Oil well data evaluation method and equipment based on heavy oil reservoir and medium

Abstract

The invention discloses an oil well data evaluation method and equipment based on a heavy oil reservoir and a medium, belongs to the technical field of heavy oil reservoir exploitation, and is used for solving the technical problems that in existing oil well exploitation of the heavy oil reservoir, the yield of an oil well is difficult to comprehensively evaluate, and yield influence factors of different oil wells are difficult to analyze. The method comprises the steps of obtaining yield data of all oil wells in a heavy oil reservoir oil field; based on the yield data, the oil wells are subjected to area division processing, so that the multiple oil wells corresponding to the similar yield data are located in the same area; grey correlation analysis of related yield influence factors is carried out on each oil well in the same area, and the influence factor correlation degree of each oil well is determined; according to the influence factor correlation degree, carrying out correlation analysis evaluation on the yield influence factors to obtain influence factor evaluation indexes of each oil well; and performing clustering decentration calculation on the influence factor evaluation indexes, and determining a yield comprehensive score of each oil well.

Description

Technical Field

[0001] The present application relates to the technical field of heavy oil reservoir exploitation, and in particular to an oil well data evaluation method, equipment and medium based on heavy oil reservoirs. Background Art

[0002] The main characteristics of heavy oil reservoirs include: high viscosity, high density, poor fluidity, which increase the difficulty and cost of mining and lead to low final recovery of oil fields. It is sensitive to temperature, and the viscosity of heavy oil will increase significantly with the decrease of temperature. The content of light components is low, while the content of char and asphaltene is high. Heavy oil reservoirs are usually located in various types of reservoirs, such as sandstone, conglomerate, etc. These reservoirs are mostly loosely cemented and have good physical properties. The burial depth varies greatly, and the burial depth of heavy oil reservoirs can range from tens of meters to more than 3,000 meters. There are various types of reservoirs, including lithology-controlled structures, loose sandstone reservoirs with developed edge and bottom water, and igneous rock structures with pore-fracture dual media. The oil saturation is low, and the heavy oil reservoir is characterized by high porosity and high permeability. In addition, during the development process, heavy oil reservoirs may show characteristics such as high initial production, rapid decline in formation pressure, increasingly thick crude oil, and rapid increase in water content in oil wells.

[0003] Existing oil wells used for heavy oil reservoir exploitation are often affected by the geological factors of the oil field and the development factors during the exploitation process, so that the single well production of the oil well is often restricted by many aspects. For technical personnel, it is difficult to achieve a comprehensive evaluation of the oil well production in a certain area. At the same time, it is also difficult to accurately judge the influencing factors of different oil wells, which is not conducive to taking targeted measures based on the changing factors of oil well production. Summary of the invention

[0004] The embodiments of the present application provide an oil well data evaluation method, device and medium based on heavy oil reservoirs, which are used to solve the following technical problems: in the existing heavy oil reservoir oil well exploitation, it is difficult to comprehensively evaluate the production of the oil wells, and it is difficult to analyze the factors affecting the production of different oil wells.

[0005] The present application embodiment adopts the following technical solutions:

[0006] On the one hand, an embodiment of the present application provides an oil well data evaluation method based on a heavy oil reservoir, comprising: obtaining production data of all oil wells in a heavy oil reservoir oil field; based on the production data, performing regional division processing on the oil wells so that several oil wells corresponding to similar production data are in the same area; performing grey correlation analysis on production influencing factors for each oil well in the same area, and determining the correlation degree of the influencing factors of each oil well; wherein the production influencing factors include: geological factors and development factors; based on the correlation degree of the influencing factors, performing correlation analysis and evaluation on the production influencing factors to obtain an influencing factor evaluation index for each oil well; performing clustering and weighted calculation on the influencing factor evaluation index to determine a comprehensive production score for each oil well.

[0007] After monitoring the production data of the oil wells mined above the oil field in the heavy oil reservoir, the embodiment of the present application can first divide the oil wells with different production into multiple regions according to the obtained production data, and then perform grey correlation analysis on the production influencing factors for each oil well in the same level, that is, determine the specific influencing factors of each different oil well and the correlation between the influencing factors, and then further determine the evaluation index of each influencing factor, so as to facilitate the subsequent clustering and weighted calculation, thereby generating a comprehensive production score for each oil well. It can further help in the production of oil wells in heavy oil reservoirs, which is conducive to the comprehensive evaluation of the production of oil wells, and at the same time analyze the production influencing factors of different oil wells, and accurately judge the influencing factors of the production of different oil wells, which is conducive to taking targeted measures based on the changing factors of oil well production.

