Oil-based drilling fluid deep shale oil reservoir classification method, device and electronic equipment based on recording and measurement fusion

Abstract

The present invention relates to a reservoir classification technology field, and is a classification method, device and electronic equipment for oil-based drilling deep shale oil reservoirs based on recording and measurement fusion, including using gas logging data to determine the gas logging total hydrocarbon anomaly multiple to obtain a first reservoir classification result; using XRF element logging data to determine the element brittleness index to obtain a second reservoir classification result; using XRF element logging data to obtain a skeleton resistivity prediction value, and determining the corresponding third reservoir classification result based on the difference between the skeleton resistivity prediction value and the skeleton resistivity measured value; and performing a comprehensive analysis on the three reservoir classification results according to the comprehensive classification standard to obtain the classification result of the oil-based drilling deep shale oil reservoir to be classified. The present invention uses three classification methods to obtain three reservoir classification results, and performs a comprehensive analysis on the three reservoir classification results to obtain the classification result of the oil-based drilling deep shale oil reservoir to be classified, so that the classification result of the base drilling deep shale oil reservoir is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of reservoir classification, and specifically relates to a method, device and electronic equipment for classifying deep shale oil reservoirs of oil-based drilling fluid based on recording and measurement fusion. Background Art

[0002] Shale oil refers to the oil resources contained in organic-rich mud shale formations, including oil in mud shale pores and cracks, and oil in dense carbonate rocks or clastic rock interlayers in mud shale formations. Shale oil resources are an important type of unconventional natural oil reservoirs. They refer to oil that is found in organic-rich nano-scale pore throat shale formations and are important unconventional oil and gas resources. The exploration and production of unconventional shale oil and gas in China has become a research hotspot in the field of unconventional oil and gas resources.

[0003] In the process of exploration and exploitation of deep shale oil reservoirs, reservoir evaluation under oil-based drilling fluid conditions has important guiding significance for the effective exploration and exploitation of deep shale oil reservoirs. In the prior art, reservoir evaluation under oil-based drilling fluid conditions is mostly achieved by using gas logging, rock pyrolysis, TOC, physical property index, mineral brittleness index and other parameters to independently or jointly establish deep shale oil reservoir classification standards under oil-based drilling fluid conditions. For example:

[0004] The first existing open patent document, with the publication number CN110965999B, discloses a method for finely identifying the dominant lithology of shale oil. According to the X-ray diffraction mineral composition data of shale layer cuttings or core samples, three main mineral components are selected to establish a chart to achieve fine division of shale lithology; according to gas logging parameters, rock pyrolysis analysis, and brittleness index data, a standard for dividing the dominant lithology of shale formations is established; the present invention uses X-ray diffraction mineral composition data to establish a chart to distinguish lithology, and combines gas logging parameters, rock pyrolysis analysis, and brittleness index data to distinguish the dominant lithology of shale formations. Firstly, the problem of unclear lithology naming of shale oil can be solved well, and the lithology can be accurately identified. Secondly, the dominant lithology data in the lithology can be identified for oil testing and layer selection. As a result, the engineering service needs are met, and a reliable basis is provided for the efficient development of oil and gas resources in shale formations.

[0005] The second existing public patent document, with the publication number CN115130309B, discloses a method, equipment, medium and terminal for determining the brittleness of shale reservoirs using a bonding degree, including: using the grey correlation method to analyze the correlation between the mineral composition, particle arrangement structure and brittleness index of shale; determining the influence of the mineral composition and particle arrangement structure on the brittleness of shale based on the correlation between the mineral composition, particle arrangement structure and brittleness index of shale; constructing a brittleness evaluation model based on mineral composition and structural directional entropy based on the influence of the mineral composition and particle arrangement structure on the brittleness of shale combined with the total organic carbon content of shale; and using the brittleness evaluation model based on mineral composition and structural directional entropy to evaluate the brittleness of shale. The method for determining the brittleness of shale reservoirs using a bonding degree of the present invention not only retains the influence of mineral components, but also considers the role of the directional arrangement structure of particles, can be better applied to oriented structural development mudstone, and can effectively predict the fracturing ability of shale.

[0006] The above-mentioned process of establishing the classification standard of deep shale oil reservoirs under oil-based drilling fluid has the following deficiencies:

[0007] (1) The high pressure in deep formations causes the gas logging background value to be artificially high. During high-angle and directional drilling, the fluctuating value affects the gas logging accuracy. The density, temperature and bottom hole pressure difference of the drilling fluid affect the amount of formation oil and gas entering the drilling fluid, resulting in low accuracy of gas logging parameters, which affects the reservoir evaluation effect.

[0008] (2) The accuracy of the judgment of rock brittleness depends to a great extent on whether the selected mineral brittleness index calculation method is reasonable. Relevant personnel often choose the mineral brittleness index calculation method based on their work experience, which sometimes leads to deviations between the final result and the actual situation. The commonly used XRD mineral brittleness evaluation and classification method currently uses X-ray diffraction mineral (XRD) acquisition equipment to collect XRD spectra. The collected XRD spectra need to be decomposed to obtain the mineral content. Different geological conditions have different mineral types. Due to the differences in geological understanding among different technicians, the mineral types and contents obtained by decomposition are not accurate, resulting in the accuracy of mineral brittleness index calculation, which affects the reservoir evaluation effect.

[0009] (3) Drilling with oil-based drilling fluids. Since drilling with oil-based drilling fluids easily makes the pyrolysis parameters invalid, conventional rock pyrolysis methods will result in inaccurate evaluation of the oil content of shale oil reservoirs. Summary of the invention

[0010] The present invention provides a method, device and electronic equipment for classifying deep shale oil reservoirs using oil-based drilling fluid based on recording and measurement fusion, which overcomes the shortcomings of the above-mentioned prior art and can effectively solve the problem of inaccurate reservoir classification due to inaccurate evaluation of reservoir oil content using conventional rock pyrolysis method.

[0011] One of the technical solutions of the present invention is achieved by the following measures: A deep shale oil reservoir classification method of oil-based drilling fluid based on recording and measurement fusion, comprising:

[0012] Determine the gas logging total hydrocarbon anomaly multiples by using gas logging well logging data, and obtain the first reservoir classification result by combining the first classification standard, wherein the first classification standard is composed of a plurality of gas logging total hydrocarbon anomaly multiples threshold intervals and corresponding reservoir types;

[0013] The element brittleness index is determined by using XRF element logging data, and a second reservoir classification result is obtained by combining the second classification standard, wherein the second classification standard is composed of a plurality of element brittleness index threshold intervals and corresponding reservoir types;

[0014] The predicted skeleton resistivity value is obtained by using XRF element logging data, and the corresponding third reservoir classification result is determined based on the difference between the predicted skeleton resistivity value and the measured skeleton resistivity value, wherein the measured skeleton resistivity value is obtained from the resistivity logging data while drilling;

[0015] According to the comprehensive classification standard, the first reservoir classification results, the second reservoir classification results and the third reservoir classification results are comprehensively analyzed to obtain the classification results of the deep shale oil reservoir of the oil-based drilling fluid to be classified.

