are adaptively adjusted to form specific treatment recommendations for current risks, including parameter adjustment plans, emergency operation procedures and prevention and control measures.

[0050] Integrate the graded risk signals and treatment suggestions into the drilling decision push system, automatically trigger the early warning process, accurately push early warning information to the drilling site engineers, and establish a drilling risk early warning mechanism. The drilling decision push system is a platform that integrates data analysis, risk assessment and information distribution functions. It can receive graded risk signals and treatment suggestions in real time, and automatically trigger the corresponding level of early warning process according to the risk level. Set differentiated response strategies for different risk levels: For emergency risks, push early warning information to the mobile terminals of all key decision makers immediately, and start the emergency disposal process; for serious risks, push early warnings to drilling engineers and geological engineers, requiring close monitoring and preparing response measures; for moderate and minor risks, push reminder information and recommend strengthening parameter monitoring. The early warning information includes key information such as risk type, location, level, development trend, possible causes and treatment suggestions.

[0051] In a specific embodiment, the process of executing step S105 may specifically include the following steps: Extract the acoustic time difference, cuttings porosity characteristics and gas logging hydrocarbon component ratio data related to reservoir physical properties from the logging data preprocessing result set, and build a reservoir physical property parameter set in combination with the oil and gas display information in the oil and gas layer evaluation result table; calculate and process the reservoir physical property parameter set through the regional conversion function, convert the logging physical property indicators into reservoir porosity, permeability and oil and gas saturation values, and generate the initial results of quantitative reservoir evaluation; combine the abnormal identification information in the drilling risk warning mechanism to evaluate the degree of damage to the reservoir during the drilling process, correct the initial results of the quantitative reservoir evaluation, and form a reservoir physical property correction table; According to the oil and gas layer sections and reservoir physical property correction table in the oil and gas layer evaluation results table, the reservoir heterogeneity factors are analyzed, the positions of the dominant seepage channels and fluid barrier layers are identified, and the reservoir seepage characteristic diagram is constructed; based on the reservoir seepage characteristic diagram, the vertical continuity and lateral distribution range of the reservoir are calculated and evaluated, the effective reservoir thickness and distribution range are determined, and the reservoir geometry data are generated; the reservoir physical property correction table, reservoir seepage characteristic diagram and reservoir geometry data are integrated to conduct a comprehensive rating of the reservoir quality, and a comprehensive reservoir evaluation report is compiled according to the reservoir depth, thickness, physical properties, heterogeneity characteristics and quality grade.

[0052] Specifically, the acoustic time difference, cuttings pore characteristics and gas logging hydrocarbon component ratio data related to reservoir physical properties are extracted from the logging data preprocessing result set, and the reservoir physical property parameter set is constructed by combining the oil and gas display information in the oil and gas layer evaluation results table. The acoustic time difference refers to the propagation time of the sound wave through the rock, which is measured in microseconds / foot and reflects the compaction degree and porosity characteristics of the rock; the cuttings pore characteristics include the pore morphology, size and distribution characteristics of the cuttings, which are obtained through microscopic observation and image analysis; the gas logging hydrocarbon component ratio data refers to the content ratio of hydrocarbon gases with different carbon numbers (such as methane, ethane, propane, etc.), reflecting the source and maturity of hydrocarbons. These parameters extracted from the logging data preprocessing result set are deeply matched and integrated with the oil and gas display information in the oil and gas layer evaluation results table (such as total hydrocarbon content, gas logging abnormal amplitude, drilling cuttings fluorescence characteristics, etc.), and a reservoir physical property parameter set containing multiple physical property related indicators is constructed. The reservoir physical property parameter set is calculated and processed through the regional conversion function, and the logging physical property indicators are converted into reservoir porosity, permeability and oil and gas saturation values ​​to generate the initial results of quantitative reservoir evaluation. The regional conversion function is a mathematical model established based on the geological characteristics of a specific area and the statistical analysis of the drilled data. It can convert the indirect physical property indicators obtained by logging into key parameters that directly reflect the reservoir quality. In practical applications, the appropriate conversion function is selected according to different lithological types. For example, the sandstone reservoir uses the time-averaged equation based on the acoustic time difference to calculate the porosity, while the carbonate reservoir uses the modified empirical equation. Permeability is usually estimated from parameters such as porosity, rock cuttings particle size and sorting through empirical formulas, while oil and gas saturation is mainly evaluated based on the proportion of hydrocarbon components in gas logging and the fluorescence characteristics of rock cuttings. Through the calculation and processing of these regional conversion functions, various logging physical property indicators are converted into quantitative reservoir parameters, including porosity (percentage), permeability (millidarcy) and oil and gas saturation (percentage) at each depth point, forming the initial results of quantitative reservoir evaluation.