[0008] In a feasible implementation manner, the production data of all oil wells in a heavy oil reservoir oilfield is obtained, specifically comprising: collecting and monitoring data on the oil wells in the heavy oil reservoir oilfield according to a preset sampling period to obtain historical single well data; wherein the historical single well data at least includes: estimated production data, recovery ratio data, water injection data, reservoir pressure data, geological change data, oil layer thickness data and oil and gas reservoir temperature data; each type of data in the historical single well data is respectively processed by curve chart generation based on the sampling period to obtain a plurality of curve distribution graphs; wherein the abscissa of the curve distribution graph is the sampling period, and the ordinate is the specific value of each type of data; the corresponding points of the plurality of curve distribution graphs are fused so that each fused point is a real production value point; and the fused curve is determined as a production data curve; based on the production data curve, the production data of all the oil wells are determined.

[0009] In a feasible implementation, based on the production data, the oil wells are divided into regions so that several oil wells corresponding to similar production data are in the same region, specifically including: marking the oil wells with serial numbers according to the value of the curve of the production data to obtain a marked oil well sequence; based on the difference factors of each block oil field in the heavy oil reservoir oil field, the heavy oil reservoir oil field is color-marked under the same difference factor to obtain a color-marked region; wherein the difference factor includes a fault cutting difference factor and an edge and bottom water energy factor; the marked oil well sequence is divided into regions through the color-marked region to obtain several marked oil well sequences in the same color-marked region; the production data corresponding to the several marked oil well sequences are approximately judged to obtain a primary division region; and an abnormal marked oil well sequence is screened out; the production data corresponding to the abnormal marked oil well sequence is approximately judged to determine an approximately abnormal marked oil well sequence; and the oil field region where the approximately abnormal marked oil well sequence is located is divided twice to obtain a secondary division region; based on the primary division region and the secondary division region, the same region corresponding to similar production data is determined.

[0010] In a feasible implementation, a grey correlation analysis of the production influencing factors is performed on each oil well in the same area to determine the correlation of the influencing factors of each oil well, specifically including: performing an overall data analysis on the production data of each oil well in the same level division area in the same area to determine the production influencing factors of each oil well; wherein the geological factors at least include: porosity, permeability and heavy oil viscosity; the development factors at least include: perforation thickness, production pressure difference, completion method and interlayer interference; performing data sequence analysis on the production influencing factors to determine the influencing factor sequence matrix; The influencing factor sequence matrix is ​​dimensionless processed, and an absolute difference matrix is ​​determined based on a reference sequence and a comparison sequence in the influencing factor sequence matrix; the absolute difference matrix is ​​transformed into a correlation coefficient matrix based on the production influencing factors; based on the correlation coefficient matrix, a correlation degree is calculated for each influencing factor in the production influencing factors to obtain the correlation degree of the influencing factors of each oil well; wherein the correlation degree is calculated as an average calculation of the correlation coefficients between the comparison sequence and the reference sequence in the correlation coefficient matrix; the influencing factor correlation degree is used to characterize the correlation degree of each influencing factor in the production influencing factors to the production data.

[0011] In a feasible implementation manner, before performing correlation analysis and evaluation on the production influencing factors according to the influencing factor correlation to obtain the influencing factor evaluation index of each oil well, the method also includes: obtaining historical evaluation indicators related to the influencing factor correlation; performing correlation evaluation on each influencing factor in the influencing factor correlation through the historical evaluation indicators to determine the correlation coefficient of each influencing factor; based on the correlation coefficient, generating a correlation coefficient matrix between each influencing factor; and based on the correlation coefficient matrix, determining the influencing factor evaluation data in the influencing factor correlation; and constructing an influencing factor index system for correlation evaluation in the influencing factor correlation according to the influencing factor evaluation data.

[0012] In a feasible implementation manner, the production influencing factors are subjected to correlation analysis and evaluation according to the correlation of the influencing factors to obtain the influencing factor evaluation index of each oil well, specifically including: determining the rough set distinction matrix of the production influencing factors through the influencing factor index system and based on the correlation of the influencing factors; obtaining the initial main evaluation index according to the main influencing factor index items in the rough set distinction matrix; obtaining the candidate main evaluation index according to the secondary influencing factor index items in the rough set distinction matrix; and merging the initial main evaluation index with the candidate main evaluation index to obtain a number of influencing factor evaluation indexes for each oil well.