[0016] The following are further optimizations and / or improvements to the above technical solutions:

[0017] The above comprehensive classification standard is used to comprehensively analyze the first reservoir classification results, the second reservoir classification results and the third reservoir classification results, and the classification results of the oil-based drilling fluid deep shale oil reservoir to be classified are obtained, including:

[0018] Scoring the first reservoir classification result, the second reservoir classification result and the third reservoir classification result according to the scoring rule, and summing the three scoring results;

[0019] The summation result is brought into the comprehensive classification standard to obtain the classification result of the deep shale oil reservoir of the oil-based drilling fluid to be classified, wherein the comprehensive classification standard is composed of multiple summation threshold intervals and corresponding reservoir types.

[0020] The above-mentioned XRF element logging data is used to determine the element brittleness index, and combined with the second classification standard to obtain the second reservoir classification result, including:

[0021] The XRF element logging data was normalized, a mineral analysis sample library was established, and the mineral brittleness index was calculated based on the mineral analysis sample library. The formula for calculating the mineral brittleness index is as follows:

[0022]

[0023] The Pearson correlation analysis method is used to screen out multiple elements in the mineral analysis sample library whose correlation with the mineral brittleness index is greater than the preset value;

[0024] All the screened elements were subjected to multiple linear regression with the mineral brittleness index to obtain the element brittleness index;

[0025] The element brittleness index is introduced into the second classification standard to obtain the second reservoir classification result, wherein the second classification standard is composed of a plurality of gas logging total hydrocarbon anomaly multiple threshold intervals and corresponding reservoir types.

[0026] The above-mentioned skeleton resistivity prediction value is obtained by using XRF element logging data, and the corresponding third reservoir classification result is determined based on the difference between the skeleton resistivity prediction value and the skeleton resistivity measured value, including:

[0027] Select multiple sensitive elements in the XRF element logging data, input them into the skeleton resistivity prediction model, and obtain the skeleton resistivity prediction value, wherein the skeleton resistivity prediction model is obtained by training the XGBoost regression model using a number of samples, each of the several samples includes multiple sensitive elements and the identification of the skeleton resistivity measured value, and the multiple sensitive elements are obtained by obtaining the gain value of each element in the XRF element logging data and screening out the elements whose gain value is greater than the threshold value;

[0028] The difference between the predicted skeleton resistivity value and the measured skeleton resistivity value is calculated, and is brought into the third classification standard to determine the corresponding third reservoir classification result, wherein the third classification standard is composed of multiple difference threshold intervals and corresponding reservoir types.

[0029] The above-mentioned method of using gas logging data to determine the total hydrocarbon anomaly multiple of gas logging and combining the first classification standard to obtain the first reservoir classification result includes:

[0030] The total hydrocarbon value is determined using gas logging data and corrected based on drilling environment data;

[0031] The total hydrocarbon abnormality multiple is obtained by using the overall trend line of total hydrocarbon value in the whole well section of the shale oil reservoir and the corrected total hydrocarbon value;

[0032] TGy=TG / y

[0033] Among them, TGy is the total hydrocarbon anomaly multiple; TG is the total hydrocarbon value after correction; y is the overall change trend line of the total hydrocarbon value of the whole well section of the shale oil reservoir;

[0034] The total hydrocarbon anomaly multiple is brought into the first classification standard to determine the corresponding first reservoir classification result, wherein the first classification standard is composed of a plurality of gas logging total hydrocarbon anomaly multiple threshold intervals and corresponding reservoir types.

[0035] The second technical solution of the present invention is achieved by the following measures: a deep shale oil reservoir classification device for oil-based drilling fluid based on recording and measurement fusion, comprising:

[0036] The first classification unit determines the gas logging total hydrocarbon anomaly multiples using gas logging well logging data, and obtains the first reservoir classification result in combination with the first classification standard, wherein the first classification standard is composed of a plurality of gas logging total hydrocarbon anomaly multiples threshold intervals and corresponding reservoir types;

[0037] The second classification unit determines the element brittleness index using XRF element logging data, and obtains the second reservoir classification result in combination with the second classification standard, wherein the second classification standard is composed of multiple element brittleness index threshold intervals and corresponding reservoir types;

[0038] The third classification unit uses XRF element logging data to obtain a skeleton resistivity prediction value, and determines the corresponding third reservoir classification result based on the difference between the skeleton resistivity prediction value and the skeleton resistivity measured value, wherein the skeleton resistivity measured value is obtained from the resistivity logging data while drilling;

[0039] The comprehensive classification unit comprehensively analyzes the first reservoir classification results, the second reservoir classification results and the third reservoir classification results according to the comprehensive classification standard to obtain the classification results of the deep shale oil reservoir of the oil-based drilling fluid to be classified.

[0040] The following are further optimizations and / or improvements to the above technical solutions:

[0041] The above comprehensive classification units include:

[0042] A scoring module scores the first reservoir classification result, the second reservoir classification result and the third reservoir classification result according to the scoring rules, and sums the three scoring results;

[0043] The comprehensive classification judgment module brings the summation result into the comprehensive classification standard to obtain the classification result of the deep shale oil reservoir of the oil-based drilling fluid to be classified, wherein the comprehensive classification standard is composed of multiple summation threshold intervals and corresponding reservoir types.

[0044] The above-mentioned second classification unit includes:

[0045] The mineral brittleness index calculation module normalizes the XRF element logging data, establishes a mineral analysis sample library, and calculates the mineral brittleness index based on the mineral analysis sample library. The formula for calculating the mineral brittleness index is as follows:

[0046]

[0047] The element screening module uses the Pearson correlation analysis method to screen out multiple elements in the mineral analysis sample library whose correlation with the mineral brittleness index is greater than the preset value;

[0048] The element brittleness index obtaining module performs multiple linear regression on all the screened elements and the mineral brittleness index to obtain the element brittleness index;

[0049] The second classification submodule brings the element brittleness index into the second classification standard to obtain the second reservoir classification result, wherein the second classification standard is composed of a plurality of gas logging total hydrocarbon anomaly multiple threshold intervals and corresponding reservoir types.

[0050] The above-mentioned first classification unit includes:

[0051] The total hydrocarbon value acquisition module determines the total hydrocarbon value using gas logging data and corrects the total hydrocarbon value based on drilling environment data;

[0052] The total hydrocarbon anomaly multiple acquisition module uses the overall trend line of the total hydrocarbon value of the entire well section of the shale oil reservoir and the corrected total hydrocarbon value to obtain the total hydrocarbon anomaly multiple;

[0053] TGy=TG / y

[0054] Among them, TGy is the total hydrocarbon anomaly multiple; TG is the total hydrocarbon value after correction; y is the overall change trend line of the total hydrocarbon value of the whole well section of the shale oil reservoir;

[0055] The first classification submodule brings the total hydrocarbon anomaly multiple into the first classification standard to determine the corresponding first reservoir classification result, wherein the first classification standard is composed of a plurality of gas logging total hydrocarbon anomaly multiple threshold intervals and corresponding reservoir types.

