Fracturing parameter determination method, device and equipment

Abstract

The invention discloses a method, a device and equipment for determining fracturing parameters. The method comprises the following steps: acquiring historical geological physical property data, historical engineering data and historical production data of a historical reservoir; constructing a crack propagation model, and determining crack form data and geological change information of the historical reservoir based on the crack propagation model, the historical geological physical property data and the historical engineering data; taking historical geological physical property data, historical engineering data, historical production data, geological change information and fracture form data of the historical reservoir as training data, and training to obtain an oil and gas productivity calculation model; and constructing a multi-target optimization model based on the oil and gas productivity calculation model, a preset cost calculation model and the target geological physical property parameters of the target reservoir, and performing optimization solution on the multi-target optimization model to obtain fracturing construction parameters of the target reservoir. By means of the method, more accurate and reliable fracturing construction parameters can be obtained, and fine design of fracturing well completion parameters is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of oil and gas exploration and development, and in particular to a method, device and equipment for determining fracturing parameters. Background Art

[0002] Hydraulic fracturing completion is a key technical means for unconventional oil and gas development. The fine design of fracturing completion parameters is an important factor affecting the single well production of oil and gas wells. Therefore, the fine design of fracturing completion parameters is of great significance to the efficient development of oil and gas.

[0003] At present, the design of hydraulic fracturing completion parameters at oil field sites is mostly based on field experience, that is, personnel design hydraulic fracturing completion parameters based on expert experience and the construction conditions at the oil field site, and then perform construction based on the designed hydraulic fracturing completion parameters. The design of the above hydraulic fracturing parameters is completely dependent on the experience of personnel, and the precision, accuracy and reliability of the designed hydraulic fracturing completion parameters are low.

[0004] Currently, no effective solution has been found to the above-mentioned problems of low precision, accuracy and reliability in the design of hydraulic fracturing completion parameters. Summary of the invention

[0005] The purpose of the embodiments of this specification is to provide a method, device and equipment for determining fracturing parameters to solve the problem of low precision, accuracy and reliability in the design of hydraulic fracturing completion parameters.

[0006] In order to solve the above technical problems, the first aspect of this specification provides a method for determining fracturing parameters, comprising:

[0007] Obtain historical geological and physical data, historical engineering data and historical production data of historical reservoirs;

[0008] Constructing a fracture propagation model, and determining fracture morphology data and geological change information of the historical reservoir based on the fracture propagation model, the historical geological property data and the historical engineering data, wherein the fracture propagation model is used to simulate the morphology of fracture propagation under different engineering parameters;

[0009] Using the historical geological property data of the historical reservoir, the historical engineering data, the historical production data, the geological change information and the fracture morphology data as training data, training to obtain an oil and gas productivity calculation model that uses geological property parameters and engineering data as input and production data as output;

[0010] A multi-objective optimization model is constructed based on the oil and gas productivity calculation model, the preset cost calculation model and the target geological property parameters of the target reservoir, and the multi-objective optimization model is optimized and solved to obtain the fracturing construction parameters of the target reservoir.

[0011] In some embodiments of the present specification, constructing a crack extension model includes:

[0012] Obtaining physical property parameters corresponding to historical geological physical property data and engineering parameters corresponding to historical engineering data;

[0013] Determine the first correlation between the fracture morphology parameters and the geological physical parameters and engineering parameters;

[0014] Determine the second correlation between the geological transformation parameters and the geological physical parameters and engineering parameters;

[0015] The crack propagation model is constructed based on the first association relationship and the second association relationship.

[0016] In some embodiments of the present specification, based on the fracture propagation model, the historical geological property data and the historical engineering data, the fracture morphology data and geological change information of the historical reservoir are determined, including:

[0017] Based on the first association relationship, the historical geological property data and the historical engineering data, the fracture morphology data of the historical reservoir is calculated;

[0018] Based on the second association relationship, the historical geological property data and the historical engineering data, the geological transformation data of the historical reservoir is calculated;

[0019] The geological change information is determined based on the geological transformation data and the historical geological physical property data.

[0020] In some embodiments of the present specification, the geological change information includes permeability change information, porosity change information, and oil saturation change information.

[0021] In some embodiments of the present specification, the historical geological property data of the historical reservoir, the historical engineering data, the historical production data, the geological change information and the fracture morphology data are used as training data to train an oil and gas productivity calculation model that uses geological property parameters and engineering data as input and production data as output, including:

[0022] The historical geological property data of the historical reservoir, the historical engineering data, the historical production data, the geological change information and the fracture morphology data are input into a pre-established artificial intelligence model;

[0023] The artificial intelligence model is used to learn the relationship between the historical geological property data, the historical engineering data, the geological change information and the fracture morphology data, as well as the relationship between the historical geological property data, the historical engineering data, the geological change information, the fracture morphology data and the historical production data, and the parameters of the artificial intelligence model are iteratively updated to obtain the oil and gas production capacity calculation model.

[0024] In some embodiments of this specification, the oil and gas productivity calculation model includes a fracturing evolution sub-model and an oil and gas productivity calculation sub-model;

[0025] The fracturing evolution sub-model is used to process the input geological physical property data and engineering data, and output target fracture morphology data and target geological change information;

[0026] The oil and gas productivity calculation sub-model is used to process the input geological property data, engineering data and the target fracture morphology data and target geological change information output by the fracturing evolution sub-model, and output the productivity calculation result.