[0013] In a feasible implementation, the influencing factor evaluation indicators are clustered and weighted to determine the comprehensive production score of each oil well, specifically including: obtaining the indicator weight of each influencing factor evaluation indicator according to a preset evaluation indicator cluster; judging the fuzzy degree of the influencing factor evaluation indicator of each oil well according to the indicator weight and the influencing factor evaluation indicator through a preset fuzzy evaluation rule, and constructing a fuzzy judgment matrix; determining the fuzzy score of each influencing factor evaluation indicator based on the fuzzy judgment matrix; and weighting the fuzzy score according to the primary and secondary levels of the influencing factor evaluation indicator to obtain a comprehensive production score for the production data in each oil well.

[0014] In a feasible implementation, after clustering and decentralizing the evaluation indicators of the influencing factors to determine the comprehensive production score of each oil well, the method further includes: based on the comprehensive production score, performing graphic and text generation processing on the oil well regarding the production influencing factors to obtain graphic and text data; identifying and marking abnormal influencing factors in the graphic and text data to determine the actual production image factors of the oil well.

[0015] In a second aspect, an embodiment of the present application also provides an oil well data evaluation device based on a heavy oil reservoir, the device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, so that the at least one processor can execute an oil well data evaluation method based on a heavy oil reservoir as described in any of the above embodiments.

[0016] In a third aspect, an embodiment of the present application further provides a non-volatile computer storage medium, characterized in that the storage medium is a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, each of which includes instructions, and when the instructions are executed by a terminal, the terminal executes an oil well data evaluation method based on a heavy oil reservoir as described in any of the above embodiments.

[0017] The present application provides an oil well data evaluation method, device and medium based on heavy oil reservoirs. Compared with the prior art, the present application has the following beneficial technical effects:

[0018] After monitoring the production data of the oil wells produced above the oil field in the heavy oil reservoir, it is possible to first divide the oil wells with different production into multiple regions according to the obtained production data, and then conduct a grey correlation analysis of the production influencing factors for each oil well in the same level, that is, determine the specific influencing factors of each different oil well and the correlation between the influencing factors, and then further determine the evaluation index of each influencing factor, so as to facilitate the subsequent clustering and weighted calculation, thereby generating a comprehensive production score for each oil well. It can further help in the production of oil wells in heavy oil reservoirs, which is conducive to the comprehensive evaluation of the production of oil wells, and at the same time analyze the production influencing factors of different oil wells, and accurately judge the influencing factors of different oil well production, which is conducive to taking targeted measures based on the changing factors of oil well production. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0020] Figure 1 A flow chart of an oil well data evaluation method based on heavy oil reservoirs provided in an embodiment of the present application;

[0021] Figure 2A schematic diagram of the structure of an oil well data evaluation device based on a heavy oil reservoir provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0023] The present application embodiment provides an oil well data evaluation method based on heavy oil reservoirs, such as Figure 1 As shown, the oil well data evaluation method based on heavy oil reservoir specifically includes steps S101-S105:

[0024] S101. Obtain production data of all oil wells in a heavy oil reservoir.

[0025] Specifically, based on the exploitation of the heavy oil reservoir that has been in operation, it is necessary to collect and monitor the data of the oil wells in the heavy oil reservoir oil field according to the preset sampling period to obtain the historical single well data, that is, to statistically analyze the data produced by the single well within a certain sampling period, and to generate the historical single well data regularly according to the sampling period. Among them, the historical single well data at least includes: estimated production data, recovery ratio data, water injection data, reservoir pressure data, geological change data, oil layer thickness data and oil and gas reservoir temperature data.

[0026] Furthermore, each type of data in the historical single well data is processed into a curve chart based on the sampling period to obtain a number of curve distribution graphs, wherein the horizontal axis of the curve distribution graph is the sampling period, and the vertical axis is the specific value of each type of data.

[0027] In one embodiment, corresponding curve distribution diagrams are drawn one by one based on the various data in the historical single well data obtained, so as to reflect the historical period situation of each type of historical single well data.

[0028] Furthermore, corresponding points of several curve distribution graphs are fused so that each fused point is a real yield value point, and the fused curve is determined as the yield data curve.