[0056] The above third classification unit includes:

[0057] The skeleton resistivity prediction module selects multiple sensitive elements from the XRF element logging data and inputs them into the skeleton resistivity prediction model to obtain the skeleton resistivity prediction value, wherein the skeleton resistivity prediction model is obtained by training the XGBoost regression model using a number of samples, each of which includes multiple sensitive elements and the identification of the skeleton resistivity measured value, and the multiple sensitive elements are obtained by obtaining the gain value of each element in the XRF element logging data and screening out the elements whose gain value is greater than the threshold value;

[0058] The third classification submodule calculates the difference between the predicted skeleton resistivity value and the measured skeleton resistivity value, and brings it into the third classification standard to determine the corresponding third reservoir classification result, wherein the third classification standard is composed of multiple difference threshold intervals and corresponding reservoir types.

[0059] The third technical solution of the present invention is achieved through the following measures: an electronic device, characterized in that it includes a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement the steps in the classification of deep shale oil reservoirs of oil-based drilling fluid based on recording and measurement fusion.

[0060] The present invention uses three classification methods to obtain three reservoir classification results, and conducts a comprehensive analysis on the three reservoir classification results to obtain the classification results of the oil-based drilling fluid deep shale oil reservoir to be classified, so that the classification results of the oil-based drilling fluid deep shale oil reservoir are more accurate, and further:

[0061] In the rock brittleness evaluation and classification method, the commonly used method is to use the relative content of brittle minerals to characterize the rock brittleness, while the present invention directly uses XRF element logging data to determine the element brittleness index. Compared with the conventional method, the analysis speed is fast, and it is not affected by the accuracy of XRD spectrum interpretation and experimental analysis. It does not reduce the accuracy of brittleness index calculation, and effectively reduces the test and detection costs of conventional methods.

[0062] Among the methods for evaluating and classifying the oil content of shale oil reservoirs, the conventional method is the rock pyrolysis method. However, since drilling with oil-based drilling fluids can easily render the pyrolysis parameters invalid, the evaluation of the oil content of shale oil reservoirs may be inaccurate. In the present invention, the skeleton resistivity prediction value is obtained using XRF element logging data, and the difference between the skeleton resistivity prediction value and the skeleton resistivity measured value is used to reflect the reservoir oil content, thereby determining the corresponding reservoir classification result. This improves the accuracy and adaptability of the overall oil content evaluation of the shale oil reservoir without being affected by the pyrolysis parameters.

[0063] In the gas logging evaluation and classification method, the gas logging background value is artificially high due to the high pressure of deep formations, the fluctuating pressure during high-angle and directional drilling affects the gas logging accuracy, and the drilling fluid density, temperature and bottom hole pressure difference affect the amount of formation oil and gas entering the drilling fluid, resulting in low accuracy of gas logging parameters. Therefore, the existing gas logging evaluation and classification method without correction is prone to inaccurate evaluation, and then makes the reservoir classification inaccurate. Therefore, the present invention corrects the total hydrocarbon value based on the drilling environment data, greatly reduces the influence of drilling fluid density, temperature and bottom hole pressure difference on gas logging parameters, and improves the accuracy of gas logging evaluation and classification. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Attached Figure 1 A schematic flow chart of a method for classifying deep shale oil reservoirs using oil-based drilling fluids provided in accordance with an embodiment of the present invention.

[0065] Attached Figure 2 A schematic diagram of a flow chart of a method for comprehensive analysis of classification results provided by an embodiment of the present invention.

[0066] Attached Figure 3A schematic flow chart of a gas testing evaluation classification method provided in accordance with an embodiment of the present invention.

[0067] Attached Figure 4 A schematic flow chart of a brittleness evaluation classification method provided in one embodiment of the present invention.

[0068] Attached Figure 5 A schematic flow chart of a method for evaluating and classifying oil content provided in accordance with an embodiment of the present invention.

[0069] Attached Figure 6 A schematic diagram of the classification results of deep shale oil reservoirs using oil-based drilling fluid provided in one embodiment of the present invention.

[0070] Attached Figure 7 A schematic structural diagram of a deep shale oil reservoir classification device for oil-based drilling fluid provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0071] The present invention is not limited by the following embodiments, and specific implementation methods can be determined based on the technical solution of the present invention and actual conditions.

[0072] Those skilled in the art will understand that, unless otherwise stated, a "module" or "unit" in the embodiments of the present invention refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as a processing circuit or memory) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0073] In addition, the term “plurality” in the embodiments of the present invention refers to two or more than two, and “first” and “second” etc. are used for distinguishing descriptions and should not be understood as implying relative importance.

[0074] The embodiment of the present invention provides a method, device and electronic device for classifying deep shale oil reservoirs of oil-based drilling fluid based on recording and measurement fusion. The device for classifying deep shale oil reservoirs of oil-based drilling fluid based on recording and measurement fusion can be integrated in a computer device, which can be a server or a terminal or other device; it can also be executed by a terminal and a server together, and the above examples should not be understood as limiting the present invention.

[0075] The above-mentioned terminal may include a mobile phone, a wearable smart device, a tablet computer, a notebook computer, a personal computer (PC), and a vehicle-mounted computer, etc., and the present invention does not limit this. The present invention does not limit the number of terminal devices.

[0076] The above-mentioned server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, as well as big data and artificial intelligence platforms. The present invention does not impose any restrictions on this.

[0077] For example, the computer equipment determines the gas logging total hydrocarbon anomaly multiples using gas logging data, and obtains the first reservoir classification result in combination with the first classification standard, wherein the first classification standard is composed of multiple gas logging total hydrocarbon anomaly multiples threshold intervals and corresponding reservoir types; determines the element brittleness index using XRF element logging data, and obtains the second reservoir classification result in combination with the second classification standard, wherein the second classification standard is composed of multiple element brittleness index threshold intervals and corresponding reservoir types; obtains the skeleton resistivity prediction value using XRF element logging data, and determines the corresponding third reservoir classification result based on the difference between the skeleton resistivity prediction value and the skeleton resistivity measured value, wherein the skeleton resistivity measured value is obtained in the resistivity logging data while drilling;

[0078] According to the comprehensive classification standard, the first reservoir classification results, the second reservoir classification results and the third reservoir classification results are comprehensively analyzed to obtain the classification results of the deep shale oil reservoir of the oil-based drilling fluid to be classified.

[0079] It should also be noted that the method provided in the embodiment of the present invention may involve artificial intelligence (AI) technology and may be implemented based on artificial intelligence technology, for example, by using machine learning to obtain a corresponding model using sample training.

