Method and device for identifying development section interlayer of shale rich in organic matters

Abstract

The invention discloses an organic matter-rich shale development section interlayer recognition method and device, and the method comprises the steps: inputting a target well sensitive curve into a lithology recognition model to obtain binary lithology data, and recognizing non-rich organic matter shale in the binary lithology data as an interlayer; establishing a model: determining the lower limit of the GR value of the shale rich in organic matters according to the binarized lithologic data of the coring section of the sample well; taking the binarized lithology data of the coring section and the sensitive curve section as a sample, establishing a sample set, training a neural network model, establishing a lithology identification model, and inputting a GR value lower limit; sensitive curve screening: obtaining a plurality of sample points including binarization lithology types and values of the to-be-screened curves; projecting the sample points in a coordinate system comprising a plurality of parallel number axes, and connecting projection points of the same sample point on different number axes to obtain a vein line; and screening a sensitive curve according to the vein line distribution characteristics. According to the method, the organic matter-rich shale development section interlayer can be quickly and accurately identified through sensitive curve screening on the basis of lithological binary interpretation.

Description

Technical Field

[0001] The invention relates to the technical field of geophysical logging, and in particular to a method and a device for identifying interlayers in organic-rich shale development sections. Background Art

[0002] In recent years, the exploration and development of unconventional oil and gas resources in my country is in a stage of vigorous development. Among them, continental shale oil resources have great potential and have become the focus of exploration and development in the unconventional field. Since the continental lake basin is significantly affected by terrigenous sediments, the frequent development of interlayers is a very common lithofacies feature of the continental organic-rich shale section. In the national standard GB / T31483-2015, the thickness and proportion of interlayers in organic-rich shale sections are stipulated: the thickness of a single interlayer is not more than 1m, and the cumulative thickness of the interlayer accounts for less than 20% of the total thickness of the shale section. The existence of interlayers will have a strong impact on the generation, displacement, migration, and accumulation of shale oil during the accumulation period, as well as fracturing and seepage during the development stage. Therefore, it is particularly important to finely characterize the frequently developed interlayers in the organic-rich shale section.

[0003] Due to the high frequency of interlayers in organic-rich shale sections and thin single-layer thickness, under existing technical conditions, unless systematic coring is carried out, conventional logging and traditional logging interpretation methods are often unable to identify interlayers with high precision. However, due to the limitations of field exploration costs, large-scale drilling of coring wells is not realistic. In the process of shale oil production and research, we still have to rely more on logging and logging data, and even many old wells only have conventional logging curves available. Summary of the invention

[0004] The inventors found that the existing technology of lithology identification based on conventional logging curves has the problems of universality but insufficient lithology identification accuracy, large interference from human factors, and low manual identification efficiency. Therefore, it is urgent to develop an efficient and high-precision interlayer identification technology suitable for organic-rich shale layers.

[0005] In order to at least partially solve the technical problems existing in the prior art, the inventors have made the present invention, and through a specific implementation method, provide a method and device for identifying interlayers in organic-rich shale development sections, which can quickly and accurately identify interlayers in organic-rich shale development sections through sensitivity curve screening and based on the binary interpretation of lithology.

[0006] In a first aspect, an embodiment of the present invention provides a method for identifying interlayers in organic-rich shale development sections, comprising:

[0007] Inputting the sensitivity curve of the target well into the lithology identification model, obtaining the depth range of the organic-rich shale development section and the binary lithology data within the range according to the output result of the model, and identifying the non-organic-rich shale in the lithology data as an interlayer;

[0008] The lithology identification model is pre-established in the following manner: determining the GR value lower limit of organic-rich shale according to the binary lithology data of the coring section of the target layer of the sample well; taking the binary lithology data of the coring section and the curve section of the selected sensitivity curve as a sample to establish a sample set; using the sample set to train the selected neural network model to establish a lithology identification model, inputting the GR value lower limit into the lithology identification model, and the GR value lower limit is used to locate the organic-rich shale development section;

[0009] The type of sensitive curve is pre-screened in the following manner: a plurality of sample points of the target layer are obtained, each sample point includes a binary lithology type and the value of each curve to be screened; each sample point is projected into a coordinate system including a plurality of parallel axes, each axis corresponds to a different curve to be screened, and the projection points of the same sample point on different axes are connected to obtain a vein line; and at least one type of lithology sensitivity curve is screened according to the distribution characteristics of the vein line.

