Method and system for constructing three-dimensional model of comprehensive logging project

Abstract

The invention relates to the technical field of geological engineering, in particular to a method and a system for constructing a three-dimensional model of a comprehensive logging project. The method comprises the following steps: acquiring comprehensive logging engineering monitoring remote sensing data, and performing geologic structure analysis according to the comprehensive logging engineering monitoring remote sensing data so as to obtain geologic structure data; carrying out comprehensive logging project multispectral feature extraction according to the comprehensive logging project monitoring remote sensing data so as to obtain comprehensive logging project multispectral data; performing surface lithology identification according to the comprehensive logging project multispectral data to obtain surface lithology data; and according to the geological structure data and the surface lithology data, constructing a three-dimensional model of the comprehensive logging project, thereby obtaining the three-dimensional model of the comprehensive logging project. According to the method, a dynamically updated accurate three-dimensional model is constructed based on a geological engineering technology, and comprehensive support is provided for development and management of oil and gas fields.

Description

Technical Field

[0001] The present invention relates to the technical field of geological engineering, and particularly relates to a method and system for constructing a three-dimensional model of comprehensive mud logging engineering. Background Art

[0002] Traditional oil and gas exploration technologies mainly rely on two-dimensional geological exploration and drilling data. However, with the increasing complexity of reservoirs, single two-dimensional data can no longer comprehensively describe the spatial characteristics and properties of oil and gas reservoirs. Once a traditional three-dimensional model is established, it usually does not have the ability to be updated in real time. During the process of oil and gas production, the properties of reservoirs change over time, such as fluctuations in parameters such as temperature and pressure, resulting in changes in reservoir properties. Traditional three-dimensional modeling methods have poor adaptability under different geological environments and different reservoir types. Due to the complex and changeable geological environment, traditional methods often need to perform customized modeling for different oil and gas fields or different reservoir types, increasing the complexity and cost of system application. In addition, for some special geological conditions (such as complex faults, fractures, etc.), the modeling accuracy and performance of traditional methods are also difficult to meet the requirements. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide a method and system for constructing a three-dimensional model of comprehensive mud logging engineering to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for constructing a three-dimensional model of comprehensive mud logging engineering includes the following steps:

[0005] Step S1: Obtain the remote sensing data of comprehensive mud logging engineering monitoring, and perform geological structure analysis based on the remote sensing data of comprehensive mud logging engineering monitoring to obtain geological structure data;

[0006] Step S2: Extract the multi-spectral features of comprehensive mud logging engineering based on the remote sensing data of comprehensive mud logging engineering monitoring to obtain the multi-spectral data of comprehensive mud logging engineering; Identify the surface lithology based on the multi-spectral data of comprehensive mud logging engineering to obtain the surface lithology data;

[0007] Step S3: Construct a three-dimensional model of comprehensive mud logging engineering based on the geological structure data and the surface lithology data to obtain a three-dimensional model of comprehensive mud logging engineering; Analyze the spatial distribution of oil and gas reservoirs based on the three-dimensional model of comprehensive mud logging engineering to obtain the spatial distribution data of oil and gas reservoirs;

[0008] Step S4: Obtain the temperature sensing data of the oil and gas reservoir, and perform reservoir deformation analysis on the spatial distribution data of the oil and gas reservoir based on the temperature sensing data of the oil and gas reservoir to obtain the reservoir deformation data; Analyze the stability of the reservoir rock formation based on the reservoir deformation data to obtain the stability data of the reservoir rock formation;

[0009] Step S5: Design the drilling path based on the reservoir rock layer stability data to obtain drilling path data; optimize the path of the comprehensive logging engineering 3D model according to the drilling path data to obtain the optimized 3D model of the comprehensive logging engineering, and upload it to the comprehensive logging engineering management platform to execute the model optimization task.

[0010] By acquiring remote sensing data and conducting geological structure analysis, the present invention can comprehensively understand the underground geological characteristics, help identify the distribution of potential oil and gas reservoirs, and lay a foundation for the subsequent construction of 3D models. The extraction of multi-spectral features and the identification of surface lithology effectively identify different lithological features, enabling more accurate lithological division based on the geological structure data, providing more reliable input data, and further improving the accuracy of the model. The construction of the 3D model combines geological structure and lithology data, enabling the model to more comprehensively display the spatial distribution and characteristics of the reservoir, facilitating more refined analysis of the spatial distribution of oil and gas reservoirs in subsequent analysis, thus ensuring the reasonable evaluation and development of oil and gas resources. During the real-time monitoring and analysis of oil and gas reservoirs, by introducing temperature sensing data and reservoir deformation analysis, the dynamic changes of the reservoir during the exploitation process can be accurately tracked, potential risks and problems can be discovered in a timely manner, and adjustments can be made in advance to avoid reservoir damage or accidents. The analysis of reservoir rock layer stability further processes the deformation data to help evaluate the stability of the reservoir, guide safe exploitation and drilling path optimization, and avoid drilling accidents caused by reservoir instability. By combining reservoir stability data and drilling path design, the drilling path is further optimized, which not only improves the safety of drilling operations but also effectively reduces costs. Overall, this method overcomes the problem that traditional models cannot adapt to reservoir changes by realizing the real-time update and optimization of 3D models, effectively improves the exploitation efficiency of oil and gas fields, reduces risks, and provides accurate and real-time data support and decision-making basis for oil and gas exploration and development.

[0011] Optionally, step S1 is specifically as follows:

[0012] Step S11: Acquire the remote sensing data for comprehensive logging engineering monitoring, and extract lidar features based on the remote sensing data for comprehensive logging engineering monitoring to obtain lidar data;

[0013] Step S12: Identify the fault structure from the lidar data to obtain fault structure data;

[0014] Step S13: Identify the fold structure from the lidar data to obtain fold structure data;

[0015] Step S14: Merge the geological structures according to the fault structure data and the fold structure data to obtain geological structure data.

[0016] By integrating lidar technology, the present invention significantly improves the accuracy and efficiency of geological feature identification in oil and gas exploration. The acquisition and feature extraction of lidar data provide high-precision and high-resolution spatial information for subsequent geological analysis, facilitating the more accurate acquisition of subsurface geological features. By identifying fault structures and fold structures from lidar data, complex structural features in oil and gas reservoirs, such as faults and folds, which are key factors affecting oil and gas distribution and reservoir stability, can be effectively identified. The identified fault and fold structure data can help exploration personnel better understand the spatial distribution and structural characteristics of oil and gas reservoirs, providing an important basis for the accurate assessment and development of oil and gas resources. Further geological structure merging enables the integration of fault and fold structure data to form more comprehensive geological structure data, thus providing high-quality and real-time updated geological information for the three-dimensional modeling of comprehensive mud logging engineering and avoiding the problem that traditional methods cannot reflect reservoir changes in a timely manner. Through this method, the three-dimensional model can be continuously optimized in a dynamically changing geological environment, improving the exploration accuracy and production efficiency of oil and gas reservoirs, while reducing the risks brought by geological complexity and ensuring the safety and sustainability of oil and gas field development.

[0017] Optionally, step S12 is specifically as follows:

[0018] Step S121: Perform high-reflection filtering on the lidar data to obtain filtered point cloud data;

[0019] Step S122: Generate a digital elevation model based on the filtered point cloud data to obtain a digital elevation model;

[0020] Step S123: Calculate the surface slope based on the digital elevation model to obtain surface slope data;

[0021] Step S124: Calculate the surface aspect based on the digital elevation model to obtain surface aspect data;

[0022] Step S125: Perform overlap analysis based on the surface slope data and the surface aspect data to obtain terrain abrupt change data;

[0023] Step S126: Obtain the data of the comprehensive mud logging engineering area;

[0024] Step S127: Divide the data of the comprehensive mud logging engineering area according to the terrain abrupt change data to obtain terrain abrupt area data;

[0025] Step S128: Draw a topographic profile based on the digital elevation model to obtain a topographic profile, and identify the fault line area based on the topographic profile to obtain fault line area data;

[0026] Step S129: Perform an intersection operation on the fault zone based on the broken line area data and the terrain abrupt change area data to obtain the fault zone data, and perform a fault dip structure analysis based on the fault zone data to obtain the fault structure data.

[0027] In the present invention, by performing point cloud high-reflection filtering on lidar data, inaccurate data caused by noise, vegetation, or other interferences can be removed, thereby obtaining more accurate point cloud data. This data processing process improves the recognition accuracy of terrain and geological features. By generating a digital elevation model (DEM), the height changes of the earth's surface can be accurately reflected, providing detailed terrain information for subsequent geological analysis. Based on the digital elevation model, the surface slope and aspect are calculated, further refining the spatial distribution of terrain features and helping to identify risk areas in the reservoir, such as steep slopes or terrain abrupt change areas. Through overlay analysis, areas with abrupt terrain changes can be effectively identified. These areas are usually closely related to complex geological structures (such as faults, folds, etc.) and are key areas for oil and gas reservoir exploration. Combining the comprehensive logging engineering area data to divide the abrupt change area can further help to determine the location and scope of the oil and gas reservoir, thereby improving the precise positioning and exploration efficiency of oil and gas resources. In addition, by drawing a terrain profile, more intuitive support can be provided for the identification of the broken line area, helping to accurately locate the fault zone within the reservoir, which is crucial for understanding the distribution and flow path of oil and gas. By performing an intersection operation on the fault zone data, the spatial distribution of the fault and its relationship with other geological structures can be further determined, assisting in the fault dip structure analysis and providing a scientific basis for the exploitation of oil and gas reservoirs. The beneficial effects of this series of steps are to improve the data accuracy and efficiency in the oil and gas exploration process, be able to update the model in real time and adapt to complex geological environment changes, and ensure the accuracy and safety of oil and gas exploitation.