[0080] Among them, machine learning (ML) is a multi-disciplinary interdisciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are in all areas of artificial intelligence.

[0081] The above-mentioned machine learning usually includes technologies such as neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and self-learning.

[0082] Based on this, the technical solution of the present invention will be introduced and explained in combination with several examples below.

[0083] Embodiment 1: As attached Figure 1As shown, the embodiment of the present invention discloses a method for classifying deep shale oil reservoirs of oil-based drilling fluid based on recording and measurement fusion, comprising:

[0084] Step S110, determining the gas logging total hydrocarbon anomaly multiple using the gas logging well logging data, and obtaining a first reservoir classification result in combination with a first classification standard, wherein the first classification standard is composed of a plurality of gas logging total hydrocarbon anomaly multiple threshold intervals and corresponding reservoir types;

[0085] Step S120, determining the element brittleness index using the XRF element logging data, and obtaining a second reservoir classification result in combination with a second classification standard, wherein the second classification standard is composed of a plurality of element brittleness index threshold intervals and corresponding reservoir types;

[0086] Step S130, using XRF element logging data to obtain a predicted skeleton resistivity value, and determining a corresponding third reservoir classification result based on a difference between the predicted skeleton resistivity value and a measured skeleton resistivity value, wherein the measured skeleton resistivity value is obtained from the resistivity logging while drilling data;

[0087] Step S140, comprehensively analyzing the first reservoir classification result, the second reservoir classification result and the third reservoir classification result according to the comprehensive classification standard to obtain the classification result of the oil-based drilling fluid deep shale oil reservoir to be classified.

[0088] The present invention uses three classification methods to obtain three reservoir classification results, and conducts a comprehensive analysis on the three reservoir classification results to obtain the classification results of the oil-based drilling fluid deep shale oil reservoir to be classified, so that the classification results of the oil-based drilling fluid deep shale oil reservoir are more accurate. Further, the specific results are as follows:

[0089] In the rock brittleness evaluation and classification method, the commonly used method is to use the relative content of brittle minerals to characterize the rock brittleness, while the present invention directly uses XRF element logging data to determine the element brittleness index. Compared with the conventional method, the analysis speed is fast, and it is not affected by the accuracy of XRD spectrum interpretation and experimental analysis. It does not reduce the accuracy of brittleness index calculation, and effectively reduces the test and detection costs of conventional methods.

[0090] Among the methods for evaluating and classifying the oil content of shale oil reservoirs, the conventional method is the rock pyrolysis method. However, since drilling with oil-based drilling fluids can easily render the pyrolysis parameters invalid, the evaluation of the oil content of shale oil reservoirs may be inaccurate. In the present invention, the skeleton resistivity prediction value is obtained using XRF element logging data, and the difference between the skeleton resistivity prediction value and the skeleton resistivity measured value is used to reflect the reservoir oil content, thereby determining the corresponding reservoir classification result. This improves the accuracy and adaptability of the overall oil content evaluation of the shale oil reservoir without being affected by the pyrolysis parameters.

[0091] Embodiment 2: As attached Figure 2As shown, the embodiment of the present invention is a further optimization of the above embodiment, wherein the first reservoir classification result, the second reservoir classification result and the third reservoir classification result are comprehensively analyzed according to the comprehensive classification standard to obtain the classification result of the oil-based drilling fluid deep shale oil reservoir to be classified, including:

[0092] Step S210, scoring the first reservoir classification result, the second reservoir classification result and the third reservoir classification result according to the scoring rule, and summing the three scoring results.

[0093] In this step, the scoring rules can be constructed by selecting an adaptive method as needed, which may include but is not limited to determining the weights of the three categories, directly setting the scores according to the reservoirs, etc. In this embodiment, the scores of different categories of reservoirs can be directly set. For example, the scoring rule is that the first category of reservoirs gets 1 point, the second category of reservoirs gets 2 points, and the third category of reservoirs gets 3 points.

[0094] Step S220, bringing the summation result into the comprehensive classification standard to obtain the classification result of the oil-based drilling fluid deep shale oil reservoir to be classified, wherein the comprehensive classification standard is composed of multiple summation threshold intervals and corresponding reservoir types.

[0095] The comprehensive classification standard in this step is composed of multiple summation threshold intervals and corresponding reservoir types, wherein the summation threshold intervals are set accordingly based on the analysis and summary of historical data, and can be, but not limited to, as follows:

[0096] (1) If the sum is ≤ 5, the comprehensive classification is one category;

[0097] (2) If 6 ≤ sum result ≤ 7, and the sum of any two of the scores of the first reservoir classification result, the second reservoir classification result, and the third reservoir classification result is less than 6, then the comprehensive classification is Class II;

[0098] (3) Other situations are classified into three categories.

[0099] Embodiment 3: As attached Figure 3 As shown, the embodiment of the present invention is a further optimization of the above embodiment, wherein the gas logging data is used to determine the gas logging total hydrocarbon abnormality multiple, and the first reservoir classification result is obtained in combination with the first classification standard, including:

[0100] Step S310, determining the total hydrocarbon value using gas logging data, and correcting the total hydrocarbon value based on drilling environment data.

[0101] In this step, the gas logging data is the gas logging data of the deep shale oil reservoir of the oil-based drilling fluid to be classified, including gas logging components C1, C2, C3, iC4, nC4, iC5, and nC5;

[0102] Based on the gas logging data of the deep shale oil reservoir of the above-mentioned oil-based drilling fluid to be classified, the total hydrocarbon value TG is calculated by the following formula:

[0103] TG=C1+C2+C3+iC4+nC4+iC5+nC5, unit: %

[0104] On the basis of obtaining the total hydrocarbon value, the total hydrocarbon value is corrected in combination with the drilling environment data, as described below:

[0105]

[0106] in, The drilling fluid density collected in real time during logging, in g / cm 3 , is the gravitational acceleration constant, take 9.81m / s 2 , is the well depth collected in real time by logging, in meters; ZS is the drilling time required to drill into 1 meter of the formation, collected in real time by logging, in minutes / meters; TG is the total hydrocarbon value; is the bottom formation temperature, according to the well depth data of adjacent wells Temperature and regional geothermal gradient calculate, The outlet drilling fluid temperature collected in real time during logging, in °C; is the atmospheric pressure on the ground, which is 0.1Mpa.

[0107] Step S320, using the overall trend line of the total hydrocarbon value of the entire well section of the shale oil reservoir and the corrected total hydrocarbon value, obtain the total hydrocarbon abnormality multiple;

[0108] TGy=TG / y

[0109] Among them, TGy is the total hydrocarbon anomaly multiple; TG is the total hydrocarbon value after correction; y is the overall change trend line of the total hydrocarbon value of the entire well section of the shale oil reservoir.

