A method for predicting oil recovery rates in oil and gas pipeline networks and related equipment.

Abstract

This application discloses a method and related equipment for predicting the oil production rate of an oil and gas pipeline network. The method includes: acquiring steady-state data and historical dynamic data of the oil and gas pipeline network; preprocessing the steady-state data using a first preprocessing method to obtain processed steady-state data, and preprocessing the historical dynamic data using a second preprocessing method to obtain processed dynamic data; constructing a pipeline network grid model based on the processed steady-state data; acquiring the measured oil production rate of known pipeline nodes in the pipeline network grid model, and obtaining a prediction model based on the measured oil production rate and the processed dynamic data; and using the prediction model to obtain the predicted oil production rate of other pipeline nodes in the pipeline network grid model besides the known pipeline nodes, thereby improving the accuracy of the prediction results and avoiding the situation where all relevant indicators need to be considered, resulting in low prediction accuracy and the inability to control the oil production rate in real time.

Description

Technical Field

[0001] This application relates to the field of oil and gas pipeline technology, and in particular to a method and related equipment for predicting the oil production rate of oil and gas pipelines. Background Technology

[0002] Oil and gas pipeline networks encompass upstream multiphase surface flow, midstream single-phase crude oil / refined oil / natural gas, and downstream urban gas distribution networks. In recent years, driven by the rapid development of technologies such as the Internet, big data, and artificial intelligence, and influenced by both internal demand and external technological factors, the construction of smart pipelines has commenced.

[0003] With the increasing demand for oil and gas extraction in my country, the requirements for controlling the oil production rate are gradually increasing. Current technologies cannot accurately obtain real-time information about the oil and gas pipeline network. When predicting the oil production rate at unknown nodes, all indicators are usually considered, and predictions are typically based on expert experience, resulting in low prediction accuracy and an inability to control the oil production rate in real time.

[0004] Therefore, improving the accuracy of predicting oil recovery rates at unknown nodes is an urgent problem to be solved. Summary of the Invention

[0005] To address the aforementioned issues, embodiments of this application provide a method and apparatus for predicting oil production rates in oil and gas pipeline networks, an electronic device, a computer-readable storage medium, and a computer program product.

[0006] Firstly, in order to solve the above-mentioned technical problems, this application provides a method for predicting the oil production rate of an oil and gas pipeline network, comprising:

[0007] Obtain steady-state and historical dynamic data of oil and gas pipeline networks;

[0008] The steady-state data is preprocessed using a first preprocessing method to obtain processed steady-state data, and the historical dynamic data is preprocessed using a second preprocessing method to obtain processed dynamic data.

[0009] A network grid model of the oil and gas pipeline network is constructed based on the processed steady-state data.

[0010] The measured oil production rate of known pipeline nodes in the pipeline network grid model is obtained, and a prediction model is obtained based on the measured oil production rate and the processed dynamic data.

[0011] Using the prediction model, the predicted oil recovery rate of other pipeline nodes in the pipeline grid model, excluding the known pipeline nodes, is obtained.

[0012] The beneficial effects are:

[0013] In the technical solution provided in the embodiments of this application, a pipeline grid model of the oil and gas pipeline network is constructed through preprocessed steady-state data. Then, the measured oil production rate of known pipeline nodes is obtained using the pipeline grid model. Based on the measured oil production rate and the processed dynamic data, a prediction model is obtained to predict the oil production rate. In this way, the accuracy of the prediction results is improved by constructing the prediction model. This avoids the situation where all relevant indicators need to be considered and subjective predictions are made based on expert experience, resulting in low prediction accuracy and the inability to control the oil production rate in real time.

[0014] Secondly, the present invention provides an oil and gas pipeline network oil production rate prediction device, comprising an acquisition unit, a preprocessing unit, a pipeline network model unit, a prediction model unit, and a processing unit;

[0015] The acquisition unit is used to acquire steady-state data and historical dynamic data of the oil and gas pipeline network;

[0016] The preprocessing unit is used to preprocess the steady-state data using a first preprocessing method to obtain processed steady-state data, and to preprocess the historical dynamic data using a second preprocessing method to obtain processed dynamic data.