[0028] Optionally, step S13 is specifically as follows:

[0029] Step S131: Separate non-ground point clouds from the lidar data to obtain ground point cloud data;

[0030] Step S132: Calculate the surface curvature based on the ground point cloud data to obtain the surface curvature data;

[0031] Step S133: Divide the surface curvature according to the surface curvature data to obtain high-curvature surface data and low-curvature surface data;

[0032] Step S134: Identify the syncline area with negative curvature from the high-curvature surface data to obtain the syncline area data;

[0033] Step S135: Identify the anticline area with positive curvature from the low-curvature surface data to obtain the anticline area data;

[0034] Step S136: Perform an intersection operation on the syncline area data and the anticline area data to obtain the fold area data.

[0035] Step S137: Analyze the fold axis structure based on the fold area data to obtain the fold structure data.

[0036] Through the separation of non-ground point clouds from lidar data, the present invention can effectively extract real ground data from complex terrains, providing more accurate basic data for terrain and geological analysis. By calculating the surface curvature, the undulation characteristics of the terrain can be further identified, helping to describe the shape and structure of the surface and laying a foundation for subsequent geological structure analysis. According to the surface curvature for curvature division, high-curvature and low-curvature surfaces can be separately extracted for analysis according to different terrain features, which provides a more detailed perspective for the identification of geological structures. For high-curvature surface data, by identifying the negative-curvature syncline areas, the low-lying areas in the surface can be accurately found, and these areas are related to the accumulation zones of oil and gas reservoirs. The identification of the positive-curvature anticline areas in the low-curvature surface data helps to find the anticline areas where oil and gas reservoirs are formed. By performing an intersection operation on the syncline area and anticline area data, the spatial distribution of the fold area can be more accurately defined, and important geological structure features can be identified. Further, by analyzing the axis structure of the fold area, potential fold structures in the reservoir can be revealed, providing key information for the exploration and exploitation of oil and gas reservoirs. The effectiveness of this series of steps is reflected in being able to provide a more refined and real-time updated three-dimensional data model for oil and gas exploration in complex geological environments, greatly improving the accuracy and efficiency of exploration, and helping to achieve more accurate positioning and evaluation of oil and gas resources in areas with complex geological environments.

[0037] Optionally, step S2 is specifically as follows:

[0038] Step S21: Extract the multi-spectral features of the comprehensive mud logging engineering based on the comprehensive mud logging engineering monitoring remote sensing data to obtain the comprehensive mud logging engineering multi-spectral data.

[0039] Step S22: Analyze the spectral reflectance of the surface lithology for the comprehensive mud logging engineering multi-spectral data to obtain the spectral reflectance data of the surface lithology.

[0040] Step S23: Analyze the absorption bands of the surface lithology for the comprehensive mud logging engineering multi-spectral data to obtain the absorption band data of the surface lithology.

[0041] Step S24: Integrate the spectral reflectance data of the surface lithology and the absorption band data of the surface lithology to obtain the surface lithology data.

[0042] Through multi-spectral feature extraction of comprehensive logging engineering monitoring remote sensing data, the present invention can extract spectral information in different bands, providing more comprehensive surface information for subsequent geological analysis. This process can not only accurately capture the optical characteristics of the surface, but also provide a relatively high resolution in space. Based on these multi-spectral data, the surface lithology spectral reflectance analysis helps to deeply understand the characteristics of surface lithology reflection, laying a foundation for the accurate identification of lithology distribution. This analysis can reveal the reflection patterns of different rock types, helping to quickly identify the main lithology components in the reservoir. Further, the surface lithology absorption band analysis can obtain the absorption characteristics of lithology in different bands by identifying the characteristics of absorption bands, which is of great significance for accurately judging the composition of the reservoir and determining favorable hydrocarbon reservoir areas. By integrating the surface lithology spectral reflectance data and absorption band data, the lithology characteristics of the reservoir can be comprehensively described, making the geological model more accurate and providing clearer and more scientific guidance for subsequent hydrocarbon reservoir evaluation, exploration and exploitation. These steps analyze lithology data from multiple angles, not only improving the accuracy of hydrocarbon exploration, but also ensuring efficient application in complex geological environments.

[0043] Optionally, step S22 is specifically as follows:

[0044] Step S221: Extract the short-wave infrared band characteristics from the comprehensive logging engineering multi-spectral data to obtain short-wave infrared band data;

[0045] Step S222: Obtain lithology absorption band data and lithology spectral data;

[0046] Step S223: Classify the short-wave infrared band data according to the lithology absorption band data to obtain rock type data;

[0047] Step S224: Perform spectral matching on the rock type data with the lithology spectral data to obtain rock spectral matching data;

[0048] Step S225: Draw a surface lithology classification map based on the rock spectral matching data for the comprehensive logging engineering area data to obtain a surface lithology classification map;

[0049] Step S226: Calculate the spectral reflectance according to the surface lithology classification map to obtain surface lithology spectral reflectance data.

[0050] Through the extraction of short-wave infrared band characteristics from the multi-spectral data of the comprehensive mud logging project, the present invention can obtain more detailed lithological information. Especially in the short-wave infrared band, the mineral characteristics of rocks are obvious, which can help distinguish different rock types. The short-wave infrared band data provides rich spectral information for the subsequent rock type classification. Furthermore, through the combination with the lithological absorption band data, the rock types can be accurately classified. This process ensures the accuracy of rock classification and provides strong support for further geological analysis. Based on the spectral matching between the lithological spectral data and the rock type data, the spectral characteristics of rocks can be more accurately reflected, thereby improving the accuracy of the rock classification results. This spectral matching process effectively reduces the human interference and errors in traditional methods and improves the reliability of the data. After obtaining the rock spectral matching data, by drawing the surface lithology classification map, the spatial distribution of various rocks in the area can be visually displayed, which helps to better understand the lithological composition and spatial structure of the reservoir. At the same time, according to the surface lithology classification map, the spectral reflectance is calculated, which provides quantitative data support for geological analysis and further improves the accuracy and practicality of the geological model. Finally, the implementation of this series of steps improves the accuracy and efficiency of oil and gas exploration. Especially in complex geological environments, it can provide more accurate surface lithological information to support efficient oil and gas reservoir evaluation and exploitation decisions.

[0051] Optionally, step S23 is specifically as follows:

[0052] Step S231: Extract the characteristics of the near-infrared band from the multi-spectral data of the comprehensive mud logging project to obtain the near-infrared band data;

[0053] Step S232: Divide the range of the iron mineral absorption peak for the near-infrared band data to obtain the iron mineral absorption peak range data;

[0054] Step S233: Detect the absorption band for the iron mineral absorption peak range data to obtain the iron mineral absorption band data;

[0055] Step S234: Calculate the depth of the absorption peak based on the iron mineral absorption band data to obtain the absorption peak depth data;

[0056] Step S235: Calculate the width of the absorption peak based on the iron mineral absorption band data to obtain the absorption peak width data;

[0057] Step S236: Calculate the iron mineral content based on the absorption peak depth data and the absorption peak width data to obtain the iron mineral content data;

[0058] Step S237: Identify the wavelength position based on the iron mineral absorption band data to obtain the wavelength position data;

[0059] Step S238: Perform feature fusion of surface lithology absorption bands based on the wavelength position data and iron mineral content data, so as to obtain surface lithology absorption band data.

[0060] Through the extraction of near-infrared band features from the multi-spectral data of comprehensive logging engineering, the present invention can more accurately capture the spectral characteristics of rocks and minerals, especially the relevant characteristics of iron minerals. The near-infrared band data helps to identify the distribution and characteristics of iron minerals in rocks, and then provides key data for subsequent iron mineral analysis. After dividing the absorption peak range of iron minerals in the near-infrared band data, the absorption characteristic region of iron minerals can be accurately located, providing a more targeted reference for mineral analysis. By detecting the absorption band, the spectral absorption band data of iron minerals can be further extracted to help analyze the types and content distributions of iron minerals in rocks. Calculating the depth and width of the absorption peak based on the iron mineral absorption band data can deeply reveal the abundance and distribution characteristics of iron minerals, which is of great significance for evaluating the iron mineral content in reservoirs. The iron mineral content data calculated from the depth and width data of the absorption peak can more accurately quantify the iron mineral composition in the reservoir, providing key mineral information for oil and gas exploration. Based on the identification of the wavelength position of the iron mineral absorption band data, the ability to identify different rock layers and minerals can be further enhanced, helping to clarify the types and distribution areas of minerals. Finally, combining the wavelength position data with the iron mineral content data for feature fusion of surface lithology absorption bands can provide a more comprehensive lithology analysis, improving the accuracy and effectiveness of geological exploration. These steps make the application of oil and gas exploration in complex geological environments more accurate, and at the same time provide more reliable data support for reservoir evaluation and production decision-making.

[0061] Optionally, step S4 is specifically as follows:

[0062] Step S41: Obtain oil and gas reservoir temperature sensing data, and draw a temperature gradient map based on the oil and gas reservoir temperature sensing data, so as to obtain an oil and gas reservoir temperature gradient map;

[0063] Step S42: Identify high-temperature regions in the oil and gas reservoir spatial distribution data based on the oil and gas reservoir temperature gradient map, so as to obtain high-temperature oil and gas reservoir spatial distribution data;

[0064] Step S43: Obtain the geological thermal expansion coefficient of the oil and gas reservoir and the reference temperature distribution data of the oil and gas reservoir;

[0065] Step S44: Perform temperature change calculations on the high-temperature oil and gas reservoir spatial distribution data based on the reference temperature distribution data of the oil and gas reservoir, so as to obtain oil and gas reservoir temperature change data;

[0066] Step S45: Perform thermal strain calculations based on the oil and gas reservoir temperature change data and the geological thermal expansion coefficient of the oil and gas reservoir, so as to obtain oil and gas reservoir thermal strain data;

[0067] Step S46: Identify the stress concentration areas from the thermal strain data of the oil and gas reservoir to obtain the reservoir deformation data;

[0068] Step S47: Analyze the stability of the reservoir rock formations based on the reservoir deformation data to obtain the reservoir rock formation stability data.

