A method, device and equipment for optimizing fracturing parameters for oil and gas production

Abstract

The present invention provides a method, device and equipment for optimizing fracturing parameters for oil and gas exploitation. The method includes: bringing the seismic parameters of a target well into a pre-established seismic physical property prediction model to obtain the reservoir physical property parameters of the target well at different depths; screening the reservoir physical property parameters at different depths according to the historical production data of adjacent wells to determine the target well section; bringing the reservoir physical property parameters of the target well section and the fracturing parameters to be optimized into the first production capacity prediction model of the adjacent wells, and optimizing the fracturing parameters to be optimized according to the prediction results to determine the target fracturing parameters. Through the characteristics of geological consistency between adjacent wells and the target well in the same work area, the optimization of the fracturing parameters of the target well can be realized by combining the data of the adjacent wells with the seismic parameters of the target well, improving the accuracy of optimizing the fracturing parameters during the exploitation of the target well, and further improving the accuracy of oil and gas prediction of the target well.

Description

Technical Field

[0001] This article belongs to the technical field of oil and gas development, and specifically relates to a method, device, and equipment for optimizing fracturing parameters in oil and gas production. Background Technique

[0002] With the rapid increase in the demand for oil and gas resources, the objects of research and exploitation are gradually facing unconventional oil and gas resources with high exploitation difficulties. In order to reduce the exploitation cost, certain stimulation measures are required to achieve the effect of economic exploitation. Hydraulic fracturing is the main technology for current reservoir stimulation. Selecting the appropriate well section and formation, combined with appropriate fracturing parameters, can maximize the fracturing stimulation effect and improve economic benefits. Therefore, optimizing the well section, formation, and fracturing parameters is very important for fracturing stimulation.

[0003] Currently, the commonly used parameter optimization method is to conduct sensitivity analysis on parameters through single-factor or multi-factor analysis methods, and then optimize the parameters in combination with laboratory tests and field application effects. The process is relatively complex and mainly relies on experience when selecting analysis factors, which will lead to less than ideal results in parameter optimization, and further greatly reduce the reliability of oil and gas production capacity prediction. Therefore, how to improve the reliability of parameter optimization in the process of oil and gas exploitation, and then ensure the accuracy of oil and gas prediction has become a technical problem that urgently needs to be solved. Summary of the Invention

[0004] Aiming at the above problems of the prior art, the purpose of this article is to provide a method, device, and equipment for optimizing fracturing parameters in oil and gas production, so as to improve the accuracy of optimizing fracturing parameters in the process of oil and gas collection, and further improve the accuracy of oil and gas prediction.

[0005] To solve the above technical problems, the specific technical solutions of this article are as follows:

[0006] On the one hand, this article provides a method for optimizing fracturing parameters in oil and gas production, and the method includes:

[0007] Substitute the seismic parameters of the target well into the pre-established seismic physical property prediction model to obtain the reservoir physical property parameters of the target well at different depths;

[0008] According to the historical production data of adjacent wells, screen the reservoir physical property parameters at different depths to determine the target well section;

[0009] Substitute the reservoir physical property parameters of the target well section and the fracturing parameters to be optimized into the first production capacity prediction model of the adjacent well, and optimize the fracturing parameters to be optimized according to the prediction results to determine the target fracturing parameters. The first production capacity prediction model is a time-series-based model trained by the reservoir physical property parameters, fracturing parameters, and historical production at the initial stage of production of the adjacent well.

[0010] Furthermore, the seismic physical property prediction model is obtained through the following steps:

[0011] Obtain the seismic parameters and reservoir physical property parameters of adjacent wells at different depths to form a training set;

[0012] Use the training set to train the initial seismic physical property prediction model to obtain the pre-established seismic physical property prediction model.

[0013] Furthermore, screening the reservoir physical property parameters at different depths according to the historical production data of adjacent wells to determine the target well section, including:

[0014] Obtain the historical fracturing parameters of adjacent wells at the initial stage of production;

[0015] Input the multiple groups of input data formed by the reservoir physical property parameters at different depths of the target well and the historical fracturing parameters into the second production capacity prediction model in sequence to obtain the production prediction results corresponding to the reservoir physical property parameters at different depths of the target well;

[0016] Determine the well section corresponding to the reservoir physical property parameters with the highest production prediction result as the target well section.

[0017] Furthermore, the second production capacity prediction model is obtained through the following steps:

[0018] Obtain the historical sampling data of multiple adjacent wells, where the historical sampling data includes different types of reservoir physical property parameters, different types of fracturing parameters, and daily production;

[0019] Normalize the reservoir physical property parameters, the fracturing parameters, and the daily production;

[0020] According to the results of the normalization process, calculate the correlation coefficients of each type of reservoir physical property parameter and each type of fracturing parameter with respect to the daily production. The correlation coefficients are used to characterize the influence weights of the reservoir physical property parameter types and the fracturing parameter types on the daily production;

[0021] Use the reservoir physical property parameter types and fracturing parameter types with correlation coefficients exceeding the preset value as inputs, and use the daily production as the target output to train the second initial production prediction model to obtain the trained second production capacity prediction model.

[0022] Furthermore, the correlation coefficient is obtained through the following formula:

[0023]

[0024] where ξ i is the correlation coefficient of the i-th factor with respect to the daily production, ξ i(k) The correlation coefficient of the value of the i-th factor in the k-th sampling data with respect to the daily production, where the factors are reservoir physical property parameter types and fracturing parameter types, x0(k) is the value of the daily production of the k-th sampling data, and x i (k) is the value of the i-th factor in the k-th sampling data, and ρ is the coefficient that controls the discrimination of ξ i (k).