[0110] In this step, the overall change trend line of the total hydrocarbon value of the whole well section of the shale oil reservoir is y=a×h+b, where a and b are obtained by linear fitting using the total hydrocarbon anomaly multiple TGx of the whole well section of the shale oil reservoir and the well depth h.

[0111] Step S330, bringing the total hydrocarbon anomaly multiple into the first classification standard to determine the corresponding first reservoir classification result, wherein the first classification standard is composed of a plurality of gas logging total hydrocarbon anomaly multiple threshold intervals and corresponding reservoir types.

[0112] In this step, the first classification standard is set accordingly based on the analysis and summary of the historical data, and may be, but is not limited to, as follows:

[0113] (1) If the total hydrocarbon anomaly multiple is greater than 0.6, it is a Class I reservoir;

[0114] (2) If ≤0.2 total hydrocarbon anomaly multiple ≤0.6, it is a Class II reservoir;

[0115] (3) If the total hydrocarbon anomaly multiple is less than 0.2, it is a Class III reservoir.

[0116] Due to the high pressure in deep formations, the gas logging background value is artificially high. The fluctuating values ​​during high-angle and directional drilling affect the gas logging accuracy. The drilling fluid density, temperature and bottom hole pressure difference affect the amount of formation oil and gas entering the drilling fluid, resulting in low accuracy of gas logging parameters. Therefore, the existing gas logging evaluation and classification methods that are not corrected are prone to inaccurate evaluation, and thus inaccurate reservoir classification. Therefore, the embodiment of the present invention corrects the total hydrocarbon value based on the drilling environment data, greatly reduces the influence of drilling fluid density, temperature and bottom hole pressure difference on gas logging parameters, and improves the accuracy of gas logging evaluation and classification.

[0117] Embodiment 4: As attached Figure 4 As shown, the embodiment of the present invention is a further optimization of the above embodiment, wherein the element brittleness index is determined by using XRF element logging data, and the second reservoir classification result is obtained in combination with the second classification standard, including:

[0118] Step S410, normalize the XRF element logging data, establish a mineral analysis sample library, and obtain the mineral brittleness index based on the mineral analysis sample library, wherein the formula for obtaining the mineral brittleness index is as follows:

[0119]

[0120] In this step, the XRF element logging data is the XRF element logging data of the deep shale oil reservoir of the oil-based drilling fluid to be classified.

[0121] Step S420, using the Pearson correlation analysis method to screen out multiple elements in the mineral analysis sample library whose correlation with the mineral brittleness index is greater than a preset value.

[0122] Step S430, performing multiple linear regression on all the screened elements and the mineral brittleness index to obtain the element brittleness index;

[0123] In this step, the element brittleness index constructed by multivariate linear regression of all the screened elements and the mineral brittleness index is as follows:

[0124]

[0125] in, is the element brittleness index; is a constant, is the regression coefficient; In order to use the Pearson correlation analysis method to screen out multiple elements in the mineral analysis sample library whose correlation with the mineral brittleness index is greater than the preset value.

[0126] Step S440, the element brittleness index is brought into the second classification standard to obtain a second reservoir classification result, wherein the second classification standard is composed of a plurality of gas logging total hydrocarbon anomaly multiple threshold intervals and corresponding reservoir types.

[0127] In this step, the second classification standard is set accordingly based on the analysis and summary of the historical data, and may be, but is not limited to, as follows:

[0128] (1) If the element brittleness index is greater than 3.0, it is a Class I reservoir;

[0129] (2) If 2.3≦element brittleness index≦3.0, it is a Class II reservoir;

[0130] (3) If the element brittleness index is less than 2.3, it is a Class III reservoir.

[0131] Compared with the commonly used rock brittleness evaluation and classification methods, this embodiment no longer uses the relative content of brittle minerals to characterize rock brittleness, but directly uses XRF element logging data to determine the element brittleness index. The analysis speed is fast, and is not affected by the accuracy of XRD spectrum interpretation and experimental analysis. It does not reduce the accuracy of brittleness index calculation, and effectively reduces the test and detection costs of conventional methods.

[0132] Embodiment 5: As attached Figure 5 As shown, the embodiment of the present invention is a further optimization of the above embodiment, wherein the skeleton resistivity prediction value is obtained by using XRF element logging data, and the corresponding third reservoir classification result is determined based on the difference between the skeleton resistivity prediction value and the skeleton resistivity measured value, including:

[0133] Step S510, select multiple sensitive elements in the XRF element logging data, input them into the skeleton resistivity prediction model, and obtain the skeleton resistivity prediction value, wherein the skeleton resistivity prediction model is obtained by training the XGBoost regression model using a number of samples, each of the several samples includes multiple sensitive elements and identifications of the actual measured values ​​of the skeleton resistivity, and the multiple sensitive elements are obtained by obtaining the gain value of each element in the XRF element logging data, and screening out the elements whose gain value is greater than the threshold.

[0134] In this step, the construction process of the skeleton resistivity prediction model includes:

[0135] Obtain historical XRF element logging data of deep shale oil reservoirs with historical oil-based drilling fluids and preprocess them, including processing missing values, outliers, and normalization;

[0136] Use decision tree and other algorithms to determine the gain values ​​of each element in the historical XRF element logging data, and select elements with gain values ​​greater than the threshold (i.e., the greatest importance) as sensitive elements;

[0137] Extract all sensitive elements from historical XRF element logging data to form a sample set, and divide the sample set into a training set and a test set in proportion;

[0138] The XGBoost regression model is trained using the training set. The loss function is introduced during the training. When the value of the loss function is stable, the training is terminated to obtain the skeleton resistivity prediction model.

[0139] The trained skeleton resistivity prediction model is tested and evaluated using the test set. Mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) are introduced as evaluation indicators to optimize the model parameters of the skeleton resistivity prediction model and output a skeleton resistivity prediction model that meets the test and evaluation requirements.

[0140] Furthermore, the code corresponding to the construction process of the skeleton resistivity prediction model may be, but is not limited to:

[0141] # Import basic tool library

[0142] import numpy as np

[0143] import pandas as pd

[0144] from sklearn.datasets import make_regression

[0145] from sklearn.model_selection import train_test_split

[0146] from xgboost.sklearn import XGBRegressor

[0147] from sklearn.metrics import mean_squared_error

[0148] from sklearn.metrics import mean_absolute_error

[0149] from sklearn.metrics import mean_absolute_percentage_error

[0150] # Import element data for data analysis

[0151] data = pd.read_table('.data.csv',delimiter=',')

[0152] x = data.iloc[:,:-1]

[0153] y = data.iloc[:,-1]

[0154] X, y = make_regression(n_samples=470, n_features=35)

[0155] # Split into training set and test set

[0156] train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.3, shuffle=False)

[0157] #Call the XGBoost model and use the training set data for training (fitting)

