Method, device and equipment for determining free hydrocarbon content of oil shale and storage medium

Abstract

The invention discloses an oil shale free hydrocarbon content determination method, device and equipment and a storage medium, and relates to the field of oil and gas field exploration, and the method comprises the steps: obtaining original logging gas logging data, and processing the original logging gas logging data to obtain target logging gas logging data; the original logging gas logging data comprises content information of key components; determining target characteristic parameters based on the target logging gas logging data, and constructing a free hydrocarbon content prediction model based on the target logging gas logging data and the target characteristic parameters; the target characteristic parameters comprise a hydrocarbon composition index, a target gas ratio and a normalized hydrocarbon concentration; judging whether the free hydrocarbon content prediction model meets a preset error condition or not, and determining the free hydrocarbon content prediction model as a target prediction model when the free hydrocarbon content prediction model meets the preset error condition, so as to predict the free hydrocarbon content of the target oil shale reservoir in real time by using the target prediction model. According to the invention, rapid, economical, real-time and comprehensive determination of the free hydrocarbon content of the oil shale is realized.

Description

Technical Field

[0001] The present invention relates to the field of oil and gas field exploration, and particularly to a method, device, equipment and storage medium for determining the free hydrocarbon content of oil shale. Background Art

[0002] In the field of oil and gas exploration and development, oil shale, as an important energy resource, the accurate determination of the free hydrocarbon content is crucial for evaluating resource potential and formulating exploitation strategies. At present, the widely used methods for determining the free hydrocarbon content of oil shale in the market mainly include laboratory chemical analysis methods, core physical property analysis methods, etc. Although these methods can reflect the free hydrocarbon content of oil shale to a certain extent, they have disadvantages such as long time consumption, high cost, poor real-time performance, and insufficient representativeness. Therefore, how to achieve rapid, economical, real-time and comprehensive determination of the free hydrocarbon content of oil shale is an urgent problem to be solved at present. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a method, device, equipment and storage medium for determining the free hydrocarbon content of oil shale, which can achieve rapid, economical, real-time and comprehensive determination of the free hydrocarbon content of oil shale. The specific scheme is as follows:

[0004] In the first aspect, the present application discloses a method for determining the free hydrocarbon content of oil shale, including:

[0005] Obtain the original logging gas measurement data, and process the original logging gas measurement data to obtain the target logging gas measurement data; the original logging gas measurement data is the logging gas measurement data collected in real time during the drilling process, and the original logging gas measurement data includes the content information of key components, and the key components include total hydrocarbon, methane, and ethane;

[0006] Determine the target characteristic parameters based on the target logging gas measurement data, and construct a free hydrocarbon content prediction model based on the target logging gas measurement data and the target characteristic parameters; the target characteristic parameters include hydrocarbon composition index, target gas ratio, and normalized hydrocarbon concentration;

[0007] Judge whether the free hydrocarbon content prediction model meets the preset error condition, and when the free hydrocarbon content prediction model meets the preset error condition, determine the free hydrocarbon content prediction model as the target prediction model, so as to use the target prediction model to predict the free hydrocarbon content of the target oil shale reservoir in real time.

[0008] Optionally, the processing of the original logging gas measurement data to obtain the target logging gas measurement data includes:

[0009] Perform denoising, calibration and standardization processing on the original logging gas measurement data based on a preset data processing algorithm to obtain the target logging gas measurement data.

[0010] Optionally, determining the target characteristic parameters based on the target mud logging gas measurement data includes:

[0011] Determining a hydrocarbon composition index based on the total hydrocarbon value of mud logging gas measurement, the content of methane component in gas measurement, the content of ethane component in gas measurement, the content of propane component in gas measurement, and the content of butane component in gas measurement in the target mud logging gas measurement data by using a preset hydrocarbon composition index determination formula;

[0012] Determining a target gas ratio based on the content of ethane component in gas measurement, the content of propane component in gas measurement, the content of normal butane component in gas measurement, and the content of isobutane component in gas measurement in the target mud logging gas measurement data by using a preset target gas ratio determination formula;

[0013] Determining a normalized hydrocarbon concentration based on the total hydrocarbon value of mud logging gas measurement, the current drilling time, and the average drilling time in the target mud logging gas measurement data by using a preset normalized hydrocarbon concentration determination formula.

