Method, apparatus, and system for intelligent prediction of flow coefficient of throttling metering apparatus, and device

Abstract

The present disclosure relates to a method, apparatus and system for intelligent prediction of a flow coefficient of a throttling metering apparatus, and a device. The method comprises: measuring a flow channel structure of a target throttling metering apparatus, so as to obtain a flow channel structure sequence vector, which comprises coordinate values of a plurality of points on an inner wall of the target throttling metering apparatus; and inputting the flow channel structure sequence vector into a pre-trained flow coefficient prediction model, and performing calculation by means of the model, so as to obtain a flow coefficient of the target throttling metering apparatus, which flow coefficient serves to guide staff in deploying the target throttling metering apparatus. By means of the embodiments of the present disclosure, fast and accurate response prediction of a flow coefficient can be provided under any given flow channel size characteristics of a throttling metering apparatus, and there is no need to measure a flow and a pressure difference on site, thereby saving on substantial time cost and overcoming the disadvantage of poor generalization capability of a conventional research method.

Description

Intelligent prediction method, device, system and equipment for flow coefficient of throttling metering device

[0001] Related applications

[0002] This application claims priority to Chinese Patent Application No. 202510206030.6, filed on February 24, 2025, and incorporates the entire contents of the aforementioned patent application as part of this disclosure. Technical Field

[0003] This disclosure relates to the field of fluid metering, and in particular to a method, apparatus, system and equipment for intelligent prediction of flow coefficient of a throttling metering device. Background Technology

[0004] When fluid flows through a throttling metering device, a pressure drop occurs, and the fluid flow rate can be calculated from this pressure drop. However, there is a discrepancy between the theoretical flow rate and the actual flow rate, requiring calibration using a flow coefficient. Obtaining an accurate flow coefficient is crucial for precise measurement and control of fluid flow.

[0005] The throttling metering devices used in fluid metering have diverse structures, most of which are non-standardized. Overseas oilfields, with their superior geological conditions and abundant formation energy, generally rely on flowing wells as the primary extraction method. Domestically, with the development of unconventional oilfields, shale oil and tight oilfields are the main battlegrounds for future reserve and production increases, resulting in a period of flowing production. Both scenarios require throttling control of production and reduction of pressure on downstream pipelines and equipment through nozzles with different flow channel diameters. Traditional methods for studying flow coefficients are usually limited to experimental studies of a few specific standard throttling metering devices, making it difficult to comprehensively consider throttling metering devices with different structures. Furthermore, multiple experiments are required each time to obtain a relatively accurate flow coefficient, consuming a significant amount of time. For some real-time field control applications, such as wellhead metering systems for oil well production, it is difficult to quickly obtain the flow coefficient to adjust system operation, prolonging the throttling system commissioning cycle and affecting the selection and optimization process of throttling devices. Therefore, industrial applications urgently need a predictive method capable of studying flow coefficients under different throttling conditions in pipelines. Summary of the Invention

[0006] To address the problems existing in related technologies, this disclosure provides a method, device, system, and equipment for intelligent prediction of the flow coefficient of a throttling metering device. By inputting the flow channel structure parameters of the throttling metering device into a deep neural network, the flow coefficient of throttling metering devices with different flow channel structures can be automatically predicted.

[0007] The specific technical solutions of this disclosure are as follows:

[0008] On one hand, embodiments of this disclosure provide an intelligent prediction method for the flow coefficient of a throttling metering device, the method comprising:

[0009] The flow channel structure of the target throttling metering device is measured to obtain the flow channel structure sequence vector, which includes the coordinate values ​​of multiple points on the inner wall of the target throttling metering device.

[0010] The flow channel structure sequence vector is input into a pre-trained flow coefficient prediction model. The flow coefficient of the target throttling metering device is calculated by the flow coefficient prediction model. The flow coefficient is used to guide the staff in deploying the target throttling metering device.

[0011] Furthermore, the steps for constructing a flow coefficient prediction model include:

[0012] Measure the flow channel structure sequence vector and throat cross-sectional area of ​​multiple throttling metering device samples;

[0013] For each sample of throttling metering device, the pressure and temperature of the fluid before throttling, the pressure difference of the fluid before and after throttling, and the mass flow rate of the fluid are measured.

[0014] Calculate the fluid density based on the pressure and / or temperature before throttling;

[0015] The flow coefficient of the throttling metering device sample is calculated based on the pressure difference, density, mass flow rate, and throat cross-sectional area using the following formula: Among them, C d Let A represent the flow coefficient, M represent the cross-sectional area of ​​the throat of the throttling device, r represent the fluid mass flow rate, r represent the fluid density, and DP represent the throttling pressure difference. The flow channel structure sequence vectors of each throttling metering device sample and the flow coefficient are used to construct a training dataset, and the flow coefficient prediction model is trained to obtain the trained flow coefficient prediction model.

