A method and device for optimizing fracturing filling construction parameters
By correcting reservoir physical properties data, determining output main control parameters, training deep learning models and optimizing construction parameters, the problem of insufficient setting of fracturing technology in loose sandstone is solved, and efficient and fine-grained Optimization of construction parameters.
Patent Information
- Application Number
- CN202410341155.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-25
- Publication Date
- 2025-02-11
- Estimated Expiration
- 2044-03-25
AI Technical Summary
The application of existing fracturing filling technology in loose sandstones has problems such as unknown morphology of hydraulic cracks, insufficient construction parameters setting, long design cycle and low efficiency.
By correcting the reservoir physical property data based on well measurement and recording data, determining the output main control parameters that affect output, training the deep learning model to obtain the output prediction model, and optimizing the construction parameters using a multi-objective optimization algorithm, with high yield and low cost as the goal.
A more accurate prediction of hydraulic crack forms in loose sandstone was achieved, construction parameter design was optimized, design cycle was shortened, and construction efficiency was improved.
Smart Images
Figure CN118094726B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and device for optimizing fracturing and filling construction parameters. Background Art
[0002] Loose sandstone has high porosity and high permeability, but poor cementation properties, and sand production is prone to occur during the production process. Years of exploration and development practices in oil fields have shown that in the initial stage of oil field development, sand production is the main problem in the development and production of oil and gas layers. As oil and gas field development enters the middle and late stages, production decreases rapidly, and increasing production becomes the primary issue for oil and gas wells. In response to this problem, fracturing and filling technology was proposed. This technology combines hydraulic fracturing technology and historical filling technology. Hydraulic fracturing provides a flow channel for reservoir fluids to increase production, and gravel filling forms a sand barrier to limit sand production in oil and gas wells. Fracturing and filling technology effectively combines the advantages of hydraulic fracturing and historical filling operations, and can achieve the dual goals of sand control and increased production in oil and gas wells, and has been widely used in oil fields.
[0003] However, at present, the application of this technology still has the following problems: 1. The morphology of hydraulic fractures is unclear. Loose sandstone has strong permeability and significant plastic deformation. The initiation and extension of fractures are complex. There is no accurate prediction method for the morphology of loose sandstone fractures. 2. The parameters of the fracturing and filling operation are not set precisely enough. Although certain experience and understanding have been gained through a large number of gravel filling operations in the past, the parameter settings are still relatively general and single, and the mutual influence between reservoir conditions, engineering parameters and production capacity has not been fully considered. The rationality and accuracy of parameter design need to be further verified and improved. 3. The design cycle is long and the efficiency is low. At present, there are many development wells, and the design of fracturing and filling construction parameters is extremely dependent on the experience of designers. It is difficult and stressful to achieve refined design of a single well and a single layer. Summary of the invention
[0004] In view of the problems in the prior art, an embodiment of the present invention provides a method and device for optimizing fracturing and filling construction parameters, which can at least partially solve the problems in the prior art.
[0005] On the one hand, the present invention provides a method for optimizing fracturing and filling construction parameters, comprising:
[0006] Correct the reservoir physical property data in the target area according to the logging data of the well to be fractured and filled, and obtain the physical property data;
[0007] Determining a primary control parameter of production that affects production based on the physical property data, engineering operation data in the target area, and production data;
[0008] Using the production master control parameters and the production data as sample data, training a deep learning model to obtain a production prediction model;
[0009] Initialization conditions are determined based on the engineering operation data, the physical property data and the production data, the physical property data is used as a constraint, the production prediction model and the pre-established cost calculation model are used as objective functions, and high production and low cost are used as desired goals to obtain optimized fracturing and filling construction parameters.
[0010] Wherein, the reservoir physical property data in the target area is corrected according to the logging data of the well to be fractured and filled to obtain the physical property data, including:
[0011] The pre-established three-dimensional reservoir geological model is modified according to the logging data of the well to be fractured and filled to obtain the physical property data.
[0012] The pre-established three-dimensional reservoir geological model includes:
[0013] The three-dimensional geological model of the reservoir is established based on the interpolation method.