[0014] Optionally, constructing a free hydrocarbon content prediction model based on the target mud logging gas measurement data and the target characteristic parameters includes:

[0015] Constructing a target training set and a target test set based on the target mud logging gas measurement data and the target characteristic parameters;

[0016] Constructing a free hydrocarbon content prediction model by using the target training set;

[0017] Correspondingly, determining whether the free hydrocarbon content prediction model meets a preset error condition includes:

[0018] Determining whether the free hydrocarbon content prediction model meets a preset error condition by using the target test set; the preset error condition is that the interpolation error of the judgment result of the free hydrocarbon content prediction model for the target test set is less than or equal to a target percentage.

[0019] Optionally, the method for determining the free hydrocarbon content of oil shale further includes:

[0020] If the free hydrocarbon content prediction model does not meet the preset error condition, increasing the training data in the target training set to obtain a new target training set, and jumping to the step of constructing a free hydrocarbon content prediction model by using the target training set.

[0021] Optionally, constructing a free hydrocarbon content prediction model based on the target mud logging gas measurement data and the target characteristic parameters includes:

[0022] Constructing a gradient boosting tree model, an extreme learning machine model, and a convolutional neural network model based on the target mud logging gas measurement data and the target characteristic parameters;

[0023] Construct a free hydrocarbon content prediction model based on the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model using a preset adaptive fusion algorithm;

[0024] Among them, the preset adaptive fusion algorithm is an adaptive fusion algorithm based on prediction confidence.

[0025] Optionally, the constructing a free hydrocarbon content prediction model based on the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model using a preset adaptive fusion algorithm includes:

[0026] Use a preset adaptive fusion algorithm to adjust the contribution weights corresponding to each base model in real time based on the weight coefficient determination formula; the base models include the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model;

[0027] Construct a free hydrocarbon content prediction model based on the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model based on the contribution weights corresponding to each base model.

[0028] In a second aspect, the present application discloses a device for determining the free hydrocarbon content of oil shale, including:

[0029] A data processing module, configured to obtain original logging gas measurement data and process the original logging gas measurement data to obtain target logging gas measurement data; the original logging gas measurement data is the logging gas measurement data collected in real time during the drilling process, and the original logging gas measurement data includes the content information of key components, and the key components include total hydrocarbon, methane, and ethane;

[0030] A prediction model construction module, configured to determine target characteristic parameters based on the target logging gas measurement data, and construct a free hydrocarbon content prediction model based on the target logging gas measurement data and the target characteristic parameters; the target characteristic parameters include hydrocarbon composition index, target gas ratio, and normalized hydrocarbon concentration;

[0031] A free hydrocarbon content prediction module, configured to determine whether the free hydrocarbon content prediction model meets a preset error condition, and when the free hydrocarbon content prediction model meets the preset error condition, determine the free hydrocarbon content prediction model as a target prediction model, so as to use the target prediction model to predict the free hydrocarbon content of the target oil shale reservoir in real time.

[0032] In a third aspect, the present application discloses an electronic device, including:

[0033] A memory, configured to store a computer program;

[0034] A processor for executing the computer program to implement the foregoing method for determining the free hydrocarbon content of oil shale.

[0035] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the foregoing method for determining the free hydrocarbon content of oil shale.

[0036] In the present application, when determining the free hydrocarbon content of oil shale, original logging gas measurement data is acquired, and the original logging gas measurement data is processed to obtain target logging gas measurement data; the original logging gas measurement data is the logging gas measurement data collected in real time during drilling, and the original logging gas measurement data includes the content information of key components, and the key components include total hydrocarbon, methane, and ethane; based on the target logging gas measurement data, target characteristic parameters are determined, and a free hydrocarbon content prediction model is constructed based on the target logging gas measurement data and the target characteristic parameters; the target characteristic parameters include a hydrocarbon composition index, a target gas ratio, and a normalized hydrocarbon concentration; it is determined whether the free hydrocarbon content prediction model meets a preset error condition, and when the free hydrocarbon content prediction model meets the preset error condition, the free hydrocarbon content prediction model is determined as the target prediction model, so as to use the target prediction model to predict in real time the free hydrocarbon content of the target oil shale reservoir. It can be seen that in the present application, original logging gas measurement data is collected during drilling, and the collected original path gas measurement data is processed to obtain target logging gas measurement data including the content information of key components. Then, based on these target logging gas measurement data, target characteristic parameters are determined, and then a free hydrocarbon content prediction model can be trained based on these target characteristic parameters to obtain a target prediction model. Since the final target prediction model is trained using target characteristic parameters that can reflect the content information of key components and the target prediction model meets the preset error condition, the target prediction model can be used to predict in real time the free hydrocarbon content of the target oil shale reservoir, thereby realizing fast, economical, real-time, and comprehensive determination of the free hydrocarbon content of oil shale. Description of the Drawings