[0017] Pipeline model unit, used to construct a pipeline grid model of the oil and gas pipeline network based on the processed steady-state data;

[0018] The prediction model unit is used to obtain the measured oil production rate of known pipeline nodes in the pipeline network grid model, and to obtain the prediction model based on the measured oil production rate and the processed dynamic data.

[0019] The processing unit is used to obtain the predicted oil production rate of other pipeline nodes in the pipeline grid model, excluding the known pipeline nodes, using the prediction model.

[0020] Thirdly, this application also provides an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the oil production rate prediction method for oil and gas pipeline networks as described above.

[0021] Fourthly, this application also provides a computer-readable storage medium storing computer-readable instructions thereon, which, when executed by a computer's processor, cause the computer to perform the oil production rate prediction method for oil and gas pipeline networks as described above.

[0022] Fifthly, this application also provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the oil and gas pipeline network oil production rate prediction method provided in the various alternative embodiments described above.

[0023] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0024] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0025] Figure 1 This is a flowchart illustrating an exemplary embodiment of the method for predicting the oil production rate of an oil and gas pipeline network.

[0026] Figure 2 yes Figure 1 A flowchart of step S103 in an exemplary embodiment shown in the illustrated example;

[0027] Figure 3 yes Figure 1 The flowchart of step S102 in the illustrated embodiment, which involves preprocessing historical dynamic data using a second preprocessing method to obtain processed dynamic data, is shown in an exemplary embodiment.

[0028] Figure 4 Is Figure 1 A flowchart of the steps following step S105 in the illustrated embodiment is provided in an exemplary embodiment.

[0029] Figure 5 yes Figure 4 A flowchart of step S402 in an exemplary embodiment shown in the illustrated example;

[0030] Figure 6 yes Figure 1 A flowchart of step S104 in an exemplary embodiment shown in the illustrated example;

[0031] Figure 7 This is a block diagram illustrating an oil and gas pipeline network oil production rate prediction device, as shown in an exemplary embodiment of this application.

[0032] Figure 8 This is a schematic diagram of the structure of a computer system suitable for implementing the electronic devices of the present application embodiments. Detailed Implementation

[0033] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0034] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0035] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0036] In this application, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0037] To address the issue of low prediction accuracy caused by considering all indicators when predicting the oil production rate of unknown nodes and relying on expert experience, this application proposes a method and apparatus for predicting the oil production rate of oil and gas pipeline networks, electronic equipment, and computer-readable storage media. The main focus is on oil production rate prediction technology within oil and gas pipeline network technology, and these embodiments will be described in detail below.

[0038] Please refer to the following first. Figure 1 , Figure 1This is a flowchart illustrating an exemplary embodiment of an oil and gas pipeline network oil recovery rate prediction method. The method can be executed by a server, which can be a standalone server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. No limitation is imposed here.

[0039] like Figure 1 As shown in an exemplary embodiment, the oil production rate prediction method for the oil and gas pipeline network may include steps S101 to S105, which are described in detail below:

[0040] Step S101: Obtain steady-state data and historical dynamic data of the oil and gas pipeline network.

[0041] In the oil and gas pipeline network model, it is necessary to visualize the structure of the oil and gas pipeline network. At the same time, it is necessary to label the real-time oil production rate of important nodes. For nodes where the real-time oil production rate cannot be obtained, it is necessary to predict the real-time oil production rate.

[0042] Therefore, in this embodiment, the prediction model is constructed by acquiring steady-state data and historical dynamic data of the oil and gas pipeline network, thereby predicting the real-time oil production rate.

[0043] Step S102: The steady-state data is preprocessed using the first preprocessing method to obtain the processed steady-state data, and the historical dynamic data is preprocessed using the second preprocessing method to obtain the processed dynamic data.

[0044] In the embodiments of this application, steady-state data is characterized as fixed and unchanging pipeline-related data, such as pipeline size, pipeline location data, map data, etc. Historical dynamic data is characterized as historical pipeline-related data that can change at any time, such as reservoir seepage velocity, water cut and water cut rise rate, temperature, real-time geological conditions, pressure, etc.