[0014] Wherein, determining the main control parameters of the output that affect the output according to the physical property data, the engineering operation data and the output data in the target area includes:
[0015] Calculate the correlation coefficients between the physical property data and the engineering operation data and the production data respectively based on a correlation analysis algorithm;
[0016] The target physical property data and target engineering operation data serving as the main control parameters of the production are screened in descending order of correlation coefficients.
[0017] The target physical property data and target engineering operation data as the main control parameters of the production are obtained by screening in descending order of correlation coefficients, including:
[0018] A preset number of physical property data and engineering operation data are selected from the sequential sequence as the target physical property data and the target engineering operation data.
[0019] Wherein, determining the initialization condition according to the engineering operation data, the physical property data and the production data includes:
[0020] Determining a fracturing and filling construction parameter space to be optimized according to the engineering operation data;
[0021] The fracturing and filling construction parameters in the engineering operation data are initialized and assigned in the fracturing and filling construction parameter space, and the physical property data and the production data are initialized and assigned.
[0022] The method of using the physical property data as a constraint, the production prediction model and the pre-established cost calculation model as the objective function, and high production and low cost as the desired goals to obtain the optimized fracturing and filling construction parameters includes:
[0023] According to the multi-objective optimization algorithm, the physical property data is used as a known constant condition, and the optimized fracturing and filling construction parameters are continuously updated according to the production prediction results and the cost calculation results until the global optimum or the maximum number of iterations is reached, thereby obtaining the optimized fracturing and filling construction parameters.
[0024] On the one hand, the present invention provides a device for optimizing fracturing and filling construction parameters, comprising:
[0025] An acquisition unit, used to correct the reservoir physical property data in the target area according to the logging data of the well to be fractured and filled, and obtain physical property data;
[0026] A determination unit, configured to determine a production master control parameter affecting production according to the physical property data, the engineering operation data in the target area and the production data;
[0027] A training unit, used to use the production master control parameters and the production data as sample data to train a deep learning model to obtain a production prediction model;
[0028] The optimization unit is used to determine the initialization conditions according to the engineering operation data, the physical property data and the production data, take the physical property data as constraints, use the production prediction model and the pre-established cost calculation model as objective functions, take high production and low cost as the desired goals, and obtain optimized fracturing and filling construction parameters.
[0029] In another aspect, an embodiment of the present invention provides an electronic device, including: a processor, a memory, and a bus, wherein:
[0030] The processor and the memory communicate with each other via the bus;
[0031] The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the following method:
[0032] Correct the reservoir physical property data in the target area according to the logging data of the well to be fractured and filled, and obtain the physical property data;
[0033] Determining a primary control parameter of production that affects production based on the physical property data, engineering operation data in the target area, and production data;
[0034] Using the production master control parameters and the production data as sample data, training a deep learning model to obtain a production prediction model;
[0035] Initialization conditions are determined based on the engineering operation data, the physical property data and the production data, the physical property data is used as a constraint, the production prediction model and the pre-established cost calculation model are used as objective functions, and high production and low cost are used as desired goals to obtain optimized fracturing and filling construction parameters.
[0036] An embodiment of the present invention provides a non-transitory computer-readable storage medium, including:
[0037] The non-transitory computer-readable storage medium stores computer instructions, which cause the computer to execute the following method:
[0038] Correct the reservoir physical property data in the target area according to the logging data of the well to be fractured and filled, and obtain the physical property data;
[0039] Determining a primary control parameter of production that affects production based on the physical property data, engineering operation data in the target area, and production data;
[0040] Using the production master control parameters and the production data as sample data, training a deep learning model to obtain a production prediction model;
[0041] Initialization conditions are determined based on the engineering operation data, the physical property data and the production data, the physical property data is used as a constraint, the production prediction model and the pre-established cost calculation model are used as objective functions, and high production and low cost are used as desired goals to obtain optimized fracturing and filling construction parameters.