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0038] Figure 1 It is a flowchart of a method for determining the free hydrocarbon content of oil shale disclosed in the present application;

[0039] Figure 2Schematic diagram of the correlation between the measured free hydrocarbon content and the measured hydrocarbon composition index disclosed in this application;

[0040] Figure 3 Schematic diagram of the correlation between the measured free hydrocarbon content and the measured gas ratio disclosed in this application;

[0041] Figure 4 Schematic diagram of the correlation between the measured free hydrocarbon content and the measured normalized hydrocarbon concentration of drilling time disclosed in this application;

[0042] Figure 5 Schematic diagram of a method for constructing a prediction model of free hydrocarbon content disclosed in this application;

[0043] Figure 6 Schematic diagram of the correlation between the output result of the target prediction model disclosed in this application and the measured free hydrocarbon content;

[0044] Figure 7 Schematic diagram of the comparison between the prediction result of the free hydrocarbon content of the target prediction model and the measured prediction result of the free hydrocarbon content at different depths disclosed in this application;

[0045] Figure 8 Schematic diagram of the structure of a device for determining the free hydrocarbon content of oil shale disclosed in this application;

[0046] Figure 9 Schematic diagram of the structure of an electronic device disclosed in this application. Detailed implementation manners

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0048] Currently, the methods for determining the free hydrocarbon content of oil shale widely used in the market mainly include laboratory chemical analysis methods, core physical property analysis methods, etc. Although these methods can reflect the free hydrocarbon content of oil shale to a certain extent, they have disadvantages such as long time consumption, high cost, poor real-time performance, and insufficient representativeness. To solve the above technical problems, this application discloses a method for determining the free hydrocarbon content of oil shale, which can realize rapid, economical, real-time and comprehensive determination of the free hydrocarbon content of oil shale.

[0049] See Figure 1 As shown, the embodiments of the present invention disclose a method for determining the free hydrocarbon content of oil shale, including:

[0050] Step S11: Obtain the original logging gas measurement data, and process the original logging gas measurement data to obtain the target logging gas measurement data; the original logging gas measurement data is the logging gas measurement data collected in real time during the drilling process, and the original logging gas measurement data includes the content information of key components, and the key components include total hydrocarbon, methane, and ethane.

[0051] In this embodiment, during the drilling process, a logging while drilling (LWD) device is used to collect the logging gas measurement data in real time, and the collected logging gas measurement data is used as the original logging gas measurement data. The content information of key components such as total hydrocarbon, methane, and ethane is included in these original logging gas measurement data. The data collection frequency can be set according to actual needs to ensure that the changes in the content of free hydrocarbons in the reservoir can be captured. After obtaining the original logging gas measurement data, the original logging gas measurement data will be processed to enhance the usability of the data and improve the data quality. Specifically, processing the original logging gas measurement data to obtain the target logging gas measurement data includes: performing denoising, calibration, and normalization processing on the original logging gas measurement data based on a preset data processing algorithm to obtain the target logging gas measurement data. Through this operation, outliers caused by equipment failures, environmental factors, etc. can be removed, and the deviation caused by measurement errors can be corrected to ensure the accuracy and reliability of the data. In addition, normalizing the data at different times and different depths according to a unified standard is conducive to the subsequent analysis work.

[0052] Step S12: Determine the target characteristic parameters based on the target logging gas measurement data, and construct a free hydrocarbon content prediction model based on the target logging gas measurement data and the target characteristic parameters; the target characteristic parameters include hydrocarbon composition index, target gas ratio, and normalized hydrocarbon concentration.