[0016] Furthermore, the fluid includes either gas or liquid, and the trained flow coefficient prediction model includes a prediction model for the flow coefficient when the throttling metering device throttles a gas and a prediction model for the flow coefficient when it throttles a liquid.

[0017] Furthermore, the flow channel structure sequence vector includes the coordinate values ​​of multiple points on the inner wall of the target throttling metering device in a coordinate system with the axial direction of the target throttling metering device as the first coordinate axis, the radial direction as the second coordinate axis, and the intersection of one end face and the axis as the origin.

[0018] On the other hand, this disclosure also provides an intelligent prediction device for the flow coefficient of a throttling metering device, the device comprising:

[0019] The flow channel structure measurement unit is used to measure the flow channel structure of the target throttling metering device and obtain the flow channel structure sequence vector, which includes the coordinate values ​​of multiple points on the inner wall of the target throttling metering device.

[0020] The flow coefficient calculation unit is used to input the flow channel structure sequence vector into the pre-trained flow coefficient prediction model, and calculate the flow coefficient of the target throttling metering device through the flow coefficient prediction model. The flow coefficient is used to guide the staff to deploy the target throttling metering device.

[0021] On the other hand, this disclosure also provides an intelligent prediction system for the flow coefficient of a throttling metering device, the system including: a flow coefficient prediction model training data generation device and the above-mentioned intelligent prediction device for the flow coefficient of a throttling metering device.

[0022] The data generation device for the flow coefficient prediction model training includes: a fluid injection module, a fluid mass flow meter, a temperature sensor, a pressure sensor, a differential pressure sensor, a data acquisition module, and a sample of a throttling metering device.

[0023] The fluid injection module is used to inject fluid into the sample of the throttling metering device;

[0024] The fluid mass flow meter is located at the inlet of the throttling metering device sample and is used to measure the mass flow rate of the fluid.

[0025] The temperature sensor is located 3-5 times the pipe diameter before the throttling metering device sample and is used to measure the temperature of the fluid before throttling.

[0026] The pressure sensor is located 3-5 times the pipe diameter before the throttling metering device sample and is used to measure the pressure of the fluid before throttling.

[0027] One end of the differential pressure sensor is located 3-5 times the pipe diameter before the throttling metering device sample, and the other end is located at the outlet of the throttling metering device sample. It is used to measure the pressure difference before and after fluid throttling.

[0028] The output terminals of the fluid mass flow meter, temperature sensor, pressure sensor, and differential pressure sensor are all connected to the data acquisition module. The data acquisition module is used to collect the outputs of the fluid mass flow meter, temperature sensor, pressure sensor, and differential pressure sensor, and send them to the flow coefficient intelligent prediction device of the throttling metering device.

[0029] The intelligent flow coefficient prediction device for throttling metering devices is used to calculate the density of the fluid based on the pressure and / or temperature before throttling; calculate the flow coefficient of the throttling metering device sample based on the pressure difference, density, mass flow rate, and throat cross-sectional area of ​​the throttling metering device sample; construct a training dataset by using the flow channel structure sequence vector of the throttling metering device sample and the flow coefficient, and train the deep network model for flow coefficient prediction to obtain the trained flow coefficient prediction model.

[0030] Furthermore, the fluid injection module includes a gas injection submodule, a liquid injection submodule, and a three-way valve. The gas injection submodule is connected to the first end of the three-way valve, the liquid injection submodule is connected to the second end of the three-way valve, and the third end of the three-way valve is connected to the inlet of the throttling metering device sample.

[0031] Fluid mass flow meters include gas mass flow meters and liquid mass flow meters.

[0032] Furthermore, the gas injection submodule includes:

[0033] Compressor, gas metering pipeline, gas flow regulating valve, gas shut-off valve;

[0034] The compressor is connected to the first end of the three-way valve via a gas metering pipeline, a gas flow regulating valve, a gas shut-off valve, and a gas mass flow meter, and is used to inject gas into the throttling metering device sample.

[0035] A gas flow regulating valve is used to regulate the flow rate of injected gas;

[0036] One end of the gas shut-off valve is connected to the first end of the three-way valve, and the gas mass flow meter is connected in series between the other end of the gas shut-off valve and the gas flow regulating valve.

[0037] Gas shut-off valves are used to open or close the injection of gas, and gas mass flow meters are used to measure the mass flow rate of gas.