[0045] Preferably, for historical dynamic data, since there are too many related data types, the prediction accuracy of real-time oil production rate will be reduced. Therefore, it is necessary to use a first preprocessing method and a second preprocessing method adapted to steady-state data and dynamic data respectively to preprocess the data so that the processed dynamic data can be applied to the construction of pipeline grid model and prediction model.

[0046] Step S103: Based on the processed steady-state data, construct the pipeline grid model of the oil and gas pipeline network.

[0047] Step S104: Obtain the measured oil production rate of known pipeline nodes in the pipeline grid model, and obtain the prediction model based on the measured oil production rate and the processed dynamic data.

[0048] After constructing the pipeline network grid model, the measured oil production rate of the known pipeline nodes in the pipeline network grid model is obtained. Based on the measured oil production rate and the processed dynamic data, a prediction model is obtained. The constructed prediction model is used to predict the oil production rate of other unknown pipeline nodes in the pipeline network grid model, excluding the known pipeline nodes.

[0049] Step S105: Using the prediction model, obtain the predicted oil production rate of other pipeline nodes in the pipeline grid model, excluding the known pipeline nodes.

[0050] As can be seen from the above, in the method provided in this embodiment, preprocessing is performed using a preprocessing method adapted to steady-state data and dynamic data. The preprocessed steady-state data is used to construct a pipeline grid model of the oil and gas pipeline network. Then, the measured oil production rate of known pipeline nodes is obtained using the pipeline grid model. Based on the measured oil production rate and the processed dynamic data, a prediction model is obtained to predict the oil production rate. In this way, the accuracy of the prediction results is improved by constructing the prediction model. This avoids the situation where all relevant indicators need to be considered and subjective predictions are made using expert experience, resulting in low prediction accuracy and the inability to control the oil production rate in real time.

[0051] In an exemplary embodiment provided in this application, a first preprocessing method is implemented for steady-state data by organizing and supplementing missing values ​​and outliers, and removing outlier data. Specifically, it can be determined whether there are missing data in the steady-state data, and if so, the missing data is supplemented; it can also be determined whether there are outliers in the steady-state data, and if so, the outlier data is removed.

[0052] In another exemplary embodiment, the steady-state data includes pipeline size, pipeline location data, and map data. See also... Figure 2 , Figure 2 yes Figure 1 The flowchart of step S103 in the illustrated embodiment is shown in an exemplary embodiment. Figure 2 As shown, step S103 may specifically include steps S201 to S203, through which a pipeline grid model of the oil and gas pipeline network is constructed, as detailed below:

[0053] Step S201: Based on pipeline size, pipeline location data and map data, obtain the target area where the oil and gas pipeline network is located.

[0054] Step S202: Divide the target area into several sub-regions, and obtain the topology layer and path layer of the oil and gas pipeline network based on the sub-regions.

[0055] Step S203: Obtain the pipeline network mesh model of the oil and gas pipeline network based on the topology layer and the path layer.

[0056] In this embodiment, the geographical location of the oil and gas pipeline network is determined based on the steady-state data, including pipeline size, pipeline location data, and map data, thereby obtaining the target area where the oil and gas pipeline network is located. Then, the target area is divided into several sub-regions, and corresponding grid images are generated based on the sub-regions. The grid image is an image after adding grids to the target area, and the grid image includes two layers: the upper layer is a topology layer used to represent the topology of the pipeline network, and the lower layer is a path layer used to represent the connection paths between nodes. Thus, the pipeline network grid model of the oil and gas pipeline network is obtained based on the topology layer and the path layer.

[0057] Please see Figure 3 , Figure 3 yes Figure 1 The flowchart of step S102 in the illustrated embodiment, which involves preprocessing historical dynamic data using a second preprocessing method to obtain processed dynamic data, is shown in an exemplary embodiment. For example... Figure 3 As shown, it may specifically include steps S301 to S303, which are described in detail below:

[0058] Step S301: Divide the historical dynamic data according to the pipeline node to which the historical dynamic data belongs to obtain multiple sets of dynamic data.

