A downhole data imaging method and system

Abstract

The present application relates to the field of data processing and imaging technology, and discloses a downhole data imaging method and system, geological parameters and engineering parameters are stored based on information bomb and guided filtering denoising processing is carried out, nonlinear scale space is constructed to enhance the features in the geological parameter and engineering parameter data; the geological parameter and engineering parameter data after feature enhancement are dynamically registered based on grid motion algorithm to filter out effective matching data; the filtered effective matching data are aligned and fused based on affine transformation to generate continuous three-dimensional well trajectory and formation structure image; the generated three-dimensional well trajectory and formation structure image are fused to form fused three-dimensional image data, and the fused three-dimensional image data are analyzed into gray or pseudo-color image for real-time display. The present application can adapt to the complex downhole environment, and can improve the imaging accuracy and real-time performance.

Description

Technical Field

[0001] This invention relates to the field of data processing and imaging technology, and in particular to a downhole data imaging method and system. Background Technology

[0002] Measurement while drilling (MSWL) technology is a core technology for intelligent decision-making in modern oil and gas drilling engineering. Traditional data transmission methods mainly rely on wired or wireless means to transmit downhole data to the surface in real time. However, these methods are limited by severe signal attenuation in complex formations, limited transmission bandwidth, and interference from harsh operating conditions such as high temperature and high pressure, making it difficult to achieve continuous, high-fidelity transmission of large amounts of data, resulting in data loss or distortion.

[0003] To address the aforementioned issues, a bomb-based storage system has been proposed and implemented. This system temporarily stores data downhole by deploying information bombs with built-in storage units, which are then physically retrieved to obtain the data, effectively circumventing the limitations of transmission links. However, the data retrieved and analyzed by such systems is mostly discrete numerical information, lacking intuitive visualization and analysis methods, making it difficult to directly use for rapid on-site decision-making. Furthermore, due to the multi-source nature (including geological parameters, engineering parameters, and trajectory parameters) and dynamic nature of downhole data, existing technologies suffer from low spatiotemporal alignment accuracy when fusing multi-source data for imaging.

[0004] Existing image registration and fusion technologies are mostly designed for static surface images, failing to fully consider the real-time requirements of dynamic downhole data during logging-while-drilling processes, as well as interference from special environments such as strong vibrations, high noise, and high temperatures. This results in insufficient robustness of feature extraction and biased imaging results when these technologies are directly applied, failing to meet the drilling site's needs for high precision, real-time geological guidance, and risk warning.

[0005] Therefore, this application provides a downhole data imaging method to solve the above-mentioned technical problems. Summary of the Invention

[0006] The purpose of this invention is to provide a downhole data imaging method and system to solve the technical problems of existing technologies that cannot adapt to complex downhole environments and have poor imaging accuracy and real-time performance.

[0007] To address the aforementioned technical problems, this invention provides a downhole data imaging method, comprising:

[0008] Responding to geological and engineering parameters acquired during drilling, and stored in a time-division manner based on information bullets, wherein the geological parameters include formation resistivity and gamma value, and the engineering parameters include drilling pressure, torque and vibration data;

[0009] The geological and engineering parameter data retrieved after time-division storage of the information bullet are subjected to guided filtering and noise reduction processing, and a nonlinear scale space is constructed to enhance the features in the geological and engineering parameter data.

[0010] Dynamic registration of feature-enhanced geological and engineering parameter data is performed based on a grid motion statistics algorithm to filter out effective matching data;

[0011] Based on affine transformation, the selected effective matching data are aligned and fused to generate continuous three-dimensional wellbore trajectory and formation structure images;

[0012] The generated 3D wellbore trajectory is fused with the formation structure image to form fused 3D image data, which is then parsed into grayscale or pseudo-color images for real-time display.

[0013] In some specific embodiments, the geological and engineering parameter data retrieved after time-division storage of the information bullets undergoes guided filtering and denoising processing, and a nonlinear scale space is constructed to enhance the features in the geological and engineering parameter data, further including:

[0014] The edge-aware weight adaptive adjustment algorithm based on the DoG operator is used to filter the recovered geological and engineering parameter data, and the filtering weight coefficients are dynamically adjusted according to the data edge gradient information.

[0015] The filtered geological and engineering parameter data are smoothed and enhanced in detail in a nonlinear scale space by using a nonlinear diffusion model. Partial differential equations are used to control the diffusion process to enhance feature significance.

[0016] Suppress noise interference in the geological and engineering parameter data while preserving the corresponding geological structural features and edge information;

[0017] Output enhanced geological and engineering parameter data.