[0069] By obtaining the temperature sensing data of the oil and gas reservoir and drawing the temperature gradient map, the present invention can visually display the spatial distribution characteristics of the reservoir temperature, helping the exploration personnel to identify the areas with large temperature differences in the reservoir. By identifying the high-temperature areas through the temperature gradient map, the reservoir areas with abnormal heat zones can be effectively marked out, providing guidance for subsequent oil and gas exploitation, especially helping to judge the impact of the high-temperature areas on reservoir exploitation. Combining the geological thermal expansion coefficient and the temperature reference distribution data of the oil and gas reservoir, the calculation of the reservoir temperature change can be carried out more accurately, further revealing the influence of temperature fluctuations on the reservoir properties. In this process, the temperature change data provides a basis for subsequent thermal strain calculations, helping to reveal the mechanical response of the reservoir in the changing thermal environment. Through the analysis of the thermal strain data, the stress concentration areas in the reservoir can be effectively identified, the structural risk areas can be discovered in time, and the engineering problems encountered during the exploitation process can be reduced. Finally, by analyzing the stability of the rock formations through the reservoir deformation data, the stability of the reservoir rock formations under the action of thermal strain can be evaluated, the risks that may occur in the reservoir under different exploitation conditions can be predicted, and the safety and feasibility of the oil and gas exploration and exploitation process can be effectively improved. This series of steps can more comprehensively and accurately evaluate the deformation behavior of the oil and gas reservoir by comprehensively considering temperature, thermal expansion coefficient and stress changes, and optimize the oil and gas exploitation plan.

[0070] Optionally, step S47 is specifically as follows:

[0071] Step S471: Draw the stress field distribution map based on the reservoir deformation data to obtain the stress field distribution map;

[0072] Step S472: Obtain the reservoir rock compressive strength data;

[0073] Step S473: Calculate the safety factor of the reservoir area based on the reservoir rock compressive strength data and the stress field distribution map to obtain the safety factor of the reservoir area;

[0074] Step S474: Evaluate the stability of the reservoir deformation data based on the safety factor of the reservoir area to obtain the reservoir rock formation stability data.

[0075] By drawing a stress field distribution map based on reservoir deformation data, the present invention can visually display the stress distribution in the reservoir, helping exploration personnel identify areas of stress concentration or uneven distribution, and providing a visualization tool for reservoir stability analysis. On this basis, obtaining the compressive strength data of reservoir rocks can provide key parameters for the physical properties of the reservoir, thus providing a scientific basis for subsequent safety assessments and mining decisions. By combining the stress field distribution map and the compressive strength data to calculate the safety factor of the reservoir area, the damage risk encountered during the mining process of the reservoir can be effectively evaluated, potential structural problems in which areas can be predicted, and then the mining plan can be optimized and potential safety hazards can be avoided. Finally, based on the safety factor of the reservoir area, the stability of the reservoir deformation data is evaluated, which helps to judge the stability of the reservoir rock formation under different stress and environmental conditions, provides safety guarantees for oil and gas extraction, and can adjust the mining strategy in real time to ensure efficient extraction and long-term sustainability under different reservoir environments.

[0076] Optionally, this specification also provides a construction system for a comprehensive mud logging engineering three-dimensional model, which is used to execute a method for constructing a comprehensive mud logging engineering three-dimensional model as described above. The construction system for the comprehensive mud logging engineering three-dimensional model includes:

[0077] A geological structure analysis module: used to obtain comprehensive mud logging engineering monitoring remote sensing data and perform geological structure analysis based on the comprehensive mud logging engineering monitoring remote sensing data to obtain geological structure data;

[0078] A surface lithology identification module: used to extract multi-spectral features of the comprehensive mud logging engineering based on the comprehensive mud logging engineering monitoring remote sensing data to obtain comprehensive mud logging engineering multi-spectral data; perform surface lithology identification based on the comprehensive mud logging engineering multi-spectral data to obtain surface lithology data;

[0079] An oil and gas reservoir spatial distribution analysis module: used to construct a comprehensive mud logging engineering three-dimensional model based on the geological structure data and the surface lithology data to obtain a comprehensive mud logging engineering three-dimensional model; perform oil and gas reservoir spatial distribution analysis based on the comprehensive mud logging engineering three-dimensional model to obtain oil and gas reservoir spatial distribution data;

[0080] A reservoir rock formation stability analysis module: used to obtain oil and gas reservoir temperature sensing data and perform reservoir deformation analysis on the oil and gas reservoir spatial distribution data based on the oil and gas reservoir temperature sensing data to obtain reservoir deformation data; perform reservoir rock formation stability analysis based on the reservoir deformation data to obtain reservoir rock formation stability data;

[0081] Integrated logging three-dimensional model path optimization module: used to design the drilling path according to the reservoir rock layer stability data, so as to obtain the drilling path data; optimize the path of the integrated logging engineering three-dimensional model according to the drilling path data, so as to obtain the optimized integrated logging engineering three-dimensional model, and upload it to the integrated logging engineering management platform to execute the model optimization task.

[0082] The construction system of the integrated logging engineering three-dimensional model of the present invention can implement any construction method of the integrated logging engineering three-dimensional model of the present invention, and is used as a medium for joint operation and signal transmission between various modules to complete the construction method of the integrated logging engineering three-dimensional model. The internal modules of the system cooperate with each other to construct an accurately three-dimensional model with dynamic update, providing comprehensive support for the development and management of oil and gas fields. Brief Description of the Drawings

[0083] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, purposes and advantages of the present invention will become more obvious:

[0084] Figure 1 It is a schematic flowchart of the steps of the construction method of the integrated logging engineering three-dimensional model of the present invention;

[0085] Figure 2 It is a schematic flowchart of the detailed steps of step S1 in the present invention;

[0086] Figure 3 It is a schematic flowchart of the detailed steps of step S13 in the present invention;

[0087] The realization, functional characteristics and advantages of the object of the present invention will be further described with reference to the embodiments and the drawings. Detailed Embodiments

[0088] The technical method of the present invention patent will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative work belong to the scope of protection of the present invention.

[0089] In addition, the drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, so repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0090] It should be understood that although terms such as "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0091] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides a method for constructing a three-dimensional model of a comprehensive mud logging project, and the method includes the following steps:

[0092] Step S1: Obtain remote sensing data for comprehensive mud logging project monitoring, and perform geological structure analysis based on the remote sensing data for comprehensive mud logging project monitoring, so as to obtain geological structure data;

[0093] In this embodiment, the acquisition of remote sensing data for comprehensive mud logging project monitoring can be carried out through a high-resolution satellite imaging system or a multi-spectral camera carried by a drone. The remote sensing data should include spectral, thermal infrared and terrain data. By applying remote sensing image processing software, preprocessing of these data is performed, including radiometric correction, atmospheric correction and geometric correction. Using image registration technology, the remote sensing data is matched with known geographical coordinates to ensure the spatial positioning accuracy. Geological structure analysis is carried out based on image processing algorithms for edge detection and morphological operations to extract structural features such as geological fracture lines and folds. The Fourier transform or wavelet transform is used to perform spectral analysis on the data to extract the ripples and trends of the rock formations. Finally, through rock classification and geological texture analysis, a detailed geological structure data set is constructed.

[0094] Step S2: Extract multi-spectral features of the comprehensive mud logging project based on the remote sensing data for comprehensive mud logging project monitoring, so as to obtain multi-spectral data of the comprehensive mud logging project; identify the surface lithology based on the multi-spectral data of the comprehensive mud logging project, so as to obtain surface lithology data;

[0095] In this embodiment, the extraction of multi-spectral features in comprehensive mud logging engineering can be carried out through multi-spectral analysis software. The core steps of data extraction include filtering and feature enhancement for different bands. The specific operation is to use a band-pass filter to decompose the multi-spectral data into different bands such as infrared, visible light, and ultraviolet. The data of each band is segmented using the Otsu algorithm (maximum between-class variance) to identify different lithological features. The identification of surface lithology is based on the reflection spectrum matching technology, and the spectral library comparison method is adopted to match the measured spectral data with the standard lithology spectrum to determine the lithology category. The spectral reflectance threshold (such as 0.4 - 0.8) and the position of the absorption peak need to be considered to accurately distinguish geological components such as sandstone, shale, and limestone.

[0096] Step S3: Construct a three-dimensional model of comprehensive mud logging engineering based on the geological structure data and the surface lithology data, so as to obtain the three-dimensional model of comprehensive mud logging engineering; perform an analysis on the spatial distribution of the oil and gas reservoir based on the three-dimensional model of comprehensive mud logging engineering, so as to obtain the spatial distribution data of the oil and gas reservoir;

[0097] In this embodiment, constructing a three-dimensional model of comprehensive mud logging engineering requires integrating multi-source data. The geological structure data and the surface lithology data are input into three-dimensional modeling software (such as Petrel or GOCAD). Through grid division, the discrete element method (DEM) and finite element analysis (FEM) are used to fit the spatial distribution of the model. In the three-dimensional model, the geological properties of each grid point need to be filled according to the spatial interpolation method (such as Kriging interpolation) to obtain a high-precision reservoir model. The analysis of the spatial distribution of the oil and gas reservoir combines the model data and uses reservoir evaluation software to calculate the reservoir thickness, porosity, and permeability to form spatial distribution data.

[0098] Step S4: Obtain the temperature sensing data of the oil and gas reservoir, and perform reservoir deformation analysis on the spatial distribution data of the oil and gas reservoir according to the temperature sensing data of the oil and gas reservoir, so as to obtain reservoir deformation data; perform reservoir rock layer stability analysis according to the reservoir deformation data, so as to obtain reservoir rock layer stability data;

[0099] In this embodiment, obtaining the temperature sensing data of the oil and gas reservoir requires deploying downhole temperature sensors, and the sensors should be arranged at different depths and positions to obtain comprehensive temperature profile data. The temperature data is transmitted to the analysis platform through a data acquisition system (such as SCADA). The reservoir deformation analysis utilizes the spatial distribution data of the reservoir and combines the coefficient of thermal expansion and the temperature change formula. The deformation analysis is performed through numerical simulation software (such as ANSYS), and a thermal-mechanical coupling model is adopted to simulate the expansion and contraction behavior of the reservoir. The key input parameters include the coefficient of thermal expansion (such as 10^-5 / ℃) and the initial temperature of the reservoir. The stress analysis uses the Von Mises criterion to detect potential instability regions to ensure that the data fully characterizes the reservoir deformation.