[0053] Combined with the abnormal identification information in the drilling risk warning mechanism, the degree of damage to the reservoir during the drilling process is evaluated, and the initial results of the quantitative reservoir evaluation are corrected to form a reservoir property correction table. Various abnormal conditions in the drilling process (such as well leakage, well kick, drilling fluid invasion, etc.) cause the measured values ​​of reservoir physical parameters to deviate from the true values, and corresponding corrections are required. Extract abnormal identification information from the drilling risk warning mechanism, including abnormal type, occurrence depth, duration and severity, etc.; then, according to the impact characteristics of different abnormal types on the reservoir, establish a damage assessment model to quantify the impact of various abnormalities on the reservoir porosity, permeability and saturation measurements; take these influencing factors into account in the initial results of the quantitative reservoir evaluation, perform parameter correction, and form a reservoir property correction table that is closer to the actual formation conditions.

[0054] According to the oil and gas layer segments and reservoir physical property correction table in the oil and gas layer evaluation results table, the reservoir heterogeneity factors are analyzed, the dominant seepage channels and fluid barrier layer positions are identified, and the reservoir seepage characteristic diagram is constructed. Reservoir heterogeneity refers to the variation characteristics of reservoir physical parameters in spatial distribution, including vertical and lateral heterogeneity. During the analysis process, the lithology changes inside the oil and gas layer are identified, including factors that affect fluid flow such as mud interlayers and dense bands; then, by comparing the permeability differences of each layer segment, the sections with abnormally high permeability (dominant seepage channels) and sections with abnormally low permeability (fluid barrier layers) are identified; considering the lithology changes, the degree of fracture development and the physical property distribution characteristics, a reservoir seepage characteristic diagram reflecting the fluid flow path and blocking position inside the reservoir is constructed to provide a basis for the design of reservoir development plans.

[0055] Based on the reservoir seepage characteristic diagram, the vertical continuity and lateral distribution range of the reservoir are calculated and evaluated to determine the effective reservoir thickness and distribution range, and generate reservoir geometry data. The vertical continuity evaluation mainly examines the connectivity of the reservoir in the vertical direction, and it is necessary to identify and eliminate the influence of the barrier layer and calculate the thickness of the continuous reservoir section; the lateral distribution range evaluation combines regional geological knowledge and sedimentary environment analysis to infer the horizontal extension law and boundary position of the reservoir. By combining these analysis results, the thickness of the effective reservoir in each layer (considering the lower limit requirements of physical properties, such as porosity>8%, permeability>1 millidarcy, etc.) and distribution range are determined, and reservoir geometry data containing three-dimensional spatial information of the reservoir is generated.

[0056] Integrate the reservoir physical property correction table, reservoir seepage characteristic diagram and reservoir geometry data to conduct a comprehensive reservoir quality rating, and compile a comprehensive reservoir evaluation report according to reservoir depth, thickness, physical properties, heterogeneity characteristics and quality grade. The comprehensive reservoir quality rating is a comprehensive assessment of the reservoir development value, taking into account a variety of factors, including reservoir depth (affecting development costs), effective thickness (affecting production capacity scale), physical property parameters (affecting production efficiency) and heterogeneity characteristics (affecting development difficulty and recovery rate). According to the comprehensive scoring results, the reservoir is divided into four grades: high-quality, good, medium and poor, and a detailed feature description and development recommendations are given for each grade of reservoir segment. Finally, all evaluation results are systematically organized and compiled into a comprehensive reservoir evaluation report containing key information such as reservoir location, geometric characteristics, physical property distribution, flow characteristics and quality grade.