[0018] In some specific embodiments, dynamic registration of feature-enhanced geological and engineering parameter data is performed based on a grid motion statistics algorithm to filter out valid matching data, further including:

[0019] The geological and engineering parameter data with enhanced features at different timestamps are divided into multiple dynamic grids;

[0020] The number of matching features contained in each grid is counted, and the spatiotemporal consistency index is calculated.

[0021] Based on the dynamic consistency threshold set by the false match probability and the average number of feature points in the grid, the matching features in each grid are screened and evaluated.

[0022] Remove incorrect matching data that is below the dynamic consistency threshold, and output the filtered valid matching data.

[0023] In some specific embodiments, the selected valid matching data are aligned and fused based on affine transformation to generate continuous three-dimensional wellbore trajectory and formation structure images, further including:

[0024] An affine transformation is applied to the selected valid matching data to achieve spatiotemporal alignment between data from different sources, resulting in spatiotemporally aligned wellbore trajectory data.

[0025] The spatiotemporally aligned wellbore trajectory data is processed using an interpolation algorithm to generate a continuous three-dimensional wellbore trajectory image.

[0026] The three-dimensional wellbore trajectory image is fused with the stratigraphic structure data extracted from the feature-enhanced geological and engineering parameter data to form a stratigraphic structure image;

[0027] Output the three-dimensional wellbore trajectory and formation structure image.

[0028] In some specific embodiments, the generated three-dimensional wellbore trajectory is fused with the formation structure image to form fused three-dimensional image data, and the fused three-dimensional image data is parsed into grayscale or pseudo-color images for real-time display, further including:

[0029] The three-dimensional wellbore trajectory image is fused with the stratigraphic structure image at the pixel level or feature level to generate fused three-dimensional image data containing comprehensive geological and engineering information.

[0030] The fused 3D image data is mapped into grayscale or pseudocolor images through image analysis to enhance the visual differentiation of different geological interfaces and engineering conditions.

[0031] Real-time display of imaging results, including formation interface changes, drill string vibration status, and drilling risk areas;

[0032] Output optimized imaging results to support drilling decisions.

[0033] In some specific embodiments, the edge-aware weight adaptive adjustment algorithm based on the DoG operator filters the recovered geological and engineering parameter data, and dynamically adjusts the filtering weight coefficients according to the data edge gradient information, further including:

[0034] Extract the edge gradient information from the geological and engineering parameter data, and calculate the gradient magnitude and direction at each location;

[0035] The weight coefficients in the DoG operator are dynamically adjusted based on the edge gradient information to preserve significant edge and structural features while smoothing noise.

[0036] By controlling the scale parameters and diffusion intensity in the filtering process using a partial differential equation diffusion model, adaptive smoothing in nonlinear scale space is achieved.

[0037] Output filtered geological and engineering parameter data.

[0038] In some specific embodiments, based on a dynamic consistency threshold set by the false match probability and the average number of feature points within the grid, the matching features within each grid are screened and evaluated, further including:

[0039] Calculate the dynamic consistency threshold based on the number of matching features within the grid and the probability of incorrect matching;

[0040] Statistical evaluation of matching features within each grid is performed, and consistency index with neighboring grids is calculated.

[0041] Remove matching data that is below the dynamic consistency threshold;

[0042] Output the filtered set of valid matching features.

[0043] Based on the same concept, the present invention also provides a downhole data imaging system, comprising:

[0044] The data acquisition and processing module is configured to respond to geological and engineering parameters acquired during drilling and to perform time-division storage based on information bullets. The geological parameters include formation resistivity and gamma value, and the engineering parameters include drilling pressure, torque and vibration data.

[0045] The denoising and feature enhancement module is configured to perform guided filtering denoising on the geological and engineering parameter data retrieved after time-division storage of the information bullet, and to construct a nonlinear scale space to enhance the features in the geological and engineering parameter data.

[0046] The effective matching data filtering module is configured to dynamically register the feature-enhanced geological parameters and engineering parameters based on the grid motion statistics algorithm in order to filter out effective matching data.

[0047] The alignment and fusion module is configured to align and fuse the selected effective matching data based on affine transformation to generate continuous three-dimensional wellbore trajectory and formation structure images.

[0048] The imaging result output module is configured to fuse the generated three-dimensional wellbore trajectory with the formation structure image to form fused three-dimensional image data, and to parse the fused three-dimensional image data into grayscale or pseudo-color images for real-time display.

[0049] Based on the same concept, the present invention also provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of a downhole data imaging method.