[0029] Furthermore, based on the production data curve, the production data of all oil wells are determined.

[0030] In one embodiment, each curve distribution map is fused one by one, that is, it is necessary to use multiple curve distribution maps as the data basis, and then comprehensively calculate the corresponding multiple historical single well data at each time point to fuse the real production value point, that is, it is necessary to preprocess the data, eliminate some noise factors, and also combine the real production data of multiple dimensions to finally obtain clean production data.

[0031] S102: Based on the production data, the oil wells are divided into regions so that several oil wells corresponding to similar production data are in the same region.

[0032] Specifically, according to the numerical values ​​of the production data curve, the oil wells are labeled with serial numbers to obtain a labeled oil well sequence.

[0033] Furthermore, based on the difference factors of each fault block oilfield in the heavy oil reservoir, the heavy oil reservoir is color-coded under the same difference factors to obtain the color-coded area. The difference factors include the fault cutting difference factor and the edge and bottom water energy factor.

[0034] Furthermore, the marked oil well sequence is divided into regions by color-marked regions, and a plurality of marked oil well sequences in the same color-marked regions are obtained.

[0035] Furthermore, the production data corresponding to several annotated oil well sequences are approximated to obtain the first-level division area, and the abnormally annotated oil well sequences are screened out.

[0036] Furthermore, the production data corresponding to the abnormally marked oil well sequence is approximately judged to determine the approximately abnormally marked oil well sequence, and the oil field area where the approximately abnormally marked oil well sequence is located is divided twice to obtain the secondary division area.

[0037] Furthermore, based on the primary and secondary division areas, the same area corresponding to similar production data is determined. By dividing into different regional layers, the oil well areas corresponding to similar production data can be better reflected. The secondary division of some high-yield or low-yield oil wells in the primary division area can better reflect the actual situation of the oil well output value, rather than simply dividing by area, achieving a more scientific and accurate oil well area division, which is conducive to the overall planning of each oil well.

[0038] S103, performing grey correlation analysis on the factors affecting production of each oil well in the same area, and determining the correlation degree of the factors affecting production of each oil well. The factors affecting production include geological factors and development factors.

[0039] Specifically, the production data of each oil well in the same level of the same area is analyzed as a whole to determine the factors affecting the production of each oil well. Among them, geological factors at least include: porosity, permeability and heavy oil viscosity. Development factors at least include: perforation thickness, production pressure difference, completion method and interlayer interference.

[0040] Furthermore, the factors affecting production are subjected to data sequence analysis to determine the sequence matrix of the factors affecting production.

[0041] Furthermore, the influencing factor sequence matrix is ​​dimensionless, and the absolute difference matrix is ​​determined based on the reference sequence and the comparison sequence in the influencing factor sequence matrix. Generally, the original influencing factor sequence matrix has different dimensions or orders of magnitude. In order to ensure the reliability of the analysis results, the variable sequence needs to be dimensionless. Commonly used dimensionless methods include averaging method, initialization method, etc.

[0042] Furthermore, the absolute difference matrix is ​​transformed into a correlation coefficient matrix based on the factors affecting production. The maximum number and the minimum number in the absolute difference matrix are the maximum difference and the minimum difference. The data transformation of the absolute difference matrix can be completed by using the maximum difference and the minimum difference, and then the above correlation coefficient matrix can be obtained.

[0043] Furthermore, based on the correlation coefficient matrix, the correlation degree of each influencing factor in the production influencing factor is calculated to obtain the correlation degree of the influencing factor of each oil well. The correlation degree is calculated as the average calculation of the correlation coefficient between the comparison sequence and the reference sequence in the correlation coefficient matrix. The correlation degree of the influencing factor is used to characterize the degree of correlation of each influencing factor in the production influencing factor with the production data.

[0044] As a feasible implementation method, the commonly used oil well production analysis methods include dynamic data method, tracer method, well test data method, fuzzy mathematics method, grey correlation analysis method, etc. Grey correlation analysis method is highly favored in determining the main factors affecting oil well production decline due to its strong applicability and high accuracy. Taking into account the dynamic and static factors affecting the change of oil well production, the method of applying grey correlation analysis to the factors affecting the change of oil well production in N oil field provides a basis for taking targeted measures.

[0045] S104. According to the correlation degree of the influencing factors, correlation analysis and evaluation are performed on the production influencing factors to obtain the influencing factor evaluation index of each oil well.

