An integrated oil and gas field modeling method and system based on intelligent algorithms

Abstract

This invention relates to the field of oilfield modeling technology, specifically a method and system for integrated oil and gas field modeling based on intelligent algorithms. The method includes: determining the oilfield region to be modeled; dividing the oilfield region into grids to obtain an original oilfield grid set; collecting oilfield data from the original grid set to obtain an original oilfield feature dataset; obtaining an original oilfield feature vector set based on the original feature dataset; clustering the original oilfield grid set into clustered oilfield regions based on the original feature vector set; correcting the number of oil wells in the clustered oilfield regions to obtain a corrected oilfield region set; and modeling independent regions based on the corrected oilfield region set to obtain an integrated model of the target oilfield. This invention can improve the accuracy of modeling non-uniform oilfields and reduce deviations during the modeling process.

Description

Technical Field

[0001] This invention relates to the field of oilfield modeling technology, and in particular to an integrated oil and gas field modeling method and system based on intelligent algorithms. Background Technology

[0002] Oil and gas field underground reservoirs have strong spatial heterogeneity. Their structure, sedimentation, and physical properties are often complex and varied in both horizontal and vertical directions. This heterogeneity is a key geological factor controlling the distribution of oil and gas and fluid seepage. Therefore, the ability to accurately and precisely characterize this heterogeneous pattern is the core prerequisite and fundamental challenge for building high-precision oil and gas reservoir geological models and realizing efficient exploration and development decisions.

[0003] Traditional techniques typically treat the entire oilfield area to be modeled as a homogeneous or simply partitioned whole, using a unified model and parameters for integrated modeling. This approach cannot effectively identify and adapt to the complex geological heterogeneity within the oilfield. Using a single variation function or modeling algorithm can severely smooth or distort the actual attribute distribution of different geological feature areas, resulting in significant deviations between the constructed model and the actual situation in some areas, and insufficient overall model accuracy and geological reliability. Summary of the Invention

[0004] This invention provides an integrated oil and gas field modeling method based on intelligent algorithms and a computer-readable storage medium. Its main purpose is to improve the accuracy of modeling non-uniform oil fields and reduce deviations in the modeling process.

[0005] To achieve the above objectives, this invention provides an integrated oil and gas field modeling method based on intelligent algorithms, comprising: The oilfield area to be modeled is determined, and the oilfield area to be modeled is divided into grids to obtain the original oilfield grid set, which includes multiple original oilfield grids. Oilfield data was collected for each original oilfield grid in the original oilfield grid set to obtain the original oilfield feature dataset; Original oilfield feature data are extracted sequentially from the original oilfield feature dataset. Based on the extracted original oilfield feature data, feature extraction is performed to obtain the original oilfield feature vector. The original oilfield feature vectors are summarized to obtain the original oilfield feature vector set. Based on the original oilfield feature vector set, the original oilfield grid set is clustered by proximity to obtain the clustered oilfield region set. The number of oil wells in the clustered oilfield region set is corrected to obtain the corrected oilfield region set; Independent regional modeling is performed based on the modified oilfield region set to obtain the target oilfield integrated model, thus completing the integrated oil and gas field modeling based on intelligent algorithms.

[0006] Optionally, the step of extracting features based on the extracted original oilfield feature data to obtain the original oilfield feature vector includes: Identify the categorical attribute data in the extracted raw oilfield feature data, perform one-hot encoding on the categorical attribute data, and obtain the categorical attribute code; Identify the geological attribute data in the extracted raw oilfield feature data, normalize the geological attribute data to obtain geologically normalized data, and generate geological feature vectors based on the geologically normalized data; Identify image feature data in the extracted raw oilfield feature data, and construct oilfield image feature vectors based on the image feature data; The original oilfield feature vector is constructed based on classification attribute encoding, geological feature vector, and oilfield image feature vector.

[0007] Optionally, before identifying the image feature data in the extracted raw oilfield feature data, the method further includes: The original oilfield image is acquired, and a low-pass filter is applied to the original oilfield image to obtain the original filtered oilfield image. The original filtered oilfield image is downsampled to obtain a low-resolution oilfield image; Construct multiple base filters, each corresponding to a different filtering angle; The base filters are extracted sequentially from multiple base filters, and the extracted base filters are used to perform directional filtering on the low-resolution oilfield image to obtain a unidirectional filtered image. By summing the unidirectional filtered images corresponding to each base filter, multiple unidirectional filtered images are obtained. Multiple unidirectional filtered images are fused to obtain a fused filtered oilfield image; Get the current downsampling quantity. If the current downsampling quantity is less than the preset standard downsampling quantity, use the fused filtered oilfield image as the original filtered oilfield image and return to the step of downsampling the original filtered oilfield image until the current downsampling quantity is not less than the standard downsampling quantity. If the current downsampling quantity is not less than the standard downsampling quantity, then the fused filtered oilfield images are summarized to obtain a fused filtered oilfield image set; Image reconstruction is performed based on a fused filtered oilfield image set to obtain a reconstructed filtered image. Feature extraction is then performed on the reconstructed filtered image to obtain image feature data.

[0008] Optionally, fusing multiple unidirectional filtered images to obtain a fused filtered oilfield image includes: For each of the multiple unidirectional filtered images, perform the following operation: Identify the set of filtered pixels in the unidirectional filtered image, wherein the set of filtered pixels includes multiple filtered pixels; Energy is calculated for each filtered pixel in the set of filtered pixels to obtain a set of pixel energy values; The directional pixel energy value is obtained by averaging the pixel energy value set. Summarize the directional pixel energy values ​​corresponding to each unidirectional filtered image to obtain a set of directional pixel energy values; Generate directional pixel energy vectors based on directional pixel energy value sets; The directional pixel energy vector is weighted by a preset scaling function to obtain a directional weight vector. The directional weight vector includes multiple directional weights, and each directional weight corresponds one-to-one with a single-directional filtered image. Multiple unidirectional filtered images are weighted and fused using directional weight vectors to obtain a fused filtered oilfield image.

[0009] Optionally, the step of correcting the number of oil wells in the clustered oilfield region set to obtain a corrected oilfield region set includes: In the clustered oilfield regions, the clustered oilfield regions are extracted sequentially, and the extracted clustered oilfield regions are recorded as the oilfield regions to be corrected. Obtain the number of regional oil wells in the oilfield area to be corrected; Based on the number of oil wells in a region, the regions of oilfields to be modified are merged to obtain the target oilfield region; The clustered oilfield region set is updated using the target oilfield region to obtain the updated oilfield region set; The updated oilfield region set is used as the clustered oilfield region set, and the step of sequentially extracting clustered oilfield regions in the clustered oilfield region set is returned until all clustered oilfield regions in the clustered oilfield region set have been extracted. The updated oilfield region set after all clustered oilfield regions have been extracted is denoted as the corrected oilfield region set.