[0050] Based on the same concept, the present invention also provides a computer-readable storage medium, characterized in that it stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a downhole data imaging method.

[0051] Compared with existing technologies, its advantages are as follows:

[0052] This invention discloses a downhole data imaging method and system, achieving high-fidelity downhole imaging with large datasets. By employing drop-type storage and dynamic data registration, it overcomes the bandwidth limitations and signal attenuation problems of traditional wireless transmission, enabling high-fidelity analysis and imaging of large volumes of recovered raw downhole data, realistically reproducing the downhole geological environment and engineering conditions. Imaging accuracy and reliability are improved: a DoG operator-based guided filtering and nonlinear scale space construction method are used to suppress strong downhole noise interference while enhancing and preserving key geological structural features. Dynamic registration is performed using the Grid Motion Statistical Algorithm (GMS) to filter effective matching data, reducing the false matching rate and minimizing the registration error in the final image, resulting in high imaging accuracy and reliability. Data processing and imaging efficiency are improved, enhancing anti-interference capabilities and applicability. Attached Figure Description

[0053] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0054] Figure 1 This is a flowchart illustrating some specific embodiments of a downhole data imaging method of the present invention;

[0055] Figure 2 This is a schematic diagram of the structure of a downhole data imaging system according to some specific embodiments of the present invention;

[0056] Figure 3 This is a schematic diagram of the structure of an electronic device according to some specific embodiments of the present invention;

[0057] In the diagram, 710 is the processor; 720 is the memory; 730 is the input device; and 740 is the output device. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0059] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0060] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0061] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0062] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0063] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0064] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0065] Reference Figure 1 A downhole data imaging method, comprising:

[0066] S101, responding to geological and engineering parameters acquired during drilling and storing them in a time-division manner based on information bullets, wherein the geological parameters include formation resistivity and gamma value, and the engineering parameters include drilling pressure, torque and vibration data;

[0067] S102, the geological and engineering parameter data retrieved after time-division storage of the information bullet are subjected to guided filtering and noise reduction processing, and a nonlinear scale space is constructed to enhance the features in the geological and engineering parameter data;

[0068] S103, based on the grid motion statistics algorithm, dynamically registers the geological parameters and engineering parameters data after feature enhancement in order to filter out the effective matching data;

[0069] S104, Based on affine transformation, the selected effective matching data are aligned and fused to generate a continuous three-dimensional wellbore trajectory and formation structure image;

[0070] S105, the generated three-dimensional wellbore trajectory and formation structure image are fused to form fused three-dimensional image data, and the fused three-dimensional image data is parsed into grayscale or pseudo-color images for real-time display.

[0071] Specifically, in this embodiment of the invention, in response to geological and engineering parameters acquired by downhole sensors during drilling, information bombs in a bomb-type storage system are used for time-division storage. The geological parameters include formation resistivity and gamma values, while the engineering parameters include drilling pressure, torque, and vibration data. The geological and engineering parameter data retrieved from the information bomb storage are subjected to guided filtering for noise reduction. An edge-aware weight adaptive adjustment algorithm based on the DoG operator is used to suppress noise and preserve structural features. A nonlinear scale space is constructed, and a partial differential equation diffusion model is used to achieve multi-scale smoothing and feature enhancement. Based on a grid motion system... The computational method dynamically registers the feature-enhanced data, dividing the data from different timestamps into dynamic grids and counting the number of matching features within each grid. Valid matching data is filtered and false matches are eliminated based on a preset consistency threshold. The valid matching data is spatiotemporally aligned based on affine transformation, and multi-source data is fused using an interpolation algorithm to generate continuous 3D wellbore trajectory and formation structure images. The 3D wellbore trajectory and formation structure images are further fused to form fused 3D image data, and the fused data is mapped to grayscale or pseudo-color images through an image parsing module to achieve real-time display of formation interfaces, drill string status, and risk areas.

[0072] For example, during well drilling, within a depth range of 350 to 355 meters, formation resistivity, gamma ray value, drilling pressure, torque, and triaxial vibration data are acquired at a sampling frequency of 10 / s and stored in an information bomb. After the information bomb is retrieved, the data is guided and filtered. The DoG operator is used with an initial standard deviation of 1 and a diffusion coefficient of 0.5 for nonlinear diffusion and multi-scale feature enhancement. In dynamic registration, the data is divided into 10 dynamic grids, and the number of matching features in each grid is counted. A consistency threshold is set for at least 8 matching points in each grid, and grid data below this threshold are removed. An affine transformation matrix is ​​applied to the effective data for alignment, and a three-dimensional wellbore trajectory is generated through bilinear interpolation, with the trajectory coordinate error controlled within 0.3 mm. Finally, the wellbore trajectory is fused with the formation image to generate a pseudo-color image, in which formation resistivity is represented by a color gradient, and the drill string vibration state is displayed by superimposed dynamic markers. The imaging refresh rate is 5 frames / s, and the image is output to the drilling decision interface in real time.