[0059] Historical dynamic data is acquired and classified according to the network nodes to which it belongs. That is, historical dynamic data belonging to the same network node are of the same type, resulting in multiple sets of dynamic data. The same set of historical dynamic data corresponds to the same network node.

[0060] Step S302: Obtain multiple mean squared errors corresponding to multiple sets of dynamic data, sort the multiple mean squared errors according to preset sorting rules, and obtain a mean squared error queue.

[0061] Determine whether all types of dynamic data have been extracted. If so, calculate the mean square error for each set of dynamic data, and the number of mean square errors is equal to the number of sets of dynamic data. Otherwise, continue to acquire historical dynamic data corresponding to each pipeline node.

[0062] After obtaining all the mean squared errors, sort the multiple mean squared errors according to the preset sorting rules to obtain the mean squared error queue. The preset sorting rules can be to sort the mean squared errors in ascending order.

[0063] Step S303: Obtain a preset number of target mean square deviations from the mean square deviation queue, and use the historical dynamic data corresponding to the target mean square deviations as the processed dynamic data.

[0064] Preferably, a predetermined number of mean squared errors, such as three, from the beginning to the end in the mean squared error queue are taken as the target mean squared error, and the dynamic data type corresponding to the target mean squared error is obtained as the preprocessed dynamic data type.

[0065] Thus, in this embodiment, for historical dynamic data, the historical dynamic data of all data types according to the pipeline nodes are calculated and sorted according to weights, thereby filtering out data that is more correlated with the prediction accuracy and improving the accuracy of the prediction model built on the processed dynamic data.

[0066] In one exemplary embodiment provided in this application, after obtaining the predicted oil production rates of pipeline nodes other than known pipeline nodes in the pipeline grid model, the data for each node is stored. Please refer to... Figure 4 , Figure 4 Is Figure 1 The steps following step S105 in the illustrated embodiment are shown in a flowchart of an exemplary embodiment. (See flowchart for example.) Figure 4 As shown, it can specifically include steps S401 to S402, through which various data are stored and used for data annotation of pipeline nodes in the pipeline network mesh model, as detailed below:

[0067] Step S401: Obtain other dynamic data from the historical dynamic data, excluding the processed dynamic data.

[0068] In this embodiment, when preprocessing historical dynamic data using the second preprocessing method, the historical dynamic data is divided according to the pipeline network node to which it belongs, resulting in multiple sets of dynamic data. Multiple mean square deviations corresponding to the multiple sets of dynamic data are obtained, and the multiple mean square deviations are sorted according to a preset arrangement rule to obtain a mean square deviation queue. A preset number of target mean square deviations are obtained from the mean square deviation queue, and the dynamic data corresponding to the target mean square deviations are used as the processed dynamic data. In this way, the historical dynamic data of the oil and gas pipeline network initially obtained is divided into two parts, including the processed dynamic data and other dynamic data other than the processed dynamic data.

[0069] In step S402, according to the preset storage rules, the processed steady-state data, processed dynamic data, other dynamic data, measured oil production rate and predicted oil production rate are stored for visualization.

[0070] In another exemplary embodiment, the preset storage rules are implemented based on the mapping relationship between various data items and network nodes. Please refer to [link / reference]. Figure 5 , Figure 5 yes Figure 4 The flowchart of step S402 in the illustrated embodiment is shown in an exemplary embodiment. Figure 5As shown, step S402 may specifically include steps S501 to S502, which are described in detail below:

[0071] Step S501: Obtain the preset processed steady-state data, processed dynamic data, other dynamic data, measured oil production rate and predicted oil production rate and the mapping relationship between pipeline nodes in the pipeline grid model.

[0072] Step S502: Based on the mapping relationship, store and process the processed steady-state data, processed dynamic data, other dynamic data, measured oil production rate and predicted oil production rate, as well as the mapping relationship.

