Natural fracture development group system identification method and system fusing well drilling and logging data, and terminal
By integrating drilling and well recording data and combining deep learning algorithms, automatic prediction of fracture development groups is achieved, and the problems of high identification costs and low accuracy in the existing technology are solved, which significantly reduces exploration and development costs and improves identification efficiency and accuracy.
Patent Information
- Application Number
- CN202510176938.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-18
- Publication Date
- 2025-06-06
AI Technical Summary
In the prior art, the problem of high cost and low accuracy of identifying crack development teams is high.
By integrating drilling and well recording data, relevant parameters of a single well are obtained, including core rolling scan photos, imaging logging crack identification results, well recording and full hydrocarbon data. Automatic prediction of fracture development systems is achieved by using core depth relocation, imaging logging full-section fracture identification, well recording data label establishment, nearest neighbor component analysis and feedforward neural network model.
It significantly reduces the cost of crack identification, improves identification efficiency, reduces subjectivity and uncertainty, provides scientific basis for the optimization of well site deployment and development segments, and optimizes reservoir development plans.
Smart Images
Figure CN120105079A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of exploration technology, and in particular relates to a method, system and terminal for identifying natural fracture development groups integrating drilling and logging data. Background Art
[0002] Fractured oil and gas reservoirs are not only the most eye-catching exploration direction in the world's oil and gas industry, but also occupy a very important position in my country in recent years and have become a hot spot for exploration and development. Fractures are the main storage space and migration channels of oil reservoirs, so the characterization and identification of natural fractures are particularly important.
[0003] In recent years, predecessors have actively used logging data to identify and evaluate fractured reservoirs. Due to the late development of logging technology, it is basically limited to the identification of fractured reservoirs, and no qualitative analysis of fracture types in fractured reservoirs has been conducted. Among them, the analysis of fractures during drilling is easily affected by engineering parameters and lithology changes, and the identification of fractures using gas logging data can only give a rough judgment on the degree of fracture development.
[0004] At present, the method of identifying fractured oil and gas reservoirs is to observe and describe the fracture characteristics through thin sections, scanning electron microscopes, cores, and imaging logging to obtain the occurrence, development density, combination mode, etc. of fractures. Although these methods are the most effective for fracture characterization and identification, the high cost and difficulty of obtaining cores in the entire well section of the target layer lead to excessively high costs for identifying fracture types; and most existing single well coring is very limited and has poor continuity, and the imaging logging projects of the entire well section are only for key wells, so the description of fractures is not comprehensive due to too few cores or imaging logging, which is easily affected by subjective factors. However, all drilling in my country must have drilling and logging data. Well leakage, well kick, gas logging of all hydrocarbons and drilling time are one of the essential objective data. Moreover, the cost and difficulty of obtaining drilling and logging data are lower than those of special logging and seismic such as imaging, which provides the necessary conditions for the study of natural fractures using drilling and logging data. Summary of the invention
[0005] The purpose of the present invention is to solve the defects of high cost and low precision in identifying fracture development groups in the prior art.
[0006] To achieve the above object, the present invention provides a method for identifying natural fracture development groups by integrating drilling and logging data, comprising: S1: Obtain relevant parameters of a known single well, including core rolling sweep photos of the single well, imaging logging fracture identification result photos corresponding to the whole well of the single well, single well core surface scanning gamma curve, single well electrical imaging logging gamma curve, logging drilling time and logging gas logging total hydrocarbon data; S2: Compare the single well core ground scanning gamma curve with the single well electrical imaging logging gamma curve to obtain a curve trend similar area of the ground scanning gamma curve of the core on the electrical imaging logging gamma curve, thereby determining the corresponding depth of the core in the whole well, completing the core depth homing, and obtaining a core homing photo; Compare the core homing photos with the imaging logging fracture identification result photos, analyze the response characteristics of the core fractures in the imaging, and determine the imaging logging fracture identification plate corresponding to the depth of the core; perform imaging logging full-well section fracture identification based on the imaging logging fracture identification plate; obtain the imaging logging full-well section fracture development group system based on the imaging logging full-well section fracture identification results; S3: Determine the base value based on the logging drilling time and logging gas logging data of the thick sandstone layer section where fractures are not developed; determine the logging drilling time and logging gas logging total hydrocarbon amplitude data corresponding to each fracture development group system based on the imaging logging fracture development group system and the corresponding logging drilling time and logging gas logging total hydrocarbon data; establish data labels for different groups of fracture development sections and data labels for fracture undeveloped sections based on different fracture development groups; S4: The correlation between the amplitude values of total hydrocarbon and drilling time and the fracture development group system of the whole well is calculated and analyzed by the neighboring component analysis method, and the weight of fracture group identification is determined. Based on the feedforward neural network, the imaging logging full-well section fracture development group identification model is constructed; S5: Based on the logging drilling time and logging gas logging full hydrocarbon data of the unknown single well, the fracture development group identification model of the whole well section of the imaging logging is used to predict the fracture development group category of the unknown adjacent single well.