[0073] In some applications, the geological and engineering parameter data retrieved after time-division storage of the information bullet undergoes guided filtering for denoising. A nonlinear scale space is constructed to enhance the features in the geological and engineering parameter data. This includes filtering the retrieved geological and engineering parameter data using an edge-aware weight adaptive adjustment algorithm based on the DoG operator, dynamically adjusting the filtering weight coefficients according to the data edge gradient information; performing multi-scale smoothing and detail enhancement on the filtered geological and engineering parameter data in the constructed nonlinear scale space using a nonlinear diffusion model, controlling the diffusion process with partial differential equations to enhance feature saliency; suppressing noise interference in the geological and engineering parameter data while preserving corresponding geological structural features and edge information; and outputting the feature-enhanced geological and engineering parameter data.

[0074] Understandably, when performing guided filtering denoising on the geological and engineering parameter data retrieved after time-division storage of the information bullet, an edge-aware weight adaptive adjustment algorithm based on the DoG operator is used to filter the retrieved geological and engineering parameter data. The filtering weight coefficients are dynamically adjusted according to the data edge gradient information to preserve edge features while smoothing noise. Multi-scale smoothing and detail enhancement of the filtered geological and engineering parameter data are performed in a constructed nonlinear scale space through a nonlinear diffusion model. Partial differential equations are used to control the intensity and direction of the diffusion process to enhance feature saliency and suppress noise interference. Under the premise of effectively preserving the corresponding geological structural features and edge information, the feature-enhanced geological and engineering parameter data are output for subsequent registration and fusion processing.

[0075] For example, guided filtering denoising was performed on the formation resistivity and drilling pressure data of the well section with a depth of 350 to 355 meters from the information missile recovery depth. The standard deviation of the Gaussian kernel in the DoG operator was set to 1.0, and the edge gradient threshold was set to 0.5. The filtering weights of each data point were dynamically adjusted accordingly. In the nonlinear diffusion process, the diffusion coefficient of the partial differential equation was set to 0.8, the number of iterations was 10, and the number of scale space layers was set to 4. Multi-scale enhancement was performed on the filtered data. After processing, the noise variance of the formation resistivity data was reduced to 20% of the original data, while the edge gradient value retention rate of the geological interface reached more than 90%. The output feature enhancement data was used for subsequent dynamic grid registration.

[0076] In some applications, a grid motion statistical algorithm is used to dynamically register feature-enhanced geological and engineering parameter data to filter out effective matching data. This includes dividing feature-enhanced geological and engineering parameter data with different timestamps into multiple dynamic grids; counting the number of matching features contained in each grid and calculating a spatiotemporal consistency index; filtering and evaluating matching features in each grid based on a dynamic consistency threshold set by the false matching probability and the average number of feature points in the grid; removing false matching data below the dynamic consistency threshold; and outputting the filtered effective matching data.

[0077] Understandably, the enhanced geological and engineering parameter data with different timestamps are divided into multiple dynamic grid cells; the number of matching features contained in each grid cell is counted, and its spatiotemporal consistency index is calculated; then, based on the dynamic consistency threshold set by the false matching probability and the average number of feature points in the grid, the reliability of the matching features in each grid cell is screened and evaluated; false matching data below the dynamic consistency threshold is removed, and the screened valid matching data is output for subsequent image fusion processing.

[0078] For example, dynamic registration was performed on the gamma values ​​and vibration data of the well section at a depth of 350m to 355m after feature enhancement. The data was divided into 10×10 dynamic grids, with each grid cell containing an average of 12 feature points within a 5s time window. The false matching probability α was set to 0.05, and the dynamic consistency threshold was calculated according to the formula T=μ-2σ (where μ is the average number of feature points in the grid, which is 12, and σ is the standard deviation, which is 2), resulting in a threshold T=8. The actual number of matching features in each grid was counted, and grid cells with fewer than 8 features were removed. After screening, the proportion of effective matching data increased from 85% to 95% of the original data, and the effective matching data was output for subsequent affine transformation fusion processing.