[0025] Further, the step of bringing the reservoir physical property parameters and the fracturing parameters to be optimized of the target well section into the first production capacity prediction model of the adjacent well, and optimizing the fracturing parameters to be optimized according to the prediction result to determine the target fracturing parameters includes:

[0026] Obtain the fracturing parameters during the full production cycle of the adjacent well, and determine the optimization range of the fracturing parameters;

[0027] According to the optimization range of the fracturing parameters and the preset optimization interval, determine multiple combinations of fracturing parameters;

[0028] According to the reservoir physical property parameters of the target well section, multiple combinations of fracturing parameters, and the production at the initial stage of production of the adjacent well, combined with the first production capacity prediction model of the adjacent well, predict the predicted production of each combination of fracturing parameters, and the prediction duration of the predicted production is the same as the duration at the initial stage of production;

[0029] Calculate the average value of the predicted production of each combination of fracturing data during the prediction duration, and take the combination of fracturing parameters with the highest average value as the target fracturing parameters.

[0030] Further, the step of bringing the reservoir physical property parameters and the fracturing parameters to be optimized of the target well section into the first production capacity prediction model of the adjacent well, and optimizing the fracturing parameters to be optimized according to the prediction result to determine the target fracturing parameters includes:

[0031] Obtain the fracturing parameters during the full production cycle of the adjacent well, and determine the optimization range of the fracturing parameters;

[0032] According to the reservoir physical property parameters of the target well section, the optimization range of the fracturing parameters, and the production at the initial stage of production of the adjacent well, combined with the first production capacity prediction model of the adjacent well, use the particle swarm optimization algorithm to determine the fracturing parameters that meet the specified conditions from the optimization range of the fracturing parameters, and determine the finally determined fracturing parameters as the target fracturing parameters.

[0033] On the other hand, this article also provides a device for optimizing fracturing parameters for oil and gas production, and the device includes:

[0034] A reservoir physical property parameter obtaining module, configured to bring the seismic parameters of the target well into a pre-established seismic physical property prediction model to obtain the reservoir physical property parameters of the target well at different depths;

[0035] A target well section determination module, configured to screen the reservoir physical property parameters at different depths according to the historical production data of adjacent wells, and determine the target well section;

[0036] An optimization module, configured to input the reservoir physical property parameters of the target well section and the fracturing parameters to be optimized into the first production capacity prediction model of the adjacent well, and optimize the fracturing parameters to be optimized according to the prediction result to determine the target fracturing parameters. The first production capacity prediction model is a time-series-based model trained by the reservoir physical property parameters, fracturing parameters and historical production at the initial stage of production of the adjacent well.

[0037] On the other hand, this article also provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method described above is implemented.

[0038] Finally, this article also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0039] Adopting the above technical solution, a fracturing parameter optimization method, device and equipment for oil and gas exploitation described in this article can obtain the reservoir physical property parameters of a target well at different depths through the seismic parameters of the target well and a pre-established seismic physical property prediction model. Then, according to the historical production data of adjacent wells, the target well section is screened out from the reservoir physical property parameters at different depths of the target well. Finally, the reservoir physical property parameters of the target well section and the fracturing parameters to be optimized are input into the first production capacity prediction model of the adjacent well, and the fracturing parameters to be optimized are optimized according to the prediction result to determine the target fracturing parameters. Through the characteristics of geological consistency between adjacent wells and the target well in the same work area, this article can realize the optimization of the fracturing parameters of the target well by combining the data of adjacent wells with the seismic parameters of the target well, improve the accuracy of fracturing parameter optimization during the exploitation of the target well, and further improve the accuracy of oil and gas prediction of the target well.

[0040] To make the above and other purposes, features and advantages of this article more obvious and understandable, the following specific preferred embodiments are given in conjunction with the accompanying drawings and described in detail as follows. Description of the Drawings

[0041] In order to more clearly illustrate the technical solutions in the embodiments of this article or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of this article. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0042] Figure 1 It shows a schematic diagram of the implementation environment of the fracturing parameter optimization method for oil and gas exploitation provided by the embodiments of the present text;

[0043] Figure 2 It shows a schematic diagram of the steps of the fracturing parameter optimization method for oil and gas exploitation provided by the embodiments of the present text;

[0044] Figure 3 It shows a schematic diagram of the steps for determining the target well section in the embodiments of the present text;

[0045] Figure 4 It shows a schematic diagram of the steps for training the second production capacity prediction model in the embodiments of the present text;

[0046] Figure 5 It shows a schematic diagram of the steps for optimizing the target fracturing parameters in the embodiments of the present text;

[0047] Figure 6 It shows a schematic diagram of the steps for optimizing the target fracturing parameters in another embodiment of the present text;

[0048] Figure 7 It shows a schematic diagram of the structure of the fracturing parameter optimization device for oil and gas exploitation provided by the embodiments of the present text;

[0049] Figure 8 It shows a schematic diagram of the structure of the computer device provided by the embodiments of the present text.

[0050] Explanation of the reference symbols in the drawings:

[0051] 10. Client;

[0052] 20. Database;

[0053] 30. Server;

[0054] 100. Reservoir physical property parameter acquisition module;

[0055] 200. Target well section determination module;

[0056] 300. Optimization module;

[0057] 802. Computer device;

[0058] 804. Processor;

[0059] 806. Memory;

[0060] 808. Driving mechanism;

[0061] 810. Input / output module;

[0062] 812. Input device;

[0063] 814. Output device;

[0064] 816. Presentation device;

[0065] 818. Graphical user interface;

[0066] 820. Network interface;

[0067] 822. Communication link;

[0068] 824. Communication bus. Detailed implementation manner

[0069] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present disclosure.

[0070] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or equipment.