[0042] The method and device for optimizing fracturing and filling construction parameters provided in the embodiments of the present invention correct the reservoir physical property data in the target area according to the logging data of the well to be fracturing and filling to obtain physical property data; determine the main production control parameters affecting the production according to the physical property data, the engineering operation data and the production data in the target area; use the main production control parameters and the production data as sample data to train a deep learning model to obtain a production prediction model; determine initialization conditions according to the engineering operation data, the physical property data and the production data, use the physical property data as constraints, use the production prediction model and a pre-established cost calculation model as objective functions, and use high production and low cost as the desired goals to obtain optimized fracturing and filling construction parameters, so as to obtain optimized fracturing and filling construction parameters. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:
[0044] Figure 1 It is a flow chart of a method for optimizing fracturing and filling construction parameters provided in one embodiment of the present invention.
[0045] Figure 2 It is a flow chart of a method for optimizing fracturing and filling construction parameters provided by another embodiment of the present invention.
[0046] Figure 3 It is a flow chart of a method for optimizing fracturing and filling construction parameters provided by another embodiment of the present invention.
[0047] Figure 4 It is a structural schematic diagram of a device for optimizing fracturing and filling construction parameters provided by one embodiment of the present invention.
[0048] Figure 5 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0049] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention. It should be noted that, in the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other arbitrarily.
[0050] Figure 1 FIG. 1 is a flow chart of a method for optimizing fracturing and filling construction parameters provided by an embodiment of the present invention. Figure 1 As shown, the method for optimizing fracturing and filling construction parameters provided by the embodiment of the present invention includes:
[0051] Step S1: Correct the reservoir physical property data in the target area according to the logging data of the well to be fractured and filled, and obtain physical property data.
[0052] Step S2: determining the main production control parameters affecting the production according to the physical property data, the engineering operation data in the target area and the production data.
[0053] Step S3: Using the production master control parameters and the production data as sample data, training a deep learning model to obtain a production prediction model.
[0054] Step S4: Determine initialization conditions based on the engineering operation data, the physical property data and the production data, take the physical property data as constraints, use the production prediction model and the pre-established cost calculation model as objective functions, take high production and low cost as desired goals, and obtain optimized fracturing and filling construction parameters.
[0055] In the above step S1, the device corrects the reservoir physical property data in the target area according to the logging data of the well to be fractured and fills, and obtains the physical property data. The device may be a computer device that executes the method, for example, it may include a server. It should be noted that the acquisition and analysis of data involved in the embodiment of the present invention are authorized by the user. The well to be fractured and fills refers to a new well. The neighboring wells that have been drilled as the new well are located in the target area. The geological properties and fluid properties of the new well and the neighboring wells are relatively similar, so as to ensure the applicability of the reservoir physical property data in the new well.
[0056] Reservoir physical property data are geological attribute parameters of each production layer, such as reservoir depth, thickness, pressure, temperature, pore permeability, geostress conditions, clay content, brittleness index, median particle size, sorting coefficient and fluid properties. Fluid properties include crude oil density, natural gas density, various volume coefficients, gasoline ratio, etc.
[0057] like Figure 2 As shown, reservoir physical property information and logging data of the drilled wells can be used to analyze the stratigraphic characteristics of the target area.
[0058] Based on the early exploration and development data of the target area, the reservoir physical property data of the target area and the logging data of the drilled and completed wells can be sorted out and summarized.
[0059] The formation sand index can be calculated based on the logging data. The basic characteristic attributes of the formation can be determined through the above reservoir physical property data and the formation sand index, which lays a good foundation for the design and optimization of fracturing and filling construction parameters.
[0060] Since the fracturing and filling construction parameters to be optimized are closely related to the logging data of the new well, it is necessary to correct some reservoir physical property data in the target area through the logging data of the new well, so as to obtain more accurate and comprehensive geological parameters and fluid parameters of the production layer of the well, so as to establish a more accurate geological model.
[0061] The method of correcting the reservoir physical property data in the target area according to the logging data of the well to be fractured and filled to obtain the physical property data includes:
[0062] The pre-established three-dimensional reservoir geological model is modified according to the logging data of the well to be fractured and filled to obtain the physical property data.