[0079] In some applications, the selected effective matching data are aligned and fused based on affine transformation to generate continuous three-dimensional wellbore trajectory and formation structure images. This includes applying an affine transformation to the selected effective matching data to achieve spatiotemporal alignment between data from different sources, obtaining spatiotemporally aligned wellbore trajectory data; processing the spatiotemporally aligned wellbore trajectory data based on an interpolation algorithm to generate continuous three-dimensional wellbore trajectory images; fusing the three-dimensional wellbore trajectory images with formation structure data extracted from feature-enhanced geological and engineering parameter data to form a formation structure image; and outputting the three-dimensional wellbore trajectory and formation structure images.

[0080] Understandably, an affine transformation model is applied to the selected valid matching data, and spatiotemporal alignment between data from different sources is achieved through rotation, translation, and scaling operations to obtain spatiotemporally aligned wellbore trajectory data. The spatiotemporally aligned wellbore trajectory data is then processed using an interpolation algorithm to fill data gaps and generate a continuous and smooth three-dimensional wellbore trajectory image. This three-dimensional wellbore trajectory image is then fused pixel-level with formation structure data extracted from feature-enhanced geological and engineering parameter data to enhance the expression of the relative spatial relationship between the wellbore and the formation, forming a complete formation structure image. Finally, a fused image containing both three-dimensional wellbore trajectory and formation structure information is output for real-time display and decision analysis.

[0081] For example, an affine transformation is applied to the effective matching data selected from well sections with depths of 350m to 355m. The transformation matrix includes a rotation angle of 2.5°, an X-axis translation of 0.3m, a Y-axis translation of 0.2m, and a scaling factor of 1.05. After alignment, the wellbore trajectory data is processed using a cubic spline interpolation algorithm to generate a continuous trajectory with a point spacing of 0.1m. The trajectory data is then fused with formation interface data extracted from gamma data. The gamma value threshold is set to 120 API, and areas above the threshold are identified as sandstone formations. The fused image has a resolution of 0.1m × 0.1m, and the positioning error between the wellbore trajectory and the formation interface is less than 0.3mm. The output image is transmitted to the decision-making system in real time.

[0082] In some applications, the generated 3D wellbore trajectory and formation structure image are fused to form fused 3D image data. This fused 3D image data is then parsed into grayscale or pseudo-color images for real-time display. This includes pixel-level or feature-level fusion of the 3D wellbore trajectory image and formation structure image to generate fused 3D image data containing comprehensive geological and engineering information; mapping the fused 3D image data into grayscale or pseudo-color images through image parsing to enhance the visualization and differentiation of different geological interfaces and engineering conditions; real-time display of imaging results, including formation interface changes, drill string vibration status, and drilling risk areas; and outputting optimized imaging results to support drilling decisions.

[0083] Understandably, the process involves pixel-level or feature-level fusion of 3D wellbore trajectory images and formation structure images. By overlaying wellbore spatial location and formation attribute information, a fused 3D image data containing comprehensive geological and engineering information is generated. Image parsing processing maps this fused 3D image data into grayscale or pseudo-color images. Grayscale values ​​or color codes are assigned based on the differences in physical parameters of different geological bodies and engineering condition characteristics to enhance the visual differentiation of different geological interfaces and engineering conditions. The imaging results are then displayed in real time, including the characteristics of formation lithological interface changes, the amplitude and frequency distribution of drill string vibration, and the spatial location of drilling risk areas. The optimized imaging results are output to provide decision support for drilling parameter adjustment and risk control.

[0084] For example, feature-level fusion is performed on the 3D wellbore trajectory image and formation structure image in the 350m to 355m depth range. The trajectory data uses a 0.1m×0.1m grid precision, and the formation gamma data uses 120API as the lithological boundary threshold. The fused data is processed by a color mapping module, setting the area with a gamma value greater than 120API to represent sandstone formations in red and the area with a gamma value less than 120API to represent mudstone formations in blue. The drill string vibration amplitude is mapped to a green to yellow gradient according to the acceleration data in the range of 0-5g. The imaging refresh rate is 5 frames / s. The real-time display interface can clearly identify the abnormal drill string vibration area (vibration value up to 4.2g) at a depth of 352.4m and the abrupt change position of the formation interface at 353.1m. The imaging results are output to the drilling decision system for real-time optimization of drilling pressure parameters.

[0085] In some applications, an edge-aware weight adaptive adjustment algorithm based on the DoG operator is used to filter the recovered geological and engineering parameter data. The filtering weight coefficients are dynamically adjusted according to the data edge gradient information. This includes extracting the edge gradient information of the geological and engineering parameter data and calculating the gradient magnitude and direction at each location; dynamically adjusting the weight coefficients in the DoG operator based on the edge gradient information to preserve significant edge and structural features while smoothing noise; controlling the scale parameters and diffusion intensity during the filtering process using a partial differential equation diffusion model to achieve adaptive smoothing in a nonlinear scale space; and outputting the filtered geological and engineering parameter data.