[0010] In a second aspect, an embodiment of the present invention provides an interlayer identification device for organic-rich shale development sections, the device comprising an interlayer identification module, a lithology identification model establishment module and a sensitivity curve screening module;

[0011] The interlayer identification module is used to input the sensitivity curve of the target well into the lithology identification model, obtain the depth range of the organic-rich shale development section and the binary lithology data within the range according to the model output result, and identify the non-organic-rich shale in the lithology data as an interlayer;

[0012] The lithology identification model is pre-established by the lithology identification model establishment module in the following manner: determining the GR value lower limit of organic-rich shale according to the binary lithology data of the coring section of the target layer of the sample well; taking the binary lithology data of the coring section and the curve section of the selected sensitivity curve as a sample to establish a sample set; using the sample set to train the selected neural network model to establish a lithology identification model, and inputting the GR value lower limit into the lithology identification model, and the GR value lower limit is used to locate the organic-rich shale development section;

[0013] The type of sensitive curve is pre-screened by the sensitive curve screening module in the following manner: obtaining multiple sample points of the target layer, each sample point including a binary lithology type and the value of each curve to be screened; projecting each sample point into a coordinate system including multiple parallel axes, each axis corresponding to a different curve to be screened, connecting the projection points of the same sample point on different axes to obtain a vein line; and screening at least one type of lithology sensitivity curve according to the distribution characteristics of the vein line.

[0014] In a third aspect, an embodiment of the present invention provides a computer storage medium, wherein the computer storage medium stores computer executable instructions, and when the computer executable instructions are executed by a processor, the above-mentioned method for identifying interlayers in organic-rich shale development sections is implemented.

[0015] In a fourth aspect, an embodiment of the present disclosure provides a server, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for identifying interlayers in organic-rich shale development sections when executing the program.

[0016] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:

[0017] (1) The method for identifying interlayers in organic-rich shale development sections provided by the embodiment of the present invention is aimed at the specific scenario of identifying thin interlayers in organic-rich shale development sections. It abandons the universal pursuit of conventional well logging lithological interpretation to interpret and characterize various lithologies developed in the study area separately, and limits the lithological interpretation objects to two types: organic-rich shale and interlayers (non-organic-rich shale). This reduces the multi-solution nature of well logging lithological interpretation and improves the interpretation accuracy. At the same time, it reduces the amount of calculation and improves the recognition speed of batch interpretation of multiple wells.

[0018] (2) The method for identifying interlayers in organic-rich shale development sections provided by the embodiment of the present invention only needs to use the core data of the sample well in the stage of establishing the lithology identification model. Once the modeling is completed, only conventional logging curves need to be used in the application stage to achieve high-precision characterization of organic-rich shale and interlayers. Under the premise of ensuring the interpretation accuracy, the requirements for data quality are greatly reduced.

[0019] (3) The method for identifying interlayers in organic-rich shale development sections provided in the embodiment of the present invention adopts artificial intelligence methods such as neural networks to eliminate human influence as much as possible and further improve the reliability of lithological interpretation.

[0020] (4) The method for identifying interlayers in organic-rich shale development sections provided in the embodiment of the present invention establishes a coordinate system including multiple parallel axes, each axis corresponding to a different curve to be screened, and draws vein lines corresponding to different sample points in the coordinate system, thereby realizing synchronous comparison of curves of different types in the same coordinate system, improving the accuracy of sensitive curve selection, making it less likely that sensitive curves will be missed, and greatly improving the screening efficiency.

[0021] (5) The method for identifying interlayers in organic-rich shale development sections provided in the embodiment of the present invention connects the projection points of the same sample point on different axes to obtain a vein line. One sample point corresponds to one vein line, and the possibility of two vein lines completely overlapping is very small, thereby avoiding the situation where a large number of points overlap due to a simple point projection method, so that the final lithology distribution vein line map is more complete and representative.

[0022] (6) The method for identifying interlayers in organic-rich shale development sections provided in the embodiment of the present invention reduces the influence of human subjective factors in the process of sensitive curve selection and improves the objectivity of the selection result by converting the correlation between logging curves and lithology into more intuitive line convergence and differentiation degrees.

