Production dynamic data prediction method and device, equipment and storage medium
By acquiring reservoir attribute data and combining data adjustment models and pre-trained prediction models, the problems of low prediction accuracy of production dynamic data and low fitting efficiency of geological models in the prior art are solved, and more efficient and reliable prediction results are achieved .
Patent Information
- Application Number
- CN202311062751.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-22
- Publication Date
- 2025-02-25
AI Technical Summary
When predicting the production dynamic data of underground oil and gas reservoirs, the prior art has low accuracy and low geological model fitting efficiency, resulting in an increased risk of well drilling and development of oil and gas reservoirs.
By obtaining reservoir attribute data of the target reservoir, combining the data adjustment model and the pre-trained prediction model, the prediction results of production dynamic data are determined. The method includes obtaining reservoir attribute data, such as porosity, permeability, etc., adjusting the data using particle swarm optimization algorithm, and predicting it through a pre-trained neural network model.
It improves the prediction accuracy of production dynamic data and the fitting efficiency of geological models, and reduces the risk of well drilling and development of oil and gas reservoirs.
Smart Images
Figure CN119514742A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device, electronic device and storage medium for predicting production dynamic data. Background Art
[0002] At present, for underground oil and gas reservoirs, reservoir researchers can usually only use limited information such as core data, seismic data and logging data, and use geostatistical methods to establish a large number of equiprobable random three-dimensional geological models to predict production dynamic data.
[0003] However, there is usually a large deviation between the randomly established three-dimensional geological model and the actual situation of the oil and gas reservoir, which in turn increases the risk of drilling and development of the oil and gas reservoir. Therefore, how to efficiently and accurately predict production dynamic data is an urgent problem to be solved. Summary of the invention
[0004] The present invention provides a prediction method, device, equipment and storage medium for production dynamic data to solve the problems of low prediction accuracy of production dynamic data and low fitting efficiency of geological models. It can improve the prediction reliability of production dynamic data while improving the fitting efficiency of geological models.
[0005] According to one aspect of the present invention, a method for predicting production dynamic data is provided, the method comprising:
[0006] Acquire reservoir property data of the target reservoir; wherein the reservoir property data includes at least one of porosity, permeability, saturation, relative permeability and rock compressibility;
[0007] The prediction results of production performance data are determined based on reservoir attribute data, data adjustment models and pre-trained prediction models.
[0008] According to another aspect of the present invention, there is provided a device for predicting production dynamic data, the device comprising:
[0009] A reservoir attribute data acquisition module, used to acquire reservoir attribute data of a target reservoir; wherein the reservoir attribute data includes at least one of porosity, permeability, saturation, relative permeability and rock compressibility;
[0010] The prediction result determination module is used to determine the prediction result of production dynamic data based on reservoir attribute data, data adjustment model and pre-trained prediction model.
[0011] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0012] at least one processor; and
[0013] a memory communicatively connected to the at least one processor; wherein,
[0014] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting production dynamic data described in any embodiment of the present invention.
[0015] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting production dynamic data described in any embodiment of the present invention when executed.
[0016] The technical solution of the embodiment of the present invention obtains the reservoir attribute data of the target reservoir, and determines the prediction result of the production dynamic data according to the reservoir attribute data, the data adjustment model and the pre-trained prediction model. The technical solution solves the problems of low prediction accuracy of production dynamic data and low fitting efficiency of geological models, and can improve the prediction reliability of production dynamic data while improving the fitting efficiency of geological models.
[0017] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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.
[0019] Figure 1 is a flow chart of a method for predicting production dynamic data provided according to Embodiment 1 of the present invention;
[0020] Figure 2 is a flow chart of a method for predicting production dynamic data provided according to Embodiment 2 of the present invention;
[0021] Figure 3 is a schematic diagram of the structure of a device for predicting production dynamic data provided according to Embodiment 3 of the present invention;
[0022] Figure 4 It is a schematic diagram of the structure of an electronic device for implementing the method for predicting production dynamic data according to an embodiment of the present invention. DETAILED DESCRIPTION
[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.
[0025] Embodiment 1
[0026] Figure 1 A flowchart of a method for predicting production dynamic data is provided for the first embodiment of the present invention. This embodiment can be applied to scenarios such as prediction of production dynamic data and reservoir fitting. The method can be executed by a prediction device for production dynamic data, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. Figure 1 As shown, the method includes:
[0027] S110, obtaining reservoir attribute data of the target reservoir.