[0038] Furthermore, the liquid injection submodule includes:

[0039] Liquid storage tank, pump, liquid metering pipeline, liquid flow regulating valve, liquid shut-off valve;

[0040] Liquid storage tanks are used to store liquids;

[0041] The pump is connected to the second end of the three-way valve via a liquid metering pipeline, a liquid flow regulating valve, a liquid shut-off valve, and a liquid mass flow meter, and is used to inject liquid into the sample of the throttling metering device.

[0042] Liquid flow control valves are used to regulate the flow rate of injected liquid;

[0043] One end of the liquid shut-off valve is connected to the second end of the three-way valve, and the liquid mass flow meter is connected in series between the other end of the liquid shut-off valve and the liquid flow regulating valve.

[0044] Liquid shut-off valves are used to open or close the injection of liquid, while liquid mass flow meters are used to measure the mass flow rate of liquid.

[0045] On the other hand, this disclosure also provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the above-described method.

[0046] On the other hand, embodiments of this disclosure also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0047] Using the embodiments of this disclosure, a rapid and accurate response prediction of the flow coefficient can be provided under any given size characteristics of the throttling metering device, eliminating the need for on-site measurement of flow rate and differential pressure, thus saving significant time and costs. It overcomes the poor generalization ability of traditional research methods and has broad application value. Furthermore, it helps to shorten the commissioning cycle of the throttling system and accelerate the selection and optimization process of the throttling device. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments or related technologies of this disclosure, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 is a flowchart illustrating an intelligent prediction method for the flow coefficient of a throttling metering device according to an embodiment of this disclosure.

[0050] Figure 2 shows a schematic diagram of the equal diameter throttling metering device in an embodiment of this disclosure;

[0051] Figure 3 shows a schematic diagram of the arc-shaped throttling metering device in an embodiment of this disclosure;

[0052] Figure 4 shows a schematic diagram of the structure of the gradually expanding throttling metering device in an embodiment of this disclosure;

[0053] Figure 5 shows a schematic diagram of the measurement of the flow channel structure sequence vectors X and Y in an embodiment of this disclosure;

[0054] Figure 6 is a schematic diagram of the process of constructing the flow coefficient prediction model in an embodiment of this disclosure;

[0055] Figure 7 is a schematic diagram of the flow coefficient prediction model in an embodiment of this disclosure;

[0056] Figure 8 is a schematic diagram of the structure of a flow coefficient intelligent prediction device for a throttling metering device according to an embodiment of the present disclosure.

[0057] Figure 9 is a schematic diagram of the structure of the flow coefficient prediction model training data generation device in an embodiment of this disclosure.

[0058] Figure 10 is a schematic diagram of the experimental process of the flow coefficient prediction model training data generation device in an embodiment of this disclosure.

[0059] Figure 11 is a schematic diagram of the structure of the computer device in an embodiment of this disclosure;

[0060] Figure 12 shows a comparative diagram of the flow coefficient prediction results of the throttling device when the circulating medium is water in the embodiments of this disclosure.

[0061] Figure 13 shows a comparative diagram of the flow coefficient prediction results of the throttling device when the circulating medium is air in the embodiments of this disclosure.

[0062] [Explanation of reference numerals in the attached diagram]: 801, Flow channel structure measurement unit; 802, Flow coefficient calculation unit; 1, Compressor; 2, Gas metering pipeline; 3, Three-way valve; 4, Gas mass flow meter; 5, Gas flow regulating valve; 6, Gas shut-off valve; 7, Liquid storage tank; 8, Pump; 9, Liquid metering pipeline; 10, Liquid mass flow meter; 11, Liquid flow regulating valve; 12, Liquid shut-off valve; 13, Upstream pipeline; 14, Throttling metering device sample; 15, Temperature sensor; 16, Pressure sensor; 17, Differential pressure sensor; 18, Downstream pipeline; 19, Cyclone separator; 20, Data acquisition module; 1102, Computer equipment; 1104, Processing equipment; 1106, Storage resources; 1108, Drive mechanism; 1110, Input / output module; 1112, Input device; 1114, Output device; 1116. Presentation device; 1118. Graphical user interface; 1120. Network interface; 1122. Communication link; 1124. Communication bus. Detailed Implementation

[0063] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. Based on the embodiments of this disclosure, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of the embodiments of this disclosure.

[0064] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, apparatus, product, or device that includes a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0065] It should be noted that the acquisition, storage, use, and processing of data in the technical solutions of this disclosure comply with the relevant provisions of national laws and regulations.

[0066] It should be noted that in the embodiments disclosed herein, certain software, components, models, and other existing solutions in the industry may be mentioned. These should be considered as exemplary and are intended only to illustrate the feasibility of implementing the technical solutions disclosed herein. However, they do not mean that the applicant has used or necessarily used such solutions.