[0100] Step S5: Design the drilling path based on the reservoir rock layer stability data to obtain the drilling path data; optimize the path of the comprehensive mud logging engineering three-dimensional model according to the drilling path data to obtain the optimized three-dimensional model of the comprehensive mud logging engineering, and upload it to the comprehensive mud logging engineering management platform to execute the model optimization task.

[0101] In this embodiment, the drilling path design utilizes the three-dimensional model data and the reservoir rock layer stability data, and adopts a path optimization algorithm. The specific algorithm includes the Dijkstra algorithm, which is used to plan the shortest path and avoid the unstable area. In the path calculation, parameters such as the well inclination angle, azimuth angle, and maximum horizontal stress direction are considered. The inclination range of the drilling (such as 10° - 60°) and the maximum offset distance are set. The optimized path is verified and iterated on the three-dimensional model through a path correction tool. After completing the path optimization, the results are uploaded to the comprehensive mud logging engineering management platform to achieve remote monitoring and dynamic adjustment of the path planning. Finally, the model and path data are uploaded and synchronized through the API interface or the File Transfer Protocol (FTP).

[0102] Optionally, step S1 is specifically as follows:

[0103] Step S11: Obtain the remote sensing data for comprehensive mud logging engineering monitoring, and extract the lidar features based on the remote sensing data for comprehensive mud logging engineering monitoring to obtain the lidar data;

[0104] In this embodiment, the remote sensing data for comprehensive mud logging engineering monitoring is obtained through a high-resolution remote sensing satellite and an unmanned aerial vehicle lidar (LiDAR) system. The lidar system should use the pulsed laser ranging method to emit and receive laser pulses at nanosecond time intervals to form high-density point cloud data. This data is synchronously recorded through a receiver and a positioning system (such as GPS and inertial measurement unit IMU) to ensure the accuracy of spatial positioning. The lidar feature extraction is performed using point cloud processing software (such as CloudCompare or LAStools), which includes data preprocessing steps such as denoising, coordinate transformation, and elevation normalization. Through an algorithm based on gradient calculation and curvature analysis, the irregular landforms and geological features are separated from the point cloud, and finally output as lidar data.

[0105] Step S12: Identify the fault structure from the lidar data to obtain the fault structure data;

[0106] In this embodiment, the identification of fault structures is based on topographic discontinuities and elevation differences in lidar data. The specific operations include using edge detection algorithms (such as the Canny algorithm) and fracture identification algorithms to identify fault lines in the point cloud. In terms of parameter settings, the elevation difference threshold should be set between 0.5 and 2 meters to distinguish major faults from small fractures. The fault dip and strike are calculated by fitting planes and normal vectors, and the RANSAC algorithm is used to improve the robustness of the identification. This process combines the overlay of high-resolution images and LiDAR data to enhance the accuracy of identification, and performs spatial coordinate correction and fault annotation.

[0107] Step S13: Identify the fold structure from the lidar data to obtain fold structure data;

[0108] In this embodiment, the identification of fold structures is performed on the three-dimensional topographic model extracted from the lidar data. The identification of folds uses geometric morphology algorithms, including curvature analysis based on the second derivative. By calculating the principal curvature and Gaussian curvature of the lidar data points, the position and trend of the fold axis are determined. A curvature threshold (such as 1 to 3 degrees / m) is set to distinguish significant folds from surface undulations to avoid false positives. Next, through the template matching algorithm, the identification results are compared with known fold models to confirm the type and geometric morphology of the folds. Finally, the data is integrated and output as structure data including the fold strike, amplitude, and frequency.

[0109] Step S14: Merge the fault structure data and the fold structure data to obtain geological structure data.

[0110] In this embodiment, the merger of the fault structure data and the fold structure data is based on the geological information integration method. A GIS platform (such as ArcGIS or QGIS) is used to overlay the data layers to ensure precise spatial alignment of the two types of data. When merging the data, Boolean operations are used to mark the overlapping areas as composite structure areas. Consistency checks are performed on the merged data, and overlapping and adjacency relationships are detected through spatial topology analysis. To improve the analysis accuracy, the merged data is spatially corrected in combination with the digital elevation model (DEM). The output result is comprehensive geological structure data, which annotates the position information and geometric features of various geological features for further geological analysis and engineering applications.

[0111] Optionally, step S12 is specifically:

[0112] Step S121: Perform high-reflection filtering on the lidar data to obtain filtered point cloud data;

[0113] In this embodiment, the high-reflection filtering of the lidar data point cloud is performed using a data preprocessing tool, and the light intensity threshold filtering method is used in the implementation process. The light intensity threshold should be set in the range of 80 to 120 units, and the specific value is determined according to the laser wavelength (such as 905 nm or 1550 nm) and the ambient light conditions. The point cloud data clears abnormally high-reflection points through a filtering algorithm (such as Gaussian filtering or median filtering), and these points are derived from the reflection of building surfaces or metal objects. The preprocessed point cloud data is converted into two-dimensional and three-dimensional formats to form point cloud filtered data, which is used for subsequent terrain analysis and model generation.

[0114] Step S122: Generate a digital elevation model based on the point cloud filtered data, thereby obtaining the digital elevation model;

[0115] In this embodiment, the point cloud filtered data is used to generate a digital elevation model (DEM). This process uses an interpolation method (such as the least squares method or Kriging interpolation) to grid the point cloud and generate elevation data. The grid resolution of the DEM is selected from 1 meter to 5 meters, and the specific value is set according to the size and detail requirements of the surveyed area. The generation process requires processing the point cloud data through the GDAL library of Python or the "Create DEM" tool in ArcGIS, and outputting it as gridded elevation data for analyzing surface features.

[0116] Step S123: Calculate the surface slope based on the digital elevation model, thereby obtaining the surface slope data;

[0117] In this embodiment, the surface slope is calculated based on the generated DEM, and the gradient algorithm based on the digital elevation is used to calculate the slope. This calculation uses derivative calculation or Sobel filtering method to obtain the slope value by detecting the elevation change of each grid cell. The output slope data is expressed in the form of angles (degrees), and the range is generally from 0° to 90°, and is implemented using the "Slope Analysis" tool in the GIS platform. During the calculation process, ensure the smoothness of the data and the processing of no null values, and perform angle smoothing through a compensation algorithm to eliminate errors.

[0118] Step S124: Calculate the surface aspect based on the digital elevation model, thereby obtaining the surface aspect data;

[0119] In this embodiment, the surface aspect calculation is based on the DEM and the slope data. The directional derivative and the "Aspect" analysis tool in ArcGIS are used to determine the aspect of each grid cell. The aspect calculation is expressed in angles, ranging from 0° (north) to 360°, representing the direction in which the grid elevation decreases. The surface aspect calculation result is output as raster data, and each pixel corresponds to a direction angle. Check these data to ensure the aspect consistency and mark the areas with relatively large aspect differences.

[0120] Step S125: Conduct overlay analysis based on the surface slope data and the surface aspect data to obtain the terrain sharp change data;

[0121] In this embodiment, the overlay analysis of the surface slope data and the surface aspect data is implemented through the "overlay analysis" module of GIS software, and intersection and difference analyses are carried out. Set specific thresholds, for example, areas with a slope greater than 30° and an aspect difference exceeding 45° are marked as sharp change areas. This analysis is achieved through spatial queries and Boolean logic, and these marked areas are output as a new data layer to form the terrain sharp change data.

[0122] Step S126: Obtain the comprehensive logging engineering area data;

[0123] In this embodiment, the comprehensive logging engineering area data is obtained using high-precision surveying data and the existing comprehensive logging geological information database. This step combines on-site measurement data and remote sensing monitoring results, divides the logging engineering area into different survey sub-areas, and forms a multi-dimensional data table and a set of spatial coordinates to ensure the unity and spatial matching of the data for subsequent operations.

[0124] Step S127: Divide the comprehensive logging engineering area data according to the terrain sharp change data to obtain the terrain sharp area data;

[0125] In this embodiment, when dividing the comprehensive logging engineering area data according to the terrain sharp change data, spatial analysis methods and clustering algorithms (such as K-Means or DBSCAN) are used to separate the sharp change areas from the gentle areas. The data is spatially segmented, and the "zone statistics" function of GIS tools is used to separate the sharp change area data layer. The divided area data is marked with geographical coordinates and features for engineering planning and further survey.

[0126] Step S128: Draw a topographic profile according to the digital elevation model to obtain the topographic profile, and identify the fracture line area according to the topographic profile to obtain the fracture line area data;

[0127] In this embodiment, the digital elevation model is used to draw the topographic profile. The profile drawing is achieved through GIS software or the Matplotlib library. A specific profile line is selected for cutting to generate the profile. The point-by-point interpolation algorithm of the elevation grid is used during the profile drawing to ensure accuracy. According to the profile, edge detection algorithms (such as Sobel or Canny) are applied to identify the fracture lines, and the edge positions are output as the fracture line area data.

[0128] Step S129: Perform an intersection operation on the fault zone based on the broken line area data and the terrain steep area data to obtain the fault zone data, and perform a fault dip structure analysis based on the fault zone data to obtain the fault structure data.

[0129] In this embodiment, the intersection operation of the broken line area data and the terrain steep area data is completed through Boolean logic operations to ensure that the identified fault zones overlap or are close to areas with steep terrain changes. The intersection operation is performed using the "Intersect" function in ArcGIS or the GeoPandas library in Python. Based on the intersection result, a dip structure analysis is performed, and a fitting algorithm and normal vector analysis are used to determine the fault dip angle and strike. The output fault structure data annotates the dip, position, and direction information.

