Method for determining pipeline leakage point location based on dimension analysis and CFD simulation

Abstract

The invention discloses a method for determining a pipeline leakage point location based on dimensional analysis and CFD simulation, relates to the technical field of pipeline detection, and can solve the problems of high cost and long time consumption of pipeline detection. According to the specific scheme, the method comprises the steps that multiple physical variables influencing the pipeline leakage behavior are obtained, the physical variables comprise influence factor variables and result variables, nondimensionalization processing is conducted on the multiple physical variables, and a nondimensionalized relation group is obtained; obtaining a historical data set through CFD simulation, wherein the historical data set stores a mapping relation between the parameter value corresponding to the influence factor variable and the parameter value corresponding to the result variable; generating a prediction model by using the training data set and the dimensionless relation group; acquiring collection data of the current pipeline, wherein the collection data comprises a pipeline leakage rate value, a density value of fluid in the pipeline, a flow velocity value of the fluid in the pipeline, a pipeline diameter value and a pressure change value between a pipeline inlet and a pipeline outlet; and inputting the collected data into the prediction model, and predicting to obtain the leakage position of the pipeline.

Description

Technical Field

[0001] The present application relates to the technical field of pipeline detection, and in particular to a method for determining pipeline leakage points based on dimensional analysis and CFD simulation. Background Art

[0002] Pipeline transportation is an important way to transport combustible gases in the coal-to-olefin production process. During the transmission process, some old pipelines may age and deteriorate due to design and construction defects, long-term operation, etc., causing pipeline leakage, causing damage to the environment. If the combustible gas encounters high-temperature open flames, it may even burn or explode, seriously threatening the safety of personnel in the production process. Therefore, it is very necessary to monitor pipeline leaks, identify leaks in a timely manner, and resolve hidden dangers, which can not only reduce product losses, but also help improve process safety. Traditional pipeline leakage technology relies on physical detection methods using sensors, but this physical detection method is costly and time-consuming. Summary of the invention

[0003] The present application provides a method for determining pipeline leakage points based on dimensional analysis and CFD simulation, which can solve the problems of high cost and long time consumption of pipeline detection.

[0004] In order to achieve the above purpose, this application adopts the following technical solutions:

[0005] In a first aspect of an embodiment of the present application, a method for determining a pipeline leakage point based on dimensional analysis and CFD simulation is provided, the method comprising:

[0006] Acquire multiple physical variables that affect pipeline leakage behavior, wherein the physical variables include influencing factor variables and result variables, wherein the influencing factor variables include: pipeline leakage rate, fluid density in the pipeline, pipeline diameter, fluid flow rate in the pipeline, and the distance between the leakage point and the pipeline outlet, and the result variables include: pressure change between the pipeline inlet and outlet;

[0007] Performing dimensionless processing on the multiple physical variables to obtain a dimensionless relationship group;

[0008] Acquire a historical data set, wherein the historical data set stores a mapping relationship between parameter values ​​corresponding to the influencing factor variables and parameter values ​​corresponding to the result variables, and the historical data set is divided into a training data set and a validation data set;

[0009] Generate a prediction model using the training data set and the dimensionless relationship group;

[0010] Acquire the collected data of the current pipeline, the collected data including: pipeline leakage rate value, fluid density value in the pipeline, fluid flow rate value in the pipeline, pipeline diameter value, and pressure change value between the pipeline inlet and outlet;

[0011] The collected data is input into the prediction model to predict the leakage position of the pipeline.

[0012] As a possible implementation manner, the dimensionless processing of the multiple physical variables to obtain a dimensionless relationship group includes:

[0013] Selecting a target variable to be dimensionless from the plurality of physical variables;

[0014] determining a basic variable from the plurality of physical variables;

[0015] The dimensionless relationship group is constructed according to the target variable and the basic variables.