[0067] Based on this, this disclosure provides an intelligent prediction method for the flow coefficient of a throttling metering device, as shown in Figure 1. The method includes:

[0068] Step 101: Measure the flow channel structure of the target throttling metering device to obtain the flow channel structure sequence vector, which includes the coordinate values ​​of multiple points on the inner wall of the target throttling metering device;

[0069] Step 102: Input the flow channel structure sequence vector into the pre-trained flow coefficient prediction model, and calculate the flow coefficient of the target throttling metering device through the flow coefficient prediction model. The flow coefficient is used to guide the staff to deploy the target throttling metering device.

[0070] In this embodiment of the disclosure, as shown in Figures 2, 3 and 4, the flow channel structure of the throttling metering device includes constant diameter throttling, gradually expanding throttling and arc-shaped throttling. In this embodiment of the disclosure, the coordinate values ​​of multiple points inside the throttling metering device are measured to obtain the flow channel structure sequence.

[0071] Specifically, the flow channel structure sequence vector includes the coordinate values ​​of multiple points on the inner wall of the target throttling metering device in a coordinate system with the axial direction of the target throttling metering device as the first coordinate axis, the radial direction as the second coordinate axis, and the intersection of one end face and the axis as the origin.

[0072] For example, as shown in Figure 5, a coordinate system is formed with the axial direction of the throttling metering device as the X-axis, the radial direction as the Y-axis, and the intersection of the left end face and the axis as the origin, where L represents the length of the throttling metering device and d represents the throat diameter of the throttling metering device.

[0073] Measure the coordinates of n points on the inner wall of the throttling metering device in the coordinate system shown in Figure 5 to obtain the flow channel structure sequence vector X = (x1,...,x...). n ), Y = (y1,...,y n ).

[0074] In this embodiment of the disclosure, as shown in FIG6, the steps for constructing the flow coefficient prediction model include:

[0075] Step 601: Measure the flow channel structure sequence vector and throat cross-sectional area of ​​multiple throttling metering device samples;

[0076] Step 602: For each throttling metering device sample, measure the pressure and temperature of the fluid before throttling, the pressure difference of the fluid before and after throttling, and the mass flow rate of the fluid;

[0077] Step 603: Calculate the density of the fluid based on the pressure and / or temperature before throttling;

[0078] Step 604: Calculate the flow coefficient of the throttling metering device sample based on the pressure difference, density, mass flow rate, and throat cross-sectional area;

[0079] Step 605: Construct a training dataset using the flow channel structure sequence vector and flow coefficient of each throttling metering device sample, train the flow coefficient prediction model, and obtain the trained flow coefficient prediction model.

[0080] In this embodiment of the disclosure, the cross-sectional area of ​​the throat can be calculated based on the diameter d of the throat cross-section.

[0081] The formula for calculating the flow coefficient of a metering device sample based on pressure difference, density, mass flow rate, and throat cross-sectional area is as follows:

[0082] Among them, C d denoted by , A represents the cross-sectional area of ​​the throat of the throttling device, M represents the mass flow rate of the fluid, r represents the fluid density, and DP represents the throttling pressure difference.

[0083] It should be noted that the flow coefficient C d This refers to the flow coefficient of a throttling device when it flows through the measured fluid. The same throttling device may have different flow coefficients for different fluids.

[0084] When the fluid is a gas, the formula for calculating the gas density based on the pressure and temperature before throttling is as follows:

[0085] Where m represents the molecular weight of the gas and R represents the gas constant. Taking air as an example, the molecular weight of the gas is 29 g / mol and the gas constant is 8.314.

[0086] When the fluid is a liquid, this embodiment of the disclosure uses interpolation for calculation. For example, the formula for calculating the density of the liquid based on its temperature before throttling is as follows:

[0087] in, Indicates the liquid at T a Density at temperature Indicates the liquid at T b Density at a given temperature.

[0088] It should be noted that temperature T a and T b The standard temperature can be obtained by looking up a table for the temperature of the liquid (e.g., water) at temperature T. a and T b The density below.

[0089] In this embodiment, the flow coefficient prediction model can be a neural network model. The model structure is shown in Figure 7. The flow channel structure sequence vectors X and Y are input into the input layer of the neural network to represent the flow channel structure size characteristics. Then, the data is divided into a training set and a test set according to a certain ratio. The model is continuously trained and tested. When the root mean square error is lower than the set error convergence value ε, the network is considered converged, and the flow coefficient C is output. d The predicted value indicates that the network output flow coefficient is close to the true solution. Conversely, a large root mean square error (RMSE) indicates poor model convergence, requiring continued iterative calculations until convergence. The specific RMSE value is calculated using the formula... Calculate, where n is the total number of training samples; The measured value of the flow coefficient for the i-th experimental group; This corresponds to the predicted value of the neural network flow coefficient.