[0027] In some embodiments of the present specification, a multi-objective optimization model is constructed based on the oil and gas productivity calculation model, the preset cost calculation model, and the target geological property parameters of the target reservoir, and the multi-objective optimization model is optimized and solved to obtain the fracturing construction parameters of the target reservoir, including:

[0028] Based on the oil and gas productivity calculation model and the preset cost calculation model, a multi-objective optimization model is constructed with the goal of minimizing cost and maximizing oil and gas production and the target geological and physical parameters of the target reservoir as constraints;

[0029] Determine initial engineering data for target reservoirs;

[0030] Inputting the initial engineering data and target geological physical parameters into the oil and gas productivity calculation model and the preset cost calculation model, and outputting productivity calculation results and cost calculation results;

[0031] The initial engineering data is continuously updated and optimized with the goal of minimizing costs and maximizing oil and gas production until the preset optimization conditions are reached, and the target engineering data is obtained as the fracturing construction parameters of the target reservoir.

[0032] A second aspect of the present specification provides a device for determining fracturing parameters, comprising:

[0033] A data acquisition module, used to acquire historical geological property data, historical engineering data and historical production data of historical reservoirs;

[0034] A data determination module, for constructing a fracture extension model, and determining fracture morphology data and geological change information of the historical reservoir based on the fracture extension model, the historical geological property data and the historical engineering data, wherein the fracture extension model is used to simulate the morphology of fracture extension under different engineering parameters;

[0035] A model training module is used to use the historical geological property data of the historical reservoir, the historical engineering data, the historical production data, the geological change information and the fracture morphology data as training data to train an oil and gas production capacity calculation model with geological property parameters and engineering data as input and production data as output;

[0036] The parameter determination module is used to construct a multi-objective optimization model based on the oil and gas production capacity calculation model, the preset cost calculation model and the target geological property parameters of the target reservoir, optimize and solve the multi-objective optimization model, and obtain the fracturing construction parameters of the target reservoir.

[0037] The third aspect of this specification provides an electronic device, comprising: a memory and a processor, the processor and the memory are communicatively connected to each other, the memory stores computer instructions, and the processor implements the steps of the method described in the first aspect by executing the computer instructions.

[0038] A fourth aspect of the present specification provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed, the steps of the method described in the first aspect are implemented.

[0039] The method, device and equipment for determining fracturing parameters provided in the embodiments of this specification obtain historical geological property data, historical engineering data and historical production data of historical reservoirs; construct a fracture extension model, and determine the fracture morphology data and geological change information of historical reservoirs based on the fracture extension model, historical geological property data and historical engineering data, and the fracture extension model is used to simulate the morphology of fracture extension under different engineering parameters; use the historical geological property data, historical engineering data, historical production data, geological change information and fracture morphology data of historical reservoirs as training data, and train to obtain an oil and gas production capacity calculation model with geological property parameters and engineering data as input and production data as output; construct a multi-objective optimization model based on the oil and gas production capacity calculation model, a preset cost calculation model and the target geological property parameters of the target reservoir, optimize and solve the multi-objective optimization model, and obtain the fracturing construction parameters of the target reservoir. Through the above method, by analyzing the geological change information before and after fracturing, and combining the characteristics of data such as fracture morphology data and geological change information when training the oil and gas production capacity calculation model, it is possible to consider multiple aspects, calculate the oil and gas production capacity more accurately and reliably, and improve the prediction accuracy of the oil and gas production capacity calculation model. Furthermore, a multi-objective optimization model constructed based on the oil and gas production capacity calculation model, the preset cost calculation model and the target geological physical property parameters can optimize and solve more accurate and reliable fracturing construction parameters, and realize the fine design of fracturing completion parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some implementation methods recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0041] Figure 1 Shown is a schematic diagram of a method for determining fracturing parameters provided in an embodiment of this specification;

[0042] Figure 2 It is a schematic diagram of a method for determining fracture morphology data and geological change information provided in an embodiment of this specification;

[0043] Figure 3 Shown is a schematic diagram of a method for fine design of fracturing completion parameters based on machine learning provided in an embodiment of this specification;

[0044] Figure 4 Shown is a schematic diagram of a device for determining fracturing parameters provided in an embodiment of this specification;

[0045] Figure 5Shown is a schematic diagram of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0047] As mentioned above, the design of on-site fracturing completion parameters in oil fields is mostly based on on-site experience, and the precision, accuracy and reliability of hydraulic fracturing completion parameter design are low. In order to solve the above problems, a method, device and equipment for determining fracturing parameters are provided in the embodiments of this specification, by obtaining historical geological property data, historical engineering data and historical production data of historical reservoirs; constructing a fracture extension model, and determining the fracture morphology data and geological change information of the historical reservoir based on the fracture extension model, historical geological property data and historical engineering data, and the fracture extension model is used to simulate the morphology of fracture extension under different engineering parameters; using the historical geological property data, historical engineering data, historical production data, geological change information and fracture morphology data of historical reservoirs as training data, training to obtain an oil and gas production capacity calculation model with geological property parameters and engineering data as input and production data as output; constructing a multi-objective optimization model based on the oil and gas production capacity calculation model, a preset cost calculation model and the target geological property parameters of the target reservoir, optimizing and solving the multi-objective optimization model, and obtaining the fracturing construction parameters of the target reservoir.

[0048] In the embodiments of this specification, by analyzing the geological change information before and after fracturing, and combining the characteristics of data such as fracture morphology data and geological change information when training the oil and gas production capacity calculation model, the oil and gas production capacity can be more accurately and reliably calculated from multiple aspects, thereby improving the prediction accuracy of the oil and gas production capacity calculation model. Furthermore, a multi-objective optimization model constructed based on the oil and gas production capacity calculation model, a preset cost calculation model, and target geological physical property parameters can optimize and solve to obtain more accurate and reliable fracturing construction parameters, thereby realizing the fine design of fracturing completion parameters.