[0016] As a possible implementation, the target variable includes: the pipeline leakage rate, the distance and the pressure change; the basic variables include: the fluid density, the fluid flow rate and the pipeline diameter; the dimensionless relationship group is constructed according to the target variable and the basic variables, including:

[0017] Performing dimensionless processing on the pipeline leakage rate to form a first dimensionless relationship based on the pipeline leakage rate, the fluid density, the fluid flow rate and the pipeline diameter;

[0018] Non-dimensionalizing the distance to form a second non-dimensional relationship based on the distance and the pipe diameter;

[0019] The pressure change is dimensionally processed to form a third dimensionless relationship based on the pressure change, the fluid density and the fluid flow rate.

[0020] As a possible implementation manner, the step of generating a prediction model by combining the training data set and the dimensionless relationship includes:

[0021] Inputting the pressure change values ​​under different influencing factor variable values ​​in the training data set into the corresponding dimensionless relationship to obtain a plurality of corresponding first conversion values, second conversion values ​​and third conversion values;

[0022] The prediction model is determined using a plurality of corresponding first conversion values, second conversion values, and third conversion values.

[0023] As a possible implementation manner, after generating a prediction model by combining the training data set and the dimensionless relationship, the method further includes:

[0024] Optimizing the parameters of the prediction model using the validation data set until the prediction accuracy of the prediction model reaches a preset accuracy, thereby obtaining a target prediction model;

[0025] The step of inputting the collected data into the prediction model comprises:

[0026] The collected data is input into the target prediction model.

[0027] As a possible implementation manner, the obtaining of the historical data set includes:

[0028] Establish simulation models for multiple different pipeline leakage scenarios, including different leakage hole diameters and leakage points;

[0029] Based on the CFD calculation method, simulation calculations are performed on the simulation models of the multiple different pipeline leakage scenarios to obtain pressure change values ​​of each pipeline under different influencing factor variable values;

[0030] The pressure change values ​​of each pipeline under different influencing factor variable values ​​are mapped and stored to obtain the historical data set.

[0031] As a possible implementation method, the acquisition of the historical technology set includes:

[0032] Obtain the pressure change values ​​of different pipelines under different leakage scenarios at historical time, using multiple sensors to test different influencing factor variable values;

[0033] The pressure change values ​​under different influencing factor variable values ​​are mapped and stored to obtain the historical data set.

[0034] In a second aspect of the embodiment of the present application, a device for determining a pipeline leakage point based on dimensional analysis and CFD simulation is provided, the device comprising:

[0035] A first acquisition module is used to acquire multiple physical variables that affect pipeline leakage behavior, wherein the physical variables include influencing factor variables and result variables, wherein the influencing factor variables include: pipeline leakage rate, fluid density in the pipeline, pipeline diameter, fluid flow rate in the pipeline, and the distance between the leakage point and the pipeline outlet, and the result variables include: pressure change between the pipeline inlet and outlet;

[0036] A first processing module is used to perform dimensionless processing on the multiple physical variables to obtain a dimensionless relationship group;

[0037] A second acquisition module is used to acquire a historical data set, wherein the historical data set stores a mapping relationship between parameter values ​​corresponding to the influencing factor variables and parameter values ​​corresponding to the result variables, and the historical data set is divided into a training data set and a validation data set;

[0038] A generation module, used to generate a prediction model using the training data set and the dimensionless relationship group;

[0039] The third acquisition module is used to acquire the collected data of the current pipeline, wherein the collected data includes: pipeline leakage rate value, fluid density value in the pipeline, fluid flow rate value in the pipeline, pipeline diameter value, and pressure change value between the pipeline inlet and outlet;

[0040] The prediction module is used to input the collected data into the prediction model to predict the leakage position of the pipeline.

[0041] According to a third aspect of an embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for determining the pipeline leakage point based on dimensional analysis and CFD simulation in the first aspect of an embodiment of the present application is implemented.

[0042] In a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for determining the pipeline leakage point based on dimensional analysis and CFD simulation described in the first aspect of the embodiment of the present application is implemented.