[0010] Optionally, the step of merging the oilfield regions to be modified based on the number of regional oil wells to obtain the target oilfield region includes: If the number of oil wells in a region is less than the preset dynamic number threshold, then multiple adjacent oil field regions of the oil field region to be corrected are identified in the clustered oil field region. Based on the oilfield region to be corrected, multiple adjacent oilfield regions are identified as merging regions to obtain the oilfield region to be merged. The oilfield area to be corrected is merged into the oilfield area to be integrated to obtain the target oilfield area; If the number of oil wells in a region is not less than the dynamic quantity threshold, then the oilfield region to be corrected is recorded as the target oilfield region.

[0011] Optionally, the step of identifying mergingable regions among multiple adjacent oilfield regions based on the oilfield region to be corrected, to obtain the oilfield region to be merged, includes: Obtain the number of oil wells to be corrected and the feature vector set of the grid to be corrected in the oilfield area to be corrected; The oilfield grid to be corrected is determined by identifying the oilfield grid to be corrected corresponding to each feature vector in the feature vector set of the grid to be corrected; Statistically determine the oilfield area set corresponding to the grid set of oilfields to be corrected; The feature vector of the region to be corrected is obtained by weighted fusion of the feature vector set of the grid to be corrected using the set of oilfield areas to be corrected. In multiple adjacent oilfield regions, adjacent oilfield regions are extracted sequentially to obtain the number of adjacent oil wells and the feature vector of the adjacent region in the extracted adjacent oilfield regions; The region fusion degree is calculated based on the number of adjacent oil wells, the feature vector of adjacent regions, the number of oil wells to be corrected, and the feature vector of regions to be corrected. By summing the regional integration degree corresponding to each adjacent oilfield region, multiple regional integration degrees are obtained; Identify the maximum degree of integration among multiple regions and record the adjacent oilfield region corresponding to the maximum degree of integration as the oilfield region to be integrated.

[0012] Optionally, the step of weightedly fusing the feature vector set of the grid to be corrected from the set of oilfield areas to be corrected to obtain the feature vector of the region to be corrected includes: The feature vector of the region to be corrected is calculated using the following formula:

[0013] in, This represents the feature vector of the region to be corrected. This indicates the number of oilfield areas requiring correction. and These represent the concentrated areas of the oilfields to be corrected. The area of ​​the oilfield to be revised and the first Area of ​​oil fields to be revised. Represents the first element in the set of eigenvectors of the grid to be corrected. One grid feature vector to be corrected.

[0014] Optionally, the step of performing independent region modeling based on the modified oilfield region set to obtain the target oilfield integrated model includes: For each corrected oilfield region in the corrected oilfield region cluster, the following operations shall be performed: Modeling data was collected for the Xiuzheng oilfield area to obtain Xiuzheng oilfield modeling data; Oilfield modeling is performed using a preset standard oilfield model template and corrected oilfield modeling data to obtain a target oilfield area model; The target oilfield region models corresponding to each modified oilfield region are summarized to obtain the target oilfield region model set; Model integration is performed based on the target oilfield regional model set to obtain the target oilfield integrated model.

[0015] To achieve the above objectives, the present invention also provides an integrated oil and gas field modeling system based on intelligent algorithms, comprising: The oilfield region division module is used to determine the oilfield region to be modeled, divide the oilfield region to be modeled into grids, and obtain the original oilfield grid set, which includes multiple original oilfield grids. The oilfield feature extraction module is used to collect oilfield data for each original oilfield grid in the original oilfield grid set to obtain the original oilfield feature dataset. The original oilfield feature data is extracted sequentially from the original oilfield feature dataset, and feature extraction is performed based on the extracted original oilfield feature data to obtain the original oilfield feature vector. The oilfield data clustering module is used to summarize the original oilfield feature vectors to obtain the original oilfield feature vector set. Based on the original oilfield feature vector set, the original oilfield grid set is clustered by proximity to obtain the clustered oilfield region set. The oilfield region integration module is used to correct the number of oil wells in the clustered oilfield region set to obtain the corrected oilfield region set. Based on the corrected oilfield region set, independent region modeling is performed to obtain the target oilfield integrated model.

[0016] To address the above problems, the present invention also provides an electronic device, the electronic device comprising: Memory, storing at least one instruction; The processor executes the instructions stored in the memory to implement the intelligent algorithm-based integrated oil and gas field modeling method described above.

[0017] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned integrated oil and gas field modeling method based on intelligent algorithms.

[0018] To address the problems described in the background art, this invention discretizes the continuous and complex geological region into multiple regular original oilfield grids by performing fine-grained grid division on the oilfield area to be modeled. This overcomes the shortcomings of traditional methods that treat the entire large, highly heterogeneous region as a whole, making it difficult to accurately represent internal geological differences due to the use of a single model parameter. This solution also introduces a proximity clustering algorithm that integrates geological attribute similarity and geographic spatial proximity. This algorithm uses a comprehensive distance metric that considers both the actual spatial distance between grids and the mathematical similarity of their feature vectors. Compared to traditional clustering algorithms that only rely on feature similarity for partitioning, this method ensures that the partitioned oilfield areas are spatially contiguous and relatively uniform in their internal geological features. Furthermore, the number of oil wells in the clustered oilfield area sets is corrected to obtain a modified... The first step, setting up a corrected oilfield region set, addresses the practical problem of sparse well data regions that may arise from intelligent clustering. It introduces a region merging mechanism based on a dynamic quantity threshold and automatically selects the optimal neighboring regions for merging by calculating the region fusion degree. This process effectively overcomes the shortcomings of clustering results relying solely on mathematical algorithms in engineering practicality, ensuring that each sub-region used for independent modeling has sufficient well control data as support. This avoids problems such as subsequent geological modeling failure or low model credibility due to insufficient data. Finally, independent region modeling is performed based on the corrected oilfield region set to obtain the integrated model of the target oilfield. This step allows for the use of the most suitable modeling strategies and parameters for sub-regions with different geological characteristics. Compared to traditional modeling methods that use the same set of model parameters for the entire oilfield, it improves the accuracy of each local model. Therefore, this invention can improve the accuracy of modeling non-uniform oilfields and reduce deviations in the modeling process. Attached Figure Description

[0019] Figure 1 A flowchart illustrating an integrated oil and gas field modeling method based on intelligent algorithms provided in an embodiment of the present invention; Figure 2 A functional module diagram of an integrated oil and gas field modeling system based on intelligent algorithms provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device for implementing the integrated oil and gas field modeling method based on intelligent algorithms, according to an embodiment of the present invention.