[0090] According to one embodiment of this disclosure, the fluid includes either gas or liquid, and the trained flow coefficient prediction model includes a prediction model for predicting the flow coefficient when the throttling metering device throttles a gas and a prediction model for predicting the flow coefficient when it throttles a liquid.

[0091] It can be understood that the embodiments of this disclosure can train a prediction model for the flow coefficient of a throttling metering device when throttling gas and a prediction model for the flow coefficient of a throttling metering device when throttling liquid, thereby predicting the flow coefficient of the target throttling metering device when throttling gas and the flow coefficient of the target throttling metering device when throttling liquid based on the structural characteristics of the target throttling metering device, so that the staff can deploy the target throttling metering device according to the flow coefficient.

[0092] Based on the same inventive concept, this disclosure also provides an intelligent prediction device for the flow coefficient of a throttling metering device, as shown in FIG8, comprising:

[0093] The flow channel structure measurement unit 801 is used to measure the flow channel structure of the target throttling metering device and obtain the flow channel structure sequence vector, which includes the coordinate values ​​of multiple points on the inner wall of the target throttling metering device.

[0094] The flow coefficient calculation unit 802 is used to input the flow channel structure sequence vector into the pre-trained flow coefficient prediction model, and calculate the flow coefficient of the target throttling metering device through the flow coefficient prediction model. The flow coefficient is used to guide the staff to deploy the target throttling metering device.

[0095] The beneficial effects obtained by the above-described device are the same as those obtained by the above-described method, and will not be described in detail in the embodiments disclosed herein.

[0096] Based on the same inventive concept, this disclosure also provides an intelligent prediction system for the flow coefficient of a throttling metering device, including: a flow coefficient prediction model training data generation device and an intelligent prediction device for the flow coefficient of a throttling metering device as shown in FIG8.

[0097] As shown in Figure 9, the data generation device for the flow coefficient prediction model training includes: a fluid injection module, a fluid mass flow meter, a temperature sensor 15, a pressure sensor 16, a differential pressure sensor 17, a data acquisition module 20, and a throttling metering device sample 14.

[0098] The fluid injection module is used to inject fluid into the throttling metering device sample 14;

[0099] The fluid mass flow meter is located at the inlet of the throttling metering device sample 14 and is used to measure the mass flow rate of the fluid.

[0100] Temperature sensor 15 is located 3-5 times the pipe diameter before the throttling metering device sample 14, and is used to measure the temperature of the fluid before throttling.

[0101] Pressure sensor 16 is located 3-5 times the pipe diameter before the throttling metering device sample 14, and is used to measure the pressure of the fluid before throttling.

[0102] One end of the differential pressure sensor 17 is located 3-5 times the pipe diameter before the throttling metering device sample 14, and the other end is located at the outlet of the throttling metering device sample 14. It is used to measure the pressure difference before and after fluid throttling.

[0103] The output terminals of the fluid mass flow meter, temperature sensor 15, pressure sensor 16, and differential pressure sensor 17 are all connected to the data acquisition module 20. The data acquisition module 20 is used to collect the outputs of the fluid mass flow meter, temperature sensor 15, pressure sensor 16, and differential pressure sensor 17, and send them to the flow coefficient intelligent prediction device of the throttling metering device.

[0104] The intelligent flow coefficient prediction device for throttling metering devices is used to calculate the density of the fluid based on the pressure and / or temperature before throttling; calculate the flow coefficient of the throttling metering device sample based on the pressure difference, density, mass flow rate, and throat cross-sectional area of ​​the throttling metering device sample; construct a training dataset by combining the flow channel structure sequence vector of the throttling metering device sample and the flow coefficient, and train the flow coefficient prediction model to obtain a trained deep network prediction model for the flow coefficient.

[0105] To improve the prediction models for the flow coefficients of the training gas and liquid respectively, as shown in Figure 9, the fluid injection module in this embodiment includes a gas injection submodule, a liquid injection submodule, and a three-way valve 3. The gas injection submodule is connected to the first end of the three-way valve 3, the liquid injection submodule is connected to the second end of the three-way valve 3, and the third end of the three-way valve is connected to the inlet of the throttling metering device sample 14.

[0106] Fluid mass flow meters include gas mass flow meters and liquid mass flow meters.

[0107] Therefore, controlling the closed state of the three-way valve can control the injection of gas or liquid into the throttling metering device, thereby facilitating the generation of data for training the respective flow coefficient prediction models.

