Oil source rock organic matter abundance area evaluation and abundance parameter determination method and device

Abstract

The invention discloses an oil source rock organic matter abundance area evaluation method and an organic matter abundance parameter determination method and device. The method comprises the following steps: acquiring organic matter abundance parameters in an oil source rock information database and a corresponding logging data set; training a neural network model according to the organic matter abundance parameters of the cored well and the logging data set; inputting the logging data set of the non-cored well into the trained neural network model to obtain a predicted organic matter abundance parameter of the non-cored well; performing weighted average on the organic matter abundance parameter and the corresponding stratum thickness to obtain an organic matter abundance indicator factor; and drawing an organic matter abundance region evaluation map according to the organic matter abundance indicator factors. According to the method, multiple organic matter abundance parameters can be synthesized to evaluate the abundance area, and the organic matter abundance can be directly predicted through the logging data set, so that the organic matter abundance parameters of the oil source rock are easy to obtain, and the judgment of the organic matter abundance of the organic matter abundance area is more comprehensive.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas exploration and development, and in particular to a method and device for evaluating the abundance region of organic matter in oil source rocks and determining abundance parameters. Background Art

[0002] In the process of sedimentary basin analysis, oil source rock is one of the key research areas, and its organic matter abundance is an important indicator for exploration and evaluation. Organic matter abundance usually refers to the percentage of organic matter in the unit weight of oil source rock; the commonly used parameters for evaluating the abundance of organic matter in oil source rock include organic carbon content, chloroform asphalt "A", total hydrocarbons and rock pyrolysis parameters, etc. These parameters are important indicators for evaluating the hydrocarbon generation capacity of oil source rock, and the hydrocarbon generation capacity of oil source rock is one of the important purposes of evaluating the abundance of organic matter.

[0003] At present, the judgment of organic matter abundance in oil source rocks is mostly based on experimental analysis of core samples, but core sampling is small and the evaluation of organic matter abundance based on a single factor cannot fully display the organic matter abundance. Therefore, there is an urgent need for a method that can evaluate the organic matter abundance area of ​​oil source rocks based on multiple factors. Summary of the invention

[0004] In view of the above problems, the present invention is proposed to provide a method and device for regional evaluation of organic matter abundance in oil source rocks and determination of abundance parameters, which overcomes the above problems or at least partially solves the above problems.

[0005] In a first aspect, an embodiment of the present invention provides a method for evaluating the organic matter abundance region of an oil source rock, comprising:

[0006] Obtaining from the sample information database the pre-stored corresponding organic matter abundance parameters of the oil source rock of the coring well and the relevant data points of the well logging data set, as well as the oil source rock thickness of the target layer corresponding to the core in the coring well;

[0007] The neural network model is trained using the data points related to the organic matter abundance parameters of the oil source rocks of the cored wells and the well logging data set, and a model for predicting the organic matter abundance parameters is obtained;

[0008] Inputting the well logging data set of the non-cored well into the prediction model of organic matter abundance parameters to obtain the organic matter abundance parameters of the non-cored well output by the prediction model of organic matter abundance parameters;

[0009] According to the organic matter abundance parameters of the uncored wells and the cored wells and the thickness of the target layer source rock corresponding to the core in the cored wells, the organic matter abundance area of ​​the target layer source rock where the uncored wells and the cored wells are located is evaluated.

[0010] In one embodiment, the organic matter abundance area of ​​the target layer of the source rock where the non-cored well and the cored well are located is evaluated based on the organic matter abundance parameters of the non-cored well and the cored well and the corresponding formation thickness, including:

[0011] For each coring well, the corresponding organic matter abundance parameter and the corresponding formation thickness are weighted averaged to obtain the organic matter abundance indicator factor of the coring well;

[0012] For each uncored well, the corresponding organic matter abundance parameter and the corresponding formation thickness are weighted averaged to obtain the organic matter abundance indicator factor of the uncored well;

[0013] According to the values ​​of the organic matter abundance indicator factors of the cored wells and the non-cored wells, an organic matter abundance regional evaluation map is obtained by the Kriging interpolation method; the organic matter abundance regional evaluation map is a plane map of organic matter indicator factor contour lines.