[0049] In the method provided in the embodiment of the present application, the execution subject of each step may be an electronic device, which refers to an electronic device with data calculation, processing and storage capabilities. The electronic device may be a terminal such as a personal computer (PC), a tablet computer, a smart phone, a wearable device, an intelligent robot, etc.; or it may be a server. Among them, the server may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0050] The following first introduces the method for determining the fracturing parameters provided in the embodiments of the present application in conjunction with the accompanying drawings.

[0051] Figure 1 Shown is a schematic diagram of a method for determining fracturing parameters provided in an embodiment of this specification. Although this specification provides method operation steps or device structures as shown in the following embodiments or drawings, the method or device may include more or fewer operation steps or module units after partial combination based on routine or no creative labor. In steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments or drawings of this specification. When the method or module structure is applied in an actual device, server or terminal product, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or drawings (for example, in an environment of parallel processors or multi-threaded processing, or even in an implementation environment of distributed processing and server clusters). As Figure 1 As shown, the method may include:

[0052] S101: Acquire historical geological property data, historical engineering data and historical production data of historical reservoirs.

[0053] It can be understood that the historical reservoir can be the reservoir where the existing production well is located, the historical geological property data can be the data corresponding to the geological property parameters of the reservoir where the existing production well is located, and the historical engineering data can be the data corresponding to the engineering parameters of the existing production well during the fracturing construction, wherein the engineering parameters can include parameters related to fracturing completion, and the historical production data can be the data generated by the existing production well during the oil and gas production process. Among them, the geological property parameters can include but are not limited to reservoir depth, permeability, porosity, ground stress size, direction, etc., the engineering parameters can include but are not limited to the number of fracturing stages, stage spacing, number of perforations, perforation parameters, sand ratio, etc., and the production data can include the oil and gas production data of the oil and gas wells, etc.

[0054] In some embodiments of the present specification, historical production data may include daily oil and gas production data of existing production wells since the date of exploitation and cumulative production data of oil and gas wells. The cumulative production data of oil and gas wells may include cumulative production data for 30 days, 180 days, 1 year, 2 years, 3 years, etc. of exploitation.

[0055] S102: constructing a fracture propagation model, and determining fracture morphology data and geological change information of the historical reservoir based on the fracture propagation model, the historical geological property data and the historical engineering data. The fracture propagation model is used to simulate the morphology of fracture propagation under different engineering parameters.

[0056] It can be understood that the fracture extension model can simulate the fracturing process based on geological physical parameters and engineering parameters, and calculate the morphological data of the fractures formed by fracturing based on the simulation results, and can also calculate the geological change information of the reservoir after fracturing based on the simulation results. Among them, the fracture morphological data can be used to characterize the data related to the morphology of the fracture, which can include but is not limited to the fracture length, fracture width, fracture height, fracture complexity, fracture tortuosity, and the effective transformation volume of the fracture. The geological change information can be used to characterize the changes in the geological physical parameters of the reservoir after fracturing. Of course, there will be some parameters in the geological physical parameters that will not change with the generation of fractures during the fracturing process. Therefore, the geological change information may include data change information corresponding to the geological physical parameters affected by fracturing, for example, the geological change information may include but is not limited to data change information corresponding to parameters such as permeability, porosity, and oil saturation.

[0057] In some embodiments of the present specification, the geological change information may include permeability change information, porosity change information, and oil saturation change information.

[0058] In some embodiments of the present specification, the fracture extension model may include multiple mathematical models, which may include mathematical calculation models related to fracture morphological parameters such as fracture length, fracture width, fracture height, fracture complexity, fracture tortuosity, and effective transformation volume of fractures, and may also include mathematical calculation models related to geological change information such as permeability, porosity, and oil saturation. Further, historical engineering data and historical geological physical property data may be substituted into the constructed mathematical model to calculate the fracture morphological data and geological change information of the historical reservoir in step S102.

[0059] refer to Figure 2 As shown, in some embodiments of this specification, when constructing the crack extension model in step S102, the following may be included:

[0060] S201: Obtaining physical property parameters corresponding to historical geological physical property data and engineering parameters corresponding to historical engineering data.

[0061] S202: Determine a first correlation relationship between the fracture morphology parameter and the geological physical property parameter and the engineering parameter.

[0062] S203: Determine a second correlation relationship between the geological transformation parameter and the geological physical property parameter and the engineering parameter.

[0063] S204: constructing the crack propagation model based on the first association relationship and the second association relationship.

[0064] Continue to refer Figure 2 As shown, in some embodiments of the present specification, when determining the fracture morphology data and geological change information of the historical reservoir based on the fracture propagation model, the historical geological property data and the historical engineering data in step S102, it may include:

[0065] S205: Based on the first association relationship, the historical geological property data and the historical engineering data, the fracture morphology data of the historical reservoir is calculated.

[0066] S206: Based on the second association relationship, the historical geological physical property data and the historical engineering data, the geological transformation data of the historical reservoir is calculated.

[0067] S207: Determine the geological change information based on the geological transformation data and the historical geological property data.

[0068] It can be understood that the fracture extension model constructed in this embodiment can include multiple mathematical models for calculating fracture morphological parameters and geological change information. By analyzing whether there is a correlation between each parameter in the geological physical property parameters and engineering parameters and the fracture morphological parameters and geological change parameters, at least one parameter affecting the fracture morphological parameters and geological changes is determined, and a corresponding mathematical model is constructed based on the determined parameters to obtain a fracture extension model. The fracture extension model can characterize the physical mechanism of fracture extension. Furthermore, after the fracture extension model is constructed, the historical geological physical property data and the historical engineering data can be substituted into the above-mentioned fracture extension model to calculate the fracture morphological data and geological transformation data, and the geological change information can be determined based on the geological transformation data and the geological physical property parameters of the reservoir before fracturing. The geological change information can include the location of the changed geological physical property parameters and the specific change value. In the above manner, the calculation and processing of the historical engineering data and the historical geological physical property data can realize the extraction of features related to geological changes and fracture morphology, and then the extracted features can be used as part of the training data when performing subsequent model training, and the relationship between the historical production data and the historical production data can be fully learned, providing a data basis for the model prediction accuracy.