[0108] Furthermore, as shown in Figure 9, the gas injection submodule includes:

[0109] 1. Compressor; 2. Gas metering pipeline; 5. Gas flow regulating valve; 6. Gas shut-off valve;

[0110] The compressor 1 is connected to the first end of the three-way valve 3 via the gas metering pipeline 2, the gas flow regulating valve 5, the gas shut-off valve 6, and the gas mass flow meter 4, and is used to inject gas into the throttling metering device sample 14.

[0111] Gas flow regulating valve 5 is used to regulate the gas injection flow rate;

[0112] One end of the gas shut-off valve 6 is connected to the first end of the three-way valve 3, and the gas mass flow meter 4 is connected in series between the other end of the gas shut-off valve 6 and the gas flow regulating valve 5.

[0113] The gas shut-off valve 6 is used to open or close the gas injection, and the gas mass flow meter 4 is used to measure the mass flow rate of the gas.

[0114] The liquid injection submodule includes:

[0115] 7. Liquid storage tank; 8. Pump; 9. Liquid metering pipeline; 11. Liquid flow regulating valve; 12. Liquid shut-off valve;

[0116] Storage tank 7 is used to store liquids;

[0117] Pump 8 is connected to the second end of three-way valve 3 via liquid metering pipe 9, liquid flow regulating valve 11, liquid shut-off valve 12 and liquid mass flow meter 10, and is used to inject liquid into throttling metering device sample 14.

[0118] The liquid flow regulating valve 11 is used to regulate the flow rate of the injected liquid;

[0119] One end of the liquid shut-off valve 12 is connected to the second end of the three-way valve 3, and the liquid mass flow meter 10 is connected in series between the other end of the liquid shut-off valve 12 and the liquid flow regulating valve 11.

[0120] The liquid shut-off valve 12 is used to open or close the injection of liquid, and the liquid mass flow meter 10 is used to measure the mass flow rate of the liquid.

[0121] Continuing as shown in Figure 9, the system may also include an upstream pipe 13 and a downstream pipe 18. The upstream pipe 13 is connected in series between the third end of the three-way valve 3 and the inlet of the throttling metering device sample 14, and the downstream pipe 18 is connected in series between the outlet of the throttling metering device sample 14 and the cyclone separator 19. The cyclone separator 19 is used to separate droplets from the fluid flowing out of the outlet of the throttling metering device sample 14 using centrifugal force, and then allow the droplets to flow into the storage tank 7.

[0122] Figure 10 is a schematic diagram of the experimental process for generating training data for the flow coefficient prediction model in this embodiment. When the fluid in the pipeline is gas, a gas mass flow meter 4 is used to measure the single-phase gas mass flow rate entering the pipeline; when the fluid in the pipeline is liquid, a liquid mass flow meter 10 is used to measure the single-phase liquid mass flow rate entering the pipeline. A temperature sensor 15 is used to measure the temperature T before throttling, a pressure sensor 16 is used to measure the pressure P before throttling, and a differential pressure sensor 17 is used to measure the pressure difference DP before and after the throttling metering device sample 14. The density r of the measured fluid is calculated based on the measured pressure P and temperature T. Combined with the throat diameter d of the throttling metering device sample 14, the measured fluid mass flow rate M, and the pressure difference DP before and after throttling, the formula is used... Calculate the flow coefficient C d .

[0123] Figure 11 shows a schematic diagram of the structure of a computer device according to an embodiment of the present disclosure. The device in the present disclosure can be the computer device in this embodiment, which executes the methods in the present disclosure described above.

[0124] Computer device 1102 may include one or more processing devices 1104, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads.

[0125] Computer device 1102 may also include any storage resource 1106 for storing information of any kind, such as code, settings, data, etc. Without limitation, storage resource 1106 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc.

[0126] More generally, any storage resource can use any technology to store information.

[0127] Furthermore, any storage resource can provide volatile or non-volatile retention of information.

[0128] Furthermore, any storage resource can represent a fixed or removable component of computer device 1102.

[0129] In one scenario, when processing device 1104 executes associated instructions stored in any storage resource or combination of storage resources, computer device 1102 may perform any operation of the associated instructions.

[0130] The computer device 1102 also includes one or more drive mechanisms 1108 for interacting with any storage resource, such as hard disk drive mechanism, optical disk drive mechanism, etc.

[0131] The computer device 1102 may also include an input / output module 1110 (I / O) for receiving various inputs (via input device 1112) and providing various outputs (via output device 1114).

[0132] A specific output mechanism may include a presentation device 1116 and an associated graphical user interface (GUI) 1118.