[0057] In a specific embodiment, the process of executing step S106 may specifically include the following steps: Based on the stratigraphic classification atlas, the oil and gas layer evaluation results table and the key stratigraphic and reservoir information in the comprehensive reservoir evaluation report, a one-dimensional geological profile model of the wellbore is constructed to display the vertical distribution characteristics of the stratigraphic formation. Based on the one-dimensional geological profile model of the wellbore combined with the regional structural background data, the single well geological information is horizontally extended through the spatial interpolation algorithm to form a three-dimensional geological skeleton. The reservoir structure in the three-dimensional geological skeleton is finely depicted using the reservoir physical property distribution and heterogeneity characteristic data in the comprehensive reservoir evaluation report to generate a fine reservoir structure map. The oil and gas display information and pressure data in the oil and gas layer evaluation results table are used to determine the position of the oil, gas and water interface, calibrate the fluid distribution boundary in the reservoir fine structure map, and establish a fluid distribution map; based on the reservoir physical properties and connectivity data in the oil and gas layer evaluation results table and the comprehensive reservoir evaluation report, predict and calculate the oil and gas migration channels and enrichment areas to generate an oil and gas enrichment distribution map; integrate the three-dimensional geological skeleton, reservoir fine structure map, fluid distribution map and oil and gas enrichment distribution map, comprehensively evaluate the resource potential and production capacity expectations of the target area, and form oil and gas reservoir description results.

[0058] Specifically, the process of geological structure reconstruction and oil and gas enrichment area prediction is based on the key information of strata and reservoirs in the stratigraphic classification map, oil and gas layer evaluation results table and comprehensive reservoir evaluation report, and a one-dimensional geological profile model of the wellbore is constructed to display the vertical distribution characteristics of the strata. Specifically, the depth of the stratigraphic interface, lithology distribution and geological age information are extracted from the stratigraphic classification map; the location, thickness and quality grade of the oil and gas layer are extracted from the oil and gas layer evaluation results table; and the distribution of reservoir physical property parameters is extracted from the comprehensive reservoir evaluation report. Then this information is integrated in depth order to generate a one-dimensional geological profile model along the wellbore direction, which intuitively displays the stratigraphic units and their characteristics passed by the wellbore, providing basic data for subsequent three-dimensional modeling. According to the one-dimensional geological profile model of the wellbore combined with the regional structural background data, the single well geological information is horizontally extended through the spatial interpolation algorithm to form a three-dimensional geological skeleton. The spatial interpolation algorithm is a mathematical method that extends known point data to a spatial region. Commonly used methods include Kriging interpolation method and inverse distance weighted method. During the implementation process, a preliminary geological conceptual model is established in combination with regional structural background data (such as structural morphology, fault distribution, sedimentary facies, etc.); then the key stratigraphic interface points in the one-dimensional geological profile model of the wellbore are used as known data points; then a suitable spatial interpolation algorithm is used to perform constrained interpolation calculations considering geological laws, and the single well stratigraphic and structural information is extended horizontally to form a three-dimensional geological skeleton model containing the main stratigraphic interfaces and structural features.

[0059] The reservoir structure in the three-dimensional geological skeleton is finely depicted by using the reservoir physical property distribution and heterogeneity characteristic data in the comprehensive reservoir evaluation report, and a reservoir fine structure map is generated. The reservoir lithology distribution, porosity, permeability change characteristics and heterogeneity description are extracted from the comprehensive reservoir evaluation report; then these reservoir physical property data are filled into the geological skeleton according to the three-dimensional spatial coordinate relationship; then the geostatistical method is used to simulate the spatial distribution of the physical property data, and the reservoir structure is finely depicted considering the lithology change law and physical property gradual change characteristics; a reservoir fine structure map reflecting the internal structure and physical property distribution of the reservoir is generated, providing a reservoir basis for subsequent fluid distribution analysis. By analyzing the oil and gas display information and pressure data in the oil and gas layer evaluation results table, the oil and gas-water interface position is determined, the fluid distribution boundary is calibrated in the reservoir fine structure map, and a fluid distribution map is established. The oil and gas-water interface is the interface between oil and gas and formation water in the oil and gas reservoir, and is a key parameter that determines the scope of the oil and gas reservoir. The judgment process extracts pressure data at different depths from the oil and gas layer evaluation results table and calculates the fluid pressure gradient; then, based on the pressure gradient change characteristics and oil and gas display information, the possible position of the oil, gas and water interface is determined; then, the interface is corrected considering the heterogeneity of the reservoir and the capillary force; the determined interface position is calibrated on the reservoir fine structure map, and the oil zone, gas zone and water zone are divided to establish a three-dimensional fluid distribution map.