[0023] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0024] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0026] Figure 1 This is a flow chart of a method for establishing a lithology identification model for an organic-rich shale development segment in Example 1 of the present invention;

[0027] Figure 2 This is a flow chart of a method for synchronously screening multiple wells, multiple curves and multiple lithology sensitivity curves in Embodiment 2 of the present invention;

[0028] Figure 3 This is an example diagram of a sample well in Embodiment 4 of the present invention;

[0029] Figure 4 This is an example diagram of the synchronous comparison and screening of sensitivity curves of all sample points and the lithology distribution vein line in the fourth embodiment of the present invention;

[0030] Figure 5 This is a process diagram of establishing a lithology identification model through a neural network in the fourth embodiment of the present invention;

[0031] Figure 6 A comparison diagram of the lithology profile and core description of the sample well automatically established by using the lithology identification model in the fourth embodiment of the present invention;

[0032] Figure 7 This is a comparison chart of the calibration results of the calibration well in the fourth embodiment of the present invention;

[0033] Figure 8 Schematic diagram of the structure of the interlayer identification device for organic-rich shale development section in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0035] It should be understood that the terms described in the present invention are only for describing special embodiments and are not intended to limit the present invention. In addition, for the numerical range in the present invention, it should be understood that each intermediate value between the upper and lower limits of the scope is also specifically disclosed. Each smaller range between the intermediate value in any stated value or stated range and any other stated value or intermediate value in the described range is also included in the present invention. The upper and lower limits of these smaller ranges can be independently included or excluded in the scope.

[0036] Unless otherwise indicated, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which the invention belongs. Although the present invention describes only preferred methods and materials, any methods and materials similar or equivalent to those described herein may also be used in the implementation or testing of the present invention. All documents mentioned in this specification are incorporated by reference to disclose and describe the methods and / or materials related to the documents. In the event of a conflict with any incorporated document, the content of this specification shall prevail.

[0037] The embodiment of the present application divides organic-rich shale and non-organic-rich shale based on the TOC lower limit of organic-rich shale. Specifically, the lithology of rocks with TOC greater than the lower limit is defined as organic-rich shale; and the lithology of rocks with TOC not greater than the lower limit is defined as non-organic-rich shale.

[0038] The lower limit of TOC of organic-rich shale is flexibly set according to the actual geological conditions of the study area, and can usually be set to 2%, 3% or 5%. Optionally, it can also be set to other values.

[0039] Embodiment 1

[0040] Embodiment 1 of the present invention provides a method for establishing a lithology identification model for an organic-rich shale development segment, and the process thereof is as follows Figure 1 As shown, the following steps are included:

[0041] Step S11: Determine the lower limit of the GR value of the organic-rich shale based on the binary lithology data of the core section of the target layer of the sample well.

[0042] Wells cored in the target layer of the study area are selected as sample wells; optionally, the selected wells can be divided into sample wells and verification wells. The relevant data of the verification wells do not participate in the training of the model and are only used for the later verification of the model.

[0043] Specifically, the binary lithology data of the coring section, including organic-rich shale and non-organic-rich shale, is obtained from the core description data, thin section identification data and TOC detection data of the coring section of the target layer of the sample well. The acquisition process includes the following steps:

[0044] (1) Based on the thin section identification data of the core sampling section of the target layer of the sample well, the lithology description data in the core description data is corrected to obtain preliminary lithology data, which includes mud shale.

[0045] The lithology description data in the core description data is only the lithology description made by geologists based on their experience of visual observation of the core. Due to the limitations of visual observation and the influence of subjective factors, the accuracy of the lithology description data needs to be further corrected. The thin section identification data can accurately realize the lithology naming, but the thin section identification data has limited sampling after all. Therefore, the lithology description data in the core description data is based on the verification of the thin section identification data to obtain preliminary lithology data.

[0046] The preliminary description data obtained may include clastic rocks such as shale, coarse sandstone, medium sandstone, fine sandstone and siltstone, and may also include carbonate rocks or other rock types.

[0047] (2) Based on the TOC detection data, the mudstone with a TOC value greater than the preset lower limit of the TOC of organic-rich shale in the preliminary lithological data is determined as organic-rich shale, and the binary lithological data of the coring section is obtained.

[0048] Mud shale with a TOC value not greater than the lower limit of the TOC value of organic-rich shale, as well as other lithologies except mud shale, are identified as non-organic-rich shale.

[0049] The lower limit of TOC of organic-rich shale is flexibly set according to the actual geological conditions of the study area, and can usually be set to 2%, 3% or 5%. Optionally, it can also be set to other values.

[0050] Determining the lower limit of the GR value of organic-rich shale may include, based on the binary lithology data and GR curve of the sample well, extracting the lithology and GR value of the sampling points with thin section identification data and TOC detection data; and obtaining the lower limit of the GR value of the organic-rich shale based on the lithology and GR values ​​of multiple sampling points.