[0043] The beneficial effects brought by the technical solution provided by the embodiment of the present application include at least:

[0044] The embodiment of the present application provides a method for determining pipeline leakage points based on dimensional analysis and CFD simulation, by obtaining multiple physical variables that affect pipeline leakage behavior, the physical variables include influencing factor variables and result variables, the influencing factor variables include: pipeline leakage rate, fluid density in the pipeline, pipeline diameter, fluid flow rate in the pipeline, and the distance between the leakage point and the pipeline outlet, the result variable includes: pressure change between the pipeline inlet and outlet; multiple physical variables are dimensionally processed to obtain a dimensionless relationship group; a historical data set is obtained, the historical data set stores a mapping relationship between parameter values ​​corresponding to the influencing factor variables and parameter values ​​corresponding to the result variables, and the historical data set is divided into a training data set and a verification data set; a prediction model is generated using the training data set and the dimensionless relationship group; the collected data of the current pipeline is obtained, the collected data includes: pipeline leakage rate value, fluid density value in the pipeline, fluid flow rate value in the pipeline, pipeline diameter value, pressure change value between the pipeline inlet and outlet; the collected data is input into the prediction model to predict the leakage position of the pipeline. This application uses dimensional analysis combined with CFD simulation to predict the process of leakage points. Through dimensionless processing, multiple physical variables can be converted into a few key dimensionless variables, which can improve the efficiency of generating prediction models, and use CFD simulation to generate training data sets and key dimensionless relationship groups for prediction models to predict leakage points. This method not only improves the accuracy of prediction, but also shortens the calculation time, allowing for rapid response in emergency situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flow chart of a method for determining pipeline leakage points based on dimensional analysis and CFD simulation provided in an embodiment of the present application;

[0046] Figure 2 A structural diagram of a device for determining pipeline leakage points based on dimensional analysis and CFD simulation provided in an embodiment of the present application;

[0047] Figure 3 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present disclosure, unless otherwise specified, "plurality" means two or more.

[0050] Additionally, the use of “based on” or “according to” is meant to be open and inclusive, as a process, step, calculation, or other action “based on” or “according to” one or more conditions or values ​​may, in practice, be based on additional conditions or beyond values.

[0051] The present application embodiment provides a method for determining pipeline leakage points based on dimensional analysis and CFD simulation, the method comprising:

[0052] Step 101: Acquire multiple physical variables that affect pipeline leakage behavior.

[0053] The physical variables include influencing factor variables and result variables. The influencing factor variables include: pipeline leakage rate, fluid density in the pipeline, pipeline diameter, fluid flow rate in the pipeline, and the distance between the leakage point and the pipeline outlet. The result variables include: pressure change between the pipeline inlet and outlet.

[0054] The pressure change between the pipeline inlet and the pipeline outlet may be a pressure difference between a first detection point at the pipeline inlet and a second detection point at the pipeline outlet.

[0055] It should be noted that the physical variables obtained here only determine the physical variables that affect the pipeline leakage behavior, rather than obtaining the corresponding values ​​of these physical variables.

[0056] Step 102: Perform dimensionless processing on the multiple physical variables to obtain a dimensionless relationship group.

[0057] Through dimensionless processing, multiple physical variables can be converted into fewer key dimensionless variables, which can improve the efficiency of generating prediction models.

[0058] Step 103: Acquire a historical data set, wherein the historical data set stores a mapping relationship between parameter values ​​corresponding to the influencing factor variables and parameter values ​​corresponding to the result variables, and the historical data set is divided into a training data set and a validation data set.

[0059] It should be noted that the historical data set stores the mapping relationship between the parameter values ​​corresponding to the impact factor variables collected at historical time and the parameter values ​​corresponding to the result variables. Here, the mapping relationship stores the variables and the data values ​​corresponding to the variables, not just the variables.

[0060] Step 104: Generate a prediction model using the training data set and the dimensionless relationship group.

[0061] Step 105, obtaining the collected data of the current pipeline, wherein the collected data includes: pipeline leakage rate value, fluid density value in the pipeline, fluid flow rate value in the pipeline, pipeline diameter value, and pressure change value between the pipeline inlet and outlet.