[0060] Based on the reservoir physical properties and connectivity data in the oil and gas layer evaluation results table and the comprehensive reservoir evaluation report, the oil and gas migration channels and enrichment areas are predicted and calculated to generate an oil and gas enrichment distribution map. The oil and gas migration channel refers to the migration path of oil and gas from the source rock to the reservoir, and the enrichment area refers to the area where oil and gas preferentially accumulate in the reservoir. During the prediction process, the permeability distribution and connectivity characteristics of the reservoir are analyzed to identify possible dominant migration channels; then, combined with the structural position and the oil, gas and water interface relationship, the structural highs and the dominant areas where oil and gas may be enriched are determined; then, the principles of fluid mechanics are used to consider gravity differentiation and buoyancy to calculate the possible distribution law of oil and gas in the reservoir; and an oil and gas enrichment distribution map reflecting the degree of oil and gas enrichment and distribution range is generated.

[0061] Integrate the three-dimensional geological skeleton, reservoir fine structure map, fluid distribution map and oil and gas enrichment distribution map, comprehensively evaluate the resource potential and production capacity expectations of the target area, and form the results of oil and gas reservoir description. During the integration process, various maps are superimposed according to a unified coordinate system to form a complete oil and gas reservoir spatial structure model; then the oil and gas resources in the area are calculated based on the reservoir volume method; then the potential production capacity level is predicted based on the reservoir physical properties and fluid characteristics; all information systems are organized to generate comprehensive oil and gas reservoir description results including geological characteristics, reservoir properties, fluid distribution and resource evaluation, providing a scientific basis for oil and gas field development decisions.

[0062] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for intelligent processing of logging data, characterized in that: The intelligent processing method for logging data comprises: The drilling process data is collected and preprocessed through multi-source logging equipment to form a logging data preprocessing result set; According to the logging data preprocessing result set, the formation characteristics are identified and classified to generate a formation stratification classification map; Based on the stratigraphic classification atlas and the logging data preprocessing result set, a comprehensive analysis of oil and gas parameters is performed to form an oil and gas layer evaluation result table; Using the oil and gas layer evaluation results table and the logging data preprocessing result set, abnormal drilling conditions are identified and risk levels are classified, and a drilling risk early warning mechanism is established; According to the oil and gas layer evaluation results table and drilling risk early warning mechanism, the reservoir physical property parameters are intelligently converted and evaluated to form a comprehensive reservoir evaluation report; The stratigraphic classification map, oil and gas layer evaluation results table and comprehensive reservoir evaluation report are integrated to carry out geological structure reconstruction and oil and gas enrichment area prediction, and generate oil and gas reservoir description results.

2. The method for intelligent processing of logging data according to claim 1, characterized in that: The drilling process data is collected and preprocessed by multi-source logging equipment to form a logging data preprocessing result set, including: The original logging parameters are collected through gas detectors, drill cuttings fluorescence detectors and gamma ray detectors to obtain the gas components of drilling fluid, drill cuttings fluorescence values ​​and natural gamma values, and generate the original logging data stream; Obtain drilling pressure, drilling speed, torque and pump pressure parameters from the drilling engineering monitoring system, and combine them with the lithology description data from geological coring analysis to form an auxiliary logging parameter set; Performing time stamp alignment and depth correction processing on the original logging data stream to eliminate hysteresis effect and depth deviation, and constructing time-depth consistent logging data; Resampling the time-depth consistent logging data and the auxiliary logging parameter set by piecewise cubic spline interpolation method to solve the problem of inconsistent sampling frequencies of data from different sources and generate a unified frequency data set; The wavelet transform filtering technology is used to suppress noise and remove abnormal points from the unified frequency data set, thereby improving the data signal-to-noise ratio and forming high-quality logging basic data; For the missing segments in the high-quality logging basic data, the data is repaired and filled through the associated parameter mapping method, and a time-depth dual index system is established to form a logging data preprocessing result set.