[0158] my_model = XGBRegressor(

[0159] max_depth=8,

[0160] learning_rate=0.1,

[0161] n_estimators=100,

[0162] silent=True,

[0163] objective='reg: squarederror',

[0164] booster='gbtree',

[0165] n_jobs=15,

[0166] nthread=None,

[0167] gamma=0,

[0168] min_child_weight=1,

[0169] max_delta_step=0,

[0170] subsample=1,

[0171] colsample_bytree=1,

[0172] colsample_bylevel=1,

[0173] reg_alpha=0,

[0174] reg_lambda=1,

[0175] scale_pos_weight=1,

[0176] base_score=0.5,

[0177] random_state=0,

[0178] seed=None,

[0179] missing=None,

[0180] importance_type='gain')

[0181] my_model.fit(train_X, train_y)

[0182] # Use the model to predict the test set data

[0183] predictions = my_model.predict(test_X)

[0184] # Evaluate the training and testing results

[0185] print("mean_squared_error: " + str(mean_squared_error(predictions,test_y)))

[0186] print("rmse: "+ str(np.sqrt(mean_squared_error(predictions, test_y)))

[0187] print("mean_absolute_error: "+ str(mean_absolute_error(predictions,test_y)))

[0188] print("mean_absolute_percentage_error: "+str(mean_absolute_percentage_error (predictions, test_y)))

[0189] Step S520, calculate the difference between the predicted skeleton resistivity value and the measured skeleton resistivity value, and bring it into the third classification standard to determine the corresponding third reservoir classification result, wherein the third classification standard is composed of multiple difference threshold intervals and corresponding reservoir types.

[0190] In this step, the measured value of the skeleton resistivity is the measured shale oil resistivity, which is the sum of the series resistivity of the shale rock mineral skeleton resistivity and the oil and gas resistivity in the pores. The shale rock mineral skeleton resistivity and the oil and gas resistivity in the pores can both be obtained from the XRF element logging data, and the difference between the predicted value of the skeleton resistivity and the measured value of the skeleton resistivity in this step can truly reflect the oil content of the reservoir.

[0191] In this step, the third classification standard is set accordingly based on the analysis and summary of the historical data, and may be, but is not limited to, as follows:

[0192] (1) If the difference is greater than 200, it is a Class I reservoir;

[0193] (2) If 100 ≤ difference ≤ 200, it is a Class II reservoir;

[0194] (3) If the difference is less than 100, it is a Class III reservoir.

[0195] This embodiment no longer uses conventional rock pyrolysis to complete the evaluation of the oil content of shale oil reservoirs, but introduces machine learning to construct a skeleton resistivity prediction model, and uses the skeleton resistivity prediction model to predict based on XRF element logging data to obtain a skeleton resistivity prediction value, and then reflects the reservoir oil content based on the difference between the skeleton resistivity prediction value and the skeleton resistivity measured value, thereby determining the corresponding reservoir classification result, thereby improving the accuracy and adaptability of the overall oil content evaluation of the shale oil reservoir without being affected by the pyrolysis parameters. In addition, the skeleton resistivity prediction model can be continuously learned and updated, dynamically adapting to the deep shale oil reservoirs of oil-based drilling fluids in various regions, ensuring the accuracy of prediction, thereby improving the accuracy of reservoir classification.

[0196] Example 6: Taking the classification of the deep shale oil reservoir of oil-based drilling fluid at 5430-5900m of the H7 well as an example using the oil-based drilling fluid deep shale oil reservoir classification method based on recording and measurement fusion disclosed in the present invention, the specific classification process is as follows:

[0197] (1) Calculation of gas logging anomaly multiples and classification of gas logging evaluation

[0198] S1, calculate the total hydrocarbon value of the section 5430-5900m of Well H7, TG=C1+C2+C3+iC4+nC4+iC5+nC5;

[0199] S2, correcting the total hydrocarbon value based on drilling environment data;

[0200] TGx = drilling time × total hydrocarbon calculation / (3.14 × (0.216 × 0.216) / 4) × ((90 / drilling fluid temperature) × (0.1 / (drilling fluid density × 0.00981 × well depth)) × 0.9 / 10000;

[0201] S3, calculate the overall trend line of total hydrocarbon value in the whole well section of shale oil reservoir, y = -4E-05*well depth + 1.3107;

[0202] S4, calculate the total hydrocarbon anomaly multiple TGy=TG / y;

[0203] S5, analyze TGy according to the classification standard in Table 1 to obtain the first reservoir classification result.

[0204] (2) Calculation of element brittleness index and classification of rock brittleness evaluation

[0205] S1, collect the XRF element logging data of the cuttings in the H7 well section from 5430 to 5900 m, with a logging collection interval of 1 m, a total of 470 data samples (including element data, Bid data, and Bif data), and collect 35 elements including Si, Fe, Ca, and Mg. The obtained element data are normalized to establish an element analysis sample library. The normalization formula is as follows:

[0206]

[0207] Wherein, E is the measured value of the element; Emax is the maximum value of the measured element; Emin is the minimum value of the measured element; E* is the normalized value of the element;

[0208] S3, calculate the mineral brittleness index BId of 5430-5900m in H7 well, and use the Pearson correlation analysis method to screen out the elements with high correlation with the mineral brittleness index BId, which are elements Na, Al, Si, S, K, Ca, Fe, Ni, and Rb. Among them, the calculation formula of the mineral brittleness index BId is as follows:

[0209]

[0210] S4, perform multiple linear regression between the elements Na, Al, Si, S, K, Ca, Fe, Ni, Rb and the mineral brittleness index BId (element data is the independent variable, BId is the dependent variable) to obtain the element brittleness index, as follows:

[0211] BIf=-1.172+1.127×Na+1.67×Al+4.185×Si+0.628×S-1.025×K+4.257×Ca-1.159×Fe+0.422×Ni+0.251×Rb;

[0212] S5. Analyze the element brittleness index according to the classification standard in Table 1 to obtain the second reservoir classification result.

[0213] (3) Calculation of rock skeleton resistivity and classification of oil content in shale oil reservoirs

[0214] S1, based on the gain value, the seven most important features are determined as sensitive elements, namely S, Ca, Si, Al, K, Mg, and Na;

[0215] S2, using machine learning to build a skeleton resistivity prediction model;

[0216] S3, input the sensitive elements S, Ca, Si, Al, K, Mg, and Na of the section 5430-5900 m of the H7 well into the skeleton resistivity prediction model to obtain the skeleton resistivity prediction value;

[0217] S4, calculating the difference between the predicted skeleton resistivity value and the measured skeleton resistivity value, analyzing the difference according to the classification standard in Table 1, and obtaining the third reservoir classification result.

[0218] (4) According to the comprehensive classification standard, the first reservoir classification results, the second reservoir classification results and the third reservoir classification results are comprehensively analyzed to obtain the classification results of the oil-based drilling fluid deep shale oil reservoir to be classified. The classification results are shown in the attached figure. Figure 6 shown.

[0219] Table 1 Classification standard table

[0220] .