[0062] The pipe diameter value can be directly measured. Taking the fluid transmitted in the pipe as gas as an example, the density of the fluid in the pipe can be calculated based on the gas pressure, temperature and molar mass of the gas in the pipe, and the gas pressure can be detected using a pressure detector.

[0063] The flow rate of the fluid in the pipeline can be detected by a gas detector. In addition, the gas detector can also detect the gas flow rate and gas concentration in the pipeline, and calculate the pipeline leakage rate when the approximate diameter range of the leak hole is known.

[0064] Step 106: input the collected data into the prediction model to predict the leakage position of the pipeline.

[0065] It should be noted that the present application may execute step 101 and step 102 first and then execute step 103, or step 103 of the present application may be executed in parallel with the process of step 101 and step 102, and the present application does not make any specific limitation on this.

[0066] The embodiment of the present application provides a method for determining pipeline leakage points based on dimensional analysis and CFD simulation, by obtaining multiple physical variables that affect pipeline leakage behavior, the physical variables include influencing factor variables and result variables, the influencing factor variables include: pipeline leakage rate, fluid density in the pipeline, pipeline diameter, fluid flow rate in the pipeline, and the distance between the leakage point and the pipeline outlet, the result variable includes: pressure change between the pipeline inlet and outlet; multiple physical variables are dimensionally processed to obtain a dimensionless relationship group; a historical data set is obtained, the historical data set stores a mapping relationship between parameter values ​​corresponding to the influencing factor variables and parameter values ​​corresponding to the result variables, and the historical data set is divided into a training data set and a verification data set; a prediction model is generated using the training data set and the dimensionless relationship group; the collected data of the current pipeline is obtained, the collected data includes: pipeline leakage rate value, fluid density value in the pipeline, fluid flow rate value in the pipeline, pipeline diameter value, pressure change value between the pipeline inlet and outlet; the collected data is input into the prediction model to predict the leakage position of the pipeline. This application uses dimensional analysis combined with CFD simulation to predict the process of leakage points. Through dimensionless processing, multiple physical variables can be converted into a few key dimensionless variables, which can improve the efficiency of generating prediction models, and use CFD simulation to generate training data sets and key dimensionless relationship groups for prediction models to predict leakage points. This method not only improves the accuracy of prediction, but also shortens the calculation time, allowing for rapid response in emergency situations.

[0067] Optionally, the process of performing dimensionless processing on the multiple physical variables in step 102 to obtain the dimensionless relationship group may be:

[0068] A target variable to be dimensionless is selected from the multiple physical variables; a basic variable is determined from the multiple physical variables; and the dimensionless relationship group is constructed based on the target variable and the basic variables.

[0069] Optionally, the target variable may include: the pipeline leakage rate, the distance and the pressure change; the basic variable may include: the fluid density, the fluid flow rate and the pipeline diameter; the process of constructing the dimensionless relationship group according to the target variable and the basic variable may be:

[0070] Performing dimensionless processing on the pipeline leakage rate to form a first dimensionless relationship based on the pipeline leakage rate, the fluid density, the fluid flow rate and the pipeline diameter;

[0071] Non-dimensionalizing the distance to form a second non-dimensional relationship based on the distance and the pipe diameter;

[0072] The pressure change is dimensionally processed to form a third dimensionless relationship based on the pressure change, the fluid density and the fluid flow rate.

[0073] Specifically, after obtaining the target variables and basic variables, the dimensionless group can be constructed using Buckmingham π theorem.

[0074] Among them, the first dimensionless relationship can be:

[0075] The second dimensionless relationship can be:

[0076] The third dimensionless relationship can be:

[0077] The above, is the pipeline leakage rate, ρ is the density of the fluid in the pipeline, u is the flow rate of the fluid in the pipeline, D is the pipeline diameter, L is the distance between the leakage point and the pipeline outlet, and P is the pressure change between two different detection points on the pipeline.

[0078] It can be understood that the above dimensionless processing can convert multiple physical variables into a few key dimensionless variables, namely π1, π2, π3.