3. The method for intelligent processing of logging data according to claim 1, characterized in that: The method of identifying and classifying formation characteristics according to the logging data preprocessing result set to generate a formation stratification classification map includes: By calculating the coefficient of variation and the first-order derivative of the natural gamma curve in the logging data preprocessing result set, the curve mutation points are identified to form a set of candidate points for formation boundary; Combined with the mutation characteristics of the drilling rate curve, the candidate stratigraphic boundary point set is screened and verified, a preliminary stratigraphic boundary depth point is determined, and a preliminary stratigraphic boundary point set is constructed; The preliminary stratigraphic boundary point set is optimized by using a Poisson change point detection algorithm to exclude non-geological boundary points and generate an accurate stratigraphic boundary point set; Extracting gas logging component ratios, drill cuttings fluorescence characteristics and natural gamma values ​​in each formation segment from the logging data preprocessing result set to construct a formation feature vector set; Based on the similarity calculation results of the stratigraphic feature vector set and the regional standard stratigraphic data, the geological age attribution of each stratigraphic section is determined to form a stratigraphic classification result; According to the morphological characteristics of drill cuttings, mineral composition and gas logging hydrocarbon component ratio, the lithological subdivisions of each stratigraphic segment in the stratigraphic classification results are carried out and integrated to form a stratigraphic stratification classification map.

4. The method for intelligent processing of logging data according to claim 1, characterized in that: Based on the stratigraphic classification atlas and the logging data preprocessing result set, the oil and gas parameters are comprehensively analyzed to form an oil and gas layer evaluation result table, including: Extracting total hydrocarbon value, methane / ethane ratio, abnormal gas component content and drill cuttings fluorescence intensity parameters from the logging data preprocessing result set to construct a basic index set for oil and gas display; According to the lithology classification result in the stratigraphic stratification classification atlas, different evaluation standard thresholds are selected for the oil and gas display basic index set for standardization processing to generate a lithology-matched normalized oil and gas display index; Extracting drilling speed mutation, drilling pressure change and mud density abnormality information from the engineering parameters in the logging data preprocessing result set, and combining with the acoustic wave time difference data to form auxiliary oil and gas identification feature data; The normalized oil and gas display index and the auxiliary oil and gas identification feature data are weighted and fused by a multi-parameter interactive verification method to calculate the comprehensive evaluation index value of the oil and gas layer and establish a comprehensive evaluation index curve of the oil and gas layer; According to the comprehensive evaluation index curve of the oil and gas layer, combined with the lithology and sedimentary environment information in the stratigraphic classification atlas, the potential oil and gas layer segments are identified and graded to form a preliminary oil and gas layer classification result; The index integral value and effective thickness of each oil and gas layer segment in the preliminary oil and gas layer division result are calculated, and the production capacity potential is predicted in combination with the regional production capacity data to form an oil and gas layer evaluation result table.

5. The method for intelligent processing of logging data according to claim 1, characterized in that: The method of using the oil and gas layer evaluation result table and the logging data preprocessing result set to identify drilling abnormalities and classify risk levels, and establish a drilling risk early warning mechanism, includes: By performing statistical calculations on the gas logging parameters, drilling engineering parameters and mud performance parameters in the logging data preprocessing result set, the parameter fluctuation range under normal drilling conditions is determined, and a drilling parameter benchmark file is established; Extract the latest drilling parameters from the logging data preprocessing result set, compare and analyze with the drilling parameter benchmark file, calculate the parameter deviation value, and generate an abnormality index matrix; According to the characteristic patterns of key abnormal types such as kick, lost circulation, stuck pipe and sudden change of formation pressure, a drilling abnormality feature library is constructed, and the abnormality index matrix is ​​matched and compared with the drilling abnormality feature library to identify the location of potential drilling risk points; Combined with the oil and gas layer information in the oil and gas layer evaluation results table, the drilling risk points are analyzed for correlation, the abnormal development trend and severity are evaluated, the drilling risks are graded, and a graded risk signal is formed; By analyzing historical drilling anomaly handling cases, targeted treatment suggestions are generated for the graded risk signals, combined with the current drilling environment and oil and gas layer characteristics; The graded risk signals and treatment suggestions are integrated into the drilling decision push system to automatically trigger the early warning process, accurately push early warning information to drilling site engineers, and establish a drilling risk early warning mechanism.