[0063] The pre-established three-dimensional reservoir geological model includes:
[0064] The reservoir three-dimensional geological model is established based on the interpolation method. The reservoir three-dimensional geological model can be drawn based on the acquired reservoir physical property data in the target area and various logging data of the fractured and filled operating wells in the target area, wherein the fractured and filled operating wells include all wells in the target area including exploration wells, production wells, and adjustment wells.
[0065] Based on the reservoir physical property data in the target area and the logging data of the fractured and filled wells in the target area, the reservoir physical property parameters of the entire target area are supplemented through interpolation algorithm, and a three-dimensional reservoir geological model of the target area is established based on this to realize the understanding of the reservoir space.
[0066] Since the logging data of the new well can reflect the status of the new well more objectively, the accurate formation attribute parameters near the new well are determined through the logging data of the new well obtained after drilling, and the reservoir 3D geological model is corrected to establish a more accurate reservoir 3D geological model, further summarize the engineering operation data and production data of the fracturing and filling operation wells in the target area, and establish a complete geology-engineering-production integrated data set.
[0067] In the above step S2, the device determines the main control parameters of production that affect the production based on the physical property data, the engineering operation data and the production data in the target area. The main control parameters of production are actually one or more parameters in the engineering operation data and the physical property data that affect the production. For example, reservoir depth, thickness, pressure, temperature, pore permeability and various fracturing and filling construction parameters. Since the physical property conditions of reservoirs in different blocks are different, the main control parameters of production also vary according to the conditions of the formation, and there are many factors that affect the production of oil and gas wells, so the content of the main control parameters of production needs to be specifically analyzed, but the analysis method is consistent.
[0068] Determining the main production control parameters affecting the production according to the physical property data, the engineering operation data and the production data in the target area includes:
[0069] Calculate the correlation coefficients between the physical property data and the engineering operation data and the production data respectively based on a correlation analysis algorithm;
[0070] The target physical property data and target engineering operation data serving as the main control parameters of the production are screened in descending order of correlation coefficients.
[0071] The target physical property data and target engineering operation data as the main control parameters of the production are obtained by screening in descending order of correlation coefficients, including:
[0072] In the sequential sequence, a preset number of physical property data and engineering operation data ranked first are selected as the target physical property data and the target engineering operation data. The preset number can be set independently according to actual conditions. If the preset number is set to a large number, the number of physical property data and engineering operation data are large, which can ensure the prediction accuracy of the yield prediction model.
[0073] If the preset quantity is set to a small value, the type of physical property data and / or the type of engineering operation data is small, and the prediction accuracy of the production prediction model may be poor, but the workload of model training can be reduced.
[0074] Correlation analysis algorithms include: Pearson method, grey correlation method, Spearman method, etc. In this embodiment, the Pearson method can be used to calculate the correlation coefficients between various fracturing and filling construction parameters and each parameter in the corrected reservoir physical property data (physical property data) and the production data, for example, parameters with higher correlation coefficients include: porosity, permeability, reservoir pressure, fracturing length, stage spacing, number of fracturing stages, fluid intensity, sand addition intensity, and test production, etc.
[0075] The correlation coefficients are sorted in order, and the sequence is intercepted to obtain the main control parameters of the output. Specifically, the larger the correlation coefficient between the two parameters, the stronger the correlation between the parameters, that is, the deeper the mutual influence, so the correlation coefficients are sorted according to the needs, and the main control parameters of the output are obtained.
[0076] In the above step S3, the device uses the production master control parameters and the production data as sample data to train a deep learning model to obtain a production prediction model.
[0077] The input of the production prediction model is the main control parameters of production, and its output is production data. The production data can be the average or median value of the liquid (oil) production for one or three months. Based on the production prediction model, if the reservoir physical property parameters, drilling and completion data, and fracturing and filling construction parameters are input, the predicted production of the new well can be obtained.
[0078] The production prediction model can be constructed based on machine learning models such as decision trees, logistic regression, and deep learning models such as neural networks. The specific machine learning model and machine learning method are the same as the relevant machine learning methods in the prior art, and will not be repeated here.