[0079] Optionally, the process of generating a prediction model using the training data set and the dimensionless relationship group in step 104 may be:

[0080] The pressure change values ​​under different influencing factor variable values ​​in the training data set are input into the corresponding dimensionless relationship to obtain multiple corresponding first conversion values, second conversion values ​​and third conversion values; and the prediction model is determined using the multiple corresponding first conversion values, the second conversion values ​​and the third conversion values.

[0081] Among them, the first conversion value is the above-mentioned π1, the second conversion value is the above-mentioned π2, and the third conversion value is the above-mentioned π3. In the actual implementation process, the data in the above-mentioned training data set can be correspondingly input into the above-mentioned first dimensional relationship, second dimensionless relationship and third dimensionless relationship to obtain the corresponding first conversion value, second conversion value and third conversion value.

[0082] It should be noted that the above prediction model is a prediction function formed by fitting multiple π1, π2, and π3 data.

[0083] Optionally, after the above step 104 generates the prediction model, the method further includes: using the verification data set to optimize the parameters of the prediction model until the prediction accuracy of the prediction model reaches a preset accuracy, and obtaining a target prediction model; inputting the collected data into the prediction model includes: inputting the collected data into the target prediction model.

[0084] In the actual implementation process, the above-mentioned process of optimizing the parameters of the prediction model using the verification data set can be: using the verification data set through the fit tool in ORIGIN or the fit function in Python to determine and optimize other parameters in the prediction function, improve the fitting accuracy, further verify the accuracy of the prediction function, and adjust other parameters of the prediction function as needed.

[0085] In addition, the above-mentioned optimization of parameters of the prediction model using the validation data set can also be: the data in the historical data set is integrated into a mathematical formula using a neural network method. First, the data in the historical data set is preprocessed, including normalization, denoising, removal of outliers, etc. A feedforward neural network is selected, the number of neurons in the input layer, hidden layer, and output layer is determined, and the neural network is trained using a training data set. The validation data set is used to evaluate the performance of the neural network, and hyperparameters (such as learning rate, number of hidden layers, etc.) are adjusted to avoid overfitting or underfitting. The validation data set is used to ultimately evaluate the generalization ability of the neural network. Finally, polynomial regression, support vector machine (SVM), etc. are used to obtain the above-mentioned prediction model.

[0086] As a possible implementation, the process of obtaining the historical data set in step 103 may be: establishing simulation models of multiple different pipeline leakage scenarios;

[0087] Based on the CFD calculation method, simulation calculations are performed on the simulation models of the multiple different pipeline leakage scenarios to obtain pressure change values ​​of each pipeline under different influencing factor variable values;

[0088] The pressure change values ​​of each pipeline under different influencing factor variable values ​​are mapped and stored to obtain the historical data set.

[0089] Among them, Computational Fluid Dynamics (CFD) is equivalent to "virtually" conducting experiments on computers to simulate actual fluid flow conditions. Its basic principle is to numerically solve the differential equations that control fluid flow, and obtain the discrete distribution of the flow field of fluid flow in a continuous area, thereby approximately simulating the fluid flow conditions. CFD can be considered a type of modern simulation technology.

[0090] In the actual implementation process, a pipeline leakage location model can be established, and the test conditions can be designed according to the Latin hypercube sampling design method. Fluent software can be used for simulation calculation to obtain the pressure change values ​​of the pipeline under different influencing factor variable values ​​under multiple different pipeline leakage scenarios, thereby obtaining the above historical data set. This can improve the efficiency of obtaining historical data sets.

[0091] As another possible implementation, the process of obtaining the historical data set in step 103 may also be:

[0092] The pressure change values ​​under different influencing factor variable values ​​obtained by testing multiple sensors at different leakage scenarios in multiple different pipelines at historical time are obtained; the pressure change values ​​under different influencing factor variable values ​​are mapped and stored to obtain the historical data set.