[0051] Since the lithology identification in this embodiment is based on the well logging curve, the well logging curve of the sample well must first be standardized; after obtaining the preliminary lithology data or binary lithology data of the coring section, the standardized well logging curve is depth-reset.

[0052] The GR values ​​of the above sampling points are extracted from the GR curve after standardization and depth return.

[0053] Step S12: taking the binary lithology data of the coring section and the curve section of the selected sensitive curve as a sample to establish a sample set.

[0054] In some embodiments, after obtaining the binary lithology data of the coring section, the method further includes screening the sensitivity curves of organic-rich shale and non-organic-rich shale from all types of logging curves of the sample well.

[0055] The sensitivity analysis method can be used to select the lithology sensitivity curve for organic-rich shale and select the curve that is most sensitive to the organic-rich shale and its interlayer. The lithology sensitivity analysis method automatically calculates the correlation between each curve and the lithology and directly selects the curve with the best correlation. Optionally, the method in Example 2 can also be used to screen the sensitive curve.

[0056] Step S13: Use the sample set to train the selected neural network model, establish a lithology recognition model, and input the GR value lower limit into the lithology recognition model.

[0057] The lower limit of GR value is used to locate the development section of organic-rich shale.

[0058] Embodiment 2

[0059] Embodiment 2 of the present invention provides a method for synchronously screening multiple wells, multiple curves and multiple lithology sensitivity curves, and the process thereof is as follows Figure 2 As shown, the following steps are included:

[0060] Step S21: Acquire multiple sample points of the target layer.

[0061] Each sample point includes the binary lithology type and the value of each curve to be screened.

[0062] The curve to be screened may be depth-calibrated based on the binary lithology data of the sample well in the first embodiment, and a matching relationship between the lithology data and the curve to be screened in depth may be established to obtain a well logging lithology calibration chart.

[0063] The extraction of sample points can be based on the sampling points of the logging curve. For example, if the logging curve is sampled at 0.125m, the sample points are also sampled at 0.125m, or the samples are sampled after thinning.

[0064] The sampling method of the above-mentioned sample points is different from the traditional method of using rock sample collection points as calibration points. This improvement will greatly improve the richness and vertical continuity of sample data.

[0065] Multiple wells with continuous core samples in the target layer of the study area can be identified as sample wells. The sample wells are representative and comprehensive, thereby greatly reducing the impact of geological heterogeneity on the accuracy of lithology sensitivity curve screening.

[0066] Step S22: Project each sample point into a coordinate system including multiple parallel axes, each axis corresponding to a different curve to be screened.

[0067] Based on the well logging lithology calibration chart, the numerical distribution range of each curve to be screened is statistically analyzed.

[0068] A coordinate system containing multiple parallel number axes is established, and the two ends of the number axes in the coordinate system are aligned, and the values ​​at both ends match the corresponding numerical distribution range. The values ​​at both ends can be consistent with the two end values ​​of the corresponding numerical distribution range, or the minimum value of the values ​​at both ends can be less than the minimum value in the numerical distribution range, and the maximum value of the values ​​at both ends can be greater than the maximum value in the numerical distribution range.

[0069] Taking the logging curve GR as an example, if the numerical distribution range of GR in the target layer is 200 API to 500 API, the two end values ​​of the number axis corresponding to the logging curve GR can be set to 200 API and 500 API respectively.

[0070] In some embodiments, the numerical values ​​of the axes in the established coordinate system change in the same direction.

[0071] Taking the example that all number axes are distributed vertically, the values ​​of each number axis gradually increase from top to bottom, or gradually decrease from top to bottom.

[0072] Step S23: Connect the projection points of the same sample point on different axes to obtain a vein line.

[0073] Use line type or color to distinguish rock types.

[0074] Step S24: Screen at least one type of lithology sensitivity curve according to the distribution characteristics of the vein lines.

[0075] In some embodiments, the method may include, according to the distribution characteristics of vein lines on the numerical axis, selecting at least one type of lithology sensitivity curve based on the following understandings:

[0076] The more convergent the vein lines of organic-rich shale on a certain numerical axis are, and the more obvious the differentiation from the vein lines of non-organic-rich shale is, the more sensitive the corresponding screening curve of the numerical axis is to organic-rich shale, and vice versa.

[0077] The method for synchronously screening multi-well, multi-curve and multi-lithology sensitivity curves provided in the second embodiment of the present invention reduces the influence of human subjective factors in the sensitivity curve selection process and improves the objectivity of the selection results by converting the correlation between logging curves and lithology into a more intuitive line convergence degree and differentiation degree.