[0046] Specifically, a historical evaluation index related to the influencing factor correlation is obtained. Through the historical evaluation index, each influencing factor in the influencing factor correlation is evaluated for correlation, and the correlation coefficient of each influencing factor is determined.

[0047] Furthermore, based on the correlation coefficient, a correlation coefficient matrix between each influencing factor is generated. Based on the correlation coefficient matrix, the influencing factor evaluation data in the influencing factor correlation is determined. Based on the influencing factor evaluation data, an influencing factor index system for correlation evaluation in the influencing factor correlation is constructed.

[0048] Furthermore, through the influencing factor index system and based on the correlation of influencing factors, the rough set discrimination matrix of production influencing factors is determined.

[0049] Furthermore, the initial main evaluation index is obtained according to the main influencing factor index items in the rough set distinction matrix.

[0050] Furthermore, according to the secondary influencing factor index items in the rough set discrimination matrix, candidate main evaluation indexes are obtained. The initial main evaluation index and the candidate main evaluation index are combined to obtain several influencing factor evaluation indexes for each oil well.

[0051] As a feasible implementation method, a rough set distinguishing matrix can be used to reduce the indicator dimension of production influencing factors and maximize the retention of the original data information. In the influencing factor indicator system, there are several indicators, and the meanings reflected by these indicators have a strong correlation. In the case of limited data, too many variables will reduce the degree of freedom of the model and thus affect the accuracy. In order to meet the subsequent classification and fitting requirements, the rough set distinguishing matrix can be used to remove redundant data and extract core indicators, that is, to extract the initial main evaluation indicators and candidate main evaluation indicators, so as to determine several actual influencing factor indicators in each oil well. In addition, the element item with the attribute combination number of 1 in the rough set distinguishing matrix indicates that the attribute must be retained, and all attributes combined into one in the matrix are the core indicators of the decision table.

[0052] S105, clustering and weighting the evaluation indicators of the influencing factors to determine the comprehensive production score of each oil well.

[0053] Specifically, it is necessary to first obtain the weight of each influencing factor evaluation index according to the preset evaluation index clustering clusters. Through the preset fuzzy evaluation rules, and according to the index weight and the influencing factor evaluation index, the fuzzy degree of the influencing factor evaluation index of each oil well is judged, and the fuzzy judgment matrix is ​​constructed.

[0054] Furthermore, based on the fuzzy judgment matrix, the fuzzy scores of the evaluation indicators of each influencing factor are determined. According to the primary and secondary levels of the evaluation indicators of the influencing factors, the fuzzy scores are weighted to obtain the comprehensive production score of each oil well on the production data.

[0055] As a feasible implementation method, the K-means clustering algorithm can first arbitrarily select k objects from n data objects as the initial cluster centers. For the remaining objects, they can be assigned to the most similar clusters (represented by the cluster center) according to the similarity (distance) between other objects and the cluster center; then the cluster center of each new cluster is calculated, and the cluster center can be obtained by calculating the mean of all objects in the cluster. This process is repeated until the standard measurement function begins to converge, and the mean square error can usually be used as the standard measurement function. The k clusters have the following characteristics: each cluster itself is as compact as possible, and the clusters are as separated as possible.

[0056] Furthermore, according to the comprehensive production score, the oil well is processed for the graphic generation of factors affecting production to obtain graphic data. The abnormal factors affecting the graphic data are identified and marked to determine the actual production image factors of the oil well.

[0057] In one embodiment, by determining the primary and secondary levels of the evaluation indicators, it is possible to ensure that appropriate weights are given to different evaluation indicators when calculating the fuzzy score. This helps to more accurately reflect the importance and influence of different indicators in the evaluation results. Improve the objectivity and reliability of the evaluation results. Based on the fuzzy judgment matrix, quantitative data of the evaluation indicators can be determined. This helps to convert the fuzzy evaluation into quantifiable data, which is convenient for subsequent comparison and analysis. The fuzzy score is weighted to obtain a comprehensive production score for the production data in each oil well.