[0130] Optionally, step S13 is specifically as follows:

[0131] Step S131: Separate the non-ground point cloud from the lidar data to obtain the ground point cloud data;

[0132] In this embodiment, the separation of the non-ground point cloud from the lidar data is implemented using a rule-based classification algorithm. First, a filtering algorithm (such as a progressive filter or a CSF filter) is applied to distinguish non-ground points from ground points. Specifically, the filtering threshold is set between 1.5 meters and 3 meters to ensure the removal of non-ground elements such as vegetation and buildings. Spatial density analysis is performed on the point cloud, and the nearest neighbor point spacing and elevation change are used for screening. The marked ground points are output as the ground point cloud data. This process is completed through lidar data processing software (such as LASTools or the PDAL library).

[0133] Step S132: Calculate the surface curvature based on the ground point cloud data to obtain the surface curvature data;

[0134] In this embodiment, the ground point cloud data is used to calculate the surface curvature. The calculation method is implemented using triangular irregular network (TIN) construction and second derivative analysis. TIN construction is completed through a triangulation algorithm (such as Delaunay triangulation). The curvature of each triangular mesh is obtained by fitting a quadratic surface and calculating its principal curvature. The curvature data is stored in a raster format, and the value of each pixel corresponds to the curvature value of that point, ranging from negative to positive. This calculation process is implemented using GIS analysis tools (such as the "Curvature Analysis" tool in ArcGIS).

[0135] Step S133: Perform curvature division based on the surface curvature data to obtain high-curvature surface data and low-curvature surface data;

[0136] In this embodiment, curvature division is performed according to the surface curvature data, and the curvature data is divided into high-curvature and low-curvature regions. The standard deviation method or a fixed threshold (such as ±0.05 curvature units) is used to classify the curvature data. Regions with an absolute curvature value greater than the threshold are marked as high-curvature, and those below the threshold are marked as low-curvature. The division process uses a Python script to implement data segmentation and annotation, and the output is completed through a raster calculation tool to generate high-curvature and low-curvature surface data.

[0137] Step S134: Identify the syncline regions with negative curvature in the high-curvature surface data to obtain syncline region data;

[0138] In this embodiment, to identify the syncline regions with negative curvature in the high-curvature surface data, it is achieved by judging the positivity and negativity of the curvature value and its spatial distribution. A negative value filter is used to extract all regions with negative curvature and further analyze the continuity and scale of the curvature value to ensure that the connectivity of this region meets the region determination standard (such as continuity greater than 100 meters). The output syncline region data includes its geographical boundary and curvature characteristics, and a spatial statistics tool is used to verify its accuracy.

[0139] Step S135: Identify the anticline regions with positive curvature in the low-curvature surface data to obtain anticline region data;

[0140] In this embodiment, to identify the anticline regions with positive curvature in the low-curvature surface data, a method similar to that for syncline regions is used. Regions with a positive curvature value are screened, and area and morphological rules are applied to determine the anticline regions. The curvature range for region identification is set between 0.01 and 0.1 to ensure the stability of this curvature feature. The "region growing" tool in GIS software is used to extract the qualified regions, and the anticline region data is output and its morphological characteristics are marked.

[0141] Step S136: Perform an intersection operation on the fold regions based on the syncline region data and the anticline region data to obtain fold region data;

[0142] In this embodiment, to perform an intersection operation on the fold regions based on the syncline region data and the anticline region data, a Boolean operation is applied for cross-analysis of data layers. Through the "intersection" function in the GIS platform or the spatial query function of the GeoPandas library, the identified syncline and anticline regions are overlaid to form fold region data. This process ensures the spatial accuracy of the overlapping regions, and the fold region data containing boundaries, areas, and position coordinates is output in a vector data format.

[0143] Step S137: Analyze the fold axis structure based on the fold region data to obtain fold structure data.

[0144] In this embodiment, the data of the fold area is used for the analysis of the fold axis structure. By using the profile line and gradient analysis method of the digital elevation model, the position of the fold axis is extracted. The profile analysis calculates the axis of each fold using the curvature change rate method to ensure the accurate position and direction of the axis are identified. This analysis is implemented using the "Profile Tool" of ArcGIS combined with a custom Python script, and the fold structure data is output, indicating the trend, dip angle, and position information of the fold axis.

[0145] Optionally, step S2 is specifically as follows:

[0146] Step S21: Extract the multi-spectral characteristics of the comprehensive mud logging engineering based on the remote sensing data of the comprehensive mud logging engineering monitoring, so as to obtain the multi-spectral data of the comprehensive mud logging engineering;

[0147] In this embodiment, when extracting the multi-spectral characteristics of the comprehensive mud logging engineering based on the remote sensing data of the comprehensive mud logging engineering monitoring, it is necessary to capture the multi-band remote sensing data covering the mud logging area through a hyperspectral imaging device and ensure that each band has a complete spectral response. The hyperspectral device used should have at least more than 200 spectral bands, covering the visible light, near-infrared, and short-wave infrared bands to ensure the integrity and accuracy of the data. The data extraction is achieved through specific optical filters and high-resolution sensors to ensure that the spectral reflectance of each pixel point can accurately represent the characteristics of the mud logging area. The spectral feature extraction needs to be combined with data preprocessing techniques, including radiometric correction and geometric correction, to eliminate the effects of atmospheric scattering and terrain. The extracted multi-spectral data shows characteristic spectral curves for different minerals and lithologies on the spectral map, clearly reflecting the reflectance differences in each band, forming a multi-spectral database, which provides a data basis for subsequent surface lithology analysis.

[0148] Step S22: Analyze the spectral reflectance of the surface lithology of the multi-spectral data of the comprehensive mud logging engineering, so as to obtain the spectral reflectance data of the surface lithology;

[0149] In this embodiment, when analyzing the spectral reflectance of the surface lithology of the multi-spectral data of the comprehensive mud logging engineering, a spectral reflectance analysis software is used to compare the reflectance data of each band with a known lithology spectral library. During the analysis process, it is necessary to ensure that the spectral library used covers common rock types in the comprehensive mud logging area, such as sandstone, shale, and limestone. In the spectral reflectance analysis, it depends on key spectral features, such as spectral feature peaks and depressions in the range of 350 - 2500 nanometers, to analyze the reflectance changes. After normalizing the reflectance data, the normalized spectral reflectance value is calculated for each pixel point to ensure that the analysis results can effectively identify the rock types and spatial distributions. Using spectral calculation methods, such as the Spectral Angle Mapper (SAM), the reflectance data is converted into a lithology feature map, and the specific spectral feature peak positions and widths of each lithology category are recorded to generate accurate spectral reflectance data of the surface lithology.

[0150] Step S23: Analyze the surface lithology absorption bands of the comprehensive logging engineering multispectral data to obtain surface lithology absorption band data;

[0151] In this embodiment, when analyzing the surface lithology absorption bands of the comprehensive logging engineering multispectral data, key absorption bands need to be identified, and lithology characteristic absorption peaks need to be extracted, usually in the short-wave infrared band (1000 - 2500 nm). Through the spectral analysis algorithm within the wavelength range, the positions, depths, widths, and other parameters of the characteristic absorption peaks of different minerals are detected, and the absorption bands of iron minerals, carbonates, and clay minerals are identified. The absorption band detection needs to use the curve fitting technology, and the least squares method is used to fit the absorption band curve to improve the detection accuracy. During the detection process, noise removal and spectral smoothing processing need to be ensured to avoid the influence of interfering data on the determination of absorption bands. The absorption band data will be displayed as an absorption coefficient map corresponding to each band, clearly marking the absorption characteristic intervals of each mineral. The generated surface lithology absorption band data includes the specific wavelength positions of the absorption peaks and relevant characteristic information.

[0152] Step S24: Integrate the surface lithology spectral reflectance data and the surface lithology absorption band data to obtain surface lithology data.

[0153] In this embodiment, when integrating the surface lithology spectral reflectance data and the surface lithology absorption band data, the two types of data are combined to generate comprehensive lithology characteristic data. The integration of spectral reflectance and absorption band characteristics needs to use a data fusion algorithm, such as the weighted average method, to ensure the effective combination of different data sources. The data fusion calculation for each pixel point considers the spectral matching degree, and the lithology information with consistent reflectance characteristics and absorption bands is preferentially integrated. A clear threshold is set during the integration process, such as the spectral matching degree > 0.8, to determine whether it belongs to the same lithology. The finally generated surface lithology data should include rock type, main mineral composition, spectral characteristic parameters, and key characteristic descriptions of the absorption bands, which is convenient for subsequent geological analysis and lithology assignment of the 3D model.

[0154] Optionally, step S22 is specifically:

[0155] Step S221: Extract the characteristics of the short-wave infrared band from the comprehensive logging engineering multispectral data to obtain short-wave infrared band data;

[0156] In this embodiment, when extracting the short-wave infrared band characteristics from the multi-spectral data of the comprehensive mud logging project, a spectral processing system is required to separate and extract the data by band. The extraction range is set between 1000 and 2500 nanometers, which covers the key bands of the short-wave infrared. Through spectral correction techniques such as dark current compensation and linear regression smoothing, the original data is preprocessed to eliminate noise and discontinuity points. Then, a band-pass filter is used to separate the spectral characteristics, ensuring that the key mineral absorption characteristics are clearly presented in the short-wave infrared band data. The data extraction needs to be carried out at a fixed spectral resolution, such as a spectral resolution of 10 nanometers, to maintain high-precision analysis. The extracted data is saved as a short-wave infrared band data file, which contains the spectral reflection information of each pixel point for subsequent analysis steps.

[0157] Step S222: Obtain lithologic absorption band data and lithologic spectral data;

[0158] In this embodiment, during the process of obtaining lithologic absorption band data and lithologic spectral data, high-precision spectral analysis software is used to decompose the multi-spectral data and identify the absorption bands therein. First, through the short-wave infrared data, the characteristic absorption bands of minerals are identified, and the parameters of the center position, depth, and width of the absorption bands are extracted. This process applies differential spectral analysis to accurately detect the minimum value and boundaries of the characteristic bands. The acquisition of lithologic spectral data is based on a standardized spectral library, which contains the reflection characteristics of common minerals such as quartz, feldspar, and clay minerals in the mud logging area, with a wavelength range of 350 to 2500 nanometers. By cross-comparing with the lithologic spectral library, the spectral characteristics of the data are verified to ensure the accuracy and effectiveness of the reflectance curve and absorption band information.