[0079] In the above step S4, the device determines the initialization conditions according to the engineering operation data, the physical property data and the production data, takes the physical property data as a constraint, takes the production prediction model and the pre-established cost calculation model as the objective function, takes high production and low cost as the desired goals, and obtains the optimized fracturing and filling construction parameters. If a new well encounters multiple reservoirs and stratified mining is adopted, the physical property data of a single layer reservoir can be used as a constraint to optimize the design of the fracturing and filling construction parameters.
[0080] The determining of the initialization condition according to the engineering operation data, the physical property data and the production data comprises:
[0081] Determining a fracturing and filling construction parameter space to be optimized according to the engineering operation data;
[0082] In the fracturing and filling construction parameter space, the fracturing and filling construction parameters in the engineering operation data are initialized and assigned, and the physical property data and the production data are initialized and assigned. Figure 3 As shown, the various fracturing and filling construction parameters included in the engineering operation data include multiple parameters, so in this step, multiple parameters in the fracturing and filling construction parameters will be randomly initialized, that is, values are randomly selected in the set parameter space. Considering the equipment load and operation safety during the operation, the appropriate parameter value boundaries are determined, for example, the maximum construction pressure cannot exceed the critical value of the equipment, and the minimum cannot be lower than the formation fracture pressure.
[0083] The method uses the physical property data as constraints, the production prediction model and the pre-established cost calculation model as objective functions, and high production and low cost as desired goals to obtain optimized fracturing and filling construction parameters, including:
[0084] According to the multi-objective optimization algorithm, the physical property data is used as a known constant condition, and the optimized fracturing and filling construction parameters are continuously updated according to the production prediction results and the cost calculation results until the global optimum or the maximum number of iterations is reached, thereby obtaining the optimized fracturing and filling construction parameters.
[0085] In this step, the reservoir physical property data of the new well is used as a known constant condition through a multi-objective optimization algorithm, and the fracturing and filling construction parameters are continuously updated and optimized according to the production prediction results and cost calculation results. Among them, the target values of the current batch of fracturing and filling construction parameters are calculated based on the production prediction model and the cost calculation model, and the fitness value of each parameter in each sample of the fracturing and filling construction parameters is calculated accordingly. The larger the fitness value, the closer it is to the objective function.
[0086] When the global optimum or maximum number of iterations is reached, the optimization of the fracturing and filling construction parameters is completed. The global optimum is an optimal curve of cost and output, and the optimal result can be flexibly determined according to actual needs. Specifically, the global optimum can be determined according to the objective function, and the maximum number of iterations can be determined according to the optimization requirements. Either the global optimum or the maximum number of iterations can be used as the final condition for optimization.
[0087] That is, when the optimization termination condition is reached, it is equivalent to the completion of the optimization of the fracturing and filling construction parameters, and the obtained fracturing and filling construction parameters reach the current optimal solution. If the global optimum or the maximum number of iterations is not reached, the above steps are cyclically executed by randomly selecting values in the parameter value space until the optimization termination condition is reached.
[0088] The global optimum is an optimal curve, which means the maximum production that can be achieved under certain cost conditions and its corresponding fracturing and filling construction parameters, or the minimum cost that can be achieved under the expected production conditions and its corresponding fracturing and filling construction parameters.
[0089] The embodiment of the present invention provides a data-driven optimization method for refined fracturing and filling construction parameters, which makes full use of the existing block geological feature data and the engineering operation and production data of historical wells, realizes the production prediction of production wells under different fracturing and filling construction parameters, fully establishes the optimization space of various construction parameter data based on historical operation experience to ensure safe operation, and uses the physical property data of the formation encountered by the new well as a constraint, and uses the production prediction model and the cost calculation model as the objective function, and optimizes the fracturing and filling construction parameters with high production and low cost as the expectation. Compared with the existing prediction methods, the present invention is based on the sufficient data resources recorded by a large number of oil and gas wells used in construction and production in decades of exploration and development, and uses advanced algorithms such as data mining, machine learning, and deep learning as tools. Under this condition, it is possible to directly optimize the fracturing and filling construction parameters with high production and low cost as the ultimate goal through data mining of historical wells. Moreover, the present invention is based on data-driven, which reduces the user's use threshold, has stronger applicability, faster and more refined calculation, and can realize the refined design of different layers in the same well.