[0020] Explanation of reference numerals in the attached figures: 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0021] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0023] This application provides an integrated oil and gas field modeling method based on intelligent algorithms. The executing entity of this integrated oil and gas field modeling method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the integrated oil and gas field modeling method based on intelligent algorithms can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0024] Reference Figure 1 The diagram shown is a flowchart illustrating an integrated oil and gas field modeling method based on intelligent algorithms according to an embodiment of the present invention. In this embodiment, the integrated oil and gas field modeling method based on intelligent algorithms includes: S1. Determine the oilfield area to be modeled, and divide the oilfield area into grids to obtain the original oilfield grid set, which includes multiple original oilfield grids.

[0025] It is clear that the oilfield area to be modeled refers to the oilfield area that requires integrated modeling. Due to the geological heterogeneity of the oilfield area to be modeled, such as uneven spatial distribution of structures, sedimentary facies, and physical properties, if the oilfield area to be modeled is treated as a whole for unified modeling, it will be difficult to accurately represent the internal differences between different areas within the oilfield area to be modeled due to the use of a single model, resulting in reduced model accuracy and insufficient reliability. The original oilfield mesh set refers to a collection of multiple original oilfield meshes. An original oilfield mesh refers to a local rectangular region within the oilfield area to be modeled, obtained after meshing. Meshing the oilfield area to be modeled means dividing the two-dimensional plane of the oilfield area to be modeled into multiple regularly arranged rectangular units according to a specified planar mesh step size; each rectangular unit is an original oilfield mesh.

[0026] S2. Collect oilfield data for each original oilfield grid in the original oilfield grid set to obtain the original oilfield feature dataset.

[0027] Understandably, the original oilfield feature dataset refers to a collection of multiple original oilfield feature data, wherein the original oilfield feature data refers to data representing the regional characteristics of a certain original oilfield grid in the original oilfield grid set, and the original oilfield feature data includes classification attribute data, geological attribute data and image feature data.

[0028] S3. Extract the original oilfield feature data sequentially from the original oilfield feature dataset, and perform feature extraction based on the extracted original oilfield feature data to obtain the original oilfield feature vector.

[0029] It is clear that the original oilfield feature vector refers to the numerical vector obtained after feature extraction from the original oilfield feature data. This original oilfield feature vector is used to further represent the regional features of the original oilfield grid corresponding to the original oilfield feature data.

[0030] In detail, the step of extracting features based on the extracted original oilfield feature data to obtain the original oilfield feature vector includes: Identify the categorical attribute data in the extracted raw oilfield feature data, perform one-hot encoding on the categorical attribute data, and obtain the categorical attribute code; Identify the geological attribute data in the extracted raw oilfield feature data, normalize the geological attribute data to obtain geologically normalized data, and generate geological feature vectors based on the geologically normalized data; Identify image feature data in the extracted raw oilfield feature data, and construct oilfield image feature vectors based on the image feature data; The original oilfield feature vector is constructed based on classification attribute encoding, geological feature vector, and oilfield image feature vector.

[0031] It should be explained that the classification attribute data refers to non-numerical data representing the geological type of the original oilfield grid. For example, if the structural unit of a certain original oilfield grid is a central anticline zone and the sedimentary facies is a subsea distributary channel, then the classification attribute data of the original oilfield grid is central anticline zone and subsea distributary channel. The classification attribute encoding refers to the binary vector obtained by performing one-hot encoding on the classification attribute data. This one-hot encoding can be implemented by existing technology and will not be elaborated here. The geological attribute data refers to the set of parameters representing the geological characteristics of the original oilfield grid. For example, the geological attribute data includes parameters such as porosity and permeability of the corresponding area of ​​the original oilfield grid. The geological normalized data refers to the data obtained by normalizing each parameter in the geological attribute data. Normalization can be performed by methods such as max-min normalization or Z-Score normalization. The geological feature vector refers to the numerical vector corresponding to the geological normalized data. For example, if the geological normalized data is 0.65, 0.72, and 0.80, then the geological feature vector is represented as: [0.65, 0.72, 0.80].

[0032] Furthermore, the image feature data refers to data representing the regional image features of the original oilfield grid. The method for obtaining this image feature data will be given in subsequent embodiments. The oilfield image feature vector refers to the numerical vector corresponding to the image feature data. The construction method of the oilfield image feature vector is the same as that of the geological feature vector, and will not be repeated here. The above-mentioned construction of the original oilfield feature vector based on classification attribute encoding, geological feature vector, and oilfield image feature vector refers to: according to the prescribed splicing order, the classification attribute encoding, geological feature vector, and oilfield image feature vector are spliced ​​end to end. The new vector obtained after splicing is the original oilfield feature vector. The splicing order can be selected as: classification attribute encoding of structural units, classification attribute encoding corresponding to sediments, geological feature vector, and oilfield image feature vector. For example, the structural unit corresponding to a certain original oilfield grid The classification attribute code of the element is [0, 1, 0], the classification attribute code of the sediment is [0, 0, 1, 0], the geological feature vector is [0.65, 0.72, 0.80], the oilfield image feature vector is [0.1, 0.4, 0.8, 0.3, 0.6], and the original oilfield feature vector obtained after splicing is [0, 1, 0, 0, 0, 1, 0, 0.65, 0.72, 0.80, 0.1, 0.4, 0.8, 0.3, 0.6].

[0033] Specifically, prior to identifying the image feature data in the extracted raw oilfield feature data, the method further includes: The original oilfield image is acquired, and a low-pass filter is applied to the original oilfield image to obtain the original filtered oilfield image. The original filtered oilfield image is downsampled to obtain a low-resolution oilfield image; Construct multiple base filters, each corresponding to a different filtering angle; The base filters are extracted sequentially from multiple base filters, and the extracted base filters are used to perform directional filtering on the low-resolution oilfield image to obtain a unidirectional filtered image. By summing the unidirectional filtered images corresponding to each base filter, multiple unidirectional filtered images are obtained. Multiple unidirectional filtered images are fused to obtain a fused filtered oilfield image; Get the current downsampling quantity. If the current downsampling quantity is less than the preset standard downsampling quantity, use the fused filtered oilfield image as the original filtered oilfield image and return to the step of downsampling the original filtered oilfield image until the current downsampling quantity is not less than the standard downsampling quantity. If the current downsampling quantity is not less than the standard downsampling quantity, then the fused filtered oilfield images are summarized to obtain a fused filtered oilfield image set; Image reconstruction is performed based on a fused filtered oilfield image set to obtain a reconstructed filtered image. Feature extraction is then performed on the reconstructed filtered image to obtain image feature data.