[0007] Furthermore, the specific method of imaging logging fracture identification chart in step S3 is as follows: By comparing the core retrieval photos and imaging logging pictures, cracks on the core will show corresponding features on the imaging logging at the corresponding depth segment. Core fractures are classified into different inclinations, different layer penetrations, and whether they penetrate the wellbore. Each type of fracture will show different features on the imaging logging. All fractures with different characteristics on the core have different display characteristics in the imaging, which are combined to form an identification plate for core fractures by imaging logging.
[0008] Furthermore, the imaging logging full-well section fracture development group system in step S2 includes: Unidentified fracture development groups, single-group isolated fracture development groups, single-group parallel fracture development groups, double-group conjugate fracture development groups, and multiple-group network fracture development groups.
[0009] Further, the step S3 comprises: S301, firstly, the drilling and logging data of a single well are loaded into the resform software in the form of two continuous curves, and the values of the fracture development and fracture non-development areas are extracted from the drilling and logging curves of the resform software, and the logging drilling time corresponding to each fracture development group is subtracted from the logging drilling time at the fracture non-development area to obtain the logging drilling time amplitude value of each fracture development group; the logging gas logging total hydrocarbon data corresponding to each fracture development group is subtracted from the logging gas logging total hydrocarbon data at the fracture non-development area to obtain the logging total hydrocarbon amplitude value of each fracture development group; S302, constructing a fracture development group identification model for the entire well section according to the logging drilling amplitude value and the logging total hydrocarbon amplitude value of each fracture development group.
[0010] A natural fracture development group identification system using the natural fracture development group identification method integrating drilling and logging data, the natural fracture development group identification system comprising: Data and image import module: used to obtain core information pictures and data of various single wells; Data and image processing module: used for core reading and positioning, imaging fracture identification and division of development groups; Create data label module: used to establish data labels of different groups of fracture development segments and data labels of fracture undeveloped segments; Data analysis and model building module: used to analyze the correlation of development group logging data and establish a fracture development group identification model for the entire well section of imaging logging; Results output module: used to identify the development group of fractures in the entire well section.
[0011] A terminal device comprises a memory, a processor and a natural fracture development group system identification program stored in the memory and executable on the processor. When the processor executes the natural fracture development group system identification program, the natural fracture development group system identification method integrating drilling and logging data is implemented.
[0012] Beneficial effects: By analyzing the base value and amplitude changes of the drilling time and gas logging total hydrocarbon curves in the logging data, and using the deep learning algorithm model, the automatic prediction of the fracture development group system of a single well without coring or imaging logging is realized. This method breaks through the reliance of traditional technology on high-cost logging data, not only significantly improving the efficiency of fracture identification, but also reducing the subjectivity and uncertainty in the manual interpretation process. Compared with the traditional fracture identification method that relies on high-cost coring and imaging logging, this method reduces the demand for complex logging data through data modeling and algorithm prediction, and significantly reduces the cost of exploration and development. At the same time, through the identification of fracture development groups in the entire well section, it provides a scientific basis for well site deployment and optimization of development layers, and further optimizes the reservoir development plan. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] Figure 1 It is a flow chart of the method for identifying the development group of natural fractures provided by the present invention; Figure 2 This is an engineering example diagram of natural fracture development group identification provided by the present invention; Figure 3 It is a schematic diagram of the comparison and repositioning of the core surface scanning gamma curve and the electrical imaging logging gamma curve provided by the present invention; Figure 4 It is a core fracture identification chart provided by the present invention; Figure 5 A schematic diagram of the development group system corresponding to the imaging logging fracture identification provided by the present invention; Figure 6 A schematic diagram of the logging data corresponding to different fracture development groups provided by the present invention; Figure 7 A scatter plot of total hydrocarbons and different fracture development groups provided by the present invention; Figure 8 A scatter plot of drilling time and different fracture development groups provided by the present invention; Fig. 9 A schematic diagram of the correlation between total hydrocarbons, drilling time and different fracture development groups provided by the present invention; Fig.10 A schematic diagram of the weights of total hydrocarbons, drilling time and different fracture development groups provided by the present invention; Fig.11 A comparison chart of the artificially divided suture development groups provided by the present invention and the suture development groups predicted by the model of the present invention. DETAILED DESCRIPTION
[0014] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0015] The application principle of the present invention is further described below in conjunction with the accompanying drawings and specific embodiments.