[0028] This solution can be executed by electronic devices such as computers and servers, and the electronic devices can obtain reservoir property data of the target reservoir through the drilling information platform. The target reservoir can be a reservoir that needs to be predicted for production dynamic data. The reservoir property data can include one or more of porosity, permeability, saturation, relative permeability and rock compressibility.
[0029] S120, determining the prediction result of the production dynamic data according to the reservoir attribute data, the data adjustment model and the pre-trained prediction model.
[0030] The electronic device can perform preprocessing such as abnormal data removal, normalization and standardization on the reservoir attribute data. The target reservoir may include multiple wells, each of which may correspond to a set of reservoir attributes. Based on the preprocessed reservoir attribute data, the electronic device can generate a reservoir parameter vector matching each well. The reservoir parameter vector is input into the data adjustment model, and the data adjustment model can optimize and adjust the reservoir parameter vector. The optimized reservoir parameter vector is input into the prediction model to obtain the prediction result of the production dynamic data.
[0031] The data adjustment model can be constructed based on particle swarm, genetic and other optimization algorithms. The prediction model can be obtained by training a pre-built neural network based on the reservoir attribute data and production dynamic data of the produced reservoir. The production dynamic data can include the oil production per unit period of each oil well, such as the daily oil production of each oil well.
[0032] The technical solution of the embodiment of the present invention obtains the reservoir attribute data of the target reservoir, and determines the prediction result of the production dynamic data according to the reservoir attribute data, the data adjustment model and the pre-trained prediction model. The technical solution solves the problems of low prediction accuracy of production dynamic data and low fitting efficiency of geological models, and can improve the prediction reliability of production dynamic data while improving the fitting efficiency of geological models.
[0033] Embodiment 2
[0034] Figure 2 This is a flowchart of a method for predicting production dynamic data provided by Embodiment 2 of the present invention. This embodiment is based on the above embodiment and is refined. Figure 2 As shown, the method includes:
[0035] S210, obtaining reservoir attribute data of the target reservoir.
[0036] In this solution, the reservoir property data includes at least one of porosity, permeability, saturation, relative permeability and rock compressibility.
[0037] S220, inputting the reservoir attribute data into the data adjustment model to obtain the adjustment result of the reservoir attribute data.
[0038] In a feasible solution, the reservoir property data includes at least one reservoir parameter vector;
[0039] The step of inputting the reservoir attribute data into the data adjustment model to obtain the adjustment result of the reservoir attribute data includes:
[0040] Based on Latin hypercube sampling, a preset number of particle vectors matching each reservoir parameter vector are determined;
[0041] Determine the fitness of each particle vector, and determine the target position of each particle vector according to the fitness of each particle vector;
[0042] Determine the target position of the particle group according to the target position of each particle vector;
[0043] If the target position of the particle group meets the preset adjustment standard, the adjustment result of each reservoir parameter vector is determined according to the target position of the particle group;
[0044] If the target position of the particle swarm does not meet the preset adjustment standard, each particle vector is updated according to the preset particle update principle, and the execution is returned to determine the fitness of each particle vector.
[0045] The electronic device can count each reservoir attribute value in each reservoir parameter vector to determine the value range of each reservoir attribute value. According to the value range of each reservoir attribute value, based on Latin hypercube sampling, a preset number of particle vectors matching each reservoir parameter vector are generated. For example, according to the number N of reservoir parameter vectors, the value range of each reservoir attribute value is evenly divided into N sub-intervals, and random sampling is performed in each sub-interval with uniform distribution to obtain the number of particles matching each reservoir parameter vector.
[0046] According to the pre-set fitness function, the electronic device can calculate the fitness of each particle vector, and determine the target position of each particle vector according to the fitness of each particle vector. Specifically, the electronic device can evaluate the fitness of this iteration, determine the optimal position in the position data of each particle vector in previous iterations, and use the optimal position as the target position. According to the target position of each particle vector, the electronic device can calculate the optimal position of the entire particle group, that is, the target position of the particle group.
[0047] If the target position of the particle swarm meets the preset adjustment standard, the adjustment result of each reservoir parameter vector is determined according to the target position of the particle swarm. If the target position of the particle swarm does not meet the preset adjustment standard, each particle vector is updated according to the particle speed and particle position according to the preset particle update principle, and the fitness of each particle vector is determined again until the target position of the particle swarm meets the preset adjustment standard. According to the target position of the particle swarm, the adjustment result of each reservoir parameter vector is output. It should be noted that the adjustment standard can be that the parameter adjustment error is less than the preset error threshold, or that the fitness meets the preset fitness threshold.