[0053] In this embodiment, determining the target characteristic parameters based on the target logging gas measurement data includes: determining the hydrocarbon composition index based on the total hydrocarbon value of the logging gas measurement, the content of the methane component in the logging gas measurement, the content of the ethane component in the logging gas measurement, the content of the propane component in the logging gas measurement, and the content of the butane component in the logging gas measurement in the target logging gas measurement data using a preset hydrocarbon composition index determination formula; determining the target gas ratio based on the content of the ethane component in the logging gas measurement, the content of the propane component in the logging gas measurement, the content of the n-butane component in the logging gas measurement, and the content of the isobutane component in the logging gas measurement in the target logging gas measurement data using a preset target gas ratio determination formula; determining the normalized hydrocarbon concentration based on the total hydrocarbon value of the logging gas measurement, the current drilling duration, and the average drilling duration in the target logging gas measurement data using a preset normalized hydrocarbon concentration determination formula. As Figure 2 shown in the schematic diagram of the correlation between the measured free hydrocarbon content and the hydrocarbon composition index, Figure 3 is the schematic diagram of the correlation between the measured free hydrocarbon content and the gas ratio, Figure 4It is a schematic diagram of the correlation between the measured free hydrocarbon content and the normalized hydrocarbon concentration with drilling time. As can be seen from the figure, there is a certain correlation between the free hydrocarbon content, hydrocarbon composition index, gas ratio, and normalized hydrocarbon concentration with drilling time. Therefore, the hydrocarbon composition index, gas ratio, and normalized hydrocarbon concentration with drilling time can be used as target characteristic parameters.

[0054] Among them, the determination formula for the hydrocarbon composition index is:

[0055] ;

[0056] The determination formula for the preset target gas ratio is:

[0057] ;

[0058] The determination formula for the preset normalized hydrocarbon concentration is:

[0059] ;

[0060] Among them, is the total hydrocarbon value in the target mud logging gas measurement data, is the content of methane component in gas measurement, is the content of ethane component in gas measurement, is the content of propane component in gas measurement, is the content of butane component in gas measurement, is the content of normal butane component in gas measurement, is the content of isobutane component in gas measurement, is the target gas ratio, is the normalized hydrocarbon concentration, is the current drilling time, is the average drilling time.

[0061] In this embodiment, the target characteristic parameters determined based on the target mud logging gas measurement data cover characteristic component ratios and concentration change trends, etc. Therefore, these target characteristic parameters can be used to analyze the characteristic differences of gas measurement data in different oil shale intervals, so as to identify characteristic variables closely related to the free hydrocarbon content. A free hydrocarbon content prediction model is constructed based on the target mud logging gas measurement data and target characteristic parameters, which specifically may include: constructing a target training set and a target test set based on the target mud logging gas measurement data and target characteristic parameters; using the target training set to construct a free hydrocarbon content prediction model. By selecting sample data of the free state content of known oil shale reservoirs covering different geological conditions and reservoir conditions at different depths as the training set and test set, the generalization ability of the finally obtained model is ensured.

[0062] In a specific embodiment, a gradient boosting tree model, an extreme learning machine model, and a convolutional neural network model can be constructed based on target mud logging gas measurement data and target characteristic parameters; a free hydrocarbon content prediction model can be constructed using a preset adaptive fusion algorithm based on the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model; wherein, the preset adaptive fusion algorithm is an adaptive fusion algorithm based on prediction confidence. When constructing the free hydrocarbon content prediction model using the preset adaptive fusion algorithm based on the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model, the contribution weights corresponding to each base model can be adjusted in real time using the preset adaptive fusion algorithm based on the weight coefficient determination formula; wherein the base models include the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model; and then a free hydrocarbon content prediction model based on the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model can be constructed based on the contribution weights corresponding to each base model. That is to say, when constructing the free hydrocarbon content prediction model, a prediction model based on machine learning (such as random forest, neural network, etc.) or statistics (such as multiple linear regression, support vector machine, etc.) will be established by combining the sample data of the known free hydrocarbon content in the oil shale reservoir (i.e., the target mud logging gas measurement data) with the extracted target characteristic parameters. The prediction model can be a heterogeneous model library constructed by base models such as GBDT (Gradient Boosting Decision Tree), ELM (Extreme Learning Machine), and CNN (Convolutional Neural Network), as Figure 3 shown. Specifically, the GBDT model is set with a learning rate of 0.05, a maximum depth of 6 layers, and a subsample rate of 0.8. The ELM network uses the Sigmoid activation function, and the number of hidden layer nodes can be determined to be 128 after being optimized by orthogonal experiments. The 1D-CNN is configured with three convolutional kernels (sizes are 5, 3, 3 respectively), and the number of channels is 16 - 32 - 64. When constructing the target training set and the target test set, geological stratification cross-validation can be performed, and the target training set and the target test set corresponding to each base model can be divided according to the organic matter maturity to ensure that the maturity distribution in each data set is consistent. In a specific embodiment, a data set with a vitrinite reflectance Ro less than 0.8% can be used to train the gradient boosting tree model, a data set with a vitrinite reflectance between 0.8% and 1.2% can be used to train the extreme learning machine model, and a data set with a vitrinite reflectance greater than 1.2% can be used to train the convolutional neural network model, so that the prediction accuracy of the trained base models is higher. By adjusting the model parameters, optimization algorithms, and other steps of each base model, the prediction accuracy and stability of the finally obtained model can be improved.