[0034] It should be explained that the original oilfield image refers to the overall image of the area corresponding to a certain original oilfield grid, which can be acquired by remote sensing equipment. The original filtered oilfield image refers to the image obtained after low-pass filtering the original oilfield image. Low-pass filtering is used to smooth the original oilfield image and suppress random noise; Gaussian filtering, mean filtering, or median filtering can be used. The low-resolution oilfield image refers to the image obtained after downsampling the original filtered oilfield image. The specific steps of downsampling are existing technologies and will not be elaborated here. The base filter refers to a filter with characteristic direction selectivity. The filtering angle refers to the angle between the principal response direction of the base filter and the horizontal axis of the image. For example, a set of Gabor filters with filtering angles of 0°, 45°, 90°, and 135° can be used as multiple base filters here. The unidirectional filtered image refers to the image obtained after directional filtering the low-resolution oilfield image. The fused filtered oilfield image refers to the fused image obtained by fusing multiple unidirectional filtered images. The current downsampling quantity refers to the number of times the downsampling step has been performed so far, and the standard downsampling quantity refers to the number of times the downsampling step needs to be performed, which can be a positive integer such as 3, 4, or 5.

[0035] Furthermore, each fused filtered oilfield image in the aforementioned fused filtered oilfield image set represents a different image resolution, and the resolution of the fused filtered oilfield images arranged further down the set is lower. The reconstructed filtered image refers to the image obtained after image reconstruction. Image reconstruction based on the fused filtered oilfield image set involves: starting with the last fused filtered oilfield image in the set, upsampling the resolution of this image to match the resolution of adjacent fused filtered oilfield images, and then merging the adjacent images with the upsampled image using a weighted summation method to obtain a fused image. This fused image is then used as the last fused filtered oilfield image in the set, and this process is iterated step-by-step until an output image with the same resolution as the original oilfield image is reconstructed. This output image is the reconstructed filtered image. The specific method for feature extraction of the reconstructed filtered image is as follows: calculate the statistical features such as the mean and variance of the reconstructed filtered image, and calculate the texture features such as the contrast, energy, and entropy of the reconstructed filtered image through the gray-level co-occurrence matrix. Both the above statistical features and texture features can be used as image feature data.

[0036] Specifically, the process of fusing multiple unidirectional filtered images to obtain a fused filtered oilfield image includes: For each of the multiple unidirectional filtered images, perform the following operation: Identify the set of filtered pixels in the unidirectional filtered image, wherein the set of filtered pixels includes multiple filtered pixels; Energy is calculated for each filtered pixel in the set of filtered pixels to obtain a set of pixel energy values; The directional pixel energy value is obtained by averaging the pixel energy value set. Summarize the directional pixel energy values ​​corresponding to each unidirectional filtered image to obtain a set of directional pixel energy values; Generate directional pixel energy vectors based on directional pixel energy value sets; The directional pixel energy vector is weighted by a preset scaling function to obtain a directional weight vector. The directional weight vector includes multiple directional weights, and each directional weight corresponds one-to-one with a single-directional filtered image. Multiple unidirectional filtered images are weighted and fused using directional weight vectors to obtain a fused filtered oilfield image.

[0037] It should be explained that the "filtered pixel set" refers to a collection of multiple filtered pixels, where each filtered pixel refers to a pixel in a unidirectional filtered image. The "pixel energy value set" refers to a collection of multiple pixel energy values, where each pixel energy value refers to the energy value of a specific filtered pixel. This pixel energy value is calculated as follows: In the unidirectional filtered image, extract multiple adjacent pixels that are 8-connected to the filtered pixel, and obtain the values ​​of these adjacent pixels. The pixel energy value of the filtered pixel is then expressed as: ,in, This represents the pixel energy value of the filtered pixel. This indicates the number of adjacent pixels among a set of adjacent pixels. Represents the first of multiple adjacent pixels The pixel value of each adjacent pixel. The directional pixel energy value refers to the average value of all pixel energy values ​​in the pixel energy value set.

[0038] Furthermore, the directional pixel energy vector refers to the numerical vector corresponding to the directional pixel energy value set. This numerical vector refers to a vector with the same value as the directional pixel energy value set. For example, if the directional pixel energy value set is B1, B2, and B3, then the directional pixel energy vector is... The direction weight vector refers to the vector obtained after weight transformation, and the scaling function mentioned above can be selected from... Since the directly calculated directional pixel energy value only represents the absolute intensity of the filter response at each filtering angle, and the numerical range of this directional pixel energy value is uncertain and the sum is not equal to 1, a weight transformation step is required. The specific method for weighted fusion of multiple unidirectional filtered images using the directional weight vector is as follows: For a certain image location in the original oilfield image, extract multiple pixels corresponding to that image location in each of the multiple unidirectional filtered images (denoted as pixels to be fused). Then, multiply the numerical vector formed by the multiple pixel values ​​corresponding to the multiple pixels to be fused by the directional weight vector, and record the multiplication result as the fused pixel value. For example, the numerical vector formed by the multiple pixel values ​​corresponding to the multiple pixels to be fused is... The directional weight vector is The product of the two can be expressed as: = The fused pixel values ​​corresponding to each image location are summarized to obtain a fused pixel value set. This fused pixel value set is then used to replace the original pixel values ​​at the corresponding image locations in the original oilfield image. The original oilfield image after replacement is the fused filtered oilfield image.

[0039] S4. Summarize the original oilfield feature vectors to obtain the original oilfield feature vector set. Based on the original oilfield feature vector set, perform proximity clustering on the original oilfield grid set to obtain the clustered oilfield region set.

[0040] It is clear that the clustered oilfield region set refers to a collection of multiple clustered oilfield regions. A clustered oilfield region refers to a region composed of multiple original oilfield grids that, after being clustered by proximity, are assigned to the same cluster. The above-mentioned method of clustering the original oilfield grid set based on the original oilfield feature vector set to obtain the clustered oilfield region set specifically includes: first, setting multiple candidate cluster numbers, where the numerical range of each candidate cluster number is 1 to 10; then, sequentially substituting each candidate cluster number into clustering algorithms such as K-means; and then calculating the silhouette coefficient of the clustering data output by the clustering algorithm. The clustering data refers to multiple clusters obtained after the calculation by the clustering algorithm, each cluster containing multiple original oilfield grids, thus obtaining multiple sets of evaluation data. Each set of evaluation data includes a candidate cluster number and a silhouette coefficient. Based on multiple sets of evaluation data, a relationship curve between the number of candidate clusters and the silhouette coefficient is constructed. The number of candidate clusters corresponding to the coordinate point with the largest silhouette coefficient on this relationship curve is selected as the optimal number of clusters. Finally, a clustering algorithm is executed according to this optimal number of clusters, thereby dividing the original oilfield grid set into multiple clusters. Each cluster contains multiple original oilfield grids, which constitute the clustered oilfield region. The above clustering algorithm is used to group original oilfield feature vectors that are spatially close and have similar feature vectors into one cluster. The comprehensive value used to quantify the similarity of spatial distance and original oilfield feature vectors is: ,in, This represents the actual distance between two original oilfield grids. This represents the vector cosine value between the feature vectors of the two original oilfields corresponding to the two original oilfield grids. These are the two original oilfield feature vectors corresponding to the two original oilfield grids.