[0093] A method for determining pipeline leakage points based on dimensional analysis and CFD simulation provided by the embodiment of the present application, applying the dimensional analysis method to the deduction process of the leakage point, can help researchers quickly identify key parameters in the leakage process in multiple physical quantities, such as leakage rate, leakage position and fluid properties, greatly simplifying the real-time detection of leakage positions to optimize the layout of pipeline sensors. The present application converts specific physical parameters (such as pressure change, leakage rate and leakage position) into dimensionless form, thereby developing a mathematical model between pressure change and leakage position and leakage rate, and associating dimensionless variables with leakage positions. The dimensionless parameters converted from dimensional analysis can effectively simplify this mathematical model, and can eliminate the influence of physical quantity units by dimensionless methods, so that the model results are more universal, not affected by specific measurement units, and can be more easily applied in different pipeline systems and conditions. Several unknown parameters contained in the model need to be simulated by CFD to change the pressure changes under dimensionless leakage position and dimensionless leakage rate, build a database, and fit the unknown parameters in the mathematical model by the fit tool in ORIGIN. By measuring the pressure changes and leakage rate of the pipeline, the leakage location can be detected in real time, thereby improving the efficiency and accuracy of pipeline safety management.

[0094] The present application also provides a device for determining the location of pipeline leakage based on dimensional analysis and CFD simulation, such as Figure 2 As shown, the device comprises:

[0095] A first acquisition module 11 is used to acquire multiple physical variables that affect pipeline leakage behavior, wherein the physical variables include influencing factor variables and result variables, wherein the influencing factor variables include: pipeline leakage rate, fluid density in the pipeline, pipeline diameter, fluid flow rate in the pipeline, and the distance between the leakage point and the pipeline outlet, and the result variables include: pressure change between the pipeline inlet and outlet;

[0096] A first processing module 12 is used to perform dimensionless processing on the multiple physical variables to obtain a dimensionless relationship group;

[0097] A second acquisition module 13 is used to acquire a historical data set, wherein the historical data set stores a mapping relationship between parameter values ​​corresponding to the influencing factor variables and parameter values ​​corresponding to the result variables, and the historical data set is divided into a training data set and a validation data set;

[0098] A generating module 14, configured to generate a prediction model using the training data set and the dimensionless relationship group;

[0099] The third acquisition module 15 is used to acquire the collected data of the current pipeline, wherein the collected data includes: pipeline leakage rate value, fluid density value in the pipeline, fluid flow rate value in the pipeline, pipeline diameter value, and pressure change value between the pipeline inlet and outlet;

[0100] The prediction module 16 is used to input the collected data into the prediction model to predict the leakage position of the pipeline.

[0101] In one embodiment, the first processing module 12 is specifically used for:

[0102] Selecting a target variable to be dimensionless from the plurality of physical variables;

[0103] determining a basic variable from the plurality of physical variables;

[0104] The dimensionless relationship group is constructed according to the target variable and the basic variables.

[0105] In one embodiment, the target variables include: the pipeline leakage rate, the distance and the pressure change; the basic variables include: the fluid density, the fluid flow rate and the pipeline diameter; the first processing module 12 is specifically used for:

[0106] Performing dimensionless processing on the pipeline leakage rate to form a first dimensionless relationship based on the pipeline leakage rate, the fluid density, the fluid flow rate and the pipeline diameter;

[0107] Non-dimensionalizing the distance to form a second non-dimensional relationship based on the distance and the pipe diameter;

[0108] The pressure change is dimensionally processed to form a third dimensionless relationship based on the pressure change, the fluid density and the fluid flow rate.

[0109] In one embodiment, the generating module 14 is specifically used for:

[0110] Inputting the pressure change values ​​under different influencing factor variable values ​​in the training data set into the corresponding dimensionless relationship to obtain a plurality of corresponding first conversion values, second conversion values ​​and third conversion values;

[0111] The prediction model is determined using a plurality of corresponding first conversion values, second conversion values, and third conversion values.

[0112] In one embodiment, the generating module 14 is further configured to:

[0113] Optimizing the parameters of the prediction model using the validation data set until the prediction accuracy of the prediction model reaches a preset accuracy, thereby obtaining a target prediction model;

[0114] The prediction module 16 is further used to: input the collected data into the target prediction model.