[0221] Embodiment 7: As attached Figure 7 As shown, the embodiment of the present invention discloses a deep shale oil reservoir classification device for oil-based drilling fluid based on recording and measurement fusion, comprising:

[0222] The first classification unit determines the gas logging total hydrocarbon anomaly multiples using gas logging well logging data, and obtains the first reservoir classification result in combination with the first classification standard, wherein the first classification standard is composed of a plurality of gas logging total hydrocarbon anomaly multiples threshold intervals and corresponding reservoir types;

[0223] The second classification unit determines the element brittleness index using XRF element logging data, and obtains the second reservoir classification result in combination with the second classification standard, wherein the second classification standard is composed of multiple element brittleness index threshold intervals and corresponding reservoir types;

[0224] The third classification unit uses XRF element logging data to obtain a skeleton resistivity prediction value, and determines the corresponding third reservoir classification result based on the difference between the skeleton resistivity prediction value and the skeleton resistivity measured value, wherein the skeleton resistivity measured value is obtained from the resistivity logging data while drilling;

[0225] The comprehensive classification unit comprehensively analyzes the first reservoir classification results, the second reservoir classification results and the third reservoir classification results according to the comprehensive classification standard to obtain the classification results of the deep shale oil reservoir of the oil-based drilling fluid to be classified.

[0226] Among them, the first classification unit includes:

[0227] The total hydrocarbon value acquisition module determines the total hydrocarbon value using gas logging data and corrects the total hydrocarbon value based on drilling environment data;

[0228] The total hydrocarbon anomaly multiple acquisition module uses the overall trend line of the total hydrocarbon value of the entire well section of the shale oil reservoir and the corrected total hydrocarbon value to obtain the total hydrocarbon anomaly multiple;

[0229] TGy=TG / y

[0230] Among them, TGy is the total hydrocarbon anomaly multiple; TG is the total hydrocarbon value after correction; y is the overall change trend line of the total hydrocarbon value of the whole well section of the shale oil reservoir;

[0231] The first classification submodule brings the total hydrocarbon anomaly multiple into the first classification standard to determine the corresponding first reservoir classification result, wherein the first classification standard is composed of a plurality of gas logging total hydrocarbon anomaly multiple threshold intervals and corresponding reservoir types.

[0232] Among them, the second classification unit includes:

[0233] The mineral brittleness index calculation module normalizes the XRF element logging data, establishes a mineral analysis sample library, and calculates the mineral brittleness index based on the mineral analysis sample library. The formula for calculating the mineral brittleness index is as follows:

[0234]

[0235] The element screening module uses the Pearson correlation analysis method to screen out multiple elements in the mineral analysis sample library whose correlation with the mineral brittleness index is greater than the preset value;

[0236] The element brittleness index obtaining module performs multiple linear regression on all the screened elements and the mineral brittleness index to obtain the element brittleness index;

[0237] The second classification submodule brings the element brittleness index into the second classification standard to obtain the second reservoir classification result, wherein the second classification standard is composed of a plurality of gas logging total hydrocarbon anomaly multiple threshold intervals and corresponding reservoir types.

[0238] Among them, the third classification unit includes:

[0239] The skeleton resistivity prediction module selects multiple sensitive elements from the XRF element logging data and inputs them into the skeleton resistivity prediction model to obtain the skeleton resistivity prediction value, wherein the skeleton resistivity prediction model is obtained by training the XGBoost regression model using a number of samples, each of which includes multiple sensitive elements and the identification of the skeleton resistivity measured value, and the multiple sensitive elements are obtained by obtaining the gain value of each element in the XRF element logging data and screening out the elements whose gain value is greater than the threshold value;

[0240] The third classification submodule calculates the difference between the predicted skeleton resistivity value and the measured skeleton resistivity value, and brings it into the third classification standard to determine the corresponding third reservoir classification result, wherein the third classification standard is composed of multiple difference threshold intervals and corresponding reservoir types.

[0241] Among them, the comprehensive classification unit includes:

[0242] A scoring module scores the first reservoir classification result, the second reservoir classification result and the third reservoir classification result according to the scoring rules, and sums the three scoring results;

[0243] The comprehensive classification judgment module brings the summation result into the comprehensive classification standard to obtain the classification result of the deep shale oil reservoir of the oil-based drilling fluid to be classified, wherein the comprehensive classification standard is composed of multiple summation threshold intervals and corresponding reservoir types.

[0244] Example 8: The embodiment of the present invention discloses an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to implement a method for classifying deep shale oil reservoirs of oil-based drilling fluid based on recording and measurement fusion.

[0245] The processor may be a central processing unit (CPU), a general purpose processor, a digital signal processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. It may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The memory may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory, a mobile hard disk, a magnetic disk or an optical disk.

[0246] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The solutions in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and interpreted scripting language JavaScript, etc.

[0247] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 produce 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.

[0248] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0249] The above content is only a specific implementation mode of the present invention, which has strong adaptability and implementation effect, but the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered within the protection scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope covered by the present invention.

Claims

1. A deep shale oil reservoir classification method for oil-based drilling fluid based on recording and measurement fusion, characterized in that: include: The gas logging data is used to determine the gas logging total hydrocarbon anomaly multiples, and combined with the first classification standard to obtain the first reservoir classification result, wherein the first classification standard is composed of multiple gas logging total hydrocarbon anomaly multiples threshold intervals and corresponding reservoir types, including: The total hydrocarbon value is determined using gas logging data and corrected based on drilling environment data; in, The drilling fluid density collected in real time for logging. is the gravitational acceleration constant, is the well depth collected in real time by logging; ZS is the drilling time required to drill into 1m of the formation; TG is the total hydrocarbon value; is the bottom formation temperature, according to the well depth data of adjacent wells Temperature and regional geothermal gradient calculate, The outlet drilling fluid temperature collected in real time for logging; is the atmospheric pressure on the ground; The total hydrocarbon abnormality multiple is obtained by using the overall trend line of total hydrocarbon value in the whole well section of the shale oil reservoir and the corrected total hydrocarbon value; TGy=TGx / y Among them, TGy is the total hydrocarbon anomaly multiple; TGx is the corrected total hydrocarbon value; y is the overall change trend line of the total hydrocarbon value of the entire well section of the shale oil reservoir; The total hydrocarbon anomaly multiple is brought into the first classification standard to determine the corresponding first reservoir classification result, wherein the first classification standard is composed of a plurality of gas logging total hydrocarbon anomaly multiple threshold intervals and corresponding reservoir types; The element brittleness index is determined using XRF element logging data, and the second reservoir classification result is obtained in combination with the second classification standard, where the second classification standard consists of multiple element brittleness index threshold intervals and corresponding reservoir types, specifically including: The XRF element logging data was normalized, a mineral analysis sample library was established, and the mineral brittleness index was calculated based on the mineral analysis sample library. The formula for calculating the mineral brittleness index is as follows: The Pearson correlation analysis method is used to screen out multiple elements in the mineral analysis sample library whose correlation with the mineral brittleness index is greater than the preset value; All the screened elements were subjected to multiple linear regression with the mineral brittleness index to obtain the element brittleness index; Substituting the element brittleness index into the second classification standard to obtain a second reservoir classification result, wherein the second classification standard is composed of a plurality of element brittleness index threshold intervals and corresponding reservoir types; The skeleton resistivity prediction value is obtained by using XRF element logging data, and the corresponding third reservoir classification result is determined based on the difference between the skeleton resistivity prediction value and the skeleton resistivity measured value, wherein the skeleton resistivity measured value is obtained from the resistivity logging data while drilling, specifically including: Select multiple sensitive elements in the XRF element logging data, input them into the skeleton resistivity prediction model, and obtain the skeleton resistivity prediction value, wherein the skeleton resistivity prediction model is obtained by training the XGBoost regression model using a number of samples, each of the several samples includes multiple sensitive elements and the identification of the skeleton resistivity measured value, and the multiple sensitive elements are obtained by obtaining the gain value of each element in the XRF element logging data and screening out the elements whose gain value is greater than the threshold value; Calculate the difference between the predicted skeleton resistivity value and the measured skeleton resistivity value, and bring it into the third classification standard to determine the corresponding third reservoir classification result, wherein the third classification standard is composed of multiple difference threshold intervals and corresponding reservoir types; According to the comprehensive classification standard, the first reservoir classification results, the second reservoir classification results and the third reservoir classification results are comprehensively analyzed to obtain the classification results of the deep shale oil reservoir of the oil-based drilling fluid to be classified.