[0071] In the prior art, reservoir stimulation can be achieved through hydraulic fracturing. By selecting appropriate well sections and horizons and combining appropriate fracturing parameters, the stimulation effect can be maximized, and the economic benefits can be improved. Therefore, it is very important to optimize the well section, horizon, and fracturing parameters for stimulation. Currently, the commonly used parameter optimization method is to perform sensitivity analysis on the parameters through single-factor or multi-factor analysis methods, and then optimize the parameters in combination with laboratory tests and field application effects. The process is relatively complex and mainly relies on experience when selecting analysis factors, which will lead to less than ideal results in parameter optimization, and further reduce the reliability of oil and gas production prediction.

[0072] To solve the above problems, the embodiments of the present specification provide a method for optimizing fracturing parameters for oil and gas exploitation, which can accurately and reliably select the fracturing parameters in the production well during the oil and gas exploitation process, thereby improving the accuracy of oil and gas prediction, such as Figure 1As shown, it is a schematic diagram of the implementation environment of the method, which may include a client 10, a database 20, and a server 30; both the client 10 and the database 20 establish a data interaction link with the server 30, for example, a communication connection can be established by wired or wireless means.

[0073] The client 10 is used to obtain the seismic parameters of the target well and send the seismic parameters of the target well to the server 30. The database 20 is used to store the production data of adjacent wells during the production process. The adjacent wells and the target well are production wells in the same work area. The production data of the adjacent wells may include seismic parameters, reservoir physical property parameters, and fracturing parameters, as well as the daily oil and gas production during the production process.

[0074] The server 30 is used to extract the production data of adjacent wells from the database 20, and pre-establish a seismic physical property prediction model and a first production capacity prediction model based on the production data. Then, the seismic parameters of the target well are brought into the pre-established seismic physical property prediction model to obtain the reservoir physical property parameters of the target well at different depths; according to the historical production data of adjacent wells, the reservoir physical property parameters at different depths are screened to determine the target well section; the reservoir physical property parameters and the fracturing parameters to be optimized of the target well section are brought into the first production capacity prediction model of the adjacent wells, and the fracturing parameters to be optimized are optimized according to the prediction results to determine the target fracturing parameters, so that the fracturing parameters during the production of the target well can be reliably and accurately optimized by combining the production data of adjacent wells with the seismic parameters of the target well, thereby improving the accuracy of the oil and gas production capacity prediction of the target well.

[0075] In an alternative embodiment, the server 30 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms.

[0076] In an alternative embodiment, the client 10 can optimize the fracturing parameters by combining the first production capacity prediction model trained by the server 30. The client 10 may include, but is not limited to, electronic devices such as smart phones, desktop computers, tablet computers, laptop computers, smart speakers, digital assistants, Augmented Reality (AR) / Virtual Reality (VR) devices, and smart wearable devices. Optionally, the operating systems running on the electronic devices may include, but are not limited to, Android, IOS, Linux, Windows, etc.

[0077] In addition, it should be noted that Figure 1 The one shown is only an application environment provided by the present disclosure. In actual applications, other application environments may also be included. For example, the training of a seismic physical property prediction model can also be implemented on the client 10.

[0078] Specifically, the embodiments of the present invention provide a method for optimizing fracturing parameters for oil and gas production, which can improve the accuracy of optimizing fracturing parameters during the oil and gas production process in production wells. Figure 2 It is a schematic diagram of the steps of a method for optimizing fracturing parameters for oil and gas production provided by the embodiments of the present invention. This specification provides the method operation steps as described in the embodiments or flowcharts, but based on routine or non-creative labor, more or fewer operation steps may be included. The order of steps listed in the embodiments is only one way among the execution orders of numerous steps and does not represent the only execution order. When the actual system or device product executes, it can be executed in the order of the method shown in the embodiments or the drawings or executed in parallel. Specifically, as Figure 2 shown, the method may include:

[0079] S101: Input the seismic parameters of the target well into a pre-established seismic physical property prediction model to obtain the reservoir physical property parameters of the target well at different depths;

[0080] S102: Screen the reservoir physical property parameters at different depths according to the historical production data of adjacent wells to determine the target well section;

[0081] S103: Input the reservoir physical property parameters of the target well section and the fracturing parameters to be optimized into the first production capacity prediction model of the adjacent well, and optimize the fracturing parameters to be optimized according to the prediction results to determine the target fracturing parameters. The first production capacity prediction model is a time-series-based model trained by the reservoir physical property parameters, fracturing parameters, and historical production at the initial stage of production of the adjacent well.

[0082] It can be understood that in this article, the optimization of pressure parameters during the production process of the target well can be achieved by combining the seismic parameters of the target well with the production data of adjacent wells. Specifically, according to the seismic parameters of the target well and the pre-established seismic physical property prediction model, the reservoir physical property parameters of the target well at different depths can be obtained, and then the reservoir physical property parameters of the target well are screened to determine the target well section to be exploited in the target well. Finally, the reservoir physical property parameters of the target well section and the fracturing parameters to be optimized are input into the first production capacity prediction model of the adjacent well, and the fracturing parameters to be optimized are optimized according to the prediction results to determine the target fracturing parameters. By performing fracturing treatment with the target fracturing parameters in the target well section, a greater oil and gas production capacity can be obtained, thereby improving the reliability of oil and gas production capacity prediction.

[0083] In the embodiments of this specification, the adjacent well and the target well are in the same work area. The formation geological characteristics (such as rock formation lithology, thickness, porosity, oil content rate, depth, etc.) in the same work area are consistent, and the oil and gas storage environments (such as the position, thickness, and lithology of the oil reservoir, etc.) are also similar. In this way, the geological characteristics of the target well can be accurately predicted through the formation geological characteristics of the adjacent well, and based on the similar oil and gas storage environments, the productivity of the target well can also be accurately and reliably predicted through the productivity prediction model established by the adjacent well.