[0016] Embodiment 1: like Figure 1-3 As shown in FIG. 1 , a natural fracture development group identification method integrating drilling and logging data is described as follows: S1. Obtain single well parameters Obtain relevant parameters of a known single well, including core rolling sweep photos of the single well, imaging logging fracture identification result photos corresponding to the whole well of the single well, single well core ground scanning gamma curve, single well electrical imaging logging gamma curve, logging drilling time and logging gas logging total hydrocarbon data.
[0017] The core rolling photograph is formed by scanning each core 360°, so that the morphology of the cracks can be observed at different angles; the ground scanning gamma curve of the single well core is obtained by continuously scanning all the cores with a gamma meter, and then the core depth is accurately returned to the actual underground depth based on the comparative analysis of the ground gamma curve and the underground gamma curve; imaging logging is the process of drilling, which uses various sensors and instruments downhole to obtain detailed data of the formation and can display it in a continuous image; the total hydrocarbon and drilling time curve is obtained through instrument measurement and processing during the drilling process.
[0018] S2. Obtain core retrieval photos, establish core fracture identification plates, and divide development groups A single-well core ground scanning gamma curve is used to compare features with a single-well electrical imaging logging gamma curve, and the depth of the single-well core ground scanning gamma curve is adjusted to unify the depth of the single-well core ground scanning gamma curve and the gamma curve trend obtained by electrical imaging logging, and a curve trend similarity area of the single-well core ground scanning gamma curve on the single-well electrical imaging logging gamma curve is analyzed, and based on the curve trend similarity area, the corresponding depth of the core in the whole well is determined to complete the core depth homing, thereby obtaining a core homing photo; The core homing photos were compared with the imaging logging fracture identification result photos to analyze the response characteristics of the core fractures in imaging. It was found that the large-scale fractures on the core that penetrated the wellbore were better identified in imaging, while the small-scale fractures that did not penetrate the wellbore could not be identified in imaging. The imaging logging fracture identification plate corresponding to the depth of the core was established ( Figure 4 ). Specifically, the core retrieval photos and imaging logging pictures are compared. The core retrieval is just to make the two in the same depth section; then the cracks on the core will show some characteristics on the imaging logging at the corresponding depth section. The core cracks are classified into different inclinations, different penetrations, and whether they penetrate the wellbore. Each type of crack will show different characteristics on the imaging logging. All the cracks with different characteristics on the core have different display characteristics in the imaging. The combination of them is the identification plate of the imaging logging for the core cracks.
[0019] According to the imaging logging fracture identification plate corresponding to the depth of the core, the imaging logging fracture identification is performed for the entire well section. According to the different combinations of fracture morphology on the imaging logging image, the categories of natural fracture development groups on the imaging logging are obtained ( Figure 5). According to the imaging logging identification results, the fractures are divided into small-scale fracture development groups that cannot be identified by imaging and large-scale fracture development groups that can be identified by imaging logging, which are further divided into unidentified fracture development groups, single-group isolated fracture development groups, single-group parallel fracture development groups, double-group conjugate fracture development groups and multi-group network fracture development groups.
[0020] S3. Obtain the logging base value and amplitude value of the fracture undeveloped and developed groups, and establish data labels Based on the logging drilling time and logging gas logging total hydrocarbon data of the thick sandstone layer without fracture development, the base value and the amplitude value of the logging data under different fracture development groups at the fracture development location are determined ( Figure 6 ); Specifically, firstly, the drilling and logging data of a single well are loaded into the resform software in the form of two continuous curves, and the values of the fracture development location and the fracture non-development location are extracted from the drilling and logging curves of the resform software, and the logging drilling time corresponding to each fracture development group is subtracted from the logging drilling time at the fracture non-development location to obtain the corresponding logging drilling time amplitude value of each fracture development group; and the logging gas logging total hydrocarbon data corresponding to each fracture development group is subtracted from the logging gas logging total hydrocarbon data at the fracture non-development location to obtain the corresponding logging gas logging total hydrocarbon amplitude value of each fracture development group.