[0090] The method for optimizing fracturing and filling construction parameters provided in an embodiment of the present invention corrects reservoir physical property information in a target area according to logging data of a well to be fracturing and filling to obtain physical property data; determines the main production control parameters affecting production according to the physical property data, engineering operation data and production data in the target area; uses the main production control parameters and the production data as sample data to train a deep learning model to obtain a production prediction model; determines initialization conditions according to the engineering operation data, the physical property data and the production data, uses the physical property data as constraints, uses the production prediction model and a pre-established cost calculation model as objective functions, takes high production and low cost as desired goals, and obtains optimized fracturing and filling construction parameters, thereby being able to obtain optimized fracturing and filling construction parameters.
[0091] Furthermore, the reservoir physical property data in the target area is corrected according to the logging data of the well to be fractured and filled to obtain the physical property data, including:
[0092] The pre-established three-dimensional reservoir geological model is modified according to the logging data of the well to be fractured and filled to obtain the physical property data. The above-mentioned embodiments can be referred to for explanation and will not be described in detail.
[0093] Furthermore, the pre-established three-dimensional reservoir geological model includes:
[0094] The three-dimensional geological model of the reservoir is established based on the interpolation method. The above-mentioned embodiments can be referred to for explanation and will not be described in detail.
[0095] Furthermore, determining the main production control parameters affecting the production according to the physical property data, the engineering operation data and the production data in the target area includes:
[0096] The correlation coefficients between the physical property data and the engineering operation data and the production data are calculated based on a correlation analysis algorithm; the description may refer to the above embodiment and will not be repeated here.
[0097] The target physical property data and target engineering operation data as the main control parameters of the production are screened in descending order according to the correlation coefficients.
[0098] Furthermore, the target physical property data and target engineering operation data as the main control parameters of the production are obtained by screening in descending order of correlation coefficients, including:
[0099] In the sequence, a preset number of physical property data and engineering operation data are selected as the target physical property data and the target engineering operation data. The above-mentioned embodiments can be referred to for explanation, and no further description is given.
[0100] Further, determining the initialization condition according to the engineering operation data, the physical property data and the production data includes:
[0101] The fracturing and filling construction parameter space to be optimized is determined according to the engineering operation data; the description can be made with reference to the above embodiment and will not be repeated here.
[0102] In the fracturing and filling construction parameter space, the fracturing and filling construction parameters in the engineering operation data are initialized and assigned, and the physical property data and the production data are initialized and assigned. The above embodiments can be referred to for explanation, and no further description is given.
[0103] Furthermore, the physical property data is used as a constraint, the production prediction model and the pre-established cost calculation model are used as objective functions, and high production and low cost are used as desired goals to obtain optimized fracturing and filling construction parameters, including:
[0104] According to the multi-objective optimization algorithm, the physical property data is used as a known constant condition, and the optimized fracturing and filling construction parameters are continuously updated according to the production prediction results and the cost calculation results until the global optimum or the maximum number of iterations is reached, and the optimized fracturing and filling construction parameters are obtained. The above-mentioned embodiments can be referred to for explanation and will not be repeated here.
[0105] Figure 4 FIG. 1 is a schematic diagram of a structural diagram of a device for optimizing fracturing and filling construction parameters provided by an embodiment of the present invention. Figure 4 As shown, the device for optimizing fracturing and filling construction parameters provided by the embodiment of the present invention includes an acquisition unit 401, a determination unit 402, a training unit 403 and an optimization unit 404, wherein:
[0106] The acquisition unit 401 is used to correct the reservoir physical property information in the target area according to the logging data of the well to be fracturing and filling, and obtain the physical property data; the determination unit 402 is used to determine the main control parameters of production that affect the production according to the physical property data, the engineering operation data and the production data in the target area; the training unit 403 is used to use the main control parameters of production and the production data as sample data to train the deep learning model to obtain the production prediction model; the optimization unit 404 is used to determine the initialization conditions according to the engineering operation data, the physical property data and the production data, take the physical property data as constraints, take the production prediction model and the pre-established cost calculation model as the objective function, take high production and low cost as the desired goals, and obtain the optimized fracturing and filling construction parameters.