[0014] In one embodiment, the sample information database obtains the pre-stored corresponding organic matter abundance parameters of the coring well oil source rock and the well logging data set in the following manner:

[0015] The organic matter abundance parameters and logging data sets of the oil source rocks of the cored wells were sorted out, the logging data sets of the non-cored wells were sorted out, and a sample information database was established.

[0016] In one embodiment, the organic matter abundance parameters of the oil source rock of the coring well are sorted out as follows:

[0017] According to the target layer of abundance area evaluation, select the coring wells with sampled cores, record the coring well numbers, and count the thickness of the target layer's oil source rock;

[0018] Classify and organize organic geochemical data and record organic matter abundance data of core wells.

[0019] In one embodiment, the step of obtaining the pre-stored corresponding data points of the organic matter abundance parameters of the oil source rocks of the coring wells and the well logging data set includes:

[0020] The data points of the core well organic matter abundance parameters and logging data sets with a one-to-many relationship are obtained; the organic matter abundance data include: total organic carbon content TOC, chloroform bitumen "A", total hydrocarbons and rock pyrolysis parameters; the relevant data points of the logging data set include: the data points in the resistivity, acoustic wave, density and neutron logging data sets with a one-to-many relationship with the total organic carbon content TOC, chloroform bitumen "A", total hydrocarbons and rock pyrolysis parameters.

[0021] In one embodiment, the use of the organic matter abundance parameters of the oil source rocks of the coring wells and the well logging data set having a corresponding relationship to train the neural network model to obtain a model for predicting organic matter abundance parameters includes:

[0022] Generate a training data set according to the organic matter abundance parameters of the oil source rocks of the coring wells with corresponding relationships and the relevant data points of the logging data set;

[0023] The training data set is used to train the neural network model to obtain a model for predicting organic matter abundance parameters.

[0024] In one embodiment, the model for predicting organic matter abundance parameters includes:

[0025] Input layer, used to input well logging data sets without coring wells;

[0026] An output layer, used for outputting the organic matter abundance parameter predicted based on the input well logging data set;

[0027] Hidden layer: a one-to-many multi-factor comprehensive evaluation function between organic matter abundance parameters and well logging data sets;

[0028] The multi-factor comprehensive evaluation function is obtained in the following manner: taking the organic matter abundance parameters at the same depth, finding different data points corresponding to one of the organic matter abundance parameters on the curves of different logging data in the same core logging data set, learning the relationship between different data points through the neural network, and obtaining the multi-factor comprehensive evaluation relationship function.

[0029] In a second aspect, an embodiment of the present invention provides a method for determining an organic matter abundance parameter, comprising:

[0030] Obtaining pre-stored corresponding data points of organic matter abundance parameters of oil source rocks in cored wells and well logging data sets from a sample information database;

[0031] The neural network model is trained using the data points related to the organic matter abundance parameters of the oil source rocks of the cored wells and the well logging data set, and a model for predicting the organic matter abundance parameters is obtained;

[0032] The well logging data set of the non-coring well is input into the prediction model of organic matter abundance parameters to obtain the organic matter abundance parameters of the non-coring well output by the prediction model of organic matter abundance parameters.

[0033] In a third aspect, an embodiment of the present invention provides a device for determining the abundance of organic matter in oil source rocks, comprising:

[0034] An acquisition module is used to acquire pre-stored corresponding data points of the organic matter abundance parameters of the oil source rocks of the coring wells and the well logging data set from the sample information database;

[0035] A training module is used to train a neural network model using data points related to the organic matter abundance parameters of the oil source rocks of the coring wells and the well logging data set with corresponding relationships, so as to obtain a model for predicting the organic matter abundance parameters;

[0036] A prediction module, used for inputting the well logging data set of the non-coring well into the prediction model of organic matter abundance parameters, and obtaining the organic matter abundance parameters of the non-coring well output by the prediction model of organic matter abundance parameters;

[0037] The evaluation module evaluates the organic matter abundance area of ​​the target layer of the source rock where the non-cored wells and the cored wells are located based on the organic matter abundance parameters of the non-cored wells and the cored wells and the corresponding formation thickness.