[0159] Step S223: Classify the short-wave infrared band data according to the lithologic absorption band data to obtain rock type data;

[0160] In this embodiment, when classifying the short-wave infrared band data according to the lithologic absorption band data, a spectral matching algorithm such as Spectral Angle Mapper (SAM) is required to calculate the matching degree between the spectral feature vectors of each pixel point and the standard lithologic absorption band. The specific operation includes normalizing each spectral vector, and setting the matching threshold to 0.9 to ensure high accuracy in data classification. The rock type classification divides the short-wave infrared data into different lithologic regions, and each region is marked with the corresponding mineral type. The result is output as a rock type data file, which contains a spatial distribution map and the lithologic annotation information of each pixel point, facilitating further lithologic analysis and classification mapping.

[0161] Step S224: Perform spectral matching on the lithologic spectral data with the rock type data to obtain rock spectral matching data;

[0162] In this embodiment, when performing spectral matching on lithologic spectral data with rock type data, a spectral matching algorithm, such as the least squares fitting method, is required to perform pixel-by-pixel comparison on the spectral data. The lithologic spectral data of each pixel point is denoised through spectral smoothing technology and spectral correction is performed to ensure that the input spectral data is consistent with the actual measurement. The matching result is presented in the form of a spectral difference value, and the matching threshold is defined as a spectral error of <5%. The points that meet the matching standard are marked as successfully matched. The matching result generates a rock spectral matching data file, in which each matching pixel is identified as the corresponding lithologic type.

[0163] Step S225: Draw a surface lithology classification map based on the rock spectral matching data for the comprehensive logging engineering area data, so as to obtain a surface lithology classification map;

[0164] In this embodiment, when drawing a surface lithology classification map based on the rock spectral matching data for the comprehensive logging engineering area data, a GIS system is used for spatial data processing. The matching data is input into the GIS platform, and different lithologic categories are marked according to pixel points. Applying a classification algorithm, the spatial data is visualized into a lithology classification map. In the map, rock categories are identified by different colors and legends. For example, red represents sandstone and blue represents shale. Ensure that the resolution is consistent with the sampling points during drawing. For example, use a resolution of 10 meters per pixel to maintain the clarity of details. The boundary and area of each lithologic area in the map are marked through vectorization technology to generate a lithology classification map with spatial reference.

[0165] Step S226: Calculate the spectral reflectance based on the surface lithology classification map, so as to obtain surface lithology spectral reflectance data.

[0166] In this embodiment, when calculating the spectral reflectance based on the surface lithology classification map, it is necessary to extract the average reflectance data for each lithologic area in the classification map. Using a spectral analysis tool, select the spectral reflectance data of each area and perform multiple samplings to ensure the accuracy of the calculation. Set the sampling interval and the number of samples. For example, sample 1000 pixel points in each area, and take the average of the sampling values to calculate the representative spectral reflectance of the area. Record the reflectance results in a spectral reflectance data table, in which each lithologic category is associated with its average reflectance value. This data is used to evaluate the lithologic characteristics and provide accurate spectral information for subsequent analysis.

[0167] Optionally, step S23 is specifically as follows:

[0168] Step S231: Extract the near-infrared band characteristics from the multi-spectral data of the comprehensive logging engineering, so as to obtain near-infrared band data;

[0169] In this embodiment, when extracting the near-infrared band characteristics from the multi-spectral data of the comprehensive logging project, a spectral analysis system is used to divide the data into spectral intervals. The near-infrared band range is set from 700 to 2500 nanometers. Through preprocessing steps such as spectral smoothing and baseline correction, the data quality and continuity are ensured. A spectral denoising algorithm, such as wavelet transform, is adopted to remove interference signals and highlight the target features. The spectral cutting technology is used to separate and extract the spectral data of each pixel. The processed near-infrared band data is stored as a spectral matrix file, which contains the reflectivity information and spatial positions of each sampling point and is used for subsequent analysis steps.

[0170] Step S232: Divide the range of the iron mineral absorption peak for the near-infrared band data to obtain the iron mineral absorption peak range data;

[0171] In this embodiment, when dividing the range of the iron mineral absorption peak for the near-infrared band data, a spectral decomposition technique needs to be applied. The absorption peaks of iron minerals are usually in the range of 850 to 1200 nanometers. The absorption peak range is determined by identifying the local minima and the change points of the curve slope in the spectral curve. A spectral segmentation algorithm, such as polynomial fitting, is used to accurately divide this range. An absorption intensity threshold is set in this process. For example, the points with a reflectivity lower than 15% are used as the preliminary boundary to ensure the accuracy of the range division. The division result is output as the iron mineral absorption peak range data, marking the starting and ending wavelengths of each region and providing a clear iron mineral characteristic range.

[0172] Step S233: Detect the absorption bands for the iron mineral absorption peak range data to obtain the iron mineral absorption band data;

[0173] In this embodiment, when detecting the absorption bands for the iron mineral absorption peak range data, the differential spectroscopy method is used to take the derivative of the spectral curve to identify the depth and position of the absorption bands. By finding the changes in the first derivative and the second derivative of the spectral curve, the central position of the absorption band is determined. A detection sensitivity threshold is set. For example, an absorption band depth greater than 5% is used as the effective detection standard. Noise elimination and correction are performed on the detected absorption band data to ensure data consistency and accuracy. The processing result is saved as an absorption band data file, providing the absorption band parameters of each detection point, including the central wavelength and the characteristic width.

[0174] Step S234: Calculate the absorption peak depth based on the iron mineral absorption band data to obtain the absorption peak depth data;

[0175] In this embodiment, when calculating the absorption peak depth based on the iron mineral absorption band data, the absorption depth algorithm is used to calculate the maximum absorption depth in the spectrum. In the spectral curve, the absorption depth is obtained by fitting its baseline and measuring the vertical distance between the curve and the baseline. A normalization formula is adopted, such as D = 1 - Rmin / Rbase, where Rmin is the lowest reflectivity of the absorption band and Rbase is the baseline reflectivity. The calculation results are stored as an absorption peak depth data table, which contains the depth parameters for each band.

[0176] Step S235: Calculate the absorption peak width based on the iron mineral absorption band data to obtain absorption peak width data;

[0177] In this embodiment, when calculating the absorption peak width based on the iron mineral absorption band data, the wavelength span of the spectral curve needs to be measured. Taking the center of the absorption band as the base point, the wavelength positions with reflectivities close to the baseline on both sides are found to determine the full width at half maximum (FWHM) of the absorption peak. The spectral resolution is set to 10 nanometers to ensure the fineness of the width measurement. The width data is output as an absorption band width data set, marking the start and end wavelengths of each absorption peak and attaching the actually measured width value.

[0178] Step S236: Calculate the iron mineral content based on the absorption peak depth data and the absorption peak width data to obtain iron mineral content data;

[0179] In this embodiment, when calculating the iron mineral content based on the absorption peak depth data and the absorption peak width data, an empirical formula is applied to convert the absorption parameters into mineral content values. The formula is as follows

[0180] C = k × D × W;

[0181] where k is the calibration coefficient, D is the absorption depth, and W is the absorption width. The calibration coefficient k is determined through experimental data, for example, by calibrating with a reference sample with a known iron ore content. The calculation results are stored in an iron mineral content data file, listing the iron mineral content percentages for each measurement point.

[0182] Step S237: Identify the wavelength position based on the iron mineral absorption band data to obtain wavelength position data;

[0183] In this embodiment, when identifying the wavelength position based on the iron mineral absorption band data, a spectral analysis tool is used to detect the center wavelength position of each absorption band. The spectral curve is interpolated to identify the center position with a higher resolution. The calculation error range is set to be less than 0.5 nanometers to ensure the accuracy of the wavelength identification. The wavelength position data is saved as a data table, providing the center wavelength position of the absorption peak and related information for each sampling point, which is convenient for subsequent geological analysis.

[0184] Step S238: Perform surface lithology absorption band feature fusion based on the wavelength position data and the iron mineral content data, so as to obtain the surface lithology absorption band data.

[0185] In this embodiment, when performing surface lithology absorption band feature fusion based on the wavelength position data and the iron mineral content data, the two types of data are integrated through spatial analysis techniques. Through overlay analysis, the wavelength position data and the content data are jointly statistically analyzed to generate an absorption band feature map. This map uses colors and numerical values to identify the iron mineral content and wavelength characteristics at different positions. The fusion process uses spatial statistical tools on the GIS platform, such as Kriging interpolation, to enhance the detail integrity and geological significance of the data fusion. The result generates the surface lithology absorption band data, which includes the characteristics of each absorption band and the distribution of mineral content.

[0186] Optionally, step S4 is specifically as follows:

[0187] Step S41: Obtain the temperature sensing data of the oil and gas reservoir, and draw a temperature gradient map based on the temperature sensing data of the oil and gas reservoir, so as to obtain the temperature gradient map of the oil and gas reservoir;

[0188] In this embodiment, during the process of obtaining the temperature sensing data of the oil and gas reservoir, a temperature sensor array with an accuracy of 0.1 °C is used for multi-point measurement. The sensors are arranged at different depths and positions in the reservoir to ensure comprehensive coverage of the spatial distribution of the data. The data acquisition system transmits the temperature data in real time through optical fiber communication technology. The collected data is subjected to temperature deviation correction and data smoothing processing to remove noise and measurement errors. Based on the processed data, interpolation analysis of the temperature data is performed using GIS software to generate a temperature gradient map, which shows the temperature change trend in the oil and gas reservoir.