[0069] In some embodiments of the present specification, the geological property data corresponding to different positions of the historical reservoir may be different, and a three-dimensional geological model of the historical reservoir may be constructed, and the three-dimensional geological model may include the values ​​of various geological property parameters at different positions to better display the geological property data at different positions. For example, the three-dimensional model of the historical reservoir may be divided into a plurality of grid units, each grid unit corresponds to a plurality of geological property data, and the geological property data of the plurality of grid units may be represented in the form of a matrix, each geological property parameter may correspond to a matrix, and each element in the matrix may represent the geological property data corresponding to a certain geological property parameter of a grid unit.

[0070] Furthermore, after the three-dimensional geological model is constructed, the calculated fracture morphology data and geological transformation data can be integrated with the three-dimensional geological model, so as to reflect the change information of the three-dimensional geological space after the historical reservoir is fracturing. Exemplarily, based on the fracture extension model, the change rate of the geological physical parameters at the fracture after fracturing, such as the increase ratio, the decrease ratio, etc., can be calculated, and then the geological transformation data after fracturing can be calculated based on the matrix corresponding to each physical parameter in the three-dimensional geological model and the change rate of the physical parameter, and the geological change information of the corresponding geological physical parameter can be obtained by calculating the difference between the geological transformation data after fracturing and the matrix of the corresponding geological physical parameter in the original three-dimensional geological model. By combining the geological change information of all geological physical parameters, the geological change information of the historical reservoir can be obtained.

[0071] In some embodiments of the present specification, the fracture extension model may also be an artificial intelligence model, such as a deep learning model such as a logistic regression model, a support vector machine model, a multi-layer perceptron model, a recurrent neural network model, a long short-term memory model, etc., which may be trained with a large amount of historical data to obtain a pre-trained model for calculating fracture morphological parameters and geological change information, and then historical engineering data and historical geological physical property data may be input into the pre-trained model to obtain the fracture morphological data and geological change information of the historical reservoir in step S102.

[0072] S103: Using the historical geological property data of the historical reservoir, the historical engineering data, the historical production data, the geological change information and the fracture morphology data as training data, a training oil and gas production capacity calculation model is obtained with geological property parameters and engineering data as input and production data as output.

[0073] It can be understood that the oil and gas production capacity calculation model can predict production data including oil and gas well production based on the input geological physical parameters and engineering data. During the training process, the artificial intelligence model can iteratively optimize the model parameters through historical geological physical data, historical engineering data, and geological change information corresponding to the historical geological physical data and historical engineering data, the relationship between the fracture morphology data and historical production data, until the preset optimization conditions (such as preset prediction accuracy, preset number of iterations, etc.) are met to obtain the oil and gas production capacity calculation model. Compared with the use of theoretical mathematical models for oil and gas production capacity calculation, the oil and gas production capacity calculation model obtained by training with the above training data can extract multi-level data features of the training data, fully learn the correlation between the training data, and improve the accuracy and practicality of the oil and gas production capacity calculation.

[0074] In some embodiments of the present specification, the historical geological property data may include at least one set of geological property data of historical reservoirs, and the historical engineering data may include at least one set of engineering data corresponding to at least one set of geological property data, and each set of geological property data and engineering data may have corresponding fracture morphology data, geological change information and production data. The geological property data, engineering data, fracture morphology data, geological change information and production data with mutual correspondence can be used as a set of training data, and each set of training data can participate in an iterative training of model parameters once. Using multiple sets of training data, iterative optimization of the artificial intelligence model can be achieved until the preset optimization conditions are met and the oil and gas production capacity calculation model is obtained.

[0075] In some embodiments of the present specification, the pre-built artificial intelligence model may be a deep learning model such as a logistic regression model, a support vector machine model, a multi-layer perceptron model, a recurrent neural network model, a long short-term memory model, etc., which may be specifically selected based on the data characteristics of the training data and the application requirements of the model, and this specification does not impose any restrictions on this.

[0076] In some embodiments of the present specification, the historical geological property data of the historical reservoir, the historical engineering data, the historical production data, the geological change information and the fracture morphology data are used as training data to train an oil and gas production capacity calculation model with geological property parameters and engineering data as input and production data as output, which may include: inputting the historical geological property data of the historical reservoir, the historical engineering data, the historical production data, the geological change information and the fracture morphology data into a pre-established artificial intelligence model; using the artificial intelligence model to learn the relationship between the historical geological property data, the historical engineering data and the geological change information and the fracture morphology data, as well as the relationship between the historical geological property data, the historical engineering data, the geological change information, the fracture morphology data and the historical production data, iteratively updating the parameters of the artificial intelligence model, and obtaining the oil and gas production capacity calculation model.

[0077] It can be understood that the pre-established artificial intelligence model may include two sub-models: a first sub-model and a second sub-model. The two sub-models may adopt the same type of artificial intelligence model, or may select different types of artificial intelligence models based on the data features of the corresponding training data, etc. This specification does not limit this. During the training process, the first sub-model is used to learn the relationship between historical geological physical property data, historical engineering data, geological change information, and fracture morphology data, and obtain a fracturing evolution sub-model for predicting fracture morphology and geological change information after fracturing. The second sub-model is used to learn the relationship between historical geological physical property data, historical engineering data, geological change information, fracture morphology data, and historical production data, and obtain an oil and gas production capacity calculation sub-model for predicting oil and gas production capacity.