6. The method for intelligent processing of logging data according to claim 1, characterized in that: According to the oil and gas layer evaluation results table and the drilling risk early warning mechanism, the reservoir physical property parameters are intelligently converted and evaluated to form a comprehensive reservoir evaluation report, including: Extracting acoustic wave time difference, cuttings pore characteristics and gas logging hydrocarbon component ratio data related to reservoir physical properties from the logging data preprocessing result set, and combining with the oil and gas display information in the oil and gas layer evaluation result table to construct a reservoir physical property parameter set; The reservoir physical property parameter set is calculated and processed by a regional conversion function, and the logging physical property index is converted into reservoir porosity, permeability and oil and gas saturation values ​​to generate an initial result of quantitative reservoir evaluation; Combined with the abnormal identification information in the drilling risk early warning mechanism, the damage degree of the drilling process to the reservoir is evaluated, and the initial result of the quantitative reservoir evaluation is corrected to form a reservoir property correction table; According to the oil and gas layer segments in the oil and gas layer evaluation results table and the reservoir physical property correction table, the reservoir heterogeneity factors are analyzed, the positions of the dominant seepage channels and fluid barrier layers are identified, and a reservoir seepage characteristic diagram is constructed; Based on the reservoir seepage characteristic diagram, the vertical continuity and lateral distribution range of the reservoir are calculated and evaluated to determine the effective reservoir thickness and distribution range, and generate reservoir geometry data; The reservoir physical property correction table, reservoir seepage characteristic diagram and reservoir geometric structure data are integrated to conduct a comprehensive reservoir quality rating, and a comprehensive reservoir evaluation report is compiled according to reservoir depth, thickness, physical properties, heterogeneity characteristics and quality grade.

7. The method for intelligent processing of logging data according to claim 1, characterized in that: The above-mentioned integration of the stratigraphic classification atlas, oil and gas layer evaluation results table and comprehensive reservoir evaluation report, the reconstruction of geological structure and prediction of oil and gas enrichment areas, and the generation of oil and gas reservoir description results include: Based on the stratigraphic classification atlas, the oil and gas layer evaluation results table and the stratigraphic and reservoir key information in the comprehensive reservoir evaluation report, a one-dimensional geological profile model of the wellbore is constructed to display the vertical distribution characteristics of the stratigraphic formation; According to the one-dimensional geological profile model of the wellbore combined with the regional structural background data, the geological information of the single well is horizontally extended through a spatial interpolation algorithm to form a three-dimensional geological skeleton; Using the reservoir physical property distribution and heterogeneity characteristic data in the comprehensive reservoir evaluation report, the reservoir structure in the three-dimensional geological framework is finely depicted to generate a reservoir fine structure map; By analyzing the oil and gas display information and pressure data in the oil and gas layer evaluation results table, the oil and gas-water interface position is determined, the fluid distribution boundary is calibrated in the reservoir fine structure map, and a fluid distribution map is established; Based on the reservoir physical properties and connectivity data in the oil and gas layer evaluation results table and the comprehensive reservoir evaluation report, the oil and gas migration channels and enrichment areas are predicted and calculated to generate an oil and gas enrichment distribution map; By integrating the three-dimensional geological framework, reservoir fine structure map, fluid distribution map and oil and gas enrichment distribution map, the resource potential and production capacity expectation of the target area are comprehensively evaluated to form oil and gas reservoir description results.

Images