[0041] S5. Correct the number of oil wells in the clustered oilfield region set to obtain the corrected oilfield region set.

[0042] Understandably, the modified oilfield region set refers to the clustered oilfield region set after adjusting for the number of oil wells. Since the above clustering algorithm relies on the mathematical similarity of the original oilfield feature vectors and the distance between the original oilfield grids for spatial partitioning, it may generate some sparse regions with few or no oil wells. Therefore, it is necessary to make practical adjustments to the clustering results based on the actual oil well distribution to ensure that each modified oilfield region has sufficient well control data to build a reliable geological model (such as the subsequent target oilfield region model), avoiding modeling failure or unreliable results due to insufficient data support.

[0043] In detail, the process of correcting the number of oil wells in the clustered oilfield region set to obtain the corrected oilfield region set includes: In the clustered oilfield regions, the clustered oilfield regions are extracted sequentially, and the extracted clustered oilfield regions are recorded as the oilfield regions to be corrected. Obtain the number of regional oil wells in the oilfield area to be corrected; Based on the number of oil wells in a region, the regions of oilfields to be modified are merged to obtain the target oilfield region; The clustered oilfield region set is updated using the target oilfield region to obtain the updated oilfield region set; The updated oilfield region set is used as the clustered oilfield region set, and the step of sequentially extracting clustered oilfield regions in the clustered oilfield region set is returned until all clustered oilfield regions in the clustered oilfield region set have been extracted. The updated oilfield region set after all clustered oilfield regions have been extracted is denoted as the corrected oilfield region set.

[0044] It should be explained that the number of oil wells in the region refers to the total number of oil wells contained in the oilfield region to be corrected. The target oilfield region refers to the new region obtained after merging the oilfield regions to be corrected. The updated oilfield region set refers to the clustered oilfield region set after regional updating. Specifically, updating the clustered oilfield region set using the target oilfield region means replacing one or more merged clustered oilfield regions in the clustered oilfield region set with the target oilfield region. The resulting clustered oilfield region set is the updated oilfield region set. For example, if the clustered oilfield region set includes region A1, region A2, region A3, and region A4, and region A1 and region A2 are merged to obtain the target oilfield region, then the updated oilfield region set is: the target oilfield region, region A3, and region A4.

[0045] Specifically, the process of merging the oilfield regions to be modified based on the number of regional oil wells to obtain the target oilfield region includes: If the number of oil wells in a region is less than the preset dynamic number threshold, then multiple adjacent oil field regions of the oil field region to be corrected are identified in the clustered oil field region. Based on the oilfield region to be corrected, multiple adjacent oilfield regions are identified as merging regions to obtain the oilfield region to be merged. The oilfield area to be corrected is merged into the oilfield area to be integrated to obtain the target oilfield area; If the number of oil wells in a region is not less than the dynamic quantity threshold, then the oilfield region to be corrected is recorded as the target oilfield region.

[0046] It should be explained that the dynamic quantity threshold refers to a threshold used to determine whether the number of oil wells in a region is too low. This dynamic quantity threshold is set as follows: The number of oil wells in each cluster of oilfield regions is obtained, thus forming a regional oil well quantity set. The average and standard deviation of the regional oil well quantity set are calculated, and the dynamic quantity threshold can then be set as follows: ,in, and These represent the average and standard deviation of the number of oil wells in a region, respectively. When the number of oil wells in a region is less than this dynamic threshold, it indicates that the number of oil wells in the oilfield region to be corrected is relatively small. In this case, the oilfield region to be corrected needs to be merged with a spatially adjacent cluster of oilfield regions. The adjacent oilfield region refers to the cluster of oilfield regions that are spatially directly adjacent to the oilfield region to be corrected. The oilfield region to be merged refers to the adjacent oilfield region that is most suitable for merging with the oilfield region to be corrected.

[0047] Specifically, the process of identifying mergingable regions among multiple adjacent oilfield regions based on the oilfield region to be corrected, to obtain the oilfield region to be merged, includes: Obtain the number of oil wells to be corrected and the feature vector set of the grid to be corrected in the oilfield area to be corrected; The oilfield grid to be corrected is determined by identifying the oilfield grid to be corrected corresponding to each feature vector in the feature vector set of the grid to be corrected; Statistically determine the oilfield area set corresponding to the grid set of oilfields to be corrected; The feature vector of the region to be corrected is obtained by weighted fusion of the feature vector set of the grid to be corrected using the set of oilfield areas to be corrected. In multiple adjacent oilfield regions, adjacent oilfield regions are extracted sequentially to obtain the number of adjacent oil wells and the feature vector of the adjacent region in the extracted adjacent oilfield regions; The region fusion degree is calculated based on the number of adjacent oil wells, the feature vector of adjacent regions, the number of oil wells to be corrected, and the feature vector of regions to be corrected. By summing the regional integration degree corresponding to each adjacent oilfield region, multiple regional integration degrees are obtained; Identify the maximum degree of integration among multiple regions and record the adjacent oilfield region corresponding to the maximum degree of integration as the oilfield region to be integrated.