[0084] The reservoir physical property parameters may include lithology, permeability, porosity, oil content rate, etc., and the seismic parameters may include seismic layer velocity, wave impedance, shear wave velocity, longitudinal wave velocity, seismic frequency, etc. Optionally, the seismic physical property prediction model is trained through the following steps:

[0085] Obtain the seismic parameters and reservoir physical property parameters of the adjacent well at different depths to form a training set;

[0086] Use the training set to train the initial seismic physical property prediction model to obtain the pre-established seismic physical property prediction model.

[0087] It can be understood that through the seismic parameters and reservoir physical property parameters at different depths determined during the historical production process in the adjacent well, a non-linear mapping relationship between the seismic parameters and the reservoir physical property parameters can be established, and this non-linear mapping relationship is also applicable to the target well in the same work area. Thus, the reservoir physical property parameters of the target well at different depths can be inversely obtained through the seismic parameters of the target well, which not only improves the accuracy of the inversion, but also saves costs and improves the efficiency of the inversion compared with the existing method of obtaining the reservoir physical property parameters at different depths by drilling.

[0088] In the embodiments of this specification, the initial seismic physical property prediction model may be a neural network algorithm of a multi-layer perceptron. In some other embodiments, it may also be other machine learning models, which are not limited in the embodiments of this specification.

[0089] In the embodiments of this specification, as Figure 3 shown, screening the reservoir physical property parameters at different depths according to the historical production data of the adjacent well to determine the target well section includes:

[0090] S201: Obtain the historical fracturing parameters of the adjacent well at the initial stage of production;

[0091] S202: Input the multiple groups of input data formed by the reservoir physical property parameters at different depths of the target well and the historical fracturing parameters into the second productivity prediction model in sequence to obtain the production prediction results corresponding to the reservoir physical property parameters at different depths of the target well;

[0092] S203: Determine the well section corresponding to the reservoir physical property parameters with the highest production prediction result as the target well section.

[0093] It can be understood that the initial production stage can be the early stage of hydraulic fracturing production in the oil reservoir of adjacent wells. For example, the initial production stage can be the first 5 days, the first 10 days, the first 30 days, etc. in front of production, which is not limited in the embodiments of this specification. Since different pressure parameters can be adopted by adjacent wells at different time periods (such as every day), the historical fracturing parameters of adjacent wells in the initial production stage can be the average value or median of the fracturing parameters of adjacent wells within the initial production stage, etc. In this way, the obtained historical fracturing parameters are representative, and further reduce the influence degree of the production prediction in the second production prediction model.

[0094] The second production prediction model can be the production prediction of the production well based on the reservoir physical property parameters and fracturing parameters. On the basis of selecting the historical fracturing parameters of adjacent wells for the fracturing parameters, the reservoir physical property parameters at different depths of the target well are selected in turn, combined with the selected fracturing parameters, so as to obtain multiple groups of input data (that is, each group of input data includes the reservoir physical property parameters and fracturing parameters at one depth), and then by calculating the prediction results of each group of input data, the reservoir physical property parameters in the group of input data with the highest prediction result are the reservoir positions that can produce greater production, which can be determined as the target well section. By fracturing the target well section, more oil and gas production can be obtained, and thus the maximum efficiency extraction of oil and gas in the target well is realized, and the production efficiency is improved.

[0095] The fracturing parameters can include horizontal section length, section spacing, liquid usage intensity, sand addition intensity, etc. In the actual production process, there are many types of the reservoir physical property parameters and the fracturing parameters. Using all types of the reservoir physical property parameters and the fracturing parameters as training data to obtain the second production prediction model will instead increase the convergence difficulty of the model and reduce the accuracy of model prediction. Therefore, before training the second production prediction model, this article can also include:

[0096] Obtain the reservoir physical property data, fracturing parameters and production data of adjacent wells, and determine the influence weights of the reservoir physical property data and the fracturing parameters on the production through grey relational analysis, and select the ones with larger weights as the types of training input data of the second production prediction model, so as to reduce the number of parameters participating in model training.

[0097] It can be understood that the relational analysis is to determine the influence weights of each parameter (that is, the reservoir physical property parameter type and the fracturing parameter type) on the production. The larger the influence weight indicates that the parameter has a greater influence on the daily production, and the smaller the influence weight indicates that the parameter has a smaller influence on the daily production.

[0098] In a specific embodiment of this specification, such as Figure 4As shown in the figure, the second production capacity prediction model is obtained through the following steps:

[0099] S301: Obtain the historical sampling data of multiple adjacent wells, where the historical sampling data includes different types of reservoir physical property parameters, different types of fracturing parameters, and daily production;

[0100] S302: Normalize the reservoir physical property parameters, the fracturing parameters, and the daily production;

[0101] S303: According to the results of the normalization process, calculate the correlation coefficients of each type of reservoir physical property parameter and each type of fracturing parameter with respect to the daily production. The correlation coefficients are used to characterize the influence weights of the reservoir physical property parameter types and the fracturing parameter types on the daily production;

[0102] S304: Use the reservoir physical property parameter types and fracturing parameter types whose correlation coefficients exceed a preset value as inputs, and use the daily production as the target output to train the second initial production prediction model, obtaining the trained second production capacity prediction model.

[0103] It can be understood that by determining the parameter types (i.e., reservoir physical property parameter types and fracturing parameter types) with relatively large influence weights on the daily production of production wells as the training input data for the second production capacity prediction model, the efficiency and accuracy of model training can be improved, and the robustness of the trained model can also be ensured. When predicting production in the same work area, the accuracy and reliability of production capacity prediction can also be improved.