[0189] Step S42: Identify the high-temperature regions in the spatial distribution data of the oil and gas reservoir based on the temperature gradient map of the oil and gas reservoir, so as to obtain the spatial distribution data of the high-temperature oil and gas reservoir;

[0190] In this embodiment, when identifying the high-temperature regions in the spatial distribution data of the oil and gas reservoir based on the temperature gradient map, a temperature stratification algorithm is used to partition the temperature changes in the map. A high-temperature threshold is set. For example, the regions above 80 °C are marked as high-temperature regions. Spatial clustering analysis is performed on the regions exceeding the threshold to identify the contours and areas of the high-temperature regions. The clustering results are visualized through the zoning tool on the GIS platform, and the spatial distribution data of the high-temperature oil and gas reservoir containing position and temperature information is output.

[0191] Step S43: Obtain the geological thermal expansion coefficient of the oil and gas reservoir and the temperature reference distribution data of the oil and gas reservoir;

[0192] In this embodiment, when obtaining the geological thermal expansion coefficient and temperature baseline distribution data of the oil and gas reservoir, the thermal expansion coefficient data of the rock samples measured in the laboratory are extracted from the geological exploration report, usually in the unit of 10^-6 / °C. The temperature baseline distribution data are generated from historical measurement data or temperature models of similar reservoirs, indicating the baseline temperature values in different regions of the reservoir. The data format is uniformly a grid table, facilitating the matching with the spatial distribution data in subsequent calculations.

[0193] Step S44: Perform temperature change calculations on the spatial distribution data of the high-temperature oil and gas reservoir according to the temperature baseline distribution data of the oil and gas reservoir, so as to obtain the temperature change data of the oil and gas reservoir;

[0194] In this embodiment, when performing temperature change calculations on the spatial distribution data of the high-temperature oil and gas reservoir according to the temperature baseline distribution data, a point-to-point data comparison method is adopted. The temperature change value within each grid cell is obtained by calculating the difference between the current temperature and the baseline temperature, and the formula is ΔT = Tcurrent - Tbaseline. The data calculations are processed using automated scripts to ensure the calculation efficiency and accuracy when dealing with a large amount of data. The output temperature change data are stored in the form of a chart, providing the spatial location and temperature difference.

[0195] Step S45: Perform thermal strain calculations according to the temperature change data of the oil and gas reservoir and the geological thermal expansion coefficient of the oil and gas reservoir, so as to obtain the thermal strain data of the oil and gas reservoir;

[0196] In this embodiment, when performing thermal strain calculations according to the temperature change data of the oil and gas reservoir and the geological thermal expansion coefficient, the linear thermal strain calculation formula

[0197] ∈ = α × ΔT;

[0198] where α is the thermal expansion coefficient and ΔT is the temperature change. The calculation process uses a scripting language, such as Python, in combination with the NumPy library for large-scale data processing. The strain value of each grid point is output to a matrix to form a thermal strain data map of the reservoir, including the spatial distribution of the strain values.

[0199] Step S46: Identify the stress concentration areas in the thermal strain data of the oil and gas reservoir, so as to obtain the reservoir deformation data;

[0200] In this embodiment, when identifying the stress concentration areas in the thermal strain data of the oil and gas reservoir, stress analysis software is used to identify the high-strain aggregation areas. A determination threshold for the strain concentration degree is set, and areas where the strain value exceeds 2% are marked as stress concentration areas. In the analysis process, the finite element analysis method is combined, and the strain data are input into the stress field calculation module to identify potential stress concentration points and the expansion directions. The output results are displayed in the form of a spatial heat map, indicating the exact locations and intensity distributions of the high-stress areas.

[0201] Step S47: Analyze the stability of the reservoir rock formation based on the reservoir deformation data to obtain the reservoir rock formation stability data.

[0202] In this embodiment, when analyzing the stability of the reservoir rock formation based on the reservoir deformation data, a rock formation instability analysis model is used to calculate the compressive strength and shear strength of the rock formation under stress. The rock physical properties in the geological parameter library, such as Young's modulus and Poisson's ratio, are used for the calculation. The reservoir deformation data is imported into the stability analysis tool to simulate the deformation behavior under high stress conditions. The result analysis outputs the reservoir rock formation stability data, indicating the stability levels of each area to help determine potential instability risks.

[0203] Optionally, step S47 is specifically as follows:

[0204] Step S471: Draw a stress field distribution map based on the reservoir deformation data to obtain the stress field distribution map;

[0205] In this embodiment, during the process of drawing the stress field distribution map based on the reservoir deformation data, a finite element analysis tool is used to calculate and process the reservoir deformation data. The reservoir deformation data is input into the analysis software, and combined with the geological structure characteristics and known boundary conditions, the stress field is simulated and calculated. The principal stress directions and magnitudes in each area are output through the stress calculation module of the software, and the stress field distribution map is drawn in GIS or a professional drawing tool. The stress field distribution map shows the stress intensity and distribution of each area in different colors or contour lines, providing visual stress information to help identify stress concentration points.

[0206] Step S472: Obtain the reservoir rock compressive strength data;

[0207] In this embodiment, when obtaining the reservoir rock compressive strength data, the compressive strength values are extracted from the rock sample data measured in the laboratory. The specific operations include conducting uniaxial compressive tests on different types of rock samples under standard conditions and recording their maximum compressive strengths. The compressive strength data is usually in MPa (megapascals) to ensure accurate identification of the strength data of rocks in different areas. The experimental data is sorted out by the database system and imported into the analysis tool for reference in subsequent steps. If there is historical data, verify its consistency to ensure the accuracy of the analysis.

[0208] Step S473: Calculate the safety factor of the reservoir area based on the reservoir rock compressive strength data and the stress field distribution map to obtain the safety factor of the reservoir area;

[0209] In this embodiment, when calculating the safety factor of the reservoir area based on the reservoir rock compressive strength data and the stress field distribution map, the safety factor calculation formula is used:

[0210]

[0211] Among them, Compressive Strength is the maximum compressive stress that the rock can withstand, and Applied Stress is the stress received by the reservoir under actual conditions, usually provided by the stress field distribution map. The stress field distribution map provides the stress values at each grid position. Combining with the compressive strength data at the corresponding positions, the safety factor of each area is calculated. The calculation process is automated through scripts or analysis programs. The safety factor results are stored as two-dimensional or three-dimensional charts, and the high-risk areas and their safety factor distributions are output to clarify the areas where damage occurs.

[0212] Step S474: Perform a stability assessment on the reservoir deformation data according to the reservoir area safety factor, so as to obtain the reservoir rock layer stability data.

[0213] In this embodiment, when performing a stability assessment on the reservoir deformation data according to the reservoir area safety factor, the reservoir rock layer stability analysis standard is applied. Usually, the areas with a safety factor less than 1.5 are marked as potentially unstable areas. Through the hierarchical processing of the analysis results, the areas within the safety factor range are divided, such as stable, metastable, and unstable areas. The stability assessment is verified by an analysis tool in combination with the historical deformation trend and the current stress state of each area to generate the reservoir rock layer stability data. The output data is provided in the form of visual graphs and reports to ensure the identification of the reservoir areas that need to be focused on and provide a safe rock layer assessment basis for the template recognition welding operation of industrial robots.

[0214] Optionally, this specification also provides a construction system for a comprehensive logging engineering three-dimensional model, which is used to execute a construction method for a comprehensive logging engineering three-dimensional model as described above. The construction system for the comprehensive logging engineering three-dimensional model includes:

[0215] Geological structure analysis module: used to obtain the comprehensive logging engineering monitoring remote sensing data and perform geological structure analysis according to the comprehensive logging engineering monitoring remote sensing data, so as to obtain geological structure data;

[0216] Surface lithology identification module: used to extract the multi-spectral characteristics of the comprehensive logging engineering according to the comprehensive logging engineering monitoring remote sensing data, so as to obtain the comprehensive logging engineering multi-spectral data; perform surface lithology identification according to the comprehensive logging engineering multi-spectral data, so as to obtain surface lithology data;

[0217] Oil and gas reservoir spatial distribution analysis module: used to construct a comprehensive logging engineering three-dimensional model according to the geological structure data and the surface lithology data, so as to obtain the comprehensive logging engineering three-dimensional model; perform oil and gas reservoir spatial distribution analysis according to the comprehensive logging engineering three-dimensional model, so as to obtain oil and gas reservoir spatial distribution data;

[0218] Reservoir Rock Stability Analysis Module: It is used to obtain the temperature sensing data of the oil and gas reservoir, and conduct reservoir deformation analysis on the spatial distribution data of the oil and gas reservoir according to the temperature sensing data of the oil and gas reservoir, so as to obtain reservoir deformation data; conduct reservoir rock stability analysis according to the reservoir deformation data, so as to obtain reservoir rock stability data;

[0219] Comprehensive Logging Three-dimensional Model Path Optimization Module: It is used to design the drilling path according to the reservoir rock stability data, so as to obtain drilling path data; optimize the path of the comprehensive logging engineering three-dimensional model according to the drilling path data, so as to obtain the optimized three-dimensional model of the comprehensive logging engineering, and upload it to the comprehensive logging engineering management platform to execute the model optimization task.

[0220] The construction system of the comprehensive logging engineering three-dimensional model of the present invention can implement any construction method of the comprehensive logging engineering three-dimensional model of the present invention, and is used as a medium for the operation and signal transmission between various modules to complete the construction method of the comprehensive logging engineering three-dimensional model. The internal modules of the system cooperate with each other to build an accurately three-dimensional model with dynamic update, providing comprehensive support for the development and management of oil and gas fields.

[0221] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be included in the present invention.