[0086] Understandably, the process involves extracting edge gradient information from the geological and engineering parameter data, calculating the gradient magnitude and direction characteristics of each data point using a gradient operator, dynamically adjusting the weight coefficients in the DoG operator based on the edge gradient information, reducing the smoothing intensity in edge regions to preserve significant edge and structural features, and enhancing the smoothing effect in flat regions to effectively suppress noise. A partial differential equation diffusion model controls the scale parameters and diffusion intensity during the filtering process, adaptively adjusting the diffusion process based on local gradient characteristics to achieve multi-scale adaptive smoothing in a nonlinear scale space. The output is filtered geological and engineering parameter data with well-preserved edge features and effectively suppressed noise.

[0087] For example, the DoG operator was used to filter the formation resistivity data from the 350m to 355m depth section of the well where the information missile was recovered. The gradient magnitude of each data point was calculated, and a gradient magnitude threshold of 0.5 was set. The gradient direction was divided into 8 intervals. The DoG weight coefficients were dynamically adjusted according to the gradient magnitude. The weight coefficients were set to 0.2 in the edge regions where the gradient magnitude was greater than 0.5, and to 0.8 in the flat regions. The diffusion process was controlled by a partial differential equation diffusion model with a diffusion coefficient of 0.8, 10 iterations, and the scale parameter gradually increased from 1.0 to 2.5. After processing, the standard deviation of the data noise was reduced from the original 15.2 Ω·m to 3.1 Ω·m, and the edge feature retention rate reached 92%. The filtered and optimized resistivity data was output for subsequent feature enhancement processing.

[0088] In some applications, a dynamic consistency threshold is set based on the false match probability and the average number of feature points in the grid. The matching features in each grid are then screened and evaluated. This includes calculating the dynamic consistency threshold based on the number of matching features in the grid and the false match probability; statistically evaluating the matching features in each grid and calculating the consistency index with adjacent grids; removing matching data that are below the dynamic consistency threshold; and outputting the filtered set of valid matching features.

[0089] Understandably, a dynamic consistency threshold is calculated based on the number of matching features within the grid and the preset false matching probability to establish a matching reliability evaluation standard; the matching features within each grid cell are statistically evaluated, and their consistency index with adjacent grid cells is calculated to analyze spatial correlation; then the evaluation results are compared with the dynamic consistency threshold, and false matching data below the threshold are removed, while matching features that meet the reliability requirements are retained; the filtered effective matching feature set is output for subsequent data fusion and imaging processing.

[0090] A dynamic consistency threshold is set based on the false match probability and the average number of feature points within the grid. Specifically, the standard deviation (σ) of the number of feature points in each grid is used to quantify the data dispersion, thus reflecting the uncertainty of the matching results. The threshold is set using the empirical formula T = μ - kσ (k = 2 in this embodiment). This formula effectively controls the false match probability (α) at ​​a low level because grids with significantly fewer feature points than the average (below μ - 2σ) have a higher statistical probability of false matches. Therefore, the false match probability is the design objective to be controlled, and the standard deviation is a direct calculation parameter for achieving this objective.

[0091] Another embodiment of the present invention is described below:

[0092] This embodiment acquires geological parameters (such as formation resistivity and gamma value), engineering parameters (drilling pressure, torque, vibration), and wellbore trajectory data through downhole sensors. Data is periodically stored using a bomb-type storage system with built-in high-temperature resistant memory (such as NOR Flash) and a wireless transmission module (BLE / NFC), supporting time-division multiplexing of downhole data writing and surface retrieval and parsing. The retrieved discrete data undergoes guided filtering for noise reduction, employing a DoG operator-based edge-aware weight adaptive adjustment algorithm to suppress noise and preserve geological structural features. A nonlinear scale space is constructed, and a partial differential equation diffusion model enhances data details. Based on the Grid Motion Statistics (GMS) algorithm, downhole data with different timestamps are divided into dynamic grids, and the spatiotemporal consistency of data within the grids is statistically analyzed. An affine transformation model is used to align multi-source data, and an interpolation algorithm is combined to generate continuous three-dimensional wellbore trajectory and formation structure images. The "Jianghai Intelligent Drilling Decision System" analyzes the registered data into grayscale / pseudocolor images, displaying the formation interface, drill string status, and risk areas in real time. The Adaboost algorithm is introduced to optimize feature matching weights, improving imaging resolution and anti-interference capabilities.