[0021] The response characteristics of the logging data of different fracture development groups were analyzed by the expansion multiples of the amplitude values relative to the base value of the fracture-undeveloped section. Figure 7 , Figure 8 ). The total hydrocarbon value of the single-group fracture development group section is low, and there is no obvious increase compared with the non-fracture section; the total hydrocarbon value of the double-group fracture development group section increases by 2~5 times; the total hydrocarbon value of the multi-group fracture development group section increases by 3~10 times, and the drilling time of multi-group and double-group fractures is faster than that of the single-group fracture development group section. According to the development groups of different fractures, a large number of data labels of different groups of fracture development sections and data labels of fracture undeveloped sections are established.
[0022] S4. Constructing a model for identifying fracture development groups in the entire well section The amplitude values of total hydrocarbon and drilling time were normalized to eliminate the dimension effect. The correlation between the amplitude values of total hydrocarbon and drilling time and different fracture development groups was calculated and analyzed using the nearest component analysis (NCA) method. Fig. 9 ), and determine the fracture development group identification weight according to the analysis results ( Fig.10 The specific calculation formula of correlation is as follows:
[0023] Where: x i -x j is the distance between samples i and j in the new space, P ijrepresents the probability that sample i selects sample j as its nearest neighbor in the feature space, x k is the distance of the sample, P ii is the probability of sample i selecting sample j as its nearest neighbor in the feature space.
[0024] Based on the feedforward neural network algorithm, continuous feature data such as total hydrocarbon and drilling time are accepted as the input layer, and 2-3 hidden layers with decreasing data are designed. The activation function uses Softmax to convert the output into a probability distribution. Combined with the constraints of natural fracture control factors, a deep learning algorithm model (i.e., a full-well fracture development group identification model) is established. The fracture development group is iteratively trained using total hydrocarbon and drilling time data, and the data is divided into a training set, a test set, and a validation set. The predicted fracture development group results are highly similar to the artificial identification results on the imaging logging ( Fig.11 ). Through the above verification process, it can be concluded that this method can use logging data to more accurately identify different development groups of fractures.
[0025] S5. Prediction of fracture development group types By using the established feedforward neural network algorithm model and the only logging data, we can determine the fracture development group of the entire well section for a single well in the same well area that lacks coring and imaging logging, and calculate and identify the response characteristics of the logging data of different fracture development groups to assist in verification.
[0026] The natural fracture development group identification system provided by this embodiment that integrates drilling and logging data includes: Data and image import module: used to obtain core information pictures and data of various single wells; Data and image processing module: used for core depth tracing and imaging fracture identification and division of development groups; Create data label module: used to establish data labels of different groups of fracture development segments and data labels of fracture undeveloped segments; Data analysis and model building module: used to analyze the correlation of development group logging data and establish a fracture development group identification model for the entire well section of imaging logging; Results output module: used to identify the development group of fractures in the entire well section.
[0027] The key technical point of the present invention is that, based on the detailed comparison and identification of core and imaging logging, the response characteristics of different fracture development groups in the logging data are analyzed, and these response characteristics are iteratively trained using intelligent algorithms, so that a preliminary judgment can be made on the fracture development group of a single well in the entire well section of the same well area that lacks core and imaging logging.
[0028] The cost and difficulty of obtaining logging data are lower than those of coring, logging and seismic. When studying fractures, fracture researchers should take into account that the logging data response characteristics of different fracture development groups are different. They can also statistically analyze the response characteristics of logging data of fractures in different development groups, combine them with intelligent algorithms, and fully tap the most intuitive first-hand data for identifying fractured oil and gas layers, effectively solve the problems of lack of cores and fracture identification in single imaging logging wells, which has important guiding significance for exploration, development and production.
[0029] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. It can be understood by a person of ordinary skill in the art that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.