[0048] It should be explained that the number of wells to be corrected refers to the total number of wells in the oilfield region to be corrected. The set of feature vectors for the grid to be corrected refers to a collection of multiple feature vectors for the grid to be corrected, where each feature vector corresponds to the original oilfield feature vector of a specific original oilfield grid within the oilfield region to be corrected. The set of oilfield grids to be corrected refers to a collection of multiple oilfield grids to be corrected, where each grid corresponds to the original oilfield grid with its feature vector. The set of oilfield areas to be corrected refers to a collection of multiple oilfield areas to be corrected, where each area refers to the actual area of ​​a specific oilfield grid. The feature vector of the region to be corrected refers to the feature vector obtained after weighted fusion, where this feature vector represents the overall regional characteristics of the oilfield region to be corrected. The number of adjacent wells refers to the total number of wells in adjacent oilfield regions. The feature vector of the adjacent region refers to the feature vector of the region to be corrected corresponding to the adjacent oilfield region; that is, the method for obtaining the feature vector of the adjacent region is the same as the method for obtaining the feature vector of the region to be corrected described above, and will not be repeated here. The regional integration degree refers to a numerical value used to quantify the degree of integration between the oilfield region to be corrected and its adjacent oilfield regions. A higher regional integration degree indicates a greater likelihood of merging the oilfield region to be corrected and its adjacent regions. The maximum integration degree refers to the regional integration degree with the highest value among multiple regional integration degrees. The formula for calculating the above regional integration degree is as follows: ,in, Indicates the number of oil wells requiring correction. Indicates the number of adjacent oil wells. Represents the cosine function. This represents the feature vector of the region to be corrected. Represents the feature vector of adjacent regions, where, The larger the value, the closer the number of oil wells in the oilfield area to be corrected is to that of adjacent oilfield areas. In this case, the oilfield area to be corrected can be preferentially merged into an adjacent oilfield area with fewer oil wells, thereby maintaining a balance in the number of oil wells among the various oilfield areas. The larger the value, the higher the similarity between the oilfield area to be corrected and the adjacent oilfield areas, and the more likely it is to be merged, i.e., the greater the degree of regional integration.

[0049] In detail, the step of weightedly fusing the feature vector set of the grid to be corrected from the set of oilfield areas to be corrected to obtain the feature vector of the region to be corrected includes: The feature vector of the region to be corrected is calculated using the following formula:

[0050] in, This represents the feature vector of the region to be corrected. This indicates the number of oilfield areas requiring correction. and These represent the concentrated areas of the oilfields to be corrected. The area of ​​the oilfield to be revised and the first Area of ​​oil fields to be revised. Represents the first element in the set of eigenvectors of the grid to be corrected. One grid feature vector to be corrected.

[0051] It needs to be explained that in the above formula for calculating the eigenvector of the region to be corrected, the numerator... The larger the value, the more important the corresponding original oilfield grid is in the oilfield region to be corrected. The greater the weight of a term in the calculation of the eigenvector of the corrected region, the higher the weight of that term in the denominator. Used for Normalize.

[0052] S6. Perform independent regional modeling based on the modified oilfield region set to obtain the target oilfield integrated model, and complete the integrated oil and gas field modeling based on intelligent algorithms.

[0053] It should be explained that the target oilfield integrated model refers to the summative model obtained after modeling independent regions.

[0054] In detail, the step of performing independent region modeling based on the modified oilfield region set to obtain the target oilfield integrated model includes: For each corrected oilfield region in the corrected oilfield region cluster, the following operations shall be performed: Modeling data was collected for the Xiuzheng oilfield area to obtain Xiuzheng oilfield modeling data; Oilfield modeling is performed using a preset standard oilfield model template and corrected oilfield modeling data to obtain a target oilfield area model; The target oilfield region models corresponding to each modified oilfield region are summarized to obtain the target oilfield region model set; Model integration is performed based on the target oilfield regional model set to obtain the target oilfield integrated model.

[0055] It should be explained that the modified oilfield modeling data refers to the data obtained after modeling data acquisition for oilfield modeling. This modified oilfield modeling data includes: geological attribute data, well production data, seismic interpretation data, and well logging interpretation data within the modified oilfield area. For example, geological attribute data may include the porosity distribution field and permeability distribution field of the modified oilfield area; well production data includes the historical oil production and water production of each well in the modified oilfield area; seismic interpretation data includes the stratigraphic and fault data of the modified oilfield area; and well logging interpretation data includes the sandstone and mudstone content and saturation curves of each well point in the modified oilfield area. The acquisition methods for each parameter in the above-mentioned modified oilfield modeling data are all existing technologies and will not be elaborated further here. The standard oilfield model template refers to a predefined geological modeling framework. This standard oilfield model template specifies the data structure, calculation steps, algorithm selection, and parameter initialization range required for modeling. Optionally, this standard oilfield model template is a reservoir attribute modeling template.

[0056] Furthermore, the target oilfield region model refers to a digital three-dimensional geological model obtained after oilfield modeling, capable of characterizing the internal geological structure, reservoir attribute spatial distribution, and fluid characteristics of the modified oilfield region. The construction method of this target oilfield region model is as follows: the modified oilfield modeling data is imported into a standard oilfield model template, which automatically runs built-in algorithms, such as the sequential Gaussian simulation algorithm, to generate the target oilfield region model corresponding to the modified oilfield modeling data. The model integration refers to splicing multiple target oilfield region models according to the original spatial relationships of the corresponding modified oilfield regions to form a comprehensive oilfield model covering the entire oilfield region to be modeled.

[0057] To address the problems described in the background art, this invention discretizes the continuous and complex geological region into multiple regular original oilfield grids by performing fine-grained grid division on the oilfield area to be modeled. This overcomes the shortcomings of traditional methods that treat the entire large, highly heterogeneous region as a whole, making it difficult to accurately represent internal geological differences due to the use of a single model parameter. This solution also introduces a proximity clustering algorithm that integrates geological attribute similarity and geographic spatial proximity. This algorithm uses a comprehensive distance metric that considers both the actual spatial distance between grids and the mathematical similarity of their feature vectors. Compared to traditional clustering algorithms that only rely on feature similarity for partitioning, this method ensures that the partitioned oilfield areas are spatially contiguous and relatively uniform in their internal geological features. Furthermore, the number of oil wells in the clustered oilfield area sets is corrected to obtain a modified... The first step, setting up a corrected oilfield region set, addresses the practical problem of sparse well data regions that may arise from intelligent clustering. It introduces a region merging mechanism based on a dynamic quantity threshold and automatically selects the optimal neighboring regions for merging by calculating the region fusion degree. This process effectively overcomes the shortcomings of clustering results relying solely on mathematical algorithms in engineering practicality, ensuring that each sub-region used for independent modeling has sufficient well control data as support. This avoids problems such as subsequent geological modeling failure or low model credibility due to insufficient data. Finally, independent region modeling is performed based on the corrected oilfield region set to obtain the integrated model of the target oilfield. This step allows for the use of the most suitable modeling strategies and parameters for sub-regions with different geological characteristics. Compared to traditional modeling methods that use the same set of model parameters for the entire oilfield, it improves the accuracy of each local model. Therefore, this invention can improve the accuracy of modeling non-uniform oilfields and reduce deviations in the modeling process.

[0058] like Figure 2 The diagram shown is a functional block diagram of an integrated oil and gas field modeling system based on intelligent algorithms provided in an embodiment of the present invention.