[0133] In other embodiments, the input / output module 1110 (I / O), input device 1112, and output device 1114 may be omitted, and the device may simply function as a computer device in the network.

[0134] Computer device 1102 may also include one or more network interfaces 1120 for exchanging data with other devices via one or more communication links 1122. One or more communication buses 1124 couple the components described above together.

[0135] The communication link 1122 can be implemented in any way, such as through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, or any combination thereof.

[0136] Communication link 1122 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0137] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0138] This disclosure also provides a computer-readable instruction, wherein when a processor executes the instruction, the program therein causes the processor to perform the above-described method.

[0139] It should be understood that in various embodiments of the present disclosure, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

[0140] It should also be understood that, in the embodiments of this disclosure, the term "and / or" is merely a description of the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, in the embodiments of this disclosure, the character " / " generally indicates that the preceding and following associated objects have an "or" relationship.

[0141] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this disclosure can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure.

[0142] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0143] In the embodiments provided in this disclosure, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, apparatuses, or units, or they may be electrical, mechanical, or other forms of connection.

[0144] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this disclosure, depending on actual needs.

[0145] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0146] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of this disclosure, in essence, or the parts that contribute to related technologies, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0147] To verify the effectiveness of the intelligent prediction method for the flow coefficient of the throttling metering device provided in this disclosure, a case study was conducted using water and air as the flow medium.

[0148] In this specific embodiment, 254 samples of throttling metering devices were selected, and flow channel structure measurements and flow coefficient calculations were performed. The distribution of the dataset is shown in Table 1. The dataset was randomly divided into a training set and a test set in a 7:3 ratio, with the training set containing 178 samples and the test set containing 76 samples. A deep network model for predicting the flow coefficient of throttling devices was trained using the training set, and the model's prediction performance was verified using the test set. Figures 12 and 13 show the comparison results of the predicted and actual flow coefficient values ​​of the deep network model on the test set when water and air are used as the flow medium, respectively. The horizontal axis represents True Values, and the vertical axis represents Predictions.

[0149] Table 1 Dataset Distribution

[0150] The comparison results in the figure show that, even for different flow media, the established flow coefficient prediction model maintains a prediction error of less than 2% for different types of throttling metering devices, indicating that the prediction model has good prediction accuracy and generalization ability.

[0151] This disclosure uses specific embodiments to illustrate the principles and implementation methods of the embodiments of this disclosure. The above description of the embodiments is only for the purpose of helping to understand the methods and core ideas of the embodiments of this disclosure. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the embodiments of this disclosure. Therefore, the content of this disclosure should not be construed as a limitation on the embodiments of this disclosure.

Claims

1. A method for intelligent prediction of flow coefficient of a throttling metering device, characterized in that, The method includes: The flow channel structure of the target throttling metering device is measured to obtain a flow channel structure sequence vector, which includes the coordinate values ​​of multiple points on the inner wall of the target throttling metering device. The flow channel structure sequence vector is input into a pre-trained flow coefficient prediction model, and the flow coefficient of the target throttling metering device is calculated by the flow coefficient prediction model. The flow coefficient is used to guide the staff in deploying the target throttling metering device.

2. The method according to claim 1, characterized in that, The steps for constructing the flow coefficient prediction model include: Measure the flow channel structure sequence vector and throat cross-sectional area of ​​multiple throttling metering device samples; For each of the throttling metering device samples, the pressure, temperature, mass flow rate of the fluid before throttling, and the pressure difference of the fluid before and after flowing through the throttling metering device are measured. The density of the fluid is calculated based on the pressure and / or temperature before throttling. The flow coefficient of the throttling metering device sample is calculated based on the pressure difference, density, mass flow rate, and throat cross-sectional area, using the following formula: Among them, C d Here, A represents the flow coefficient, M represents the cross-sectional area of ​​the throat of the throttling device, r represents the fluid mass flow rate, and DP represents the throttling pressure difference. Using the flow channel structure sequence vector of each of the throttling metering device samples as input features and the flow coefficient as output label, a dataset is constructed to train the flow coefficient prediction model, resulting in the trained flow coefficient prediction model.

3. The method according to claim 2, characterized in that, The fluid includes either gas or liquid, and the trained flow coefficient prediction model includes a prediction model for the flow coefficient when the throttling metering device throttles gas and a prediction model for the flow coefficient when it throttles liquid.

4. The method according to claim 1, characterized in that, The flow channel structure sequence vector includes the coordinate values ​​of multiple points on the inner wall of the target throttling metering device in a coordinate system with the axial direction of the target throttling metering device as the first coordinate axis, the radial direction as the second coordinate axis, and the intersection of one end face and the axis as the origin.