[0107] Specifically, the acquisition unit 401 in the device is used to correct the reservoir physical property information in the target area according to the logging data of the well to be fracturing and filling, and obtain physical property data; the determination unit 402 is used to determine the main control parameters of production that affect the production according to the physical property data, the engineering operation data and the production data in the target area; the training unit 403 is used to use the main control parameters of production and the production data as sample data to train the deep learning model to obtain the production prediction model; the optimization unit 404 is used to determine the initialization conditions according to the engineering operation data, the physical property data and the production data, take the physical property data as constraints, take the production prediction model and the pre-established cost calculation model as objective functions, take high production and low cost as the desired goals, and obtain the optimized fracturing and filling construction parameters.
[0108] The fracturing and filling construction parameter optimization device provided by the embodiment of the present invention corrects the reservoir physical property data in the target area according to the logging data of the well to be fracturing and filling, and obtains physical property data; determines the production master control parameters affecting the production according to the physical property data, the engineering operation data and the production data in the target area; uses the production master control parameters and the production data as sample data to train a deep learning model to obtain a production prediction model; determines the initialization conditions according to the engineering operation data, the physical property data and the production data, takes the physical property data as a constraint, takes the production prediction model and a pre-established cost calculation model as the objective function, takes high production and low cost as the desired goals, and obtains the optimized fracturing and filling construction parameters, so as to obtain the optimized fracturing and filling construction parameters.
[0109] The embodiment of the device for optimizing fracturing and filling construction parameters provided by the embodiment of the present invention can be specifically used to execute the processing flow of the above-mentioned method embodiments. Its functions are not described in detail here, and reference can be made to the detailed description of the above-mentioned method embodiments.
[0110] Figure 5 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as Figure 5 As shown, the electronic device includes: a processor (processor) 501, a memory (memory) 502 and a bus 503;
[0111] The processor 501 and the memory 502 communicate with each other via a bus 503;
[0112] The processor 501 is used to call the program instructions in the memory 502 to execute the methods provided by the above method embodiments, for example, including:
[0113] Correct the reservoir physical property data in the target area according to the logging data of the well to be fractured and filled, and obtain the physical property data;
[0114] Determining a primary control parameter of production that affects production based on the physical property data, engineering operation data in the target area, and production data;
[0115] Using the production master control parameters and the production data as sample data, training a deep learning model to obtain a production prediction model;
[0116] Initialization conditions are determined based on the engineering operation data, the physical property data and the production data, the physical property data is used as a constraint, the production prediction model and the pre-established cost calculation model are used as objective functions, and high production and low cost are used as desired goals to obtain optimized fracturing and filling construction parameters.
[0117] This embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can perform the methods provided by the above method embodiments, for example, including:
[0118] Correct the reservoir physical property data in the target area according to the logging data of the well to be fractured and filled, and obtain the physical property data;
[0119] Determining a primary control parameter of production that affects production based on the physical property data, engineering operation data in the target area, and production data;
[0120] Using the production master control parameters and the production data as sample data, training a deep learning model to obtain a production prediction model;
[0121] Initialization conditions are determined based on the engineering operation data, the physical property data and the production data, the physical property data is used as a constraint, the production prediction model and the pre-established cost calculation model are used as objective functions, and high production and low cost are used as desired goals to obtain optimized fracturing and filling construction parameters.
[0122] This embodiment provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program enables the computer to execute the methods provided by the above method embodiments, for example, including:
[0123] Correct the reservoir physical property data in the target area according to the logging data of the well to be fractured and filled, and obtain the physical property data;
[0124] Determining a primary control parameter of production that affects production based on the physical property data, engineering operation data in the target area, and production data;
[0125] Using the production master control parameters and the production data as sample data, training a deep learning model to obtain a production prediction model;
[0126] Initialization conditions are determined based on the engineering operation data, the physical property data and the production data, the physical property data is used as a constraint, the production prediction model and the pre-established cost calculation model are used as objective functions, and high production and low cost are used as desired goals to obtain optimized fracturing and filling construction parameters.