[0030] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for identifying natural fracture development groups by integrating drilling and logging data, characterized in that: include: S1: Obtain relevant parameters of a known single well, including core rolling sweep photos of the single well, imaging logging fracture identification result photos corresponding to the whole well of the single well, single well core surface scanning gamma curve, single well electrical imaging logging gamma curve, logging drilling time and logging gas logging total hydrocarbon data; S2: Compare the single well core ground scanning gamma curve with the single well electrical imaging logging gamma curve to obtain a curve trend similar area of the ground scanning gamma curve of the core on the electrical imaging logging gamma curve, thereby determining the corresponding depth of the core in the whole well, completing the core depth homing, and obtaining a core homing photo; Compare the core homing photos with the imaging logging fracture identification result photos, analyze the response characteristics of the core fractures in the imaging, and determine the imaging logging fracture identification plate corresponding to the depth of the core; perform imaging logging full-well section fracture identification based on the imaging logging fracture identification plate; obtain the imaging logging full-well section fracture development group system based on the imaging logging full-well section fracture identification results; S3: Determine the base value based on the logging drilling time and logging gas logging data of the thick sandstone layer section where fractures are not developed; determine the logging drilling time and logging gas logging total hydrocarbon amplitude data corresponding to each fracture development group system based on the imaging logging fracture development group system and the corresponding logging drilling time and logging gas logging total hydrocarbon data; establish data labels for different groups of fracture development sections and data labels for fracture undeveloped sections based on different fracture development groups; S4: The correlation between the amplitude values of total hydrocarbon and drilling time and the fracture development group system of the whole well is calculated and analyzed by the neighboring component analysis method, and the weight of fracture group identification is determined. Based on the feedforward neural network, the imaging logging full-well section fracture development group identification model is constructed; S5: Based on the logging drilling time and logging gas logging full hydrocarbon data of the unknown single well, the fracture development group identification model of the whole well section of the imaging logging is used to predict the fracture development group category of the unknown adjacent single well.
2. The method for identifying natural fracture development groups by integrating drilling and logging data according to claim 1, characterized in that: The specific method of imaging logging fracture identification chart in step S3 is as follows: By comparing the core retrieval photos and imaging logging pictures, cracks on the core will show corresponding features on the imaging logging at the corresponding depth segment. Core fractures are classified into different inclinations, different layer penetrations, and whether they penetrate the wellbore. Each type of fracture will show different features on the imaging logging. All fractures with different characteristics on the core have different display characteristics in the imaging, which are combined to form an identification plate for core fractures by imaging logging.
3. The method for identifying natural fracture development groups by integrating drilling and logging data according to claim 1, characterized in that: The imaging logging full-well section fracture development group system in step S2 includes: Unidentified fracture development groups, single-group isolated fracture development groups, single-group parallel fracture development groups, double-group conjugate fracture development groups, and multiple-group network fracture development groups.
4. The method for identifying natural fracture development groups by integrating drilling and logging data according to claim 1, characterized in that: The step S3 comprises: S301, firstly, the drilling and logging data of a single well are loaded into the resform software in the form of two continuous curves, and the values of the fracture development and fracture non-development areas are extracted from the drilling and logging curves of the resform software, and the logging drilling time corresponding to each fracture development group is subtracted from the logging drilling time at the fracture non-development area to obtain the logging drilling time amplitude value of each fracture development group; the logging gas logging total hydrocarbon data corresponding to each fracture development group is subtracted from the logging gas logging total hydrocarbon data at the fracture non-development area to obtain the logging total hydrocarbon amplitude value of each fracture development group; S302, constructing a fracture development group identification model for the entire well section according to the logging drilling amplitude value and the logging total hydrocarbon amplitude value of each fracture development group.
5. A natural fracture development group identification system using the natural fracture development group identification method integrating drilling and logging data as described in any one of claims 1 to 4, characterized in that: The natural fracture development group identification system includes: Data and image import module: used to obtain core information pictures and data of various single wells; Data and image processing module: used for core reading and positioning, imaging fracture identification and division of development groups; Create data label module: used to establish data labels of different groups of fracture development segments and data labels of fracture undeveloped segments; Data analysis and model building module: used to analyze the correlation of development group logging data and establish a fracture development group identification model for the entire well section of imaging logging; Results output module: used to identify the development group of fractures in the entire well section.
6. A terminal device, characterized in that: The method comprises a memory, a processor and a natural fracture development group identification program stored in the memory and executable on the processor. When the processor executes the natural fracture development group identification program, the method for natural fracture development group identification integrating drilling and logging data as described in any one of claims 1 to 4 is implemented.
Citation Information
Cited By
Method for identifying volcanic rock structure crack after weathering transformation
CN120910670A