[0115] In one embodiment, the third acquisition module 15 is specifically used for:

[0116] Establish simulation models for multiple different pipeline leakage scenarios;

[0117] Based on the CFD calculation method, simulation calculations are performed on the simulation models of the multiple different pipeline leakage scenarios to obtain pressure change values ​​of each pipeline under different influencing factor variable values;

[0118] The pressure change values ​​of each pipeline under different influencing factor variable values ​​are mapped and stored to obtain the historical data set.

[0119] In one embodiment, the third acquisition module 15 is specifically used for:

[0120] Obtain the pressure change values ​​of different pipelines under different leakage scenarios at historical time, using multiple sensors to test different influencing factor variable values;

[0121] The pressure change values ​​under different influencing factor variable values ​​are mapped and stored to obtain the historical data set.

[0122] The device for determining pipeline leakage points based on dimensional analysis and CFD simulation provided in the embodiment of the present application can execute the above-mentioned method embodiment for determining pipeline leakage points based on dimensional analysis and CFD simulation. Its implementation principle and technical effects are similar and will not be elaborated here.

[0123] For the specific definition of the device for determining the pipeline leakage point based on dimensional analysis and CFD simulation, please refer to the definition of the method for determining the pipeline leakage point based on dimensional analysis and CFD simulation above, which will not be repeated here. Each module in the above-mentioned device for determining the pipeline leakage point based on dimensional analysis and CFD simulation can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor of the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0124] The executor of the method for determining pipeline leakage points based on dimensional analysis and CFD simulation provided in the embodiment of the present application may be an electronic device, which may include a server, a server cluster, a computer device, a terminal device or a processing chip, etc. The embodiment of the present application does not make any specific limitations on this.

[0125] Figure 3 This is a schematic diagram of the internal structure of an electronic device provided in an embodiment of the present application. Figure 3 As shown, the electronic device includes a processor and a memory connected via a system bus. The processor is used to provide computing and control capabilities. The memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The computer program can be executed by the processor to implement the steps of the method for determining the pipeline leakage point based on dimensional analysis and CFD simulation provided in the above embodiments. The internal memory provides a cache operating environment for the operating system and the computer program in the non-volatile storage medium.

[0126] Those skilled in the art will understand that Figure 3 The internal structure diagram of the electronic device shown in the figure is only a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0127] In another embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of determining the pipeline leakage point based on dimensional analysis and CFD simulation as in the embodiment of the present application are implemented.

[0128] In another embodiment of the present application, a computer program product is also provided, which includes computer instructions. When the computer instructions are executed on a device for determining pipeline leakage points based on dimensional analysis and CFD simulation, the device for determining pipeline leakage points based on dimensional analysis and CFD simulation executes each step of the method for determining pipeline leakage points based on dimensional analysis and CFD simulation in the method flow shown in the above method embodiment.

[0129] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing computer execution instructions on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server, data center, etc. that contains one or more servers that can be integrated with a medium. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0130] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0131] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for determining pipeline leakage points based on dimensional analysis and CFD simulation, characterized in that: The method comprises: Acquire multiple physical variables that affect pipeline leakage behavior, wherein the physical variables include influencing factor variables and result variables, wherein the influencing factor variables include: pipeline leakage rate, fluid density in the pipeline, pipeline diameter, fluid flow rate in the pipeline, and the distance between the leakage point and the pipeline outlet, and the result variables include: pressure change between the pipeline inlet and outlet; Performing dimensionless processing on the multiple physical variables to obtain a dimensionless relationship group; Acquire a historical data set, wherein the historical data set stores a mapping relationship between parameter values ​​corresponding to the influencing factor variables and parameter values ​​corresponding to the result variables, and the historical data set is divided into a training data set and a validation data set; Generate a prediction model using the training data set and the dimensionless relationship group; Acquire the collected data of the current pipeline, the collected data including: pipeline leakage rate value, fluid density value in the pipeline, fluid flow rate value in the pipeline, pipeline diameter value, and pressure change value between the pipeline inlet and outlet; The collected data is input into the prediction model to predict the leakage position of the pipeline.