[0093] For the purpose of simplicity, the method steps disclosed in the above embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0094] like Figure 2 As shown, the present invention also provides a downhole data imaging system, comprising:

[0095] The data acquisition and processing module 201 is configured to respond to geological parameters and engineering parameters acquired during drilling and to perform time-division storage based on information bullets. The geological parameters include formation resistivity and gamma value, and the engineering parameters include drilling pressure, torque and vibration data.

[0096] The denoising and feature enhancement module 202 is configured to perform guided filtering denoising on the geological and engineering parameter data retrieved after time-division storage of the information bullet, and to construct a nonlinear scale space to enhance the features in the geological and engineering parameter data.

[0097] The effective matching data filtering module 203 is configured to dynamically register the geological parameters and engineering parameters data after feature enhancement based on the grid motion statistics algorithm in order to filter out effective matching data.

[0098] The alignment and fusion module 204 is configured to align and fuse the selected effective matching data based on affine transformation to generate a continuous three-dimensional wellbore trajectory and formation structure image.

[0099] The imaging result output module 205 is configured to fuse the generated three-dimensional wellbore trajectory and formation structure image to form fused three-dimensional image data, and to parse the fused three-dimensional image data into grayscale or pseudo-color images for real-time display.

[0100] It is worth noting that although only some basic functional modules are disclosed in the embodiments of this invention, it does not mean that the composition of this system is limited to the above-mentioned basic functional modules. On the contrary, what this embodiment intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with existing technology to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. The fact that this embodiment only discloses a few basic functional modules should not be considered as the scope of protection of the claims of this invention being limited to the disclosed basic functional modules. At the same time, for the convenience of description, the above device is described separately according to its functions as various units and modules. Of course, in implementing this invention, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0101] like Figure 3 As shown, the present invention also provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of a downhole data imaging method.

[0102] Figure 3This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. For example... Figure 3 The structure shown in this embodiment of the invention includes an electronic device comprising one or more processors 710 and a memory 720; the processors 710 in this electronic device may be one or more. Figure 3 Taking a processor 710 as an example; a memory 720 is used to store one or more programs; the one or more programs are executed by the one or more processors 710, so that the one or more processors 710 implement a downhole data imaging method as described in any one of the embodiments of the present invention.

[0103] The electronic device may also include an input device 730 and an output device 740.

[0104] The processor 710, memory 720, input device 730, and output device 740 in this electronic device can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0105] The memory 720 in this electronic device serves as a computer-readable storage medium, capable of storing one or more programs. These programs can be software programs, computer-executable programs, or modules, such as the program instructions / modules corresponding to the downhole data imaging method provided in this embodiment of the invention. The processor 710 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 720, thereby implementing the downhole data imaging method described in the above embodiment.

[0106] The memory 720 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device. Furthermore, the memory 720 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 720 may further include memory remotely located relative to the processor 710, which can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0107] Input device 730 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the electronic device. Output device 740 may include display devices such as a display screen.

[0108] The present invention also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a downhole data imaging method.

[0109] Specifically, the computer storage medium in this embodiment of the invention can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be—but is not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A downhole data imaging method, characterized in that, include: Responding to geological and engineering parameters acquired during drilling, and stored in a time-division manner based on information bullets, wherein the geological parameters include formation resistivity and gamma value, and the engineering parameters include drilling pressure, torque and vibration data; The geological and engineering parameter data retrieved after time-division storage of the information bullet are subjected to guided filtering and noise reduction processing, and a nonlinear scale space is constructed to enhance the features in the geological and engineering parameter data. Dynamic registration of feature-enhanced geological and engineering parameter data is performed based on a grid motion statistics algorithm to filter out effective matching data; Based on affine transformation, the selected effective matching data are aligned and fused to generate continuous three-dimensional wellbore trajectory and formation structure images; The generated three-dimensional wellbore trajectory and formation structure image are fused to form fused three-dimensional image data, and the fused three-dimensional image data is parsed into grayscale or pseudo-color images for real-time display. Among them, an affine transformation is applied to the selected valid matching data to achieve spatiotemporal alignment between data from different sources, resulting in spatiotemporally aligned wellbore trajectory data. The spatiotemporally aligned wellbore trajectory data is processed using an interpolation algorithm to generate a continuous three-dimensional wellbore trajectory image. The three-dimensional wellbore trajectory image is fused with the stratigraphic structure data extracted from the feature-enhanced geological and engineering parameter data to form a stratigraphic structure image; Output the three-dimensional wellbore trajectory and formation structure image.