[0063] In this embodiment, the preset adaptive fusion algorithm is designed based on the prediction confidence, and the contribution weights corresponding to each base model can be adjusted in real time according to the weight coefficient determination formula. The weight coefficient determination formula is as follows:

[0064] ;

[0065] where is the weight coefficient corresponding to the th base model, is the prediction weight, and is the true weight.

[0066] Step S13: Determine whether the free hydrocarbon content prediction model meets the preset error condition, and when the free hydrocarbon content prediction model meets the preset error condition, determine the free hydrocarbon content prediction model as the target prediction model, so as to use the target prediction model to predict the free hydrocarbon content of the target oil shale reservoir in real time.

[0067] In this embodiment, when determining whether the free hydrocarbon content prediction model meets the preset error condition, the target test set can be used to determine whether the free hydrocarbon content prediction model meets the preset error condition; the preset error condition is that the interpolation error of the judgment result of the free hydrocarbon content prediction model for the target test set is less than or equal to the target percentage. If the free hydrocarbon content prediction model does not meet the preset error condition, the training data in the target training set is increased to obtain a new target training set, and the process jumps to the step of constructing the free hydrocarbon content prediction model using the target training set. That is to say, this embodiment can use the test set data to verify the established free hydrocarbon content prediction model, evaluate its prediction accuracy and generalization ability. Make necessary adjustments and optimizations to the free hydrocarbon content prediction model according to the verification results to ensure that the free hydrocarbon content prediction model can meet the actual application requirements. Specifically, the target percentage can be set to 5%. Compare the free hydrocarbon content value calculated by the free hydrocarbon content prediction model with the actual measured value of the analysis and test, and it is most reasonable that the interpolation error of the calculated data does not exceed 5%. Therefore, when the interpolation error of the calculated data does not exceed 5%, the free hydrocarbon content prediction model can be used to calculate the free hydrocarbon content; when the interpolation error of the calculated data exceeds 5%, the number of samples for learning is increased until the interpolation error of the calculated data does not exceed 5%, so as to continuously optimize the model parameters and ensure the accuracy and generalization ability of the finally obtained target prediction model, so as to use the target prediction model to predict the free hydrocarbon content of the target oil shale reservoir in real time and obtain more accurate and objective results. Figure 6 It is a schematic diagram of the correlation between the output result of the target prediction model obtained in this embodiment and the measured free hydrocarbon content.

[0068] In this embodiment, applying the established target prediction model to the real-time logging gas measurement data can achieve rapid prediction of the free hydrocarbon content in oil shale and obtain more accurate and objective results. The prediction results can be fed back to the exploration and development team in real time through a visualization interface or a data interface, and the drilling plan, production strategy, etc. can be adjusted according to the prediction results, providing an important basis for subsequent oil and gas exploration and development. For example, Figure 7 As shown, the free hydrocarbon content in the well section of 3520 - 3605m of Well A in a certain oilfield is calculated based on the logging gas measurement data by using the method for determining the free hydrocarbon content in oil shale disclosed in this embodiment. By comparing with the actual measured data of analysis and testing, the calculation accuracy can reach over 90%, indicating that this embodiment has good application effects. At the same time, it has a broad prospect of popularization and application in areas with a high degree of exploration and development.