2. The method according to claim 1, characterized in that The step of performing dimensionless processing on the plurality of physical variables to obtain a dimensionless relationship group includes: Selecting a target variable to be dimensionless from the plurality of physical variables; determining a basic variable from the plurality of physical variables; The dimensionless relationship group is constructed according to the target variable and the basic variables.

3. The method according to claim 2, characterized in that The target variables include: the pipeline leakage rate, the distance and the pressure change; the basic variables include: the fluid density, the fluid flow rate and the pipeline diameter; the dimensionless relationship group constructed according to the target variables and the basic variables includes: Performing dimensionless processing on the pipeline leakage rate to form a first dimensionless relationship based on the pipeline leakage rate, the fluid density, the fluid flow rate and the pipeline diameter; Non-dimensionalizing the distance to form a second non-dimensional relationship based on the distance and the pipe diameter; The pressure change is dimensionally processed to form a third dimensionless relationship based on the pressure change, the fluid density and the fluid flow rate.

4. The method according to claim 3, characterized in that: The step of generating a prediction model by using the training data set and the dimensionless relationship combination includes: Inputting the pressure change values ​​under different influencing factor variable values ​​in the training data set into the corresponding dimensionless relationship to obtain a plurality of corresponding first conversion values, second conversion values ​​and third conversion values; The prediction model is determined using a plurality of corresponding first conversion values, second conversion values, and third conversion values.

5. The method according to claim 1, characterized in that After generating a prediction model by using the training data set and the dimensionless relationship combination, the method further includes: Optimizing the parameters of the prediction model using the validation data set until the prediction accuracy of the prediction model reaches a preset accuracy, thereby obtaining a target prediction model; The step of inputting the collected data into the prediction model comprises: The collected data is input into the target prediction model.

6. The method according to claim 1, characterized in that The obtaining of the historical data set includes: Establish simulation models for multiple different pipeline leakage scenarios; Based on the CFD calculation method, simulation calculations are performed on the simulation models of the multiple different pipeline leakage scenarios to obtain pressure change values ​​of the pipeline under different influencing factor variable values; The pressure change values ​​of the pipeline under different influencing factor variable values ​​are mapped and stored to obtain the historical data set.

7. The method according to claim 1, characterized in that The acquisition of the historical technology set includes: Obtain the pressure change values ​​of different pipelines under different leakage scenarios at historical time, using multiple sensors to test different influencing factor variable values; The pressure change values ​​under different influencing factor variable values ​​are mapped and stored to obtain the historical data set.

8. A device for determining pipeline leakage points based on dimensional analysis and CFD simulation, characterized in that: The device comprises: A first acquisition module is used to acquire multiple physical variables that affect pipeline leakage behavior, wherein the physical variables include influencing factor variables and result variables, wherein the influencing factor variables include: pipeline leakage rate, fluid density in the pipeline, pipeline diameter, fluid flow rate in the pipeline, and the distance between the leakage point and the pipeline outlet, and the result variables include: pressure change value between the pipeline inlet and outlet; A first processing module is used to perform dimensionless processing on the multiple physical variables to obtain a dimensionless relationship group; A second acquisition module is used to acquire a historical data set, wherein the historical data set stores a mapping relationship between parameter values ​​corresponding to the influencing factor variables and parameter values ​​corresponding to the result variables, and the historical data set is divided into a training data set and a validation data set; A generation module, used to generate a prediction model using the training data set and the dimensionless relationship group; The third acquisition module is used to acquire the collected data of the current pipeline, wherein the collected data includes: pipeline leakage rate value, fluid density value in the pipeline, fluid flow rate value in the pipeline, pipeline diameter value, and pressure change value between the pipeline inlet and outlet; The prediction module is used to input the collected data into the prediction model to predict the leakage position of the pipeline.

9. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for determining the pipeline leakage point based on dimensional analysis and CFD simulation as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method for determining the pipeline leakage point based on dimensional analysis and CFD simulation as described in any one of claims 1 to 7 is implemented.

Images