[0127] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0128] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0129] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0130] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0131] In the description of this specification, the description with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0132] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A method for optimizing fracturing and filling construction parameters, characterized in that: include: Correct the reservoir physical property data in the target area according to the logging data of the well to be fractured and filled, and obtain the physical property data; Determining a primary control parameter of production that affects production based on the physical property data, engineering operation data in the target area, and production data; Using the production master control parameters and the production data as sample data, training a deep learning model to obtain a production prediction model; Determine initialization conditions according to the engineering operation data, the physical property data and the production data, take the physical property data as constraints, use the production prediction model and the pre-established cost calculation model as objective functions, take high production and low cost as desired goals, and obtain optimized fracturing and filling construction parameters; Determining the main production control parameters affecting the production according to the physical property data, the engineering operation data and the production data in the target area includes: Calculate the correlation coefficients between the physical property data and the engineering operation data and the production data respectively based on a correlation analysis algorithm; The target physical property data and target engineering operation data serving as the main control parameters of the production are screened in descending order of correlation coefficients.
2. The method for optimizing fracturing and filling construction parameters according to claim 1, characterized in that: The method of correcting the reservoir physical property data in the target area according to the logging data of the well to be fractured and filled to obtain the physical property data includes: The pre-established three-dimensional reservoir geological model is modified according to the logging data of the well to be fractured and filled to obtain the physical property data.
3. The method for optimizing fracturing and filling construction parameters according to claim 2, characterized in that: The pre-established three-dimensional reservoir geological model includes: The three-dimensional geological model of the reservoir is established based on the interpolation method.
4. The method for optimizing fracturing and filling construction parameters according to claim 1, characterized in that: The target physical property data and target engineering operation data as the main control parameters of the production are obtained by screening in descending order of correlation coefficients, including: A preset number of physical property data and engineering operation data are selected from the sequential sequence as the target physical property data and the target engineering operation data.
5. The method for optimizing fracturing and filling construction parameters according to any one of claims 1 to 4, characterized in that: The determining of the initialization condition according to the engineering operation data, the physical property data and the production data comprises: Determining a fracturing and filling construction parameter space to be optimized according to the engineering operation data; The fracturing and filling construction parameters in the engineering operation data are initialized and assigned in the fracturing and filling construction parameter space, and the physical property data and the production data are initialized and assigned.
6. The method for optimizing fracturing and filling construction parameters according to any one of claims 1 to 4, characterized in that: The method uses the physical property data as constraints, the production prediction model and the pre-established cost calculation model as objective functions, and high production and low cost as desired goals to obtain optimized fracturing and filling construction parameters, including: According to the multi-objective optimization algorithm, the physical property data is used as a known constant condition, and the optimized fracturing and filling construction parameters are continuously updated according to the production prediction results and the cost calculation results until the global optimum or the maximum number of iterations is reached, thereby obtaining the optimized fracturing and filling construction parameters.
7. A device for optimizing fracturing and filling construction parameters, characterized in that: include: An acquisition unit, used to correct the reservoir physical property data in the target area according to the logging data of the well to be fractured and filled, and obtain physical property data; A determination unit, configured to determine a production master control parameter affecting production according to the physical property data, the engineering operation data in the target area and the production data; A training unit, used to use the production master control parameters and the production data as sample data to train a deep learning model to obtain a production prediction model; An optimization unit is used to determine initialization conditions according to the engineering operation data, the physical property data and the production data, take the physical property data as constraints, use the production prediction model and the pre-established cost calculation model as objective functions, and take high production and low cost as desired goals to obtain optimized fracturing and filling construction parameters; The determining unit is specifically used for: Calculate the correlation coefficients between the physical property data and the engineering operation data and the production data respectively based on a correlation analysis algorithm; The target physical property data and target engineering operation data serving as the main control parameters of the production are screened in descending order of correlation coefficients.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.