[0038] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:

[0039] The method and device for evaluating the organic matter abundance area of ​​the oil source rock and determining the organic matter abundance parameters provided by the embodiment of the present invention use a neural network model to learn the relationship between the core organic matter abundance parameters of the cored well and the logging data set to obtain a model for predicting organic matter abundance parameters, and use the logging data set of the uncored well to input it into the model for predicting organic matter abundance parameters to obtain the organic matter abundance parameters of the uncored well, and based on the organic matter abundance parameters of the cored well and the uncored well and the thickness of the target layer oil source rock, the organic matter abundance area of ​​the target layer of the oil source rock is evaluated, and a new method for evaluating organic matter abundance based on the neural network model is proposed, and an organic matter abundance indicator factor is created for the first time as a regional evaluation indicator, which provides an adaptive tool for the regional evaluation of oil source rocks in the oil and gas exploration and evaluation stage, avoids the operation of coring the oil source rock on the spot, and can also correctly evaluate the organic matter abundance area of ​​the oil source rock, saving manpower and material resources, and has important practical significance in well exploration, evaluation deployment and new project selection.

[0040] 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.

[0041] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] 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:

[0043] Figure 1A flow chart of a method for regional evaluation of organic matter abundance in oil source rocks provided by an embodiment of the present invention;

[0044] Figure 2 A schematic diagram of a one-to-many relationship between an organic matter abundance parameter and a well logging data set provided in an embodiment of the present invention;

[0045] Figure 3 A flow chart of a neural network for predicting organic matter abundance parameters provided by an embodiment of the present invention;

[0046] Figure 4 Flow chart of an embodiment provided for an embodiment of the present invention;

[0047] Figure 5 A flow chart of a method for determining organic matter abundance parameters provided in an embodiment of the present invention;

[0048] Figure 6 A structural block diagram of a device for determining the abundance of organic matter in oil source rocks provided by an embodiment of the present invention;

[0049] Figure 7 A regional evaluation map of organic matter abundance in oil source rocks provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] 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.

[0051] In order to solve the problem of sparse core sampling and single reference parameter for evaluating the organic matter abundance of oil source rocks in the prior art, the embodiment of the present invention provides a method for regional evaluation of the organic matter abundance of oil source rocks, and the process is as follows: Figure 1 As shown, the following steps are included:

[0052] Step S11, obtaining pre-stored corresponding data points of the organic matter abundance parameters of the oil source rocks of the coring wells and the well logging data set from the sample information database;

[0053] Step S12, using the data points related to the organic matter abundance parameters of the oil source rocks of the cored wells and the well logging data set having a corresponding relationship, training the neural network model to obtain a model for predicting organic matter abundance parameters;

[0054] Step S13, inputting the well logging data set of the non-coring well into the prediction model of organic matter abundance parameters, and obtaining the organic matter abundance parameters of the non-coring well output by the prediction model of organic matter abundance parameters;

[0055] Step S14, evaluating the organic matter abundance area of ​​the target layer of the source rock where the non-cored wells and the cored wells are located according to the organic matter abundance parameters of the non-cored wells and the cored wells and the corresponding formation thickness.

[0056] In one embodiment, in the above step S11, the data in the sample information database may include, for example: corresponding data points of the correspondence between the organic matter abundance parameters of the target layer of the coring well and the logging data set; the thickness of the oil source rock of the target layer; the logging data set of the non-coring well, and the like.

[0057] The above organic matter abundance parameters include, for example, total organic carbon content (Total Organic Carbon, TOC), chloroform bitumen "A", total hydrocarbons and rock pyrolysis parameters; the above logging data set includes: resistivity, acoustic wave, density and neutron logging data.

[0058] The total organic carbon content in the above-mentioned organic matter abundance parameters refers to the total content of organic carbon in the unit weight of oil source rock; chloroform asphalt "A" refers to the content of soluble organic matter soluble in chloroform in the unit weight of oil source rock; total hydrocarbons refer to the content of saturated hydrocarbons and aromatic hydrocarbons in chloroform asphalt "A" in the unit weight of oil source rock; rock pyrolysis parameters refer to the content of hydrogen-containing compounds and oxygen-containing compounds emitted during the pyrolysis process of the unit weight of oil source rock.

[0059] The method for obtaining the above organic matter abundance parameter may be, for example, a method of performing organic geochemical experimental analysis on the core of the coring well.

[0060] In the above step S11, the corresponding relationship between the organic matter abundance parameters of the oil source rocks of the coring wells and the logging data sets may be, for example, a one-to-many corresponding relationship between the organic matter abundance parameters of the coring wells and the data points of the logging data sets.