[0078] In some embodiments of the present specification, the oil and gas productivity calculation model may include a fracturing evolution sub-model and an oil and gas productivity calculation sub-model; the fracturing evolution sub-model may be used to process the input geological property data and engineering data, and output target fracture morphology data and target geological change information; the oil and gas productivity calculation sub-model may be used to process the input geological property data, engineering data and the target fracture morphology data and target geological change information output by the fracturing evolution sub-model, and output the productivity calculation results.

[0079] Specifically, in actual application, the geological physical property parameters and engineering parameter data can be input into the fracturing evolution sub-model in the oil and gas productivity calculation model, and the predicted target fracture morphology data and target geological change information can be output. Then, the geological physical property parameters and engineering parameter data as well as the predicted target fracture morphology data and target geological change information can be input into the oil and gas productivity calculation sub-model in the oil and gas productivity calculation model to obtain the final oil and gas production prediction results.

[0080] In some embodiments of the present specification, when training an oil and gas productivity calculation model, part of the training data can be used to train to obtain a fracturing evolution sub-model and an oil and gas productivity calculation sub-model, and then another part of the training data can be input into the fracturing evolution sub-model to output the predicted data of the sub-model, and the predicted data together with the data related to geological properties and engineering in the training data can be input into the oil and gas productivity calculation sub-model to output the predicted data of the oil and gas productivity calculation sub-model, and then based on the difference between the predicted data of the oil and gas productivity calculation sub-model and the production data as the expected output in the training data, the parameters of the two sub-models are optimized and updated at the same time, and the optimized and updated fracturing evolution sub-model and oil and gas productivity calculation sub-model are used as the final oil and gas productivity calculation model.

[0081] In some embodiments of the present specification, if the fracture extension model in the aforementioned step S102 is a trained artificial intelligence model, the fracture extension model can be used as the fracturing evolution sub-model in the above-mentioned oil and gas productivity calculation model.

[0082] S104: constructing a multi-objective optimization model based on the oil and gas productivity calculation model, the preset cost calculation model and the target geological property parameters of the target reservoir, optimizing and solving the multi-objective optimization model to obtain the fracturing construction parameters of the target reservoir.

[0083] It can be understood that the preset cost calculation model may include but is not limited to calculation models of material consumption cost, equipment operation cost and labor cost, and a cost calculation model for calculating the fracturing construction cost can be constructed based on the above costs.

[0084] In some embodiments of the present specification, a multi-objective optimization model is constructed based on the oil and gas production capacity calculation model, the preset cost calculation model, and the target geological and physical property parameters of the target reservoir, and the multi-objective optimization model is optimized and solved to obtain the fracturing construction parameters of the target reservoir, which may include: based on the oil and gas production capacity calculation model and the preset cost calculation model, constructing a multi-objective optimization model with minimizing cost and maximizing oil and gas production as the goals and with the target geological and physical property parameters of the target reservoir as constraints; determining the initial engineering data of the target reservoir; inputting the initial engineering data and the target geological and physical property parameters into the oil and gas production capacity calculation model and the preset cost calculation model, and outputting the production capacity calculation results and the cost calculation results; continuously updating and optimizing the initial engineering data with minimizing cost and maximizing oil and gas production as the goals until the preset optimization conditions are met, and obtaining the target engineering data as the fracturing construction parameters of the target reservoir.

[0085] It can be understood that when performing multi-objective optimization solutions, the initial engineering parameters or optimized engineering parameters can be input into the oil and gas capacity calculation model and the cost calculation model, and the capacity calculation results and the cost calculation results can be output respectively. Then, based on the obtained capacity calculation results and cost calculation results, with the minimum cost and the maximum oil and gas production as the goal, the initial engineering parameters or optimized engineering parameters are iteratively optimized until the global optimum or the preset number of iterations is met. The iterative optimization ends, and the engineering data input into the oil and gas capacity calculation model and the cost calculation model for the last time is the target engineering data. The target engineering data can be used as the designed fracturing construction parameters to use the fracturing construction parameters to perform fracturing construction on the target reservoir. In the embodiments of this specification, the trained oil and gas capacity calculation model is used to calculate the oil and gas production. Compared with the calculation of the traditional data model, the accuracy and reliability of the oil and gas production prediction are higher.

[0086] In some embodiments of the present specification, when optimizing and solving a multi-objective optimization model, an optimization algorithm may be used, and the optimization algorithm includes but is not limited to a particle swarm optimization algorithm, a genetic algorithm, a collaborative evolution algorithm, and the like.

[0087] The embodiments of this specification also provide a method for fine design of fracturing completion parameters based on machine learning. This method predicts the production capacity of new wells through geological and engineering data, thereby optimizing the fracturing completion parameters and providing a reference for the design of fracturing completion parameters for oil and gas wells. In addition, when predicting the production capacity of new wells, the evolution characteristics of the geological spatiotemporal information field are integrated, which may include the fracture morphology data and geological change information mentioned above. Figure 3 As shown, the method may include:

[0088] S1: Obtain historical data. The historical data may include reservoir geological property parameters, engineering parameter data, and oil and gas well production data.

[0089] S2: Establish a numerical simulation library for unconventional crack propagation based on the principle of crack propagation.