[0104] Among them, the correlation coefficient is obtained through the following formula (1):

[0105]

[0106] Among them, ξ i is the correlation coefficient of the i-th factor with respect to the daily production, ξ i (k) is the correlation coefficient of the value of the i-th factor in the k-th sampling data with respect to the daily production. The factors are reservoir physical property parameter types and fracturing parameter types, x0(k) is the value of the daily production in the k-th sampling data, x i (k) is the value of the i-th factor in the k-th sampling data, and ρ is the coefficient that controls the discrimination of ξ i (k). The value range is in [0, 1], and generally, 0.5 can be taken.

[0107] Exemplarily, the reservoir physical property parameters are selected as porosity, permeability, and oil saturation; the fracturing parameters are selected as segment spacing, sand addition intensity, and liquid usage intensity. Five samples of adjacent wells are obtained, and the initial data corresponding to each sample is shown in Table 1 below:

[0108] Table 1 Initial Data

[0109]

[0110] The process of determining the training parameters is as follows:

[0111] Step 1: Determine the mother sequence and the child sequence

[0112] The mother sequence is the reference sequence, that is, "oil production per day"; the child sequence is the comparison sequence, that is, reservoir physical property parameters and fracturing parameters, so as to determine the influence degree of the data in the child sequence relative to the data in the mother sequence.

[0113] Step 2: Normalization processing

[0114] The purpose of normalization is to reduce the differences in the absolute values of the data, unify them into an approximate range, and then the focus can be shifted to the changes and trends of the data.

[0115] There are two common ways of normalization: initialization and mean value method. Here, the mean value method is selected. The mean value method can divide each data in a column by the mean value of that column. The initial data in Table 1 can be normalized to obtain the data in Table 2.

[0116] Table 2 Normalization results of the initial data

[0117]

[0118] Step 3: Calculate the correlation coefficient corresponding to each data

[0119] The correlation coefficient between the corresponding data of each parameter and the oil production per day in each sample can be obtained through the following formula (2), and the results are shown in Table 3 below:

[0120]

[0121] Among them, ξ i (k) is the correlation coefficient of the value of the i-th factor in the k-th sampling data relative to the daily production. The factors are reservoir physical property parameter types and fracturing parameter types. x0(k) is the value of the daily production of the k-th sampling data, and x i (k) is the value of the i-th factor in the k-th sampling data, and ρ is the coefficient that controls the discrimination of ξ i (k).

[0122] Table 3 Correlation coefficients corresponding to the parameter data in each sample

[0123] Sample Serial Number Porosity Permeability Oil Saturation Interval Spacing Sand Addition Intensity Fluid Injection Intensity 1 0.5890411 0.4770206 0.333333333 0.3568465 0.4601167 0.4456963 2 0.5890411 0.6105477 0.843137255 0.6323529 0.5678271 0.5997574 3 1 0.704918 0.704918033 0.8514851 0.9131274 0.824854 4 0.5890411 0.9261538 0.728813559 0.4623656 0.6925329 0.7672614 5 0.5890411 0.5110357 0.349593496 0.8958333 0.9403579 0.6732471

[0124] Step 4: Calculate the correlation coefficient between each parameter and the oil production per day.

[0125] The correlation coefficient between each of the parameters and the daily oil production can be the average of the correlation coefficients corresponding to the data of each parameter in all samples, and can be obtained through the following formula (3):

[0126]

[0127] where ξ i is the correlation coefficient of the i-th factor relative to the daily production, and ξ i (k) is the correlation coefficient of the value of the i-th factor in the k-th sampling data relative to the daily production. The factors are reservoir physical property parameter types and fracturing parameter types.

[0128] Of course, the correlation coefficient between each parameter and the daily oil production can also be directly obtained through the above formula (1). The calculation results are shown in Table 4:

[0129] Table 4 Correlation coefficients between each parameter and the daily oil production

[0130] Porosity Permeability Oil Saturation Interval Spacing Sand Addition Intensity Fluid Injection Intensity 0.6712329 0.6459352 0.591959135 0.6397767 0.7147924 0.6621633

[0131] Step 5: Determine the number of parameters

[0132] As can be seen from Table 4, the correlation coefficients corresponding to different parameters are also different. The preset value can be determined to be 0.6. Then, five parameters, namely porosity, permeability, section spacing, sand addition intensity, and fluid usage intensity, can be selected as the input parameters for the subsequent training of the second production capacity prediction model. In some other embodiments, a specified number of parameters can also be selected as the input parameters for the subsequent training of the second production capacity prediction model. For example, if 4 parameters are selected, the four parameters with the highest correlation coefficients are determined as the input parameters for the subsequent training of the second production capacity prediction model. In some other embodiments, the preset value or the specified number selected can also be other data, which is not limited in the embodiments of this specification.

[0133] In the embodiments of this specification, the second production capacity prediction model can be a neural network model of a multi-layer perceptron, or other machine learning models, which is not limited in the embodiments of this specification.

[0134] In the embodiments of this specification, the first production capacity prediction model is a time-series-based model trained through the reservoir physical property parameters, fracturing parameters, and initial production history of adjacent wells.

[0135] It can be understood that as a time series model, the first production capacity prediction model can predict the production capacity data in a subsequent period of time in the future. During model training, the reservoir physical property parameters, fracturing parameters, and production capacity data within a specified time period of adjacent wells can be used as the training set, so as to obtain the production capacity data of adjacent wells within a subsequent specified time period. The first production capacity prediction model can be a long short-term memory (LSTM) model. The training of the LSTM model is a conventional means of model training and will not be elaborated here. In some other embodiments, the first production capacity prediction model can also be other time series models, which are not limited in the embodiments of this specification.