[0061] Reference Figure 2 As shown in the figure, an organic matter abundance parameter corresponds to data points on the data curves in multiple well logging data sets, with a one-to-many relationship, for example: Figure 2 As shown on the left, for the coring well, the total organic carbon content in the organic matter abundance parameter of the oil source sample corresponds to the data points on multiple logging curves in the logging data set, namely resistivity, acoustic wave, density and electronic logging curves.

[0062] In the above step S12, the one-to-many correspondence between the organic matter abundance parameter and the logging data set is found, and a training data set should be generated according to the organic matter abundance parameter of the oil source rock of the core well having the corresponding relationship and the relevant data points of the logging data set;

[0063] The training data set is used to train the neural network model to obtain a model for predicting organic matter abundance parameters.

[0064] The neural network model may adopt various neural network models in the prior art, such as a feedforward neural network, a Hopfield network, etc., which is not limited in the embodiment of the present invention.

[0065] When the training data set is used to train the neural network, the organic matter abundance parameter and the logging data set having a one-to-many correspondence are input as the training data. After the training of the neural network model, a multi-factor comprehensive evaluation function between the organic matter abundance parameter and the logging data set is obtained, that is, a neural network model for predicting the organic matter abundance parameter is obtained.

[0066] In one embodiment, the architecture of the above-mentioned model for predicting organic matter abundance parameters, the neural network model for predicting organic matter abundance parameters may include the following three parts:

[0067] Input layer, used to input well logging data sets without coring wells;

[0068] An output layer, used for outputting the organic matter abundance parameter predicted based on the input well logging data set;

[0069] Hidden layer: a one-to-many multi-factor comprehensive evaluation function between organic matter abundance parameters and well logging data sets;

[0070] The multi-factor comprehensive evaluation function is obtained by taking the organic matter abundance parameters at the same depth, finding different data points corresponding to one of the organic matter abundance parameters on the curves of different logging data in the same core logging data set, learning the relationship between different data points through the neural network, and obtaining the multi-factor comprehensive evaluation relationship function.

[0071] In the above step S13, the process of predicting the organic matter abundance parameter of the non-cored well according to the input non-cored well logging data set can be referred to Figure 3 , the data points in the logging data set of the non-coring well are input into the neural network model for predicting organic matter abundance parameters, and the neural network model for organic matter abundance parameters outputs the predicted organic matter abundance parameters of the non-coring well.

[0072] For example Figure 2 As shown in the figure on the right, the data points on the resistivity, acoustic wave, density and electron logging curves of the non-cored well are input into the organic matter abundance parameter neural network model, and the corresponding calculation results of the organic matter abundance parameter can be derived. The data points in the input logging data set have a many-to-one relationship with the output single organic matter abundance parameter. For example: the data points of the resistivity, acoustic wave, density and neutron logging curves of the non-cored well correspond to one data point of total organic carbon content.

[0073] In one embodiment, in the above step S14, the organic matter abundance area of ​​the target layer of the source rock where the non-cored well and the cored well are located is evaluated according to the organic matter abundance parameters of the non-cored well and the cored well and the corresponding formation thickness, for example, the following method can be used:

[0074] For each coring well, the corresponding organic matter abundance parameter and the corresponding formation thickness are weighted averaged to obtain the organic matter abundance indicator factor of the coring well;

[0075] For each uncored well, the corresponding organic matter abundance parameter and the corresponding formation thickness are weighted averaged to obtain the organic matter abundance indicator factor of the uncored well;

[0076] Then, according to the values ​​of the organic matter abundance indicator factors of the cored wells and the non-cored wells, the regional evaluation map of organic matter abundance was obtained by the Kriging interpolation method; among them, the regional evaluation map of organic matter abundance was a plane map of the contour lines of the organic matter indicator factors.

[0077] Organic matter indicator factor contour plane Figure 1 On the one hand, various types of organic matter abundance parameters can be used to evaluate organic matter abundance areas. On the other hand, the organic matter abundance areas of source rocks can be evaluated directly through the data in the logging data set, avoiding coring.

[0078] The following is an example to illustrate the method of regional evaluation of organic matter abundance in oil source rocks.