[0058] In addition, the present application also provides an oil well data evaluation device based on heavy oil reservoirs, such as Figure 2 As shown, the oil well data evaluation device 200 based on heavy oil reservoir specifically includes:

[0059] At least one processor. And a memory in communication with the at least one processor. The memory stores instructions executable by the at least one processor, so that the at least one processor can execute:

[0060] Obtain production data for all oil wells in a heavy oil reservoir field;

[0061] Based on the production data, the oil wells are divided into regions so that several oil wells corresponding to similar production data are in the same region;

[0062] Grey correlation analysis of production influencing factors is conducted on each oil well in the same area to determine the correlation of the influencing factors of each oil well; the production influencing factors include geological factors and development factors;

[0063] According to the correlation degree of influencing factors, the correlation analysis and evaluation of production influencing factors are carried out to obtain the evaluation index of influencing factors for each oil well;

[0064] The evaluation indicators of influencing factors are clustered and weighted to determine the comprehensive production score of each oil well.

[0065] The present application provides an oil well data evaluation method, equipment and medium based on heavy oil reservoirs. After monitoring the production data of oil wells exploited above the oil field in the heavy oil reservoir, it can first divide the oil wells with different production into multiple regions according to the obtained production data, and then conduct a gray correlation analysis of the production influencing factors for each oil well in the same level, that is, determine the specific influencing factors of each different oil well and the correlation between the influencing factors, and then further determine the evaluation index of each influencing factor, so as to facilitate the subsequent clustering and weighted calculation, thereby generating a comprehensive production score for each oil well. It can further help in the production of oil wells in heavy oil reservoirs, which is conducive to the comprehensive evaluation of the production of oil wells, and at the same time analyze the production influencing factors of different oil wells, and accurately judge the influencing factors of the production of different oil wells, which is conducive to taking targeted measures based on the changing factors of oil well production.

[0066] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0067] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0068] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0069] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0070] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0071] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0072] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0073] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the embodiments of the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for evaluating oil well data based on heavy oil reservoirs, characterized in that: The method comprises: Obtain production data for all oil wells in a heavy oil reservoir field; Based on the production data, the oil wells are divided into regions so that several oil wells corresponding to similar production data are in the same region; Conducting grey correlation analysis on factors affecting production of each oil well in the same area to determine the correlation of factors affecting production of each oil well; wherein the factors affecting production include geological factors and development factors; According to the correlation degree of the influencing factors, the production influencing factors are evaluated by correlation analysis to obtain the evaluation index of the influencing factors of each oil well; The evaluation indexes of the influencing factors are clustered and weighted to determine the comprehensive production score of each oil well.

2. The oil well data evaluation method based on heavy oil reservoir according to claim 1, characterized in that: Obtain production data for all oil wells in a heavy oil reservoir field, including: According to a preset sampling period, data is collected and monitored for the oil wells in the heavy oil reservoir oil field to obtain historical single well data; wherein the historical single well data at least includes: estimated production data, recovery ratio data, water injection data, reservoir pressure data, geological change data, oil layer thickness data and oil and gas reservoir temperature data; Each type of data in the historical single well data is processed into a curve chart based on the sampling period to obtain a plurality of curve distribution charts; wherein the abscissa of the curve distribution chart is the sampling period, and the ordinate is the specific value of each type of data; The plurality of curve distribution graphs are subjected to a fusion process of corresponding points, so that each fusion point is a real yield value point; and the fused curve is determined as a yield data curve; Based on the production data curve, the production data of all the oil wells are determined.

3. The oil well data evaluation method based on heavy oil reservoir according to claim 1, characterized in that: Based on the production data, the oil wells are divided into regions so that several oil wells corresponding to similar production data are in the same region, specifically including: According to the numerical value of the curve of the production data, the oil wells are labeled with serial numbers to obtain a labeled oil well sequence; Based on the difference factors of each fault block oil field in the heavy oil reservoir oil field, the heavy oil reservoir oil field is color-coded under the same difference factors to obtain a color-coded area; wherein the difference factors include fault cutting difference factors and edge and bottom water energy factors; By using the color-marked regions, the marked oil well sequence is divided into regions to obtain a plurality of marked oil well sequences in the same color-marked regions; Approximately judge the production data corresponding to the plurality of annotated oil well sequences to obtain a primary division area; and filter out abnormal annotated oil well sequences; Approximately judge the production data corresponding to the abnormally marked oil well sequence to determine the approximate abnormally marked oil well sequence; and divide the oil field area where the approximate abnormally marked oil well sequence is located into secondary divisions to obtain secondary division areas; Based on the primary divided area and the secondary divided area, the same area corresponding to similar production data is determined.