[0048] Before predicting production dynamic data, this scheme uses the particle swarm optimization algorithm to tune the reservoir parameter vector, which can reduce the adverse effects of reservoir attribute data uncertainty on production dynamic data prediction, thereby improving the accuracy of production dynamic data prediction.
[0049] S230: Input the adjustment result into the prediction model to determine the prediction result of the production dynamic data.
[0050] In this solution, optionally, the training process of the prediction model includes:
[0051] Acquire reservoir property data and production performance data of a produced reservoir; wherein the reservoir property data includes a plurality of reservoir parameter vectors;
[0052] Taking each reservoir parameter vector as the input of the pre-built prediction network in turn, and training the prediction network at least once iteratively according to the output of the prediction network and the production dynamic data matched by each reservoir parameter vector, to obtain a candidate model matched by each iteration;
[0053] The prediction model is determined based on the candidate models matched in each iteration.
[0054] It is easy to understand that the electronic device can obtain the reservoir property data and production dynamic data of the produced reservoir. The reservoir property data of the produced reservoir can include multiple reservoir parameter vectors. It should be noted that each group of reservoir property data can correspond to a group of production dynamic data. Each reservoir parameter vector is used as the input of the pre-built prediction network in turn to obtain the prediction result of the production dynamic data output by the prediction network. Among them, the prediction network can be built based on a neural network, and the prediction network can include at least one fully connected layer, each fully connected layer can include at least two neurons, and the number of neurons in each fully connected layer can be the same or different.
[0055] The output of the prediction network is compared with the production dynamic data matched with each reservoir parameter vector, the loss error is calculated, and the prediction network is iteratively trained at least once according to the loss error to obtain the candidate model matched in each iteration. According to the candidate model matched in each iteration, the electronic device can determine the prediction model. Specifically, the electronic device can pre-set the number of iterations and use the candidate model matched in the last iteration as the prediction model, or set the model evaluation index and use the candidate model that meets the model evaluation index as the prediction model.
[0056] In a specific example, the prediction network includes three fully connected layers, the three fully connected layers can be connected sequentially, the first fully connected layer and the second fully connected layer include an activation function, and the activation function can be a hyperbolic tangent function. The third fully connected layer includes a loss function, and the loss function is used to calculate the loss error. The calculation formula of the loss error can be expressed as:
[0057]
[0058] Where i represents the reservoir parameter vector index, n represents the number of reservoir parameter vectors, and d pred-irepresents the output vector of the prediction network corresponding to the reservoir parameter vector i, d ture-i The representation vector of production dynamic data corresponding to reservoir parameter vector i, L d Denotes the dimension of the representation vector.
[0059] In a preferred embodiment, before determining a preset number of particle vectors matching each reservoir parameter vector, the method includes:
[0060] Normalize each reservoir parameter vector;
[0061] Accordingly, before taking each reservoir parameter vector as the input of the pre-built prediction network in turn, the method further includes:
[0062] Each reservoir parameter vector is normalized.
[0063] In order to avoid the influence of singular sample data on the prediction model and speed up the convergence of the prediction model, in the training stage of the prediction model, before determining the preset number of particle vectors that match each reservoir parameter vector, the electronic device can normalize each reservoir parameter vector. Correspondingly, in the application stage of the prediction model, before taking each reservoir parameter vector as the input of the pre-built prediction network in turn, the electronic device also needs to normalize each reservoir parameter vector.
[0064] Based on the above solution, optionally, the normalization process of each reservoir parameter vector includes:
[0065] According to each reservoir parameter vector, determine the maximum value and average value of each reservoir parameter;
[0066] According to the average value of each reservoir parameter, each reservoir parameter vector is decomposed into an average value vector and a deviation value vector;
[0067] According to the deviation value vector of each reservoir parameter vector and the maximum value of each reservoir parameter, each reservoir parameter vector is normalized to obtain the normalized processing result of each reservoir parameter vector.
[0068] It can be understood that the electronic device can perform statistics on the reservoir parameter values in each reservoir parameter vector to determine statistical indicators such as the maximum value, minimum value and average value of each reservoir parameter. According to the average value of each reservoir parameter, the electronic device can generate an average value vector. According to the average value vector and each reservoir parameter vector, the deviation value vector matching each reservoir parameter vector can be calculated, that is, each reservoir parameter vector is decomposed into the form of the sum of the average value vector and the deviation value vector. It should be noted that the deviation value vector includes the deviation value of each reservoir parameter value in the reservoir parameter vector and the matched average value. According to the deviation value vector of each reservoir parameter vector and the maximum value of each reservoir parameter, the electronic device can perform normalization processing on each reservoir parameter vector to obtain the normalization processing result of each reservoir parameter vector.