[0059] The intelligent algorithm-based integrated oil and gas field modeling system 100 of this invention can be installed in an electronic device. Depending on the functions implemented, the intelligent algorithm-based integrated oil and gas field modeling system 100 may include an oilfield region division module 101, an oilfield feature extraction module 102, an oilfield data clustering module 103, and an oilfield region integration module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device. The oilfield area division module 101 is used to determine the oilfield area to be modeled, divide the oilfield area to be modeled into grids, and obtain the original oilfield grid set, wherein the original oilfield grid set includes multiple original oilfield grids. The oilfield feature extraction module 102 is used to collect oilfield data for each original oilfield grid in the original oilfield grid set to obtain an original oilfield feature dataset, extract original oilfield feature data sequentially from the original oilfield feature dataset, and perform feature extraction based on the extracted original oilfield feature data to obtain an original oilfield feature vector. The oilfield data clustering module 103 is used to summarize the original oilfield feature vectors to obtain the original oilfield feature vector set, and to perform proximity clustering on the original oilfield grid set based on the original oilfield feature vector set to obtain the clustered oilfield region set. The oilfield region integration module 104 is used to correct the number of oil wells in the clustered oilfield region set to obtain a corrected oilfield region set, and to perform independent region modeling based on the corrected oilfield region set to obtain the target oilfield integrated model.

[0060] In detail, the modules in the intelligent algorithm-based integrated oil and gas field modeling system 100 described in this embodiment of the invention employ the same methods as described above. Figure 1 The method uses the same technical means as the intelligent algorithm-based integrated oil and gas field modeling method described in the article, and can produce the same technical effects, so it will not be repeated here.

[0061] like Figure 3 The diagram shown is a schematic representation of an electronic device for implementing an integrated oil and gas field modeling method based on intelligent algorithms, according to an embodiment of the present invention.

[0062] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a program for an integrated oil and gas field modeling method based on intelligent algorithms.

[0063] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as the portable hard drive of the electronic device 1. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of an integrated oil and gas field modeling method program based on intelligent algorithms, but also to temporarily store data that has been output or will be output.

[0064] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., an integrated oil and gas field modeling method program based on intelligent algorithms) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0065] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0066] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0067] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0068] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0069] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0070] The program for the integrated oil and gas field modeling method based on intelligent algorithms, stored in the memory 11 of the electronic device 1, is a combination of multiple instructions. When run in the processor 10, it can achieve the following: The oilfield area to be modeled is determined, and the oilfield area to be modeled is divided into grids to obtain the original oilfield grid set, which includes multiple original oilfield grids. Oilfield data was collected for each original oilfield grid in the original oilfield grid set to obtain the original oilfield feature dataset; Original oilfield feature data are extracted sequentially from the original oilfield feature dataset. Based on the extracted original oilfield feature data, feature extraction is performed to obtain the original oilfield feature vector. The original oilfield feature vectors are summarized to obtain the original oilfield feature vector set. Based on the original oilfield feature vector set, the original oilfield grid set is clustered by proximity to obtain the clustered oilfield region set. The number of oil wells in the clustered oilfield region set is corrected to obtain the corrected oilfield region set; Independent regional modeling is performed based on the modified oilfield region set to obtain the target oilfield integrated model, thus completing the integrated oil and gas field modeling based on intelligent algorithms.

[0071] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0072] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0073] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following: The oilfield area to be modeled is determined, and the oilfield area to be modeled is divided into grids to obtain the original oilfield grid set, which includes multiple original oilfield grids. Oilfield data was collected for each original oilfield grid in the original oilfield grid set to obtain the original oilfield feature dataset; Original oilfield feature data are extracted sequentially from the original oilfield feature dataset. Based on the extracted original oilfield feature data, feature extraction is performed to obtain the original oilfield feature vector. The original oilfield feature vectors are summarized to obtain the original oilfield feature vector set. Based on the original oilfield feature vector set, the original oilfield grid set is clustered by proximity to obtain the clustered oilfield region set. The number of oil wells in the clustered oilfield region set is corrected to obtain the corrected oilfield region set; Independent regional modeling is performed based on the modified oilfield region set to obtain the target oilfield integrated model, thus completing the integrated oil and gas field modeling based on intelligent algorithms.

[0074] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0075] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0076] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0077] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An integrated oil and gas field modeling method based on intelligent algorithms, characterized in that, The method includes: The oilfield area to be modeled is determined, and the oilfield area to be modeled is divided into grids to obtain the original oilfield grid set, which includes multiple original oilfield grids. Oilfield data was collected for each original oilfield grid in the original oilfield grid set to obtain the original oilfield feature dataset; Original oilfield feature data are extracted sequentially from the original oilfield feature dataset. Based on the extracted original oilfield feature data, feature extraction is performed to obtain the original oilfield feature vector. The original oilfield feature vectors are summarized to obtain the original oilfield feature vector set. Based on the original oilfield feature vector set, the original oilfield grid set is clustered by proximity to obtain the clustered oilfield region set. The number of oil wells in the clustered oilfield region set is corrected to obtain the corrected oilfield region set; Independent regional modeling is performed based on the modified oilfield region set to obtain the target oilfield integrated model, thus completing the integrated oil and gas field modeling based on intelligent algorithms.

2. The integrated oil and gas field modeling method based on intelligent algorithms as described in claim 1, characterized in that, The process of extracting features from the extracted original oilfield feature data to obtain the original oilfield feature vector includes: Identify the categorical attribute data in the extracted raw oilfield feature data, perform one-hot encoding on the categorical attribute data, and obtain the categorical attribute code; Identify the geological attribute data in the extracted raw oilfield feature data, normalize the geological attribute data to obtain geologically normalized data, and generate geological feature vectors based on the geologically normalized data; Identify image feature data in the extracted raw oilfield feature data, and construct oilfield image feature vectors based on the image feature data; The original oilfield feature vector is constructed based on classification attribute encoding, geological feature vector, and oilfield image feature vector.

3. The integrated oil and gas field modeling method based on intelligent algorithms as described in claim 2, characterized in that, Before identifying the image feature data in the extracted raw oilfield feature data, the method further includes: The original oilfield image is acquired, and a low-pass filter is applied to the original oilfield image to obtain the original filtered oilfield image. The original filtered oilfield image is downsampled to obtain a low-resolution oilfield image; Construct multiple base filters, each corresponding to a different filtering angle; The base filters are extracted sequentially from multiple base filters, and the extracted base filters are used to perform directional filtering on the low-resolution oilfield image to obtain a unidirectional filtered image. By summing the unidirectional filtered images corresponding to each base filter, multiple unidirectional filtered images are obtained. Multiple unidirectional filtered images are fused to obtain a fused filtered oilfield image; Get the current downsampling quantity. If the current downsampling quantity is less than the preset standard downsampling quantity, use the fused filtered oilfield image as the original filtered oilfield image and return to the step of downsampling the original filtered oilfield image until the current downsampling quantity is not less than the standard downsampling quantity. If the current downsampling quantity is not less than the standard downsampling quantity, then the fused filtered oilfield images are summarized to obtain a fused filtered oilfield image set; Image reconstruction is performed based on a fused filtered oilfield image set to obtain a reconstructed filtered image. Feature extraction is then performed on the reconstructed filtered image to obtain image feature data.