[0069] It can be seen that in this application, the original logging gas measurement data is collected during drilling, and the collected original path gas measurement data is processed to obtain the target logging gas measurement data containing the content information of key components. Then, based on these target logging gas measurement data, target characteristic parameters are determined, and then the free hydrocarbon content prediction model can be trained according to these target characteristic parameters, thereby obtaining the target prediction model. Since the final target prediction model is trained using the target characteristic parameters that can reflect the content information of key components and the target prediction model meets the preset error conditions, the target prediction model can be used to predict the free hydrocarbon content in the target oil shale reservoir in real time, thus realizing rapid, economical, real-time and comprehensive determination of the free hydrocarbon content in oil shale.

[0070] See Figure 8 As shown, this application discloses a device for determining the free hydrocarbon content in oil shale, including:

[0071] A data processing module 11, configured to obtain the original logging gas measurement data and process the original logging gas measurement data to obtain the target logging gas measurement data; the original logging gas measurement data is the logging gas measurement data collected in real time during drilling, and the original logging gas measurement data includes the content information of key components, and the key components include total hydrocarbon, methane, and ethane;

[0072] A prediction model construction module 12, configured to determine target characteristic parameters based on the target logging gas measurement data and construct a free hydrocarbon content prediction model based on the target logging gas measurement data and the target characteristic parameters; the target characteristic parameters include hydrocarbon composition index, target gas ratio, and normalized hydrocarbon concentration;

[0073] The free hydrocarbon content prediction module 13 is used to determine whether the free hydrocarbon content prediction model meets the preset error condition, and when the free hydrocarbon content prediction model meets the preset error condition, determine the free hydrocarbon content prediction model as the target prediction model, so as to use the target prediction model to predict the free hydrocarbon content of the target oil shale reservoir in real time.

[0074] It can be seen that in this application, the original logging gas measurement data is collected during drilling, and the collected original path gas measurement data is processed to obtain the target logging gas measurement data containing the content information of key components. Then, based on these target logging gas measurement data, the target characteristic parameters are determined. After that, the free hydrocarbon content prediction model can be trained according to these target characteristic parameters, so as to obtain the target prediction model. Since the final target prediction model is trained by using the target characteristic parameters that can reflect the content information of key components, and the target prediction model meets the preset error condition, the free hydrocarbon content of the target oil shale reservoir can be predicted in real time by using this target prediction model, thus realizing the rapid, economical, real-time and comprehensive determination of the free hydrocarbon content of oil shale.

[0075] In a specific embodiment, the data processing module 11 may specifically include:

[0076] The data processing sub-module is used to perform denoising, calibration and standardization processing on the original logging gas measurement data based on a preset data processing algorithm to obtain the target logging gas measurement data.

[0077] In a specific embodiment, the prediction model construction module 12 may specifically include:

[0078] The hydrocarbon composition index determination sub-module is used to determine the hydrocarbon composition index based on the total hydrocarbon value of the logging gas measurement, the content of methane component in the gas measurement, the content of ethane component in the gas measurement, the content of propane component in the gas measurement and the content of butane component in the gas measurement in the target logging gas measurement data by using a preset hydrocarbon composition index determination formula;

[0079] The gas ratio determination sub-module is used to determine the target gas ratio based on the content of ethane component in the gas measurement, the content of propane component in the gas measurement, the content of normal butane component in the gas measurement and the content of isobutane component in the gas measurement in the target logging gas measurement data by using a preset target gas ratio determination formula;

[0080] The normalized hydrocarbon concentration determination sub-module is used to determine the normalized hydrocarbon concentration based on the total hydrocarbon value of the logging gas measurement, the current drilling time and the average drilling time in the target logging gas measurement data by using a preset normalized hydrocarbon concentration determination formula.

[0081] In a specific embodiment, the prediction model construction module 12 may specifically include:

[0082] A dataset construction sub-module for constructing a target training set and a target test set based on the target mud logging gas logging data and the target characteristic parameters;

[0083] A prediction model construction sub-module for constructing a free hydrocarbon content prediction model using the target training set;

[0084] Correspondingly, the free hydrocarbon content prediction module 13 may specifically include:

[0085] An error judgment sub-module for using the target test set to judge whether the free hydrocarbon content prediction model meets the preset error condition; the preset error condition is that the interpolation error of the judgment result of the free hydrocarbon content prediction model for the target test set is less than or equal to the target percentage.