[0078] The method for synchronous screening of multi-well, multi-curve and multi-lithology sensitive curves provided in the second embodiment of the present invention establishes a coordinate system including multiple parallel axes, each axis corresponds to a different curve to be screened, and vein lines corresponding to different sample points are drawn in the coordinate system, so that curves of different types can be placed in the same coordinate system for synchronous comparison, thereby improving the accuracy of sensitive curve selection, making it less likely that sensitive curves will be missed, and greatly improving the screening efficiency.

[0079] The method for synchronous screening of multiple wells, multiple curves and multiple lithology sensitivity curves provided in the second embodiment of the present invention connects the projection points of the same sample point on different number axes to obtain a vein line. One sample point corresponds to one vein line, and the possibility of two vein lines completely overlapping is very small, avoiding the situation of a large number of points overlapping caused by a simple point casting method, so that the final lithology distribution vein line map is more complete and representative.

[0080] Embodiment 3

[0081] Embodiment 3 of the present invention provides a method for identifying interlayers in an organic-rich shale development section, comprising inputting a sensitivity curve of a target well into a lithology identification model, obtaining a depth range of the organic-rich shale development section and binary lithology data within the range according to an output result of the model, and identifying non-organic-rich shale in the lithology data as an interlayer.

[0082] The lithology identification model is pre-established in the manner described in the first embodiment above.

[0083] The type of the sensitivity curve is pre-screened in the manner described in the second embodiment above.

[0084] The working principle of the lithology identification model is to preliminarily locate the organic-rich shale development section according to the GR curve based on the lower limit of the GR value of organic-rich shale; for the organic-rich shale development section, the binary lithology data is determined according to the neural network learning results of its sensitive curve to obtain the results for output.

[0085] In some embodiments, before inputting the sensitivity curve of the target well into the lithology identification model, the process further includes removing the high GR value abnormal values ​​of non-organic-rich shale from the sensitivity curve of the target well using the rock logging data. For example, the interference of special high GR rocks on the high GR response of organic-rich shale is removed, such as high uranium content sandstone.

[0086] The working principle of the interlayer identification method of the organic-rich shale development section provided in Example 3 of the present application is: based on the fact that organic-rich shale is formed in a reducing environment that makes uranium elements more easily precipitated, resulting in the characteristics of high uranium and high natural gamma that are different from other lithologies, natural gamma is combined with conventional rock cuttings logging to eliminate the interference of other non-shale high GR rocks (such as sandstone-type uranium mines), and the vertical distribution of high GR organic-rich shale development sections is identified. In the identified organic-rich shale development section, by automatically calculating the correlation between various conventional logging curves and organic-rich shale, the curve with the best correlation is directly selected as the input curve, and a neural network method is used to automatically establish a lithology identification model of organic-rich shale and non-organic-rich shale. The interpretation results are consistent with the actual results through continuous verification and iteration of the lithology identification model through the verification well. Finally, the front-end inputs various conventional logging curves, and the terminal automatically generates a high-precision lithology profile containing organic-rich shale and non-organic-rich shale.

[0087] The method for identifying interlayers in organic-rich shale development sections provided in Example 3 of the present invention is aimed at the specific scenario of identifying thin interlayers in organic-rich shale development sections. It abandons the universal pursuit of conventional well logging lithological interpretation to interpret and characterize various lithologies developed in the study area separately, and limits the lithological interpretation objects to two types: organic-rich shale and interlayers (non-organic-rich shale), thereby reducing the multi-solution nature of well logging lithological interpretation and improving the interpretation accuracy; at the same time, it reduces the amount of calculation and improves the recognition speed of batch interpretation of multiple wells.

[0088] The method for identifying interlayers in organic-rich shale development sections provided in the third embodiment of the present invention only needs to use the core data of the sample well in the stage of establishing the lithology identification model. Once the modeling is completed, only conventional logging curves need to be used in the application stage to achieve high-precision characterization of organic-rich shale and interlayers. Under the premise of ensuring the accuracy of interpretation, the requirements for data quality are greatly reduced.

[0089] The method for identifying interlayers in organic-rich shale development sections provided in the third embodiment of the present invention adopts artificial intelligence methods such as neural networks to eliminate human influence as much as possible and further improve the reliability of lithological interpretation.