2. The downhole data imaging method according to claim 1, characterized in that, The geological and engineering parameter data retrieved after time-division storage of the information bullets are subjected to guided filtering and denoising processing, and a nonlinear scale space is constructed to enhance the features in the geological and engineering parameter data, further including: The edge-aware weight adaptive adjustment algorithm based on the DoG operator is used to filter the recovered geological and engineering parameter data, and the filtering weight coefficients are dynamically adjusted according to the data edge gradient information. The filtered geological and engineering parameter data are smoothed and enhanced in detail in a nonlinear scale space by using a nonlinear diffusion model. Partial differential equations are used to control the diffusion process to enhance feature significance. Suppress noise interference in the geological and engineering parameter data while preserving the corresponding geological structural features and edge information; Output enhanced geological and engineering parameter data.

3. The downhole data imaging method according to claim 1, characterized in that, Dynamic registration of feature-enhanced geological and engineering parameter data based on a grid motion statistics algorithm is performed to filter out effective matching data, further including: The geological and engineering parameter data with enhanced features at different timestamps are divided into multiple dynamic grids; The number of matching features contained in each grid is counted, and the spatiotemporal consistency index is calculated. Based on the dynamic consistency threshold set by the false match probability and the average number of feature points in the grid, the matching features in each grid are screened and evaluated. Remove incorrect matching data that is below the dynamic consistency threshold, and output the filtered valid matching data.

4. The downhole data imaging method according to claim 1, characterized in that, The generated 3D wellbore trajectory is fused with the formation structure image to form fused 3D image data. This fused 3D image data is then parsed into grayscale or pseudo-color images for real-time display. Further steps include: The three-dimensional wellbore trajectory image is fused with the stratigraphic structure image at the pixel level or feature level to generate fused three-dimensional image data containing comprehensive geological and engineering information. The fused 3D image data is mapped into grayscale or pseudocolor images through image analysis to enhance the visual differentiation of different geological interfaces and engineering conditions. Real-time display of imaging results, including formation interface changes, drill string vibration status, and drilling risk areas; Output optimized imaging results to support drilling decisions.

5. A downhole data imaging method according to claim 2, characterized in that, The edge-aware weight adaptive adjustment algorithm based on the DoG operator filters the recovered geological and engineering parameter data, and dynamically adjusts the filtering weight coefficients according to the data edge gradient information, further including: Extract the edge gradient information from the geological and engineering parameter data, and calculate the gradient magnitude and direction at each location; The weight coefficients in the DoG operator are dynamically adjusted based on the edge gradient information to preserve significant edge and structural features while smoothing noise. By controlling the scale parameters and diffusion intensity in the filtering process using a partial differential equation diffusion model, adaptive smoothing in nonlinear scale space is achieved. Output filtered geological and engineering parameter data.

6. The downhole data imaging method according to claim 3, characterized in that, Based on a dynamic consistency threshold set using the false match probability and the average number of feature points within a grid, the matching features within each grid are screened and evaluated, further including: Calculate the dynamic consistency threshold based on the number of matching features within the grid and the probability of incorrect matching; Statistical evaluation of matching features within each grid is performed, and consistency index with neighboring grids is calculated. Remove matching data that is below the dynamic consistency threshold; Output the filtered set of valid matching features.

7. A downhole data imaging system, used in the downhole data imaging method of claim 1, characterized in that, include: The data acquisition and processing module is configured to respond to geological and engineering parameters acquired during drilling and to perform time-division storage based on information bullets. The geological parameters include formation resistivity and gamma value, and the engineering parameters include drilling pressure, torque and vibration data. The denoising and feature enhancement module is configured to perform guided filtering denoising on the geological and engineering parameter data retrieved after time-division storage of the information bullet, and to construct a nonlinear scale space to enhance the features in the geological and engineering parameter data. The effective matching data filtering module is configured to dynamically register the feature-enhanced geological parameters and engineering parameters based on the grid motion statistics algorithm in order to filter out effective matching data. The alignment and fusion module is configured to align and fuse the selected effective matching data based on affine transformation to generate continuous three-dimensional wellbore trajectory and formation structure images. The imaging result output module is configured to fuse the generated three-dimensional wellbore trajectory with the formation structure image to form fused three-dimensional image data, and to parse the fused three-dimensional image data into grayscale or pseudo-color images for real-time display.

8. An electronic device, characterized in that, include: The system includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; the memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the method according to any one of claims 1 to 6.

Images