[0090] Specifically, a numerical model of hydraulic fracture expansion is constructed based on reservoir geological physical parameters and engineering parameter data in historical data to simulate fracture morphological parameters under various hydraulic fracturing parameters of existing production wells. For example, an unconventional fracture expansion model is established based on a three-dimensional geological model. The input geological physical parameters may include reservoir depth, permeability, porosity, ground stress magnitude, direction, etc.; the engineering parameter data may include data corresponding to parameters such as the number of fracturing stages, stage spacing, number of fracturing sections, section spacing, pump pressure, sand ratio, etc.; the output fracture morphological parameters may include but are not limited to fracture length, width, height, complexity, tortuosity, effective transformation volume, etc.; the output geological change information may include change data of geological physical parameters affected by fracturing.

[0091] The following introduces the specific calculation process of geological change information by taking geological change information including permeability change information, porosity change information and oil saturation change information as an example.

[0092] In 3D geological modeling, geological parameters such as permeability are usually represented by a 3D array (or matrix). Here, permeability is used as an example, and each element corresponds to the permeability value of a specific location in the geological model. Assuming there is a 3D geological model of n×m×p, the permeability can be represented by a 3D array K, where each element k ijl Represents the permeability value at position (i, j, l).

[0093] Hydraulic fracturing can significantly affect the parameters of the geological model, such as permeability, porosity and oil saturation. Assume that there is a three-dimensional geological model with initial parameters of permeability Kee, and oil saturation S. o Assume that the fracturing affects some grid cells at location (i, j, l), and the set of these cells is denoted by F.

[0094] Assuming that the permeability increases by ΔK after fracturing, the updated permeability K′ can be expressed as:

[0095]

[0096] ΔK may represent a proportional factor, for example, ΔK=0.5 represents a 50% increase in permeability.

[0097] Assuming that the porosity increases by Δφ after fracturing, the updated porosity φ′ can be expressed as:

[0098] φ′(i,j,l)=φ(i,j,l)×(1+Δφ) Formula (2)

[0099] Here, Δφ can be used to measure a proportional factor, for example, Δφ=0.1 means that the porosity increases by 10%.

[0100] Assume that the oil saturation decreases after fracturing by ΔS e , then the updated oil saturation S o ′ can be expressed as:

[0101] S′ o (i,j,l)=S o (i,j,l)×(1-ΔS o ) Formula (3)

[0102] Among them, ΔS e Can represent a proportionality factor, such as ΔS e =0.1 means that the oil saturation decreases by 10%.

[0103] For the three-dimensional geological data after fracturing, including the location information data of all grid cells affected by fracturing, these updated matrices can be incorporated into the model as new features. Assuming there is a target variable y, the original feature matrix is ​​X e , the updated feature matrix is ​​X updated .

[0104] The original geological feature matrix can be expressed as:

[0105] X origin =[K(i,j,l),φ(i,j,l),S o (i,j,l)...] Formula (4)

[0106] The updated permeability, porosity and oil saturation matrices are added as new features to the original feature matrix. The difference in three-dimensional geological spatial change information after fracturing (i.e., the geological change information mentioned above) is:

[0107]

[0108] The difference matrix X change That is, it is the quantitative matrix value of the change of the three-dimensional information field obtained by the transformation of unconventional fractures, which can reflect the specific impact of hydraulic fracturing on the parameters of the geological model. By comparing the parameter changes before and after fracturing, the impact of fracturing on the geological model can be quantified. It can be integrated with other subsequent features as input features for training artificial intelligence models. In this way, the artificial intelligence model can not only use the original geological features, but also use the change information after fracturing transformation, thereby improving the prediction accuracy of the model. Of course, the above permeability, porosity and oil saturation are only an example of this specification. In other embodiments, the permeability, porosity and oil saturation can also be expressed in other forms, or can also include more or less changes in geological parameters than in the above examples.

[0109] S3: Fusion agent model to establish oil and gas production capacity calculation model.

[0110] Specifically, based on the geological data of the new production wells on site (i.e., the target geological physical parameters of the target reservoir), the proxy model can be used to predict the quantitative values ​​of the changes in the three-dimensional information field, and the production intelligent prediction model can be established by coupling the deep learning model. The training set and the test set are defined according to the input parameters, of which 80% of the data can be used as the training set and 20% of the data can be used as the test set. According to the training set data, the deep learning model is trained to obtain the trained oil and gas production capacity calculation model. Furthermore, when performing subsequent multi-objective optimization, according to the reservoir geological parameters of the new well, the trained oil and gas production capacity calculation model is used to calculate the production capacity data under different completion parameters.

[0111] S4: Obtain the optimal combination of fracturing and completion parameters through optimization algorithm.

[0112] Specifically, a multi-objective optimization mathematical model for fracturing parameters is established with the goal of maximizing economic net present value and maximizing production. The optimal solution of the mathematical model is found through an artificial intelligence algorithm to obtain the best combination of fracturing parameters. It is then tested whether it conforms to engineering practice, and ultimately the fine design of fracturing completion parameters is achieved.

[0113] The machine learning-based fracturing completion parameter fine design method provided in the embodiments of this specification can simulate the expansion of fracturing cracks based on reservoir geological parameters, engineering parameters, etc., and establish an agent model by forming a simulation database to predict oil and gas production. Based on the reservoir geological parameters of the new well and the predicted cumulative production, the fracturing completion parameters are optimized with the goal of maximizing production capacity and economic benefits to obtain the optimal completion parameter combination, thereby significantly increasing the production of oil and gas wells.

[0114] Based on the above-mentioned method for determining the fracturing parameters, one or more embodiments of this specification also provide a device for determining the fracturing parameters. The device may include a device (including a distributed system), software (application), module, plug-in, server, client, etc. using the method described in the embodiments of this specification and a device combined with necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided in the embodiments of this specification is as described in the following embodiments. Since the implementation scheme and method for solving the problem of the device are similar, the implementation of the specific device in the embodiments of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived. Figure 4 FIG. 1 is a schematic diagram of a device for determining fracturing parameters provided in an embodiment of the present application. Figure 4 As shown, the fracturing parameter determination device 400 may include:

[0115] The data acquisition module 401 is used to acquire historical geological property data, historical engineering data and historical production data of historical reservoirs.