[0086] In a specific embodiment, the device may further include:

[0087] A training set reconstruction module for, if the free hydrocarbon content prediction model does not meet the preset error condition, increasing the training data in the target training set to obtain a new target training set, and jumping to the step of constructing a free hydrocarbon content prediction model using the target training set.

[0088] In a specific embodiment, the prediction model construction module 12 may specifically include:

[0089] A first model construction sub-module for constructing a gradient boosting tree model, an extreme learning machine model, and a convolutional neural network model based on the target mud logging gas logging data and the target characteristic parameters;

[0090] A second model construction sub-module for constructing a free hydrocarbon content prediction model based on the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model using a preset adaptive fusion algorithm;

[0091] Wherein, the preset adaptive fusion algorithm is an adaptive fusion algorithm based on prediction confidence.

[0092] In a specific embodiment, the second model construction sub-module may specifically include:

[0093] A contribution weight determination unit for using a preset adaptive fusion algorithm to adjust the contribution weights corresponding to each base model in real time based on a weight coefficient determination formula; the base models include the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model;

[0094] A prediction model construction unit for constructing a free hydrocarbon content prediction model based on the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model based on the contribution weights corresponding to each base model.

[0095] Furthermore, an embodiment of the present application also discloses an electronic device. Figure 9 It is a structural diagram of an electronic device 20 shown according to an exemplary embodiment. The content in the figure should not be considered as any limitation on the scope of use of the present application.

[0096] Figure 9 It is a schematic structural diagram of an electronic device 20 provided by an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the oil shale free hydrocarbon content determination method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0097] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol applicable to the technical solution of the present application, and specific limitations are not imposed on it here; the input / output interface 25 is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application needs, and no specific limitations are imposed here.

[0098] In addition, as a carrier for resource storage, the memory 22 may be a read-only memory, a random access memory, a magnetic disk, or an optical disc, etc. The resources stored thereon may include an operating system 221, a computer program 222, etc., and the storage method may be temporary storage or permanent storage.

[0099] Among them, the operating system 221 is used to manage and control each hardware device and the computer program 222 on the electronic device 20, and it may be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the oil shale free hydrocarbon content determination method executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs that can be used to complete other specific tasks.

[0100] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the oil shale free hydrocarbon content determination method disclosed above. For the specific steps of this method, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details are not repeated here.

[0101] In this specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description in the method section.

[0102] Those skilled in the art can further realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0103] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of both. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0104] Finally, it should also be noted that in this text, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0105] The above has introduced the technical solutions provided by this application in detail. Specific examples are used herein to elaborate on the principles and implementation manners of this application. The descriptions of the above embodiments are only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A method for determining the free hydrocarbon content of oil shale, characterized in that Including: Obtain the original logging gas measurement data, and process the original logging gas measurement data to obtain target logging gas measurement data; The original logging gas measurement data is the logging gas measurement data collected in real time during the drilling process. The original logging gas measurement data includes the content information of key components, and the key components include total hydrocarbon, methane, and ethane; Determine target characteristic parameters based on the target logging gas measurement data, and construct a free hydrocarbon content prediction model based on the target logging gas measurement data and the target characteristic parameters; the target characteristic parameters include hydrocarbon composition index, target gas ratio, and normalized hydrocarbon concentration; Judge whether the free hydrocarbon content prediction model meets the preset error condition, and when the free hydrocarbon content prediction model meets the preset error condition, determine the free hydrocarbon content prediction model as the target prediction model, so as to use the target prediction model to predict the free hydrocarbon content of the target oil shale reservoir in real time.

2. The method for determining the free hydrocarbon content of oil shale according to claim 1, wherein The processing of the original logging gas measurement data to obtain target logging gas measurement data includes: Perform denoising, calibration, and standardization processing on the original logging gas measurement data based on a preset data processing algorithm to obtain target logging gas measurement data.