[0069] Optionally, the extreme value includes a maximum value and a minimum value; the calculation expression of the normalization processing is:
[0070]
[0071] in, represents the normalized value of reservoir parameter P in reservoir parameter vector m, Δm P represents the deviation value of reservoir parameter P matching in reservoir parameter vector m, P max represents the maximum value of reservoir parameter P, P min Represents the minimum value of reservoir parameter P.
[0072] The normalization processing method of the above scheme is conducive to avoiding the influence of abnormal data in the reservoir parameter vector on the prediction model training and production dynamic data prediction, improving the convergence efficiency of the prediction model, and ensuring the accuracy of production dynamic data prediction.
[0073] The technical solution of the embodiment of the present invention obtains the reservoir attribute data of the target reservoir, and determines the prediction result of the production dynamic data according to the reservoir attribute data, the data adjustment model and the pre-trained prediction model. The technical solution solves the problems of low prediction accuracy of production dynamic data and low fitting efficiency of geological models, and can improve the prediction reliability of production dynamic data while improving the fitting efficiency of geological models.
[0074] Embodiment 3
[0075] Figure 3 This is a schematic diagram of the structure of a prediction device for production dynamic data provided by the third embodiment of the present invention. Figure 3 As shown, the device comprises:
[0076] The reservoir attribute data acquisition module 310 is used to acquire the reservoir attribute data of the target reservoir; wherein the reservoir attribute data includes at least one of porosity, permeability, saturation, relative permeability and rock compressibility;
[0077] The prediction result determination module 320 is used to determine the prediction result of the production performance data according to the reservoir attribute data, the data adjustment model and the pre-trained prediction model.
[0078] In this solution, optionally, the prediction result determination module 320 includes:
[0079] An adjustment result determination unit, used for inputting the reservoir attribute data into the data adjustment model to obtain an adjustment result of the reservoir attribute data;
[0080] The prediction result determination unit is used to input the adjustment result into the prediction model to determine the prediction result of the production dynamic data.
[0081] In a feasible solution, the reservoir property data includes at least one reservoir parameter vector;
[0082] The adjustment result determination unit is specifically used to:
[0083] Based on Latin hypercube sampling, a preset number of particle vectors matching each reservoir parameter vector are determined;
[0084] Determine the fitness of each particle vector, and determine the target position of each particle vector according to the fitness of each particle vector;
[0085] Determine the target position of the particle group according to the target position of each particle vector;
[0086] If the target position of the particle group meets the preset adjustment standard, the adjustment result of each reservoir parameter vector is determined according to the target position of the particle group;
[0087] If the target position of the particle swarm does not meet the preset adjustment standard, each particle vector is updated according to the preset particle update principle, and the execution is returned to determine the fitness of each particle vector.
[0088] In this embodiment, optionally, the device further includes a prediction model training module, and the prediction model training module is specifically used to:
[0089] Acquire reservoir property data and production performance data of a produced reservoir; wherein the reservoir property data includes a plurality of reservoir parameter vectors;
[0090] Taking each reservoir parameter vector as the input of the pre-built prediction network in turn, and training the prediction network at least once iteratively according to the output of the prediction network and the production dynamic data matched by each reservoir parameter vector, to obtain a candidate model matched by each iteration;
[0091] The prediction model is determined based on the candidate models matched in each iteration.
[0092] Based on the above solution, optionally, the device further includes a normalization processing module, and the normalization processing module is used to:
[0093] Before determining a preset number of particle vectors matching each reservoir parameter vector and before sequentially using each reservoir parameter vector as an input to a pre-built prediction network, each reservoir parameter vector is normalized.
[0094] In a preferred solution, the normalization processing module is specifically used to:
[0095] According to each reservoir parameter vector, determine the maximum value and average value of each reservoir parameter;
[0096] According to the average value of each reservoir parameter, each reservoir parameter vector is decomposed into an average value vector and a deviation value vector;
[0097] According to the deviation value vector of each reservoir parameter vector and the maximum value of each reservoir parameter, each reservoir parameter vector is normalized to obtain the normalized processing result of each reservoir parameter vector.
[0098] Based on the above solution, optionally, the maximum value includes a maximum value and a minimum value; and the calculation expression of the normalization processing is:
[0099]
[0100] in, represents the normalized value of reservoir parameter P in reservoir parameter vector m, Δm P represents the deviation value of reservoir parameter P matching in reservoir parameter vector m, P max represents the maximum value of reservoir parameter P, P min Represents the minimum value of reservoir parameter P.