[0073] Preferably, a mapping table is pre-set in the database. This mapping table represents the mapping relationship between the processed steady-state data, processed dynamic data, other dynamic data and pipeline nodes. Therefore, when storing and processing the steady-state data, processed dynamic data and other dynamic data, the corresponding mapping relationship can be obtained from the database. The processed steady-state data, processed dynamic data and other dynamic data are stored with the pipeline node as the root, and their mapping relationship is also stored.

[0074] For the measured and predicted oil recovery rates, the correspondence between the measured and predicted oil recovery rates and pipeline network nodes is obtained. Based on the correspondence, a mapping relationship between the measured and predicted oil recovery rates and pipeline network nodes is constructed. Therefore, when storing the measured and predicted oil recovery rates, the pipeline network nodes can be used as the roots of the constructed mapping relationship to store the measured and predicted oil recovery rates, and the mapping relationship is also stored.

[0075] The aforementioned steady-state data is used to construct the pipeline network model; the aforementioned other state data is only used for data annotation of pipeline nodes in the pipeline network grid model after storage, and is not used for prediction of oil production rate of unknown nodes; the aforementioned processed steady-state data is used for data annotation of pipeline nodes in the pipeline network grid model, and for prediction of oil production rate of unknown nodes through the prediction model.

[0076] Therefore, the above embodiments obtain the processed steady-state data, processed dynamic data, other dynamic data, measured oil production rate and predicted oil production rate and their corresponding pipeline network nodes, store the data and the mapping relationship, and then visualize the pipeline network grid model based on the obtained processed steady-state data, processed dynamic data, other dynamic data, measured oil production rate and predicted oil production rate.

[0077] Please see Figure 6 , Figure 6 yes Figure 1The flowchart of step S104 in the illustrated embodiment is shown in an exemplary embodiment. Figure 6 As shown, step S104 may include steps S601 to S605, through which a prediction model is constructed, as detailed below:

[0078] Step S601: Input the measured oil recovery rate and the processed dynamic data as the training set into the BP neural network model.

[0079] Step S602: The training set is iteratively processed using at least two sets of convolutional layers and pooling layers of the BP neural network model to obtain the iterative results, and the iterative results are input into the dropout layer of the BP neural network model.

[0080] Preferably, the measured oil recovery rate and the processed dynamic data are used as the training set and input into the first convolutional layer of the BP (backpropagation) neural network model. Convolution operation is performed along the direction of the preset sequence length, and then the output value after convolution is nonlinearly mapped through the activation function. Each sample data in the training set includes input data composed of the measured oil recovery rate and the processed dynamic data, and output data composed of the predicted oil recovery rate of other pipeline nodes.

[0081] The output of the first group of convolutional layers after nonlinear mapping is used as the input of the first group of pooling layers. The maximum value at the corresponding position is obtained through max pooling. Then, the same operation is performed on the maximum value at the corresponding position through the other groups of convolutional and pooling layers in the BP neural network model according to the same logic. The output generated in the previous iteration is input into the dropout layer. Each iteration ignores a part of the network to reduce the mutual dependence between nodes.

[0082] Step S603: The output generated by the discard layer based on the iteration results is fed into the bidirectional long short-term neural network to obtain the output value of the bidirectional long short-term neural network.

[0083] Step S604: Perform nonlinear mapping processing on the output value of the bidirectional long short-term neural network to obtain the output result of the BP neural network.

[0084] Preferably, the output of the discard layer is fed into the bidirectional long short-term memory neural network for a dimensionality transformation. Then, based on the input dimension of the sample, the hidden state and cell state are initialized. The input value, hidden state, and cell state are fed into the bidirectional long short-term memory neural network together. During the data circulation process, selective forgetting and memory are performed through the gating unit. Then, the output value of the bidirectional long short-term memory neural network is nonlinearly mapped using the tanh activation function to obtain the output result of the BP neural network.

[0085] Step S605: Based on the output of the BP neural network model and the reference results corresponding to the training set, a prediction model is obtained.