[0079] Reference Figure 4 As shown, this example includes the following steps:

[0080] S41. Arrange the source rock data of the target layer of the coring well:

[0081] The system sorted out the exploration wells and evaluation wells that encountered N groups of target layers in the block, and screened out 10 wells that obtained core samples with organic matter abundance data, also called core wells; and 15 other wells that did not obtain organic matter abundance data, also called non-cored wells.

[0082] Well logging data sets such as resistivity, acoustic wave, density, and neutron were obtained from these cored wells and non-cored wells, and the data of the well logging data sets were normalized.

[0083] S42. Establishing oil source rock sample information database:

[0084] For the 10 core wells selected in S1 above, the organic geochemical data of the core samples of the oil source rock organic matter abundance of the target layer N group are classified and sorted to obtain the organic matter abundance parameters of the oil source rock of the target layer; the thickness of the oil source rock of the target layer N group is counted.

[0085] After classifying and arranging the information in the above S41 and S42, an oil source rock sample information database of the selected block is established.

[0086] S43. Establish the relationship between the organic matter abundance parameters of the coring well and the logging data set model:

[0087] A one-to-many (1:N) correspondence was established based on the rock sample organic matter abundance dataset and the well logging dataset of 10 core wells (e.g. Figure 2 As shown in the figure, the one-to-many relationship between organic matter abundance parameters and logging data sets is clarified, and the one-to-many relationship is learned by using the neural network model, thereby establishing a multi-factor comprehensive evaluation function relationship and obtaining a neural network model for predicting organic matter abundance parameters.

[0088] S44. Prediction of organic matter abundance data in non-cored wells:

[0089] The normalized logging data set of 15 non-cored wells was input into the neural network model for predicting organic matter abundance parameters to predict the organic matter abundance value of the target layer of the non-cored wells. This process can be referred to Figure 3 .

[0090] S45. Create an indicator factor for organic matter abundance:

[0091] Based on the organic matter abundance parameters of 10 cored wells and 15 uncored wells and the weighted average of the corresponding formation thickness, the organic matter abundance indicator factor Q of the selected block N group was created as the regional evaluation indicator.

[0092] S46. Prepare regional evaluation maps of organic matter abundance:

[0093] According to the values ​​of the regional indicator factor Q of organic matter abundance in 10 cored wells and 15 uncored wells, the contour plane map of organic matter abundance indicator factor was obtained by the Kriging interpolation method, that is, the regional evaluation map of organic matter abundance in the selected block.

[0094] The Kriging interpolation method in S46 above is an interpolation method based on statistics. The principle is to use regionalized variables as the basis and the variance function as the basic tool to make unbiased and optimal estimates of unknown sample points.

[0095] The organic matter abundance regional evaluation map in S46 above can be referred to Figure 7 , Figure 7 The solid points in the middle are data points of the organic matter abundance indicator factor of the coring wells, the hollow points are data points of the organic matter abundance indicator factor of the wells without coring, the curves are the contour lines of the organic matter abundance indicator factor, and the numbers 0, 20, 40, 60 and 80 in the figure are the values ​​of the organic matter abundance indicator factor.

[0096] Based on the same inventive concept, in order to solve the problem that the number of sampled cores of oil source rocks is small, the number of samples available for organic geochemical experimental analysis is small, and it is difficult to determine the abundance of organic matter, the embodiment of the present invention also proposes a method for determining the abundance parameter of organic matter, such as Figure 5 As shown, including:

[0097] Step S51, obtaining pre-stored corresponding data points of the organic matter abundance parameters of the oil source rocks of the coring wells and the well logging data set from the sample information database;

[0098] Step S52, using the data points related to the organic matter abundance parameters of the oil source rocks of the cored wells and the well logging data set having a corresponding relationship, training the neural network model to obtain a model for predicting organic matter abundance parameters;

[0099] Step S53, inputting the well logging data set of the non-coring well into the model for predicting organic matter abundance parameters, and obtaining the organic matter abundance parameters of the non-coring well output by the model for predicting organic matter abundance parameters.

[0100] The specific implementation of the above method for determining organic matter abundance parameters may refer to steps S11, S12 and S13 in the aforementioned method for evaluating the regional organic matter abundance of oil source rocks, and the repeated parts will not be repeated here.