3. The method for determining the free hydrocarbon content of oil shale according to claim 1, characterized in that, The determining of the target characteristic parameters based on the target logging gas measurement data includes: Determine the hydrocarbon composition index based on the logging gas measurement total hydrocarbon value, the content of the logging gas measurement methane component, the content of the logging gas measurement ethane component, the content of the logging gas measurement propane component, and the content of the logging gas measurement butane component in the target logging gas measurement data by using a preset hydrocarbon composition index determination formula; Determine the target gas ratio based on the content of the logging gas measurement ethane component, the content of the logging gas measurement propane component, the content of the logging gas measurement normal butane component, and the content of the logging gas measurement isobutane component in the target logging gas measurement data by using a preset target gas ratio determination formula; Determine the normalized hydrocarbon concentration based on the logging gas measurement total hydrocarbon value, the current drilling time, and the average drilling time in the target logging gas measurement data by using a preset normalized hydrocarbon concentration determination formula.

4. The method for determining the free hydrocarbon content of oil shale according to claim 1, characterized in that, The constructing of the free hydrocarbon content prediction model based on the target logging gas measurement data and the target characteristic parameters includes: Construct a target training set and a target test set based on the target logging gas measurement data and the target characteristic parameters; Construct a free hydrocarbon content prediction model by using the target training set; Correspondingly, the judging of whether the free hydrocarbon content prediction model meets the preset error condition includes: Judge whether the free hydrocarbon content prediction model meets the preset error condition by using the target test set; the preset error condition is that the interpolation error of the judgment result of the free hydrocarbon content prediction model for the target test set is less than or equal to the target percentage.

5. The method for determining the free hydrocarbon content of oil shale according to claim 4, wherein Also including: If the free hydrocarbon content prediction model does not meet the preset error condition, then increase the training data in the target training set to obtain a new target training set, and jump to the step of constructing a free hydrocarbon content prediction model by using the target training set.

6. The method for determining the free hydrocarbon content of oil shale according to claim 1, wherein The constructing of the free hydrocarbon content prediction model based on the target logging gas measurement data and the target characteristic parameters includes: Construct a gradient boosting tree model, an extreme learning machine model, and a convolutional neural network model based on the target logging gas measurement data and the target characteristic parameters; Construct a free hydrocarbon content prediction model based on the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model by using a preset adaptive fusion algorithm; Among them, the preset adaptive fusion algorithm is an adaptive fusion algorithm based on prediction confidence.

7. The method for determining the free hydrocarbon content of oil shale according to claim 6, wherein The step of constructing a free hydrocarbon content prediction model based on the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model by using a preset adaptive fusion algorithm includes: Using the preset adaptive fusion algorithm to adjust the contribution weights corresponding to each base model in real time according to the weight coefficient determination formula; the base models include the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model; Construct a free hydrocarbon content prediction model based on the gradient boosting tree model, the extreme learning machine model, and the convolutional neural network model based on the contribution weights corresponding to each base model.

8. An apparatus for determining the free hydrocarbon content of oil shale, characterized in that, It includes: A data processing module, configured to obtain original mud logging gas measurement data and process the original mud logging gas measurement data to obtain target mud logging gas measurement data; the original mud logging gas measurement data is the mud logging gas measurement data collected in real time during the drilling process, and the original mud logging gas measurement data includes the content information of key components, and the key components include total hydrocarbon, methane, and ethane; A prediction model construction module, configured to determine target characteristic parameters based on the target mud logging gas measurement data, and construct a free hydrocarbon content prediction model based on the target mud logging gas measurement data and the target characteristic parameters; the target characteristic parameters include hydrocarbon composition index, target gas ratio, and normalized hydrocarbon concentration; A free hydrocarbon content prediction module, configured to determine whether the free hydrocarbon content prediction model meets a preset error condition, and when the free hydrocarbon content prediction model meets the preset error condition, determine the free hydrocarbon content prediction model as the target prediction model, so as to use the target prediction model to predict the free hydrocarbon content of the target oil shale reservoir in real time.

9. An electronic device, characterized in that, It includes: A memory, configured to store a computer program; A processor, configured to execute the computer program to implement the method for determining the free hydrocarbon content of oil shale according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, For storing a computer program, wherein the computer program, when executed by a processor, implements the method for determining the free hydrocarbon content of oil shale according to any one of claims 1 to 7.

Images