4. The oil well data evaluation method based on heavy oil reservoir according to claim 1, characterized in that: Grey correlation analysis of production influencing factors is performed on each oil well in the same area to determine the correlation of the influencing factors of each oil well, specifically including: Performing an overall data analysis on the production data of each of the oil wells in the same level of the same area to determine the production influencing factors of each of the oil wells; wherein the geological factors at least include: porosity, permeability and heavy oil viscosity; the development factors at least include: perforation thickness, production pressure difference, completion method and interlayer interference; Performing data sequence analysis on the yield influencing factors to determine an influencing factor sequence matrix; Performing dimensionless processing on the influencing factor sequence matrix, and determining an absolute difference matrix based on a reference sequence and a comparison sequence in the influencing factor sequence matrix; Transforming the absolute difference matrix into a correlation coefficient matrix based on the yield influencing factors; Based on the correlation coefficient matrix, the correlation degree of each influencing factor among the production influencing factors is calculated to obtain the correlation degree of the influencing factors of each oil well; wherein, the correlation degree is calculated as the average calculation of the correlation coefficient between the comparison sequence and the reference sequence in the correlation coefficient matrix; the influencing factor correlation degree is used to characterize the degree of correlation of each influencing factor among the production influencing factors to the production data.

5. The oil well data evaluation method based on heavy oil reservoir according to claim 1, characterized in that: Before performing correlation analysis and evaluation on the production influencing factors according to the correlation degree of the influencing factors to obtain the influencing factor evaluation index of each oil well, the method further includes: Obtaining historical evaluation indicators related to the correlation of the influencing factors; By using the historical evaluation index, each influencing factor in the influencing factor correlation degree is evaluated for relevance, and a correlation coefficient of each influencing factor is determined; Based on the correlation coefficient, a correlation coefficient matrix between each influencing factor is generated; and based on the correlation coefficient matrix, influencing factor evaluation data in the influencing factor correlation degree is determined; According to the influencing factor evaluation data, an influencing factor index system for correlation evaluation in the influencing factor correlation degree is constructed.

6. The oil well data evaluation method based on heavy oil reservoir according to claim 5, characterized in that: According to the correlation degree of the influencing factors, the production influencing factors are analyzed and evaluated to obtain the influencing factor evaluation index of each oil well, which specifically includes: Determine the rough set discrimination matrix of the production influencing factors through the influencing factor index system and based on the influencing factor correlation degree; According to the main influencing factor index items in the rough set distinction matrix, an initial main evaluation index is obtained; Obtaining candidate main evaluation indicators according to the secondary influencing factor indicator items in the rough set discrimination matrix; The initial main evaluation index and the candidate main evaluation index are combined to obtain several influencing factor evaluation indexes of each oil well.

7. The oil well data evaluation method based on heavy oil reservoir according to claim 1, characterized in that: The evaluation index of the influencing factors is clustered and weighted to determine the comprehensive score of the production of each oil well, which specifically includes: According to the preset evaluation index clustering clusters, the indicator weight of each of the influencing factor evaluation indicators is obtained; By using the preset fuzzy evaluation rules and according to the indicator weight and the influencing factor evaluation indicator, the fuzzy degree of the influencing factor evaluation indicator of each oil well is judged, and a fuzzy judgment matrix is ​​constructed; Based on the fuzzy judgment matrix, determining the fuzzy score of each of the influencing factor evaluation indicators; The fuzzy scores are weighted according to the primary and secondary levels of the evaluation indicators of the influencing factors to obtain a comprehensive production score for the production data in each of the oil wells.

8. The oil well data evaluation method based on heavy oil reservoir according to claim 1, characterized in that: After clustering and weighting the evaluation indicators of the influencing factors to determine the comprehensive production score of each oil well, the method further includes: According to the comprehensive production score, the oil well is processed with graphics and texts related to the production influencing factors to obtain graphic and text data; The abnormal influencing factors in the graphic data are identified and marked to determine the actual production image factors of the oil well.

9. An oil well data evaluation device based on heavy oil reservoirs, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, so that the at least one processor can execute the oil well data evaluation method based on heavy oil reservoir according to any one of claims 1-8.

10. A non-volatile computer storage medium, characterized in that: The storage medium is a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, each of which includes instructions, and when the instructions are executed by the terminal, the terminal executes the oil well data evaluation method based on heavy oil reservoirs according to any one of claims 1-8.

Images