[0101] Based on the same inventive concept, the embodiment of the present invention also provides a device for judging the abundance of organic matter in oil source rocks, the structure of which is as follows: Figure 6 As shown, including:

[0102] An acquisition module 61 is used to acquire pre-stored corresponding data points of the organic matter abundance parameters of the oil source rocks of the coring wells and the well logging data set from the sample information database;

[0103] A training module 62 is used to train a neural network model using data points related to the organic matter abundance parameters of the oil source rocks of the coring wells and the well logging data set that have a corresponding relationship, so as to obtain a model for predicting the organic matter abundance parameters;

[0104] The prediction module 63 is used to input the well logging data set of the non-coring well into the prediction model of organic matter abundance parameters to obtain the organic matter abundance parameters of the non-coring well output by the prediction model of organic matter abundance parameters;

[0105] The evaluation module 64 evaluates the organic matter abundance area of ​​the target layer of the source rock where the non-cored wells and the cored wells are located according to the organic matter abundance parameters of the non-cored wells and the cored wells and the corresponding formation thickness.

[0106] Based on the same inventive concept, an embodiment of the present invention also provides a computing device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements a method for evaluating the organic matter abundance area of ​​oil source rocks, or a method for determining organic matter abundance parameters.

[0107] Based on the same inventive concept, an embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements a method for evaluating the organic matter abundance area of ​​oil source rocks, or a method for determining organic matter abundance parameters.

[0108] The method and device for evaluating the organic matter abundance area of ​​the oil source rock and determining the organic matter abundance parameters provided by the embodiment of the present invention use a neural network model to learn the relationship between the core organic matter abundance parameters of the cored well and the logging data set to obtain a model for predicting organic matter abundance parameters, and use the logging data set of the uncored well to input it into the model for predicting organic matter abundance parameters to obtain the organic matter abundance parameters of the uncored well, and based on the organic matter abundance parameters of the cored well and the uncored well and the thickness of the target layer oil source rock, the organic matter abundance area of ​​the target layer of the oil source rock is evaluated, and a new method for evaluating organic matter abundance based on the neural network model is proposed, and an organic matter abundance indicator factor is created for the first time as a regional evaluation indicator, which provides an adaptive tool for the regional evaluation of oil source rocks in the oil and gas exploration and evaluation stage, avoids the operation of coring the oil source rock on the spot, and can also correctly evaluate the organic matter abundance area of ​​the oil source rock, saving manpower and material resources, and has important practical significance in well exploration, evaluation deployment and new project selection.

[0109] Those skilled in the art will appreciate that 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 and optical storage, etc.) containing computer-usable program code.

[0110] 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 1A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] 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.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0113] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for evaluating the organic matter abundance region of oil source rocks, characterized in that: include: Obtaining from the sample information database the pre-stored corresponding organic matter abundance parameters of the oil source rock of the coring well and the relevant data points of the logging data set, as well as the oil source rock thickness of the target layer corresponding to the core in the coring well; The neural network model is trained using the data points related to the organic matter abundance parameters of the oil source rocks of the cored wells and the well logging data set, and a model for predicting the organic matter abundance parameters is obtained; Inputting the well logging data set of the non-cored well into the prediction model of organic matter abundance parameters to obtain the organic matter abundance parameters of the non-cored well output by the prediction model of organic matter abundance parameters; According to the organic matter abundance parameters of the uncored wells and the cored wells and the thickness of the target layer source rock corresponding to the core in the cored wells, the organic matter abundance area of ​​the target layer source rock where the uncored wells and the cored wells are located is evaluated.

2. The method according to claim 1, characterized in that The organic matter abundance area of ​​the target layer of the source rock where the non-cored well and the cored well are located is evaluated based on the organic matter abundance parameters of the non-cored well and the cored well and the corresponding formation thickness, including: For each coring well, the corresponding organic matter abundance parameter and the corresponding formation thickness are weighted averaged to obtain the organic matter abundance indicator factor of the coring well; For each uncored well, the corresponding organic matter abundance parameter and the corresponding formation thickness are weighted averaged to obtain the organic matter abundance indicator factor of the uncored well; According to the values ​​of the organic matter abundance indicator factors of the cored wells and the non-cored wells, an organic matter abundance regional evaluation map is obtained by the Kriging interpolation method; the organic matter abundance regional evaluation map is a plane map of organic matter indicator factor contour lines.