[0116] The data determination module 402 is used to construct a fracture propagation model, and determine the fracture morphology data and geological change information of the historical reservoir based on the fracture propagation model, the historical geological property data and the historical engineering data. The fracture propagation model is used to simulate the morphology of fracture propagation under different engineering parameters.

[0117] The model training module 403 is used to use the historical geological property data of the historical reservoir, the historical engineering data, the historical production data, the geological change information and the fracture morphology data as training data to train an oil and gas production capacity calculation model with geological property parameters and engineering data as input and production data as output.

[0118] The parameter determination module 404 is used to construct a multi-objective optimization model based on the oil and gas productivity calculation model, the preset cost calculation model and the target geological property parameters of the target reservoir, optimize and solve the multi-objective optimization model, and obtain the fracturing construction parameters of the target reservoir.

[0119] In some embodiments of the present specification, when constructing a fracture extension model, the data determination module 402 is specifically used to: obtain physical property parameters corresponding to historical geological physical property data and engineering parameters corresponding to historical engineering data; determine a first correlation relationship between fracture morphology parameters and geological physical property parameters and engineering parameters; determine a second correlation relationship between geological transformation parameters and geological physical property parameters and engineering parameters; and construct the fracture extension model based on the first correlation relationship and the second correlation relationship.

[0120] In some embodiments of the present specification, when the data determination module 402 determines the fracture morphology data and geological change information of the historical reservoir based on the fracture extension model, the historical geological property data and the historical engineering data, it is specifically used to: calculate the fracture morphology data of the historical reservoir based on the first association relationship, the historical geological property data and the historical engineering data; calculate the geological transformation data of the historical reservoir based on the second association relationship, the historical geological property data and the historical engineering data; and determine the geological change information based on the geological transformation data and the historical geological property data.

[0121] In some embodiments of the present specification, the geological change information may include permeability change information, porosity change information, and oil saturation change information.

[0122] In some embodiments of the present specification, the model training module 403 is specifically used to: input the historical geological property data of the historical reservoir, the historical engineering data, the historical production data, the geological change information, and the fracture morphology data into a pre-established artificial intelligence model; use the artificial intelligence model to learn the relationship between the historical geological property data, the historical engineering data and the geological change information and the fracture morphology data, as well as the relationship between the historical geological property data, the historical engineering data, the geological change information, the fracture morphology data and the historical production data, iteratively update the parameters of the artificial intelligence model, and obtain the oil and gas production capacity calculation model.

[0123] In some embodiments of the present specification, the oil and gas productivity calculation model may include a fracturing evolution sub-model and an oil and gas productivity calculation sub-model; the fracturing evolution sub-model may be used to process the input geological property data and engineering data, and output target fracture morphology data and target geological change information; the oil and gas productivity calculation sub-model may be used to process the input geological property data, engineering data and the target fracture morphology data and target geological change information output by the fracturing evolution sub-model, and output the productivity calculation results.

[0124] In some embodiments of the present specification, the parameter determination module 404 can be specifically used to: construct a multi-objective optimization model with the goal of minimizing cost and maximizing oil and gas production based on the oil and gas production capacity calculation model and the preset cost calculation model, and with the target geological and physical parameters of the target reservoir as constraints; determine the initial engineering data of the target reservoir; input the initial engineering data and the target geological and physical parameters into the oil and gas production capacity calculation model and the preset cost calculation model, and output the production capacity calculation results and the cost calculation results; continuously update and optimize the initial engineering data with the goal of minimizing cost and maximizing oil and gas production until the preset optimization conditions are met, and obtain the target engineering data as the fracturing construction parameters of the target reservoir.

[0125] The description and functions of the above modules can be understood by referring to the content of the method for determining fracturing parameters, which will not be repeated here.

[0126] The present application also provides an electronic device, such as Figure 5 As shown, the electronic device may include a processor 501 and a memory 502, wherein the processor 501 and the memory 502 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0127] The processor 501 may be a central processing unit (CPU). The processor 501 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0128] The memory 502 is a non-transitory computer-readable storage medium that can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the method for determining fracturing parameters in the embodiment of the present invention (for example, Figure 4 The processor 501 executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory 502, that is, the method for determining the fracturing parameters in the above method embodiment is implemented.

[0129] The memory 502 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created by the processor 501, etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 502 may optionally include a memory remotely arranged relative to the processor 501, and these remote memories may be connected to the processor 501 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0130] The one or more modules are stored in the memory 502, and when executed by the processor 501, the following method for determining fracturing parameters is performed:

[0131] Acquire historical geological property data, historical engineering data and historical production data of historical reservoirs; construct a fracture extension model, and determine fracture morphological data and geological change information of the historical reservoir based on the fracture extension model, the historical geological property data and the historical engineering data, wherein the fracture extension model is used to simulate the morphology of fracture extension under different engineering parameters; use the historical geological property data of the historical reservoir, the historical engineering data, the historical production data, the geological change information and the fracture morphological data as training data to obtain an oil and gas production capacity calculation model with geological property parameters and engineering data as input and production data as output; construct a multi-objective optimization model based on the oil and gas production capacity calculation model, a preset cost calculation model and target geological property parameters of the target reservoir, optimize and solve the multi-objective optimization model, and obtain the fracturing construction parameters of the target reservoir.

[0132] The specific details of the above electronic device can be understood by referring to the corresponding descriptions and effects in the above method embodiments, and will not be repeated here.