5. A flow coefficient intelligent prediction device for a throttling metering device, characterized in that, The device includes: The flow channel structure measurement unit is used to measure the flow channel structure of the target throttling metering device and obtain a flow channel structure sequence vector, which includes the coordinate values ​​of multiple points on the inner wall of the target throttling metering device. The flow coefficient calculation unit is used to input the flow channel structure sequence vector into a pre-trained flow coefficient prediction model, and calculate the flow coefficient of the target throttling metering device through the flow coefficient prediction model. The flow coefficient is used to guide the staff to deploy the target throttling metering device.

6. A flow coefficient intelligent prediction system for a throttling metering device, characterized in that, The system includes: a flow coefficient prediction model training data generation device and a flow coefficient intelligent prediction device for the throttling metering device as described in claim 5. The flow coefficient prediction model training data generation device includes: a fluid injection module, a fluid mass flow meter, a temperature sensor, a pressure sensor, a differential pressure sensor, a data acquisition module, and a sample of a throttling metering device. The fluid injection module is used to inject fluid into the sample of the throttling metering device; The fluid mass flow meter is located at the inlet of the throttling metering device sample and is used to measure the mass flow rate of the fluid. The temperature sensor is located 3-5 times the pipe diameter before the throttling metering device sample, and is used to measure the temperature of the fluid before throttling. The pressure sensor is located 3-5 times the pipe diameter before the throttling metering device sample and is used to measure the pressure of the fluid before throttling. One end of the differential pressure sensor is located 3-5 times the pipe diameter before the sample of the throttling metering device, and the other end is located at the outlet of the sample of the throttling metering device, used to measure the pressure difference before and after the fluid is throttled; The output terminals of the fluid mass flow meter, temperature sensor, pressure sensor, and differential pressure sensor are all connected to the data acquisition module. The data acquisition module is used to collect the outputs of the fluid mass flow meter, temperature sensor, pressure sensor, and differential pressure sensor, and send them to the intelligent flow coefficient prediction device of the throttling metering device. The intelligent flow coefficient prediction device for the throttling metering device is used to calculate the density of the fluid based on the pressure and / or temperature before throttling; calculate the flow coefficient of the throttling metering device sample based on the pressure difference, the density, the mass flow rate, and the throat cross-sectional area of ​​the throttling metering device sample; construct a training dataset using the flow channel structure sequence vector and flow coefficient of the throttling metering device sample, and train the deep network prediction model for the flow coefficient to obtain the trained flow coefficient prediction model.

7. The intelligent flow coefficient prediction system for the throttling metering device according to claim 6, characterized in that, The fluid injection module includes a gas injection submodule, a liquid injection submodule, and a three-way valve. The gas injection submodule is connected to the first end of the three-way valve, the liquid injection submodule is connected to the second end of the three-way valve, and the third end of the three-way valve is connected to the inlet of the throttling metering device sample. The fluid mass flow meter includes a gas mass flow meter and a liquid mass flow meter.

8. The intelligent flow coefficient prediction system for the throttling metering device according to claim 7, characterized in that, The gas injection submodule includes: Compressor, gas metering pipeline, gas flow regulating valve, gas shut-off valve; The compressor is connected to the first end of the three-way valve via the gas metering pipeline, the gas flow regulating valve, the gas shut-off valve, and the gas mass flow meter, for injecting gas into the throttling metering device sample. The gas flow regulating valve is used to regulate the flow rate of the injected gas; One end of the gas shut-off valve is connected to the first end of the three-way valve, and the gas mass flow meter is connected in series between the other end of the gas shut-off valve and the gas flow regulating valve. The gas shut-off valve is used to open or close the injection of the gas, and the gas mass flow meter is used to measure the mass flow rate of the gas.

9. The intelligent flow coefficient prediction system for the throttling metering device according to claim 8, characterized in that, The liquid injection submodule includes: Liquid storage tank, pump, liquid metering pipeline, liquid flow regulating valve, liquid shut-off valve; The liquid storage tank is used to store liquid; The pump is connected to the second end of the three-way valve via the liquid metering pipeline, the liquid flow regulating valve, the liquid shut-off valve, and the liquid mass flow meter, and is used to inject the liquid into the throttling metering device sample. The liquid flow regulating valve is used to regulate the flow rate of the injected liquid; One end of the liquid shut-off valve is connected to the second end of the three-way valve, and the liquid mass flow meter is connected in series between the other end of the liquid shut-off valve and the liquid flow regulating valve; The liquid shut-off valve is used to open or close the injection of the liquid, and the liquid mass flow meter is used to measure the mass flow rate of the liquid.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 4.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 4.

Images