[0090] Embodiment 4

[0091] The fourth embodiment of the present invention provides a specific application of a method for identifying interlayers in organic-rich shale development sections based on lithology binarization, comprising the following steps:

[0092] S101: In a shale oil and gas exploration block, two wells with continuous coring in the organic-rich shale development section are selected as sample wells and verification wells respectively to provide test samples and lithology description objects for the lithology division and high-precision lithology characterization of the organic-rich shale development section.

[0093] Figure 3, Figure 7 The sample well and the calibration well selected in the embodiment are respectively shown. Systematic coring was performed in the organic-rich shale development section and its overlying and underlying rock formations in both wells, and the conventional logging curves are complete.

[0094] S102: Combined with core observation, thin section identification and TOC test data, lithology binarization is carried out for the organic-rich shale development section: the mud-grade mineral structure of the organic-rich shale accounts for no less than 50%, and the TOC is ≥2.0%; the mud-grade minerals in the interlayer account for less than 50%, or the TOC is <2.0%.

[0095] S103: Calculate the lower limit of the GR value of organic-rich shale.

[0096] The GR values ​​of the organic-rich shale sample collection points determined in step S102 are counted to determine the lower limit of the GR value of the organic-rich shale. In the embodiment, according to the results of mathematical statistics, the lower limit of the GR value of the organic-rich shale is set to 180 API, and the rock layer with a GR value above this lower limit is defined as an interlayer.

[0097] The examples only provide lower limits for specific regions. The lower limits of the GR values ​​for organic-rich shales in different regions vary, but they can all be determined by combing and statistically analyzing the TOC values ​​and GR values ​​of rock samples.

[0098] When promoting and applying it in wells other than sample wells, the selected high GR rock formations (GR value greater than the lower limit of GR value of organic-rich shale) should also be combined with conventional rock cuttings logging to exclude non-shale high GR rock formations, such as sandstone-type uranium mines.

[0099] After determining the distribution of high GR organic-rich shale, the vertical distribution range of the organic-rich shale development section is determined based on the indicator that the interlayer ratio does not exceed 20% in the embodiment, such as Figure 3 The well depth shown is between 1240.20m and 1255.26m.

[0100] S104: For the organic-rich shale development section determined in step S103, a sensitivity analysis method is used to select a lithology sensitivity curve.

[0101] In this step, only the organic-rich shale and its interlayers are selected for sensitivity curves, with fewer lithology types, and the determined sensitivity curves are more sensitive and accurate in responding to the corresponding lithology.

[0102] In the embodiment, through lithological sensitivity analysis, the lithological interpretation sensitivity curves of the organic-rich shale development section are determined to be GR, CNL and AC. Among the five curves, the GR, CNL and AC curves can clearly distinguish the organic-rich shale from the sandstone interlayer. Figure 4 shown.

[0103] S105: In the embodiment, the lithology interpretation sensitivity curves GR, CNL and AC are used as input curves, and a binary lithology identification model of organic-rich shale and interlayer based on the three sensitivity curves is established through a neural network algorithm. The model establishment process is as follows: Figure 5 shown.

[0104] S106: In the embodiment, the binary lithology recognition model described in step S105 is used to convert the GR, CNL and AC curve data of the sample well into two types of lithology data, namely organic-rich shale and interlayer, and automatically generate a lithology profile. Figure 6 shown.

[0105] S107: In the embodiment, the lithology recognition model is applied to the calibration well. The conventional logging curves GR, CNL and AC curve data in the calibration well are used to automatically generate a lithology profile. The established lithology profile is as follows: Figure 7 As shown in the figure, the lithology profile automatically generated by using the logging curve data is highly consistent with the lithology profile of the real core, proving that the present invention is reliable in identifying organic-rich shale and interlayers.

[0106] Based on the inventive concept of the present invention, an embodiment of the present invention further provides an organic-rich shale interlayer identification device, the structure of which is as follows: Figure 8 As shown, interlayer identification module 81, lithology identification model building module 82 and sensitivity curve screening module 83;

[0107] The interlayer identification module 81 is used to input the sensitivity curve of the target well into the lithology identification model, obtain the depth range of the organic-rich shale development section and the binary lithology data within the range according to the model output result, and identify the non-organic-rich shale in the lithology data as an interlayer;

[0108] The lithology identification model is pre-established by the lithology identification model establishment module 82 in the following manner: determining the GR value lower limit of the organic-rich shale according to the binary lithology data of the coring section of the target layer of the sample well; taking the binary lithology data of the coring section and the curve section of the selected sensitivity curve as a sample to establish a sample set; using the sample set to train the selected neural network model to establish a lithology identification model, inputting the GR value lower limit into the lithology identification model, and the GR value lower limit is used to locate the organic-rich shale development section;

[0109] The type of sensitive curve is pre-screened by the sensitive curve screening module 83 in the following manner: obtaining multiple sample points of the target layer, each sample point including a binary lithology type and the value of each curve to be screened; projecting each sample point into a coordinate system including multiple parallel axes, each axis corresponding to a different curve to be screened, connecting the projection points of the same sample point on different axes to obtain a vein line; and screening at least one type of lithology sensitivity curve according to the distribution characteristics of the vein line.