[0136] Since the adjacent well and the target well are in the same work area, the first production capacity prediction model trained with the data in the adjacent well is also applicable to the target well. Therefore, the fracturing parameters in the target well can be optimized through the first production capacity prediction model. Optionally, as Figure 5 shown, bringing the reservoir physical property parameters of the target well section and the fracturing parameters to be optimized into the first production capacity prediction model of the adjacent well, and optimizing the fracturing parameters to be optimized according to the prediction results to determine the target fracturing parameters includes:

[0137] S401: Obtain the fracturing parameters during the entire production cycle of the adjacent well and determine the optimization range of the fracturing parameters;

[0138] S402: Determine multiple combinations of fracturing parameters according to the optimization range of the fracturing parameters and the preset optimization interval;

[0139] S403: According to the reservoir physical property parameters of the target well section, multiple combinations of fracturing parameters, and the production volume at the initial stage of production of the adjacent well, combined with the first production capacity prediction model of the adjacent well, predict the predicted production volume of each combination of fracturing parameters. The prediction duration of the predicted production volume is the same as the duration at the initial stage of production;

[0140] S404: Calculate the average value of the predicted production volume of each combination of fracturing data during the prediction duration, and use the combination of fracturing parameters with the highest average value as the target fracturing parameters.

[0141] It can be understood that in order to narrow the optimization range of the fracturing parameters, the historical fracturing parameters of the adjacent well can be referred to. For example, the maximum and minimum values of the historical fracturing parameters of the adjacent well can be used to determine the optimization range of the fracturing parameters of the target well. It should be noted that since the fracturing parameters include multiple types of data, an optimization range needs to be determined for each type of data. For example, the fracturing parameters can include three types of data: section spacing, fluid usage intensity, and sand addition intensity, and an optimization range needs to be determined for each type of data.

[0142] In the embodiments of this specification, different types of fracturing parameters correspond to different preset preferred spacings. For example, the preferred ranges determined by the stage spacing (unit: m), fluid injection intensity (unit: m 3 / m), and proppant injection intensity (unit: t / m) are [50 - 100], [20 - 50], and [1 - 3] respectively. The preset preferred spacings set for each fracturing parameter are 10, 10, and 1 respectively. Then, there are 6 data determined by the stage spacing, which are 50, 60, 70, 80, 90, and 100; there are 4 data determined by the fluid injection intensity, which are 20, 30, 40, and 50; there are 3 data determined by the proppant injection intensity, which are 1, 2, and 3. Arranging and combining the above data can obtain 6×4×3 = 72 fracturing parameter combinations. The input data of the above first production capacity prediction model is composed of each fracturing parameter combination, the reservoir physical property parameters of the target well section, and the production of the adjacent well in the initial stage of exploitation. Thus, the predicted production corresponding to each fracturing parameter combination can be obtained. The predicted production is actually a set of multiple daily productions in a certain exploitation duration (i.e., the prediction duration). Therefore, by using the fracturing parameter combination with the highest average predicted production, it can ensure the maximum oil and gas production during the exploitation of the target well section, improving the exploitation efficiency and benefit.

[0143] To improve the accuracy of fracturing parameter optimization, on the basis of determining the fracturing parameter combination with the highest average predicted production through the preset preferred spacing, the preferred spacing can be further reduced. For example, on the basis of the data corresponding to the determined fracturing parameter combination, a preset number of second fracturing parameter combinations are determined with a second preferred spacing (i.e., a smaller spacing). Through the above steps, a more optimal fracturing parameter combination is further optimized from multiple second fracturing parameter combinations, and this fracturing parameter combination is determined as the target fracturing parameter.

[0144] Exemplarily, taking the stage spacing (unit: m), fluid injection intensity (unit: m 3Taking the fluid injection intensity (unit: t / m) and proppant addition intensity (unit: t / m) as examples, the fracturing parameter combination with the highest average predicted production is determined to be [85, 40, 2] by presetting the preferred spacing. The second preferred spacings are 1, 1, and 0.2 respectively, and the further preferred numbers of each type of fracturing parameter are 5, 5, and 5 respectively. Then, corresponding numbers of data (such as two data) can be selected above and below the corresponding data of each fracturing parameter at the second preferred spacing. The data determined by the section spacing are 5, which are 83, 84, 85, 86, and 87 respectively; the data determined by the fluid injection intensity are 5, which are 38, 39, 40, 41, and 42 respectively; the data determined by the proppant addition intensity are 5, which are 0.6, 0.8, 1, 1.2, and 1.4 respectively. Arranging and combining the above data can obtain 5×5×5 = 125 second fracturing parameter combinations. The input data of the first production capacity prediction model are composed of each second fracturing parameter combination, the reservoir physical property parameters of the target well section, and the production of the adjacent well in the initial stage of exploitation. Repeating the above selection steps can obtain the target fracturing parameters from the second fracturing parameter combinations. This article can further reduce the preferred granularity, improve the preferred accuracy of fracturing parameters, and thus increase the oil production.

[0145] In some other embodiments of this specification, such as Figure 6 shown, bringing the reservoir physical property parameters of the target well section and the fracturing parameters to be optimized into the first production capacity prediction model of the adjacent well, and optimizing the fracturing parameters to be optimized according to the prediction results to determine the target fracturing parameters, includes:

[0146] S501: Obtain the fracturing parameters during the entire production cycle of the adjacent well, and determine the preferred range of fracturing parameters;

[0147] S502: According to the reservoir physical property parameters of the target well section, the preferred range of fracturing parameters, and the production of the adjacent well in the initial stage of exploitation, combined with the first production capacity prediction model of the adjacent well, use the particle swarm optimization algorithm to determine the fracturing parameters that meet the specified conditions from the preferred range of fracturing parameters, and determine the finally determined fracturing parameters as the target fracturing parameters.