[0086] As can be seen from the above, in the method provided in this embodiment, a prediction model is obtained by measuring the oil production rate and processing the dynamic data to predict the oil production rate. In this way, the prediction model obtained by the construction improves the accuracy of the prediction results and avoids the situation where all relevant indicators need to be considered and subjective predictions are made based on expert experience, resulting in low prediction accuracy and the inability to control the oil production rate in real time.

[0087] Figure 7 This is a block diagram illustrating an oil and gas pipeline network oil production rate prediction device 700, as shown in an exemplary embodiment of this application. Figure 7 As shown, the device includes:

[0088] Acquisition unit 701 is used to acquire steady-state data and historical dynamic data of oil and gas pipeline networks;

[0089] The preprocessing unit 702 is used to preprocess the steady-state data using a first preprocessing method to obtain processed steady-state data, and to preprocess the historical dynamic data using a second preprocessing method to obtain processed dynamic data.

[0090] Pipeline model unit 703 is used to construct a pipeline mesh model of the oil and gas pipeline network based on the processed steady-state data;

[0091] Prediction model unit 704 is used to obtain the measured oil production rate of known pipeline nodes in the pipeline grid model, and to obtain the prediction model based on the measured oil production rate and the processed dynamic data.

[0092] Processing unit 705 is used to obtain the predicted oil production rate of other pipeline nodes in the pipeline grid model, excluding known pipeline nodes, using the prediction model.

[0093] This device applies the oil production rate prediction method for oil and gas pipeline networks provided in this application. Preprocessing is performed by a preprocessing unit 702 using a preprocessing method adapted to both steady-state and dynamic data. A pipeline network model unit 703 constructs a pipeline network grid model using the preprocessed steady-state data. Then, a prediction model unit 704 uses the pipeline network grid model to obtain the measured oil production rates of known pipeline nodes and obtains a prediction model based on the measured oil production rates and the processed dynamic data. This allows the processing unit 705 to predict the oil production rate. In this way, the accuracy of the prediction results is improved by constructing the prediction model, avoiding the need to consider all relevant indicators and rely on expert experience for subjective prediction, which leads to low prediction accuracy and the inability to control the oil production rate in real time.

[0094] In another exemplary embodiment, the preprocessing unit 702 is further configured to perform missing value supplementation and abnormal data removal processing on the steady-state data to obtain processed steady-state data.

[0095] In another exemplary embodiment, the steady-state data includes pipeline size, pipeline location data, and map data; the pipeline model unit 703 is further used to obtain the target area where the oil and gas pipeline is located based on the pipeline size, pipeline location data, and map data; to divide the target area into sub-regions, and to obtain the topology layer and path layer of the oil and gas pipeline based on the sub-regions; and to obtain the pipeline grid model of the oil and gas pipeline based on the topology layer and path layer.

[0096] In another exemplary embodiment, the preprocessing unit 702 is further configured to divide the historical dynamic data according to the network node to which the historical dynamic data belongs, to obtain multiple sets of dynamic data; obtain multiple mean square deviations corresponding to the multiple sets of dynamic data, sort the multiple mean square deviations according to a preset sorting rule, to obtain a mean square deviation queue; obtain a preset number of target mean square deviations from the mean square deviation queue, and use the historical dynamic data corresponding to the target mean square deviations as the processed dynamic data.

[0097] In another exemplary embodiment, the device further includes:

[0098] The storage unit is used to acquire other dynamic data in the historical dynamic data besides the processed dynamic data; according to the preset storage rules, it stores the processed steady-state data, processed dynamic data, other dynamic data, measured oil production rate and predicted oil production rate for visualization display.

[0099] In another exemplary embodiment, the storage unit is further configured to acquire preset mapping relationships between processed steady-state data, processed dynamic data, other dynamic data, measured oil production rate and predicted oil production rate and pipeline nodes of the pipeline grid model; and to store the processed steady-state data, processed dynamic data, other dynamic data, measured oil production rate and predicted oil production rate and mapping relationships based on the mapping relationships.

[0100] In another exemplary embodiment, the prediction model unit 704 is further configured to input the measured oil recovery rate and the processed dynamic data as a training set into the BP neural network model.