2. The method for deep shale oil reservoir classification of oil-based drilling fluid based on recording and measurement fusion according to claim 1 is characterized in that: The first reservoir classification result, the second reservoir classification result and the third reservoir classification result are comprehensively analyzed according to the comprehensive classification standard to obtain the classification result of the oil-based drilling fluid deep shale oil reservoir to be classified, including: Scoring the first reservoir classification result, the second reservoir classification result and the third reservoir classification result according to the scoring rule, and summing the three scoring results; The summation result is brought into the comprehensive classification standard to obtain the classification result of the deep shale oil reservoir of the oil-based drilling fluid to be classified, wherein the comprehensive classification standard is composed of multiple summation threshold intervals and corresponding reservoir types.

3. A deep shale oil reservoir classification device for oil-based drilling fluid based on recording and measurement fusion using the method as described in claim 1 or 2, characterized in that: include: The first classification unit uses gas logging data to determine the gas logging total hydrocarbon anomaly multiples, and combines the first classification standard to obtain the first reservoir classification result, wherein the first classification standard is composed of multiple gas logging total hydrocarbon anomaly multiples threshold intervals and corresponding reservoir types, specifically including: The total hydrocarbon value acquisition module determines the total hydrocarbon value using gas logging data and corrects the total hydrocarbon value based on drilling environment data; in, The drilling fluid density collected in real time for logging. is the gravitational acceleration constant, is the well depth collected in real time by logging; ZS is the drilling time required to drill into 1m of the formation; TG is the total hydrocarbon value; is the bottom formation temperature, according to the well depth data of adjacent wells Temperature and regional geothermal gradient calculate, The outlet drilling fluid temperature collected in real time for logging; is the atmospheric pressure on the ground; The total hydrocarbon anomaly multiple acquisition module uses the overall trend line of the total hydrocarbon value of the entire well section of the shale oil reservoir and the corrected total hydrocarbon value to obtain the total hydrocarbon anomaly multiple; TGy=TGx / y Among them, TGy is the total hydrocarbon anomaly multiple; TGx is the corrected total hydrocarbon value; y is the overall change trend line of the total hydrocarbon value of the entire well section of the shale oil reservoir; The first classification submodule brings the total hydrocarbon anomaly multiple into the first classification standard to determine the corresponding first reservoir classification result, wherein the first classification standard is composed of a plurality of gas logging total hydrocarbon anomaly multiple threshold intervals and corresponding reservoir types; The second classification unit uses XRF element logging data to determine the element brittleness index, and combines the second classification standard to obtain the second reservoir classification result, where the second classification standard consists of multiple element brittleness index threshold ranges and corresponding reservoir types, specifically including: The mineral brittleness index calculation module normalizes the XRF element logging data, establishes a mineral analysis sample library, and calculates the mineral brittleness index based on the mineral analysis sample library. The formula for calculating the mineral brittleness index is as follows: The element screening module uses the Pearson correlation analysis method to screen out multiple elements in the mineral analysis sample library whose correlation with the mineral brittleness index is greater than the preset value; The element brittleness index obtaining module performs multiple linear regression on all the screened elements and the mineral brittleness index to obtain the element brittleness index; The second classification submodule brings the element brittleness index into the second classification standard to obtain a second reservoir classification result, wherein the second classification standard is composed of a plurality of element brittleness index threshold intervals and corresponding reservoir types; The third classification unit uses XRF element logging data to obtain a skeleton resistivity prediction value, and determines the corresponding third reservoir classification result based on the difference between the skeleton resistivity prediction value and the skeleton resistivity measured value, wherein the skeleton resistivity measured value is obtained from the resistivity logging data while drilling, specifically including: The skeleton resistivity prediction module selects multiple sensitive elements from the XRF element logging data and inputs them into the skeleton resistivity prediction model to obtain the skeleton resistivity prediction value, wherein the skeleton resistivity prediction model is obtained by training the XGBoost regression model using a number of samples, each of which includes multiple sensitive elements and the identification of the skeleton resistivity measured value, and the multiple sensitive elements are obtained by obtaining the gain value of each element in the XRF element logging data and screening out the elements whose gain value is greater than the threshold value; The third classification submodule calculates the difference between the predicted skeleton resistivity value and the measured skeleton resistivity value, and brings it into the third classification standard to determine the corresponding third reservoir classification result, wherein the third classification standard is composed of multiple difference threshold intervals and corresponding reservoir types; The comprehensive classification unit comprehensively analyzes the first reservoir classification results, the second reservoir classification results and the third reservoir classification results according to the comprehensive classification standard to obtain the classification results of the deep shale oil reservoir of the oil-based drilling fluid to be classified.

4. The oil-based drilling fluid deep shale oil reservoir classification device based on recording and measurement fusion according to claim 3 is characterized in that: The comprehensive classification unit includes: A scoring module scores the first reservoir classification result, the second reservoir classification result and the third reservoir classification result according to the scoring rules, and sums the three scoring results; The comprehensive classification judgment module brings the summation result into the comprehensive classification standard to obtain the classification result of the deep shale oil reservoir of the oil-based drilling fluid to be classified, wherein the comprehensive classification standard is composed of multiple summation threshold intervals and corresponding reservoir types.

5. An electronic device, characterized in that: The method comprises a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement the steps in the method as claimed in claim 1 or 2.

Images