[0148] It can be understood that the embodiments of this specification find the optimal solution of fracturing parameters from the preferred range of fracturing parameters through the particle swarm optimization algorithm. Specifically, starting from a random solution, the optimal solution is found through iteration. The optimal solution can be the global optimal. Finding the target fracturing parameters through the particle swarm optimization algorithm can reduce human intervention, ensure the objectivity and reliability of data optimization, and at the same time improve the efficiency of determining the target fracturing parameters.

[0149] The specified condition can be that the optimal solution determined by the particle swarm optimization algorithm meets the global optimal, or the number of iterations of the particle swarm optimization algorithm meets the specified number. The method of optimizing through the particle swarm optimization algorithm is a commonly used technical means in the field of data optimization. The specific optimization process is not elaborated in the embodiments of this specification.

[0150] An embodiment of this specification provides a method for optimizing fracturing parameters for oil and gas production. By using the seismic parameters and reservoir physical property parameters of adjacent wells, a non-linear mapping relationship between the two is established. Furthermore, the reservoir physical property parameters of the target well at different depths can be predicted through the seismic parameters of the target well. Then, the reservoir physical property parameters in the target well are screened to determine the target well section. Based on the first production capacity prediction model based on time series established by the reservoir physical property parameters, fracturing parameters, and production data of adjacent wells, the fracturing parameters in the target well section are optimized to determine the target fracturing parameters. Through the target fracturing parameters, the production of the target well section can be increased, and the efficiency and benefit of energy storage oil and gas production are improved.

[0151] Based on the above-provided method for optimizing fracturing parameters for oil and gas production, an embodiment of this specification also provides an oil and gas production capacity prediction method. By using the reservoir physical property parameters and target fracturing parameters of the determined target well section, the above data are input into the second production capacity prediction model, so that the predicted production capacity of the target well section at the initial stage of production can be obtained.

[0152] Based on the same inventive concept, an embodiment of this specification also provides a device for optimizing fracturing parameters for oil and gas production, as Figure 7 shown. The device includes:

[0153] A reservoir physical property parameter obtaining module 100, configured to input the seismic parameters of the target well into a pre-established seismic physical property prediction model to obtain the reservoir physical property parameters of the target well at different depths;

[0154] A target well section determining module 200, configured to screen the reservoir physical property parameters at different depths according to the historical production data of adjacent wells to determine the target well section;

[0155] An optimization module 300, configured to input the reservoir physical property parameters and the fracturing parameters to be optimized of the target well section into the first production capacity prediction model of adjacent wells, and optimize the fracturing parameters to be optimized according to the prediction results to determine the target fracturing parameters. The first production capacity prediction model is a time-series-based model trained by the reservoir physical property parameters, fracturing parameters, and historical production at the initial stage of production of adjacent wells.

[0156] The beneficial effects obtained by the above-provided device are the same as those obtained by the above method, and are not elaborated in this embodiment of the specification.

[0157] As Figure 8As shown, a computer device provided by an embodiment of this article. The device in this article may be the computer device in this embodiment and execute the method in the above-mentioned article. The computer device 802 may include one or more processors 804, such as one or more central processing units (CPUs), and each processing unit may implement one or more hardware threads. The computer device 802 may also include any memory 806, which is used to store any kind of information such as code, settings, data, etc. Non-limiting, for example, the memory 806 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory devices, hard disks, optical discs, etc. More generally, any memory may use any technology to store information. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent a fixed or removable component of the computer device 802. In one case, when the processor 804 executes the associated instructions stored in any memory or combination of memories, the computer device 802 may perform any operation of the associated instructions. The computer device 802 also includes one or more drive mechanisms 808 for interacting with any memory, such as a hard disk drive mechanism, an optical disc drive mechanism, etc.

[0158] The computer device 802 may also include an input / output module 810 (I / O), which is used to receive various inputs (via the input device 812) and provide various outputs (via the output device 814). A specific output mechanism may include a presentation device 816 and an associated graphical user interface (GUI) 818. In other embodiments, the input / output module 810 (I / O), the input device 812, and the output device 814 may not be included, and it may only be a computer device in the network. The computer device 802 may also include one or more network interfaces 820, which are used to exchange data with other devices via one or more communication links 822. One or more communication buses 824 couple the components described above together.

[0159] The communication link 822 may be implemented in any way, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 822 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.

[0160] Corresponding to Figures 2 - 6 the method in, an embodiment of this article also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it executes the steps of the above method.

[0161] Embodiments of the present disclosure also provide a computer-readable instruction. When a processor executes the instruction, the program therein causes the processor to execute as Figures 2 to 6 shown in the method.

[0162] It should be understood that in various embodiments of the present disclosure, the sequence numbers of the above processes do not imply the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present disclosure.

[0163] It should also be understood that in the embodiments of the present disclosure, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present disclosure generally represents an "or" relationship between the associated objects before and after.

[0164] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present disclosure can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to 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. Professional technicians 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 the present disclosure.

[0165] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0166] In several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection to each other can be an indirect coupling or communication connection through some interfaces, devices, or units, and can also be an electrical, mechanical, or other form of connection.

[0167] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of this article.

[0168] In addition, each functional unit in the embodiments of this article can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0169] If the above integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this article, in essence, or the part that contributes to the prior art, or all or part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of this article. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0170] Specific embodiments are used in this article to elaborate on the principles and implementation manners of this article. The description of the above embodiments is only used to help understand the method and its core idea of this article; at the same time, for those of ordinary skill in the art, according to the idea of this article, 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 article.