[0110] In some embodiments, the lithology identification model building module 82 is used to:

[0111] According to the thin section identification data of the coring section of the target layer of the sample well, the lithology description data in the core description data is corrected to obtain preliminary lithology data, and the preliminary lithology data includes mud shale; according to the TOC detection data, the mud shale with a TOC value greater than a preset organic-rich shale TOC lower limit in the preliminary lithology data is determined as organic-rich shale, and the binary lithology data of the organic-rich shale in the coring section is obtained.

[0112] In some embodiments, the lithology identification model building module 82 is used to:

[0113] Based on the binary lithology data and GR curve of the sample well, the lithology and GR value of the sampling points with thin section identification data and TOC detection data are extracted; according to the lithology and GR values ​​of multiple sampling points, the lower limit of the GR value of organic-rich shale is statistically obtained.

[0114] In some embodiments, the interlayer identification module 81, before inputting the sensitivity curve of the target well into the lithology identification model, is further used to:

[0115] Using cuttings logging data, the sensitivity curve of the target well is used to eliminate high GR outliers of non-organic-rich shale.

[0116] In some embodiments, the sensitivity curve screening module 83 is used to screen at least one type of lithology sensitivity curve according to the distribution characteristics of vein lines on the number axis based on the following understandings:

[0117] The more convergent the vein lines of organic-rich shale on a certain numerical axis are, and the more obvious the differentiation from the vein lines of non-organic-rich shale is, the more sensitive the corresponding screening curve of the numerical axis is to organic-rich shale, and vice versa.

[0118] The specific implementation methods of the above steps refer to the descriptions in Embodiment 1, Embodiment 2 and Embodiment 3.

[0119] Based on the inventive concept of the present invention, an embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium stores computer executable instructions, and when the computer executable instructions are executed by a processor, the above-mentioned method for identifying interlayers in organic-rich shale development sections is implemented.

[0120] Based on the inventive concept of the present invention, an embodiment of the present invention further provides a server, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for identifying interlayers in organic-rich shale development sections when executing the program.

[0121] Unless otherwise specifically stated, terms such as processing, computing, calculating, determining, displaying, etc. may refer to the actions and / or processes of one or more processing or computing systems, or similar devices, which operate and convert data represented as physical (e.g., electronic) quantities within registers or memories of a processing system into other data similarly represented as physical quantities within memories, registers, or other such information storage, transmission, or display devices of the processing system. Information and signals may be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, light fields or particles, or any combination thereof.

[0122] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0123] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that an embodiment of the claimed subject matter requires more features than those set forth in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0124] Those skilled in the art will also appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments herein can all be implemented as electronic hardware, computer software, or a combination thereof. In order to clearly illustrate the interchangeability between hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above around their functions. Whether such functions are implemented as hardware or software depends on specific applications and the design constraints imposed on the entire system. A skilled person can implement the described functions in an alternative manner for each specific application, but such implementation decisions should not be interpreted as departing from the scope of protection of the present disclosure.

[0125] The steps of the method or algorithm described in conjunction with the embodiments herein may be directly embodied as hardware, a software module executed by a processor, or a combination thereof. The software module may be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The ASIC may be located in a user terminal. Of course, the processor and the storage medium may also be present in a user terminal as discrete components.

[0126] For software implementation, the techniques described in this application can be implemented with modules (e.g., procedures, functions, etc.) that perform the functions described in this application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is coupled to the processor in a communication manner via various means, which are well known in the art.

[0127] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".