3. The method according to claim 1, characterized in that The sample information database obtains the pre-stored corresponding organic matter abundance parameters of the coring well source rock and the logging data set in the following way: The organic matter abundance parameters and logging data sets of the oil source rocks of the cored wells were sorted out, the logging data sets of the non-cored wells were sorted out, and a sample information database was established.

4. The method according to claim 3, characterized in that The organic matter abundance parameters of the oil source rock of the coring wells include: According to the target layer of abundance area evaluation, select the coring wells with sampled cores, record the coring well numbers, and count the thickness of the target layer's oil source rock; Classify and organize organic geochemical data and record organic matter abundance data of core wells.

5. The method according to claim 1, characterized in that Obtain the pre-stored corresponding data points of the organic matter abundance parameters of the coring well source rock and the well logging data set, including: The data points of the core well organic matter abundance parameters and logging data sets with a one-to-many relationship are obtained; the organic matter abundance data include: total organic carbon content TOC, chloroform bitumen "A", total hydrocarbons and rock pyrolysis parameters; the relevant data points of the logging data set include: the data points in the resistivity, acoustic wave, density and neutron logging data sets with a one-to-many relationship with the total organic carbon content TOC, chloroform bitumen "A", total hydrocarbons and rock pyrolysis parameters.

6. The method according to claim 1, characterized in that The neural network model is trained using the corresponding organic matter abundance parameters of the oil source rock of the coring well and the well logging data set to obtain a model for predicting organic matter abundance parameters, including: Generate a training data set according to the organic matter abundance parameters of the oil source rocks of the coring wells with corresponding relationships and the relevant data points of the logging data set; The training data set is used to train the neural network model to obtain a model for predicting organic matter abundance parameters.

7. The method according to claim 1, characterized in that The model for predicting organic matter abundance parameters includes: Input layer, used to input well logging data sets without coring wells; An output layer, used for outputting the organic matter abundance parameter predicted based on the input well logging data set; Hidden layer: a one-to-many multi-factor comprehensive evaluation function between organic matter abundance parameters and well logging data sets; The multi-factor comprehensive evaluation function is obtained in the following manner: taking the organic matter abundance parameters at the same depth, finding different data points corresponding to one of the organic matter abundance parameters on the curves of different logging data in the same core logging data set, learning the relationship between different data points through the neural network, and obtaining the multi-factor comprehensive evaluation relationship function.

8. A method for determining organic matter abundance parameters, characterized in that: include: Obtaining pre-stored corresponding data points of organic matter abundance parameters of oil source rocks in cored wells and well logging data sets from a sample information database; The neural network model is trained using the data points related to the organic matter abundance parameters of the oil source rocks of the cored wells and the well logging data set, and a model for predicting the organic matter abundance parameters is obtained; The well logging data set of the non-coring well is input into the prediction model of organic matter abundance parameters to obtain the organic matter abundance parameters of the non-coring well output by the prediction model of organic matter abundance parameters.

9. A device for judging the abundance of organic matter in oil source rocks, characterized in that: include: An acquisition module is used to acquire pre-stored corresponding data points of the organic matter abundance parameters of the oil source rocks of the coring wells and the well logging data set from the sample information database; A training module is used to train a neural network model using data points related to the organic matter abundance parameters of the oil source rocks of the coring wells and the well logging data set with corresponding relationships, so as to obtain a model for predicting the organic matter abundance parameters; A prediction module, used for inputting the well logging data set of the non-coring well into the prediction model of organic matter abundance parameters, and obtaining the organic matter abundance parameters of the non-coring well output by the prediction model of organic matter abundance parameters; The evaluation module evaluates the organic matter abundance area of ​​the target layer of the source rock where the non-cored wells and the cored wells are located based on the organic matter abundance parameters of the non-cored wells and the cored wells and the corresponding formation thickness.

10. A computing device, characterized in that include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the program executed by the processor implements the method for evaluating the organic matter abundance area of ​​the oil source rock as described in claim 1, or the method for determining the organic matter abundance parameter as described in claim 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for evaluating the organic matter abundance area of ​​the oil source rock according to claim 1 or the method for determining the organic matter abundance parameter according to claim 8 is implemented.

Images