Claims

1. A method for optimizing fracturing parameters for oil and gas exploitation, characterized in that The method includes: Inputting the seismic parameters of the target well into a pre-established seismic physical property prediction model to obtain the reservoir physical property parameters of the target well at different depths; Screening the reservoir physical property parameters at different depths according to the historical production data of adjacent wells to determine the target well section; Obtaining the historical fracturing parameters of the adjacent well at the initial stage of production; Sequentially inputting multiple groups of input data formed by the reservoir physical property parameters at different depths of the target well and the historical fracturing parameters into the second production capacity prediction model to obtain the production prediction results corresponding to the reservoir physical property parameters at different depths of the target well; Determining the well section corresponding to the reservoir physical property parameters with the highest production prediction result as the target well section; Inputting the reservoir physical property parameters of the target well section and the fracturing parameters to be optimized into the first production capacity prediction model of the adjacent well, and optimizing the fracturing parameters to be optimized according to the prediction result to determine the target fracturing parameters. The first production capacity prediction model is a time-series-based model trained by the reservoir physical property parameters, fracturing parameters, and historical production at the initial stage of production of the adjacent well.

2. The method according to claim 1, wherein The seismic physical property prediction model is trained through the following steps: Obtaining the seismic parameters and reservoir physical property parameters of the adjacent well at different depths to form a training set; Training the initial seismic physical property prediction model using the training set to obtain the pre-established seismic physical property prediction model.

3. The method according to claim 1, wherein The second production capacity prediction model is obtained through the following steps: Obtaining the historical sampling data of multiple adjacent wells, where the historical sampling data includes different types of reservoir physical property parameters, different types of fracturing parameters, and daily production; Performing normalization processing on the reservoir physical property parameters, the fracturing parameters, and the daily production; Calculating the correlation coefficient of each type of reservoir physical property parameter and each type of fracturing parameter relative to the daily production according to the results of the normalization processing. The correlation coefficient is used to characterize the influence weight of the reservoir physical property parameter type and the fracturing parameter type on the daily production; Using the reservoir physical property parameter types and fracturing parameter types with correlation coefficients exceeding the preset value as inputs and the daily production as the target output to train the second initial production prediction model to obtain the trained second production capacity prediction model.

4. The method according to claim 3, wherein The correlation coefficient is obtained through the following formula: Among them, ξi is the correlation coefficient of the i-th factor relative to the daily output, ξ i (k) is the correlation coefficient of the value of the i-th factor in the k-th sampling data relative to the daily output. The factors are reservoir physical property parameter types and fracturing parameter types. x0(k) is the value of the daily output in the k-th sampling data, x i (k) is the value of the i-th factor in the k-th sampling data, and ρ is the coefficient that controls the discrimination of ξ i (k).

5. The method according to claim 1, characterized in that The step of inputting the reservoir physical property parameters of the target well section and the fracturing parameters to be optimized into the first production capacity prediction model of the adjacent well, and optimizing the fracturing parameters to be optimized according to the prediction result to determine the target fracturing parameters includes: Obtaining the fracturing parameters during the entire production cycle of the adjacent well to determine the fracturing parameter optimization range; Determining multiple fracturing parameter combinations according to the fracturing parameter optimization range and the preset optimization interval; Predicting the predicted production of each fracturing parameter combination according to the reservoir physical property parameters of the target well section, multiple fracturing parameter combinations, and the production at the initial stage of production of the adjacent well, in combination with the first production capacity prediction model of the adjacent well. The prediction duration of the predicted production is the same as the duration at the initial stage of production; Calculating the average value of the predicted production of each fracturing data combination during the prediction duration, and taking the fracturing parameter combination with the highest average value as the target fracturing parameter.

6. The method according to claim 1, wherein Bringing the reservoir physical property parameters and the fracturing parameters to be optimized of the target well section into the first production capacity prediction model of the adjacent well, and optimizing the fracturing parameters to be optimized according to the prediction result to determine the target fracturing parameters, including: Obtaining the fracturing parameters during the entire production period of the adjacent well, and determining the optimization range of the fracturing parameters; According to the reservoir physical property parameters of the target well section, the optimization range of the fracturing parameters, and the production volume of the adjacent well in the initial stage of exploitation, combining with the first production capacity prediction model of the adjacent well, using the particle swarm optimization algorithm to determine the fracturing parameters that meet the specified conditions from the optimization range of the fracturing parameters, and determining the finally determined fracturing parameters as the target fracturing parameters.

7. A fracturing parameter optimization device for oil and gas exploitation, characterized in that, The device includes: A reservoir physical property parameter obtaining module, configured to bring the seismic parameters of the target well into a pre-established seismic physical property prediction model to obtain the reservoir physical property parameters of the target well at different depths; A target well section determining module, configured to screen the reservoir physical property parameters at different depths according to the historical production data of the adjacent well to determine the target well section; Obtaining the historical fracturing parameters of the adjacent well in the initial stage of exploitation; Sequentially inputting multiple groups of input data formed by the reservoir physical property parameters at different depths of the target well and the historical fracturing parameters into the second production capacity prediction model to obtain the production volume prediction results corresponding to the reservoir physical property parameters at different depths of the target well; Determining the well section corresponding to the reservoir physical property parameters with the highest production volume prediction result as the target well section; An optimization module, configured to bring the reservoir physical property parameters of the target well section and the fracturing parameters to be optimized into the first production capacity prediction model of the adjacent well, and optimize the fracturing parameters to be optimized according to the prediction result to determine the target fracturing parameters, where the first production capacity prediction model is a time-series-based model trained by the reservoir physical property parameters, fracturing parameters, and historical production volume in the initial stage of exploitation of the adjacent well.

8. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

9. 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 the processor, the method according to any one of claims 1 to 7 is implemented.

Images