[0101] The training set is iteratively processed using at least two sets of convolutional and pooling layers of a BP neural network model to obtain the iterative results, which are then input into the dropout layer of the BP neural network model. The output generated by the dropout layer based on the iterative results is fed into a bidirectional long short-term neural network to obtain the output value of the bidirectional long short-term neural network. The output value of the bidirectional long short-term neural network is nonlinearly mapped to obtain the output result of the BP neural network. Based on the output result of the BP neural network model and the reference result corresponding to the training set, a prediction model is obtained.

[0102] It should be noted that the oil and gas pipeline network oil production rate prediction device and the oil and gas pipeline network oil production rate prediction method provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the oil and gas pipeline network oil production rate prediction device provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0103] Embodiments of this application also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by one or more processors, enable the electronic device to implement the oil and gas pipeline network oil production rate prediction method provided in the above embodiments.

[0104] Figure 8 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 8 The computer system 800 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0105] like Figure 8 As shown, the computer system 800 includes a Central Processing Unit (CPU) 801, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, based on a program stored in Read-Only Memory (ROM) 802 or a program loaded from storage portion 808 into Random Access Memory (RAM) 803. The RAM 803 also stores various programs and data required for system operation. The CPU 801, ROM 802, and RAM 803 are interconnected via a bus 804. An Input / Output (I / O) interface 805 is also connected to the bus 804.

[0106] The following components are connected to I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to I / O interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 810 as needed so that computer programs read from it can be installed into storage section 808 as needed.

[0107] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by central processing unit (CPU) 801, it performs various functions defined in the system of this application.

[0108] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0109] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0110] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0111] Another aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the oil production rate prediction method for oil and gas pipeline networks as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not incorporated into the electronic device.

[0112] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the oil and gas pipeline network oil production rate prediction method provided in the various embodiments above.

[0113] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for predicting the oil recovery rate of an oil and gas pipeline network, characterized in that, The method includes: The steady-state data and historical dynamic data of the oil and gas pipeline network are obtained. The steady-state data is characterized by fixed and unchanging pipeline network-related data, including pipeline size, pipeline location data, and map data. The historical dynamic data is characterized by historical pipeline network-related data that can change at any time, including reservoir seepage velocity, water cut and water cut rise rate, temperature, real-time geological conditions, and pressure. The steady-state data is preprocessed using a first preprocessing method to obtain processed steady-state data, and the historical dynamic data is preprocessed using a second preprocessing method to obtain processed dynamic data. A network grid model of the oil and gas pipeline network is constructed based on the processed steady-state data. The measured oil production rate of known pipeline nodes in the pipeline network grid model is obtained, and a prediction model is obtained based on the measured oil production rate and the processed dynamic data. Using the prediction model, the predicted oil recovery rate of other pipeline nodes in the pipeline grid model, excluding the known pipeline nodes, is obtained; The step of preprocessing the historical dynamic data using the second preprocessing method to obtain processed dynamic data includes: The historical dynamic data is divided according to the pipeline network node to which it belongs, resulting in multiple sets of dynamic data. Obtain multiple mean squared errors corresponding to the multiple sets of dynamic data, sort the multiple mean squared errors according to a preset sorting rule, and obtain a mean squared error queue; A preset number of target mean square errors are obtained from the mean square error queue, and the historical dynamic data corresponding to the target mean square errors are used as the processed dynamic data. The process of constructing a pipeline grid model of the oil and gas pipeline network based on the processed steady-state data includes: The target area where the oil and gas pipeline network is located is obtained based on the pipeline network size, the pipeline network location data, and the map data. The target area is divided into sub-regions, and the topology layer and path layer of the oil and gas pipeline network are obtained based on the sub-regions. The pipeline network mesh model of the oil and gas pipeline network is obtained based on the topology layer and the path layer.

2. The method according to claim 1, characterized in that, The step of preprocessing the steady-state data using the first preprocessing method to obtain processed steady-state data includes: The steady-state data is processed by adding missing values ​​and removing outliers to obtain the processed steady-state data.