[0133] The present specification also provides a computer storage medium, wherein the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the steps of the above-mentioned method for determining fracturing parameters are implemented.

[0134] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0135] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0136] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions.

[0137] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0138] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute certain parts of the methods of each implementation method of the present application.

[0139] The present application can be used in many general or special computer system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0140] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0141] Although the present application has been described through embodiments, those skilled in the art will appreciate that there are many modifications and variations to the present application without departing from the spirit of the present application, and it is intended that the appended claims include these modifications and variations without departing from the spirit of the present application.

Claims

1. A method for determining fracturing parameters, characterized in that: include: Obtain historical geological and physical data, historical engineering data and historical production data of historical reservoirs; Constructing a fracture propagation model, and determining fracture morphology data and geological change information of the historical reservoir based on the fracture propagation model, the historical geological property data and the historical engineering data, wherein the fracture propagation model is used to simulate the morphology of fracture propagation under different engineering parameters; Using the historical geological property data of the historical reservoir, the historical engineering data, the historical production data, the geological change information and the fracture morphology data as training data, training to obtain an oil and gas productivity calculation model that uses geological property parameters and engineering data as input and production data as output; A multi-objective optimization model is constructed based on the oil and gas productivity calculation model, the preset cost calculation model and the target geological property parameters of the target reservoir, and the multi-objective optimization model is optimized and solved to obtain the fracturing construction parameters of the target reservoir.

2. The method for determining fracturing parameters according to claim 1, characterized in that: Construct a crack propagation model, including: Obtaining physical property parameters corresponding to historical geological physical property data and engineering parameters corresponding to historical engineering data; Determine the first correlation between the fracture morphology parameters and the geological physical parameters and engineering parameters; Determine the second correlation between the geological transformation parameters and the geological physical parameters and engineering parameters; The crack propagation model is constructed based on the first association relationship and the second association relationship.

3. The method for determining fracturing parameters according to claim 2, characterized in that: Based on the fracture propagation model, the historical geological property data and the historical engineering data, the fracture morphology data and geological change information of the historical reservoir are determined, including: Based on the first association relationship, the historical geological property data and the historical engineering data, the fracture morphology data of the historical reservoir is calculated; Based on the second association relationship, the historical geological property data and the historical engineering data, the geological transformation data of the historical reservoir is calculated; The geological change information is determined based on the geological transformation data and the historical geological physical property data.

4. The method for determining fracturing parameters according to claim 3, characterized in that: The geological change information includes permeability change information, porosity change information and oil saturation change information.

5. The method for determining fracturing parameters according to claim 1, characterized in that: The historical geological property data of the historical reservoir, the historical engineering data, the historical production data, the geological change information and the fracture morphology data are used as training data to obtain an oil and gas productivity calculation model that uses geological property parameters and engineering data as input and production data as output, including: The historical geological property data of the historical reservoir, the historical engineering data, the historical production data, the geological change information and the fracture morphology data are input into a pre-established artificial intelligence model; The artificial intelligence model is used to learn the relationship between the historical geological property data, the historical engineering data, the geological change information and the fracture morphology data, as well as the relationship between the historical geological property data, the historical engineering data, the geological change information, the fracture morphology data and the historical production data, and the parameters of the artificial intelligence model are iteratively updated to obtain the oil and gas production capacity calculation model.

6. The method for determining fracturing parameters according to claim 1 or 5, characterized in that: The oil and gas productivity calculation model includes a fracturing evolution sub-model and an oil and gas productivity calculation sub-model; The fracturing evolution sub-model is used to process the input geological physical property data and engineering data, and output target fracture morphology data and target geological change information; The oil and gas productivity calculation sub-model is used to process the input geological property data, engineering data and the target fracture morphology data and target geological change information output by the fracturing evolution sub-model, and output the productivity calculation result.

7. The method for determining fracturing parameters according to claim 1, characterized in that: A multi-objective optimization model is constructed based on the oil and gas productivity calculation model, the preset cost calculation model and the target geological property parameters of the target reservoir, and the multi-objective optimization model is optimized and solved to obtain the fracturing construction parameters of the target reservoir, including: Based on the oil and gas productivity calculation model and the preset cost calculation model, a multi-objective optimization model is constructed with the goal of minimizing cost and maximizing oil and gas production and the target geological and physical parameters of the target reservoir as constraints; Determine initial engineering data for target reservoirs; Inputting the initial engineering data and target geological physical parameters into the oil and gas productivity calculation model and the preset cost calculation model, and outputting productivity calculation results and cost calculation results; The initial engineering data is continuously updated and optimized with the goal of minimizing costs and maximizing oil and gas production until the preset optimization conditions are reached, and the target engineering data is obtained as the fracturing construction parameters of the target reservoir.

8. A device for determining fracturing parameters, characterized in that: include: A data acquisition module, used to acquire historical geological property data, historical engineering data and historical production data of historical reservoirs; A data determination module, for constructing a fracture extension model, and determining fracture morphology data and geological change information of the historical reservoir based on the fracture extension model, the historical geological property data and the historical engineering data, wherein the fracture extension model is used to simulate the morphology of fracture extension under different engineering parameters; A model training module is used to use the historical geological property data of the historical reservoir, the historical engineering data, the historical production data, the geological change information and the fracture morphology data as training data to train an oil and gas production capacity calculation model with geological property parameters and engineering data as input and production data as output; The parameter determination module is used to construct a multi-objective optimization model based on the oil and gas production capacity calculation model, the preset cost calculation model and the target geological property parameters of the target reservoir, optimize and solve the multi-objective optimization model, and obtain the fracturing construction parameters of the target reservoir.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the processor and the memory are communicatively connected to each other, the memory stores computer instructions, and the processor implements the steps of the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images