[0101] The production dynamic data prediction device provided in the embodiment of the present invention can execute the production dynamic data prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0102] Embodiment 4
[0103] Figure 4A schematic diagram of an electronic device 410 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0104] like Figure 4 As shown, the electronic device 410 includes at least one processor 411, and a memory connected to the at least one processor 411 in communication, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 to the random access memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.
[0105] Multiple components in the electronic device 410 are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, a mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, an optical disk, etc.; and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the electronic device 410 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0106] The processor 411 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 411 executes the various methods and processes described above, such as a prediction method for producing dynamic data.
[0107] In some embodiments, the prediction method of production dynamics data may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the prediction method of production dynamics data described above may be performed. Alternatively, in other embodiments, the processor 411 may be configured to execute the prediction method of production dynamics data in any other appropriate manner (e.g., by means of firmware).
[0108] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0109] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable prediction device for producing dynamic data, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed completely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or completely on a remote machine or server.
[0110] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0111] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0112] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0113] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0114] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0115] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for predicting production dynamic data, characterized in that: The method comprises: Acquire reservoir property data of the target reservoir; wherein the reservoir property data includes at least one of porosity, permeability, saturation, relative permeability and rock compressibility; The prediction results of production performance data are determined based on reservoir attribute data, data adjustment models and pre-trained prediction models.
2. The method according to claim 1, characterized in that Determining the prediction result of production performance data according to the reservoir attribute data, the data adjustment model and the pre-trained prediction model includes: Inputting the reservoir attribute data into the data adjustment model to obtain the adjustment result of the reservoir attribute data; The adjustment results are input into the forecasting model to determine the forecast results of production dynamics data.
3. The method according to claim 2, characterized in that The reservoir property data includes at least one reservoir parameter vector; The step of inputting the reservoir attribute data into the data adjustment model to obtain the adjustment result of the reservoir attribute data includes: Based on Latin hypercube sampling, a preset number of particle vectors matching each reservoir parameter vector are determined; Determine the fitness of each particle vector, and determine the target position of each particle vector according to the fitness of each particle vector; Determine the target position of the particle group according to the target position of each particle vector; If the target position of the particle group meets the preset adjustment standard, the adjustment result of each reservoir parameter vector is determined according to the target position of the particle group; If the target position of the particle swarm does not meet the preset adjustment standard, each particle vector is updated according to the preset particle update principle, and the execution is returned to determine the fitness of each particle vector.
4. The method according to claim 3, characterized in that: The training process of the prediction model includes: Acquire reservoir property data and production performance data of a produced reservoir; wherein the reservoir property data includes a plurality of reservoir parameter vectors; Taking each reservoir parameter vector as the input of the pre-built prediction network in turn, and training the prediction network at least once iteratively according to the output of the prediction network and the production dynamic data matched by each reservoir parameter vector, to obtain a candidate model matched by each iteration; The prediction model is determined based on the candidate models matched in each iteration.
5. The method according to claim 4, characterized in that Before determining a preset number of particle vectors matching each reservoir parameter vector, the method includes: Normalize each reservoir parameter vector; Accordingly, before taking each reservoir parameter vector as the input of the pre-built prediction network in turn, the method further includes: Each reservoir parameter vector is normalized.
6. The method according to claim 5, characterized in that The normalization process of each reservoir parameter vector includes: According to each reservoir parameter vector, determine the maximum value and average value of each reservoir parameter; According to the average value of each reservoir parameter, each reservoir parameter vector is decomposed into an average value vector and a deviation value vector; According to the deviation value vector of each reservoir parameter vector and the maximum value of each reservoir parameter, each reservoir parameter vector is normalized to obtain the normalized processing result of each reservoir parameter vector.
7. The method according to claim 6, characterized in that The extreme value includes the maximum value and the minimum value; the calculation expression of the normalization processing is: in, represents the normalized value of reservoir parameter P in reservoir parameter vector m, Δm P represents the deviation value of reservoir parameter P matching in reservoir parameter vector m, P max represents the maximum value of reservoir parameter P, P min Represents the minimum value of reservoir parameter P.
8. A prediction device for production dynamic data, characterized in that: include: A reservoir attribute data acquisition module, used to acquire reservoir attribute data of a target reservoir; wherein the reservoir attribute data includes at least one of porosity, permeability, saturation, relative permeability and rock compressibility; The prediction result determination module is used to determine the prediction result of production dynamic data based on reservoir attribute data, data adjustment model and pre-trained prediction model.
9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting production dynamics data according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting production dynamics data according to any one of claims 1 to 7 when executed.