3. The method according to claim 1, characterized in that, The method further includes: Obtain other dynamic data from the historical dynamic data besides the processed dynamic data; According to preset storage rules, the processed steady-state data, the processed dynamic data, the other dynamic data, the measured oil recovery rate, and the predicted oil recovery rate are stored for visualization.

4. The method according to claim 3, characterized in that, The step of storing the processed steady-state data, the processed dynamic data, the other dynamic data, the measured oil recovery rate, and the predicted oil recovery rate according to preset storage rules includes: Obtain the preset mapping relationship between the processed steady-state data, the processed dynamic data, the other dynamic data, the measured oil recovery rate and the predicted oil recovery rate and the pipeline nodes of the pipeline network grid model; Based on the mapping relationship, the processed steady-state data, the processed dynamic data, the other dynamic data, the measured oil recovery rate, the predicted oil recovery rate, and the mapping relationship are stored and processed.

5. The method according to any one of claims 1 to 4, characterized in that, The step of obtaining the measured oil recovery rate of known pipeline nodes in the pipeline network grid model, and obtaining a prediction model based on the measured oil recovery rate and the processed dynamic data, includes: The measured oil recovery rate and the processed dynamic data are used as training sets and input into the BP neural network model. The training set is iteratively processed using at least two sets of convolutional layers and pooling layers of the BP neural network model to obtain iterative results, and the iterative results are input into the dropout layer of the BP neural network model. The output generated by the discard layer based on the iteration result is fed into the bidirectional long short-term neural network to obtain the output value of the bidirectional long short-term neural network; The output value of the bidirectional long short-term neural network is subjected to nonlinear mapping processing to obtain the output result of the BP neural network; Based on the output of the BP neural network model and the reference results corresponding to the training set, a prediction model is obtained.

6. An oil and gas pipeline network oil production rate prediction device, characterized in that, include: The acquisition unit is used to acquire steady-state data and historical dynamic data of the oil and gas pipeline network. The steady-state data is characterized by fixed pipeline network-related data, including pipeline size, pipeline location data, and map data. The historical dynamic data is characterized by historical pipeline network-related data that can change at any time, including reservoir seepage velocity, water cut and water cut rise rate, temperature, real-time geological conditions, and pressure. The preprocessing unit is used to preprocess the steady-state data using a first preprocessing method to obtain processed steady-state data, and to preprocess the historical dynamic data using a second preprocessing method to obtain processed dynamic data. Pipeline model unit, used to construct a pipeline grid model of the oil and gas pipeline network based on the processed steady-state data; The prediction model unit is used to obtain the measured oil production rate of known pipeline nodes in the pipeline network grid model, and to obtain the prediction model based on the measured oil production rate and the processed dynamic data. The processing unit is used to obtain the predicted oil recovery rate of other pipeline nodes in the pipeline grid model, excluding the known pipeline nodes, using the prediction model. The preprocessing unit is used to preprocess the historical dynamic data using the second preprocessing method to obtain processed dynamic data. Specifically, it is used for: The historical dynamic data is divided according to the pipeline network node to which it belongs, resulting in multiple sets of dynamic data. Obtain multiple mean squared errors corresponding to the multiple sets of dynamic data, sort the multiple mean squared errors according to a preset sorting rule, and obtain a mean squared error queue; A preset number of target mean square errors are obtained from the mean square error queue, and the historical dynamic data corresponding to the target mean square errors are used as the processed dynamic data. Pipeline model unit, specifically used for: The target area where the oil and gas pipeline network is located is obtained based on the pipeline network size, the pipeline network location data, and the map data. The target area is divided into sub-regions, and the topology layer and path layer of the oil and gas pipeline network are obtained based on the sub-regions. The pipeline network mesh model of the oil and gas pipeline network is obtained based on the topology layer and the path layer.

7. An electronic device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the oil production rate prediction method for oil and gas pipeline networks as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, It stores computer-readable instructions, which, when executed by the computer's processor, cause the computer to perform the oil production rate prediction method for the oil and gas pipeline network as described in any one of claims 1 to 5.

Images