4. The integrated oil and gas field modeling method based on intelligent algorithms as described in claim 3, characterized in that, The process of fusing multiple unidirectional filtered images to obtain a fused filtered oilfield image includes: For each of the multiple unidirectional filtered images, perform the following operation: Identify the set of filtered pixels in the unidirectional filtered image, wherein the set of filtered pixels includes multiple filtered pixels; Energy is calculated for each filtered pixel in the set of filtered pixels to obtain a set of pixel energy values; The directional pixel energy value is obtained by averaging the pixel energy value set. Summarize the directional pixel energy values ​​corresponding to each unidirectional filtered image to obtain a set of directional pixel energy values; Generate directional pixel energy vectors based on directional pixel energy value sets; The directional pixel energy vector is weighted by a preset scaling function to obtain a directional weight vector. The directional weight vector includes multiple directional weights, and each directional weight corresponds one-to-one with a single-directional filtered image. Multiple unidirectional filtered images are weighted and fused using directional weight vectors to obtain a fused filtered oilfield image.

5. The integrated oil and gas field modeling method based on intelligent algorithms as described in claim 4, characterized in that, The process of correcting the number of oil wells in the clustered oilfield region set to obtain the corrected oilfield region set includes: In the clustered oilfield regions, the clustered oilfield regions are extracted sequentially, and the extracted clustered oilfield regions are recorded as the oilfield regions to be corrected. Obtain the number of regional oil wells in the oilfield area to be corrected; Based on the number of oil wells in a region, the regions of oilfields to be modified are merged to obtain the target oilfield region; The clustered oilfield region set is updated using the target oilfield region to obtain the updated oilfield region set; The updated oilfield region set is used as the clustered oilfield region set, and the step of sequentially extracting clustered oilfield regions in the clustered oilfield region set is returned until all clustered oilfield regions in the clustered oilfield region set have been extracted. The updated oilfield region set after all clustered oilfield regions have been extracted is denoted as the corrected oilfield region set.

6. The integrated oil and gas field modeling method based on intelligent algorithms as described in claim 5, characterized in that, The process of merging the oilfield regions to be modified based on the number of oil wells in a region to obtain the target oilfield region includes: If the number of oil wells in a region is less than the preset dynamic number threshold, then multiple adjacent oil field regions of the oil field region to be corrected are identified in the clustered oil field region. Based on the oilfield region to be corrected, multiple adjacent oilfield regions are identified as merging regions to obtain the oilfield region to be merged. The oilfield area to be corrected is merged into the oilfield area to be integrated to obtain the target oilfield area; If the number of oil wells in a region is not less than the dynamic quantity threshold, then the oilfield region to be corrected is recorded as the target oilfield region.

7. The integrated oil and gas field modeling method based on intelligent algorithms as described in claim 6, characterized in that, The process of identifying merging regions among multiple adjacent oilfield regions based on the oilfield region to be corrected, to obtain the oilfield region to be merged, includes: Obtain the number of oil wells to be corrected and the feature vector set of the grid to be corrected in the oilfield area to be corrected; The oilfield grid to be corrected is determined by identifying the oilfield grid to be corrected corresponding to each feature vector in the feature vector set of the grid to be corrected; Statistically determine the oilfield area set corresponding to the grid set of oilfields to be corrected; The feature vector of the region to be corrected is obtained by weighted fusion of the feature vector set of the grid to be corrected using the set of oilfield areas to be corrected. In multiple adjacent oilfield regions, adjacent oilfield regions are extracted sequentially to obtain the number of adjacent oil wells and the feature vector of the adjacent region in the extracted adjacent oilfield regions; The region fusion degree is calculated based on the number of adjacent oil wells, the feature vector of adjacent regions, the number of oil wells to be corrected, and the feature vector of regions to be corrected. By summing the regional integration degree corresponding to each adjacent oilfield region, multiple regional integration degrees are obtained; Identify the maximum degree of integration among multiple regions and record the adjacent oilfield region corresponding to the maximum degree of integration as the oilfield region to be integrated.

8. The integrated oil and gas field modeling method based on intelligent algorithms as described in claim 7, characterized in that, The process of weightedly fusing the feature vector set of the grid to be corrected from the area set of the oilfield to be corrected to obtain the feature vector of the region to be corrected includes: The feature vector of the region to be corrected is calculated using the following formula: ； in, This represents the feature vector of the region to be corrected. This indicates the number of oilfield areas requiring correction. and These represent the concentrated areas of the oilfields to be corrected. The area of ​​the oilfield to be revised and the first The area of ​​the nth oilfield to be corrected represents the nth feature vector in the set of feature vectors to be corrected. One grid feature vector to be corrected.

9. The integrated oil and gas field modeling method based on intelligent algorithms as described in claim 8, characterized in that, The process of modeling independent regions based on the modified oilfield region set to obtain the integrated model of the target oilfield includes: For each corrected oilfield region in the corrected oilfield region cluster, the following operations shall be performed: Modeling data was collected for the Xiuzheng oilfield area to obtain Xiuzheng oilfield modeling data; Oilfield modeling is performed using a preset standard oilfield model template and corrected oilfield modeling data to obtain a target oilfield area model; The target oilfield region models corresponding to each modified oilfield region are summarized to obtain the target oilfield region model set; Model integration is performed based on the target oilfield regional model set to obtain the target oilfield integrated model.

10. An integrated oil and gas field modeling system based on intelligent algorithms, characterized in that, The system includes: The oilfield region division module is used to determine the oilfield region to be modeled, divide the oilfield region to be modeled into grids, and obtain the original oilfield grid set, which includes multiple original oilfield grids. The oilfield feature extraction module is used to collect oilfield data for each original oilfield grid in the original oilfield grid set to obtain the original oilfield feature dataset. The original oilfield feature data is extracted sequentially from the original oilfield feature dataset, and feature extraction is performed based on the extracted original oilfield feature data to obtain the original oilfield feature vector. The oilfield data clustering module is used to summarize the original oilfield feature vectors to obtain the original oilfield feature vector set. Based on the original oilfield feature vector set, the original oilfield grid set is clustered by proximity to obtain the clustered oilfield region set. The oilfield region integration module is used to correct the number of oil wells in the clustered oilfield region set to obtain the corrected oilfield region set. Based on the corrected oilfield region set, independent region modeling is performed to obtain the target oilfield integrated model.

Images