[0222] The above are only the specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for constructing a three-dimensional model of a comprehensive mud logging project, characterized in that It includes the following steps: Step S1: Obtain remote sensing data for comprehensive mud logging engineering monitoring, and conduct geological structure analysis based on the remote sensing data for comprehensive mud logging engineering monitoring to obtain geological structure data; Step S2: Extract multi-spectral features of the comprehensive mud logging engineering based on the remote sensing data for comprehensive mud logging engineering monitoring to obtain multi-spectral data of the comprehensive mud logging engineering; Identify surface lithology based on the multi-spectral data of the comprehensive mud logging engineering to obtain surface lithology data; Step S3: Construct a 3D model of the comprehensive mud logging engineering based on the geological structure data and the surface lithology data to obtain a 3D model of the comprehensive mud logging engineering; Analyze the spatial distribution of oil and gas reservoirs based on the 3D model of the comprehensive mud logging engineering to obtain spatial distribution data of oil and gas reservoirs; Step S4: Obtain temperature sensing data of the oil and gas reservoir, and conduct reservoir deformation analysis on the spatial distribution data of the oil and gas reservoir based on the temperature sensing data of the oil and gas reservoir to obtain reservoir deformation data; Conduct reservoir rock layer stability analysis based on the reservoir deformation data to obtain reservoir rock layer stability data; Step S5: Design a drilling path based on the reservoir rock layer stability data to obtain drilling path data; Optimize the path of the 3D model of the comprehensive mud logging engineering according to the drilling path data to obtain an optimized 3D model of the comprehensive mud logging engineering, and upload it to the comprehensive mud logging engineering management platform to execute the model optimization task.

2. The construction method of the comprehensive mud logging engineering three-dimensional model according to claim 1, characterized in that Specifically, step S1 is as follows: Step S11: Obtain remote sensing data for comprehensive mud logging engineering monitoring, and extract lidar features based on the remote sensing data for comprehensive mud logging engineering monitoring to obtain lidar data; Step S12: Identify fault structures from the lidar data to obtain fault structure data; Step S13: Identify fold structures from the lidar data to obtain fold structure data; Step S14: Merge the geological structures according to the fault structure data and the fold structure data to obtain geological structure data.

3. The construction method of the comprehensive logging engineering three-dimensional model according to claim 2, characterized in that, Specifically, step S12 is as follows: Step S121: Filter the high reflectivity of the point cloud from the lidar data to obtain filtered point cloud data; Step S122: Generate a digital elevation model based on the filtered point cloud data to obtain a digital elevation model; Step S123: Calculate the surface slope based on the digital elevation model to obtain surface slope data; Step S124: Calculate the surface aspect based on the digital elevation model to obtain surface aspect data; Step S125: Conduct overlay analysis based on the surface slope data and the surface aspect data to obtain data on rapid terrain changes; Step S126: Obtain data on the comprehensive mud logging engineering area; Step S127: Divide the comprehensive mud logging engineering area data according to the data on rapid terrain changes to obtain data on rapidly changing terrain areas; Step S128: Draw a topographic profile based on the digital elevation model to obtain a topographic profile, and identify the fault line area based on the topographic profile to obtain fault line area data; Step S129: Perform an intersection operation on the fault area based on the fractured line area data and the terrain steep area data to obtain the fault area data, and perform a fault dip structure analysis based on the fault area data to obtain the fault structure data.

4. The construction method of the comprehensive logging engineering three-dimensional model according to claim 2, wherein Step S13 is specifically as follows: Step S131: Separate the non-ground point cloud from the lidar data to obtain the ground point cloud data; Step S132: Calculate the surface curvature based on the ground point cloud data to obtain the surface curvature data; Step S133: Perform curvature division based on the surface curvature data to obtain the high-curvature surface data and the low-curvature surface data; Step S134: Identify the syncline area with negative curvature in the high-curvature surface data to obtain the syncline area data; Step S135: Identify the anticline area with positive curvature in the low-curvature surface data to obtain the anticline area data; Step S136: Perform an intersection operation on the fold area based on the syncline area data and the anticline area data to obtain the fold area data; Step S137: Perform a fold axis structure analysis based on the fold area data to obtain the fold structure data.

5. The construction method of the comprehensive mud logging engineering three-dimensional model according to claim 1, characterized in that, Step S2 is specifically as follows: Step S21: Extract the multi-spectral features of the comprehensive mud logging engineering monitoring remote sensing data to obtain the comprehensive mud logging engineering multi-spectral data; Step S22: Analyze the spectral reflectivity of the surface lithology for the comprehensive mud logging engineering multi-spectral data to obtain the surface lithology spectral reflectivity data; Step S23: Analyze the absorption band of the surface lithology for the comprehensive mud logging engineering multi-spectral data to obtain the surface lithology absorption band data; Step S24: Integrate the surface lithology features based on the surface lithology spectral reflectivity data and the surface lithology absorption band data to obtain the surface lithology data.

6. The method for constructing a three-dimensional model of a comprehensive mud logging project according to claim 5, wherein, Step S22 is specifically as follows: Step S221: Extract the features of the short-wave infrared band for the comprehensive mud logging engineering multi-spectral data to obtain the short-wave infrared band data; Step S222: Obtain the lithology absorption band data and the lithology spectral data; Step S223: Classify the rock types for the short-wave infrared band data based on the lithology absorption band data to obtain the rock type data; Step S224: Perform spectral matching on the rock type data with the lithology spectral data to obtain the rock spectral matching data; Step S225: Draw a surface lithology classification map for the comprehensive mud logging engineering area data based on the rock spectral matching data to obtain the surface lithology classification map; Step S226: Calculate the spectral reflectivity based on the surface lithology classification map to obtain the surface lithology spectral reflectivity data.

7. The construction method of the comprehensive mud logging engineering three-dimensional model according to claim 5, characterized in that Step S23 is specifically as follows: Step S231: Extract the features of the near-infrared band for the comprehensive mud logging engineering multi-spectral data to obtain the near-infrared band data; Step S232: Divide the range of the iron mineral absorption peak for the near-infrared band data to obtain the iron mineral absorption peak range data; Step S233: Detect the absorption band for the iron mineral absorption peak range data to obtain the iron mineral absorption band data; Step S234: Calculate the depth of the absorption peak based on the iron mineral absorption band data to obtain the absorption peak depth data; Step S235: Calculate the absorption peak width based on the iron mineral absorption band data, so as to obtain the absorption peak width data; Step S236: Calculate the iron mineral content based on the absorption peak depth data and the absorption peak width data, so as to obtain the iron mineral content data; Step S237: Identify the wavelength position based on the iron mineral absorption band data, so as to obtain the wavelength position data; Step S238: Perform fusion of the surface lithology absorption band characteristics based on the wavelength position data and the iron mineral content data, so as to obtain the surface lithology absorption band data.

8. The method for constructing a three-dimensional model of a comprehensive mud logging project according to claim 1, wherein Step S4 specifically is: Step S41: Obtain the temperature sensing data of the oil and gas reservoir, and draw a temperature gradient map based on the temperature sensing data of the oil and gas reservoir, so as to obtain the temperature gradient map of the oil and gas reservoir; Step S42: Identify the high-temperature area in the spatial distribution data of the oil and gas reservoir according to the temperature gradient map of the oil and gas reservoir, so as to obtain the spatial distribution data of the high-temperature oil and gas reservoir; Step S43: Obtain the geological thermal expansion coefficient of the oil and gas reservoir and the temperature reference distribution data of the oil and gas reservoir; Step S44: Calculate the temperature change of the spatial distribution data of the high-temperature oil and gas reservoir according to the temperature reference distribution data of the oil and gas reservoir, so as to obtain the temperature change data of the oil and gas reservoir; Step S45: Calculate the thermal strain according to the temperature change data of the oil and gas reservoir and the geological thermal expansion coefficient of the oil and gas reservoir, so as to obtain the thermal strain data of the oil and gas reservoir; Step S46: Identify the stress concentration area in the thermal strain data of the oil and gas reservoir, so as to obtain the reservoir deformation data; Step S47: Analyze the stability of the reservoir rock formation according to the reservoir deformation data, so as to obtain the stability data of the reservoir rock formation.

9. The construction method of the comprehensive mud logging engineering three-dimensional model according to claim 8, characterized in that, Step S47 specifically is: Step S471: Draw a stress field distribution map according to the reservoir deformation data, so as to obtain the stress field distribution map; Step S472: Obtain the compressive strength data of the reservoir rock; Step S473: Calculate the safety factor of the reservoir area according to the compressive strength data of the reservoir rock and the stress field distribution map, so as to obtain the safety factor of the reservoir area; Step S474: Evaluate the stability of the reservoir deformation data according to the safety factor of the reservoir area, so as to obtain the stability data of the reservoir rock formation.

10. A construction system for a three-dimensional model of a comprehensive mud logging project, characterized in that, A system for constructing a three-dimensional model of a comprehensive logging project for implementing the method for constructing a three-dimensional model of a comprehensive logging project as described in claim 1, the system for constructing a three-dimensional model of a comprehensive logging project includes: Geological structure analysis module: Used to obtain the monitoring remote sensing data of the comprehensive logging project, and perform geological structure analysis according to the monitoring remote sensing data of the comprehensive logging project, so as to obtain geological structure data; Surface lithology identification module: Used to extract the multi-spectral characteristics of the comprehensive logging project according to the monitoring remote sensing data of the comprehensive logging project, so as to obtain the multi-spectral data of the comprehensive logging project; identify the surface lithology according to the multi-spectral data of the comprehensive logging project, so as to obtain the surface lithology data; Oil and gas reservoir spatial distribution analysis module: Used to construct a three-dimensional model of the comprehensive logging project according to the geological structure data and the surface lithology data, so as to obtain the three-dimensional model of the comprehensive logging project; analyze the spatial distribution of the oil and gas reservoir according to the three-dimensional model of the comprehensive logging project, so as to obtain the spatial distribution data of the oil and gas reservoir; Reservoir rock layer stability analysis module: It is used to obtain the temperature sensing data of the oil and gas reservoir, and conduct reservoir deformation analysis on the spatial distribution data of the oil and gas reservoir according to the temperature sensing data of the oil and gas reservoir, so as to obtain reservoir deformation data; conduct reservoir rock layer stability analysis according to the reservoir deformation data, so as to obtain reservoir rock layer stability data; Comprehensive logging three-dimensional model path optimization module: It is used to design the drilling path according to the reservoir rock layer stability data, so as to obtain drilling path data; optimize the path of the comprehensive logging engineering three-dimensional model according to the drilling path data, so as to obtain the optimized three-dimensional model of the comprehensive logging engineering, and upload it to the comprehensive logging engineering management platform to execute the model optimization task.

Images