Claims

1. A method for identifying interlayers in organic-rich shale development sections, characterized in that: include: Inputting the sensitivity curve of the target well into the lithology identification model, obtaining the depth range of the organic-rich shale development section and the binary lithology data within the range according to the output result of the model, and identifying the non-organic-rich shale in the lithology data as an interlayer; The lithology identification model is pre-established in the following manner: determining the GR value lower limit of organic-rich shale according to the binary lithology data of the coring section of the target layer of the sample well; taking the binary lithology data of the coring section and the curve section of the selected sensitivity curve as a sample to establish a sample set; using the sample set to train the selected neural network model to establish a lithology identification model, inputting the GR value lower limit into the lithology identification model, and the GR value lower limit is used to locate the organic-rich shale development section; The type of sensitive curve is pre-screened in the following manner: a plurality of sample points of the target layer are obtained, each sample point includes a binary lithology type and the value of each curve to be screened; each sample point is projected into a coordinate system including a plurality of parallel axes, each axis corresponds to a different curve to be screened, and the projection points of the same sample point on different axes are connected to obtain a vein line; and at least one type of lithology sensitivity curve is screened according to the distribution characteristics of the vein line.

2. The method according to claim 1, characterized in that The model output result is obtained by the lithology identification model in the following way: Locating the organic-rich shale development section according to the GR value lower limit and the GR curve of the target well; According to the neural network learning result of the corresponding sensitive curve segment of the organic-rich shale development segment, the binary lithology data thereof is determined to obtain the result for output.

3. The method according to claim 1, characterized in that The binary lithology data of the coring section of the target layer of the sample well is obtained based on the core description data, thin section identification data and TOC detection data of the coring section of the target layer of the sample well.

4. The method according to claim 3, characterized in that The binary lithology data of the core section of the target layer of the sample well is obtained by the following method: According to the thin section identification data of the coring section of the target layer of the sample well, the lithology description data in the core description data is corrected to obtain preliminary lithology data, wherein the preliminary lithology data includes mud shale; According to the TOC detection data, the mud shale with a TOC value greater than a preset lower limit of TOC of organic-rich shale in the preliminary lithological data is determined as organic-rich shale, and the binary lithological data of the organic-rich shale in the coring section is obtained.

5. The method according to claim 4, characterized in that Determining the lower limit of the GR value of organic-rich shale includes: Based on the binary lithology data and GR curve of the sample well, the lithology and GR value of the sampling point with thin section identification data and TOC detection data are extracted; According to the lithology and GR values ​​of multiple sampling points, the lower limit of the GR value of organic-rich shale was obtained statistically.

6. The method according to claim 1, characterized in that Before inputting the sensitivity curve of the target well into the lithology identification model, the method further includes: Using cuttings logging data, the sensitivity curve of the target well is used to eliminate high GR outliers of non-organic-rich shale.

7. The method according to claim 1, characterized in that The two ends of the number axis in the coordinate system are aligned, and the values ​​at the two ends match the numerical distribution range of the corresponding to-be-screened curve determined according to the multiple sample points.

8. The method according to claim 1, characterized in that: The screening of at least one type of lithology sensitivity curve according to the distribution characteristics of the vein lines includes screening at least one type of lithology sensitivity curve according to the distribution characteristics of the vein lines on the number axis based on the following understanding: The more convergent the vein lines of organic-rich shale on a certain axis, and the more obvious the differentiation from the vein lines of non-organic-rich shale, the more sensitive the corresponding screening curve to organic-rich shale is, and vice versa.

9. A device for identifying interlayers in organic-rich shale development sections, characterized in that: The device comprises an interlayer identification module, a lithology identification model building module and a sensitivity curve screening module; The interlayer identification module is used to input the sensitivity curve of the target well into the lithology identification model, obtain the depth range of the organic-rich shale development section and the binary lithology data within the range according to the model output result, and identify the non-organic-rich shale in the lithology data as an interlayer; The lithology identification model is pre-established by the lithology identification model establishment module in the following manner: determining the GR value lower limit of organic-rich shale according to the binary lithology data of the coring section of the target layer of the sample well; taking the binary lithology data of the coring section and the curve section of the selected sensitivity curve as a sample to establish a sample set; using the sample set to train the selected neural network model to establish a lithology identification model, and inputting the GR value lower limit into the lithology identification model, and the GR value lower limit is used to locate the organic-rich shale development section; The type of sensitive curve is pre-screened by the sensitive curve screening module in the following manner: obtaining multiple sample points of the target layer, each sample point including a binary lithology type and the value of each curve to be screened; projecting each sample point into a coordinate system including multiple parallel axes, each axis corresponding to a different curve to be screened, connecting the projection points of the same sample point on different axes to obtain a vein line; and screening at least one type of lithology sensitivity curve according to the distribution characteristics of the vein line.

10. A computer storage medium, characterized in that: The computer storage medium stores computer executable instructions, and when the computer executable instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

11. A server, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 8 is implemented.

Images