Valve control method based on inverse calculation of gas pipeline commissioning pressure regulating valve flow

Abstract

The disclosure provides a valve control method based on natural gas pipeline commissioning pressure regulating valve flow back calculation, relates to the natural gas pipeline valve regulation and control technical field, and the method comprises the following steps: obtaining a predetermined reproduction constraint; extracting a first historical record; obtaining an intelligent flow prediction model; acquiring first regulation and control data, reproducing the first regulation and control data; obtaining a plurality of reproduction regulation and control flow prediction values; obtaining optimal regulation and control parameters; iteratively optimizing to obtain first target regulation and control parameters and performing initial regulation and control setting. Through the disclosure, the technical problems of low reliability of valve flow determined only by the valve characteristic curve in the prior art and prediction accuracy of the change of the flow coefficient under different working conditions and different types of gas conditions can be solved, the valve flow in the natural gas pipeline commissioning operation is determined through targeted calculation, and the technical effect of improving the fitting degree between the calculation result and the valve flow during the natural gas pipeline commissioning operation is achieved.

Description

Technical Field

[0001] This disclosure relates to the field of natural gas pipeline valve regulation technology, specifically to a valve control method based on back-calculation of flow rate of pressure regulating valves during natural gas pipeline commissioning. Background Technology

[0002] When natural gas pipelines are put into operation, the relationship between valve opening and gas flow rate is not yet clearly quantified. However, to improve the accuracy of gas input in natural gas pipelines, research on valve flow rate back-calculation is urgently needed. Existing technologies use valve characteristic curves to analyze and determine the relative valve opening and corresponding relative flow rate. However, for compressible fluids like natural gas, the pressure upstream of the valve often directly affects the flow rate, making it impossible to determine the valve flow rate solely through the valve characteristic curve. Therefore, existing technologies, in addition to analyzing the valve characteristic curve, can also use formulas to calculate the valve flow rate, such as calculating the flow coefficient. Current methods for determining the valve flow rate of compressible fluids like natural gas generally include upstream density method, downstream density method, average density method, compressibility coefficient method, critical flow coefficient method, sine method, polynomial method, and expansion coefficient method. However, research has found that the mathematical expression of the flow coefficient varies for different operating conditions and different types of gas. Furthermore, the mathematical expression and correction coefficients also differ for different types of control valves. Furthermore, existing methods have used numerical simulations, experiments, and theoretical studies to fit flow formulas for valves under different operating conditions. However, the resulting fitted formulas are often empirical or semi-empirical formulas.

[0003] Therefore, it is urgent to study and develop an objective, efficient, and accurate method for back-calculating valve flow rates, so as to perform targeted calculations and determinations of valve flow rates during the commissioning of natural gas pipelines, and improve the fit between the calculation results and the valve flow rates during the commissioning of natural gas pipelines on site. Summary of the Invention

[0004] This disclosure provides a valve control method based on the back calculation of flow rate of pressure regulating valves during the commissioning of natural gas pipelines, in order to solve the technical problems of low reliability in determining valve flow rate solely through valve characteristic curves in the prior art and the accuracy of predicting flow coefficient changes under different operating conditions and different types of gas.

[0005] According to a first aspect of this disclosure, a valve control method based on back-calculation of flow rate of pressure regulating valves in natural gas pipelines is provided, comprising: analyzing preset control indicators to obtain predetermined proliferation constraints; extracting a first historical record from historical control records of similar valve products of the target pressure regulating valve, the first historical record including a first historical control indicator parameter set and a first historical valve flow rate; performing supervised training on the first historical control indicator parameter set and the first historical valve flow rate based on neural network principles to obtain an intelligent flow prediction model; randomly acquiring first control data and proliferating the first control data in combination with the predetermined proliferation constraints to obtain a first proliferation set, the first proliferation set including multiple proliferation control data; sequentially analyzing the multiple proliferation control data through the intelligent flow prediction model to obtain multiple proliferation control flow prediction values; taking the proliferation control data corresponding to the proliferation control flow prediction value with the smallest deviation from the preset valve flow rate among the multiple proliferation control flow prediction values ​​obtained by back-matching as the optimal control parameter; iteratively optimizing until a predetermined iteration threshold is reached, and taking the optimal control parameter obtained at that time as a first target control parameter, the first target control parameter being used for initial control settings of the target pressure regulating valve.

[0006] According to a second aspect of this disclosure, a valve control system based on flow back calculation of pressure regulating valves in natural gas pipeline commissioning is provided, comprising: a predetermined propagation constraint acquisition module, which is used to analyze preset control indicators to obtain predetermined propagation constraints; a first historical record acquisition module, which is used to extract a first historical record from historical control records of similar valve products of the target pressure regulating valve, the first historical record including a first historical control indicator parameter set and a first historical valve flow; an intelligent flow prediction model acquisition module, which is used to perform supervised training on the first historical control indicator parameter set and the first historical valve flow based on neural network principles to obtain an intelligent flow prediction model; and a first propagation set acquisition module, which is used to randomly acquire first control data and combine it with the predetermined propagation constraints to obtain a first historical control indicator parameter set and a first historical valve flow. The system comprises: a first set of propagated data, including multiple propagated control data; a module for obtaining multiple propagated control flow prediction values, which analyzes the multiple propagated control data sequentially using the intelligent flow prediction model to obtain multiple propagated control flow prediction values; an optimal control parameter acquisition module, which selects the propagated control flow prediction value with the smallest deviation from the preset valve flow rate among the multiple propagated control flow prediction values ​​obtained through reverse matching as the optimal control parameter; and a first target control parameter acquisition module, which iteratively optimizes the system until a predetermined iteration threshold is reached, and uses the optimal control parameter obtained at that time as the first target control parameter, which is used to initially control the target pressure regulating valve.

[0007] According to a third aspect of this disclosure, a computer device includes a memory and a processor, the memory storing a computer program and the processor implementing the method described in any one of the first aspects.

[0008] According to a fourth aspect of this disclosure, a computer-readable storage medium has a computer program stored thereon, which, when executed by a processor, implements the method described in any one of the first aspects.

[0009] One or more technical solutions provided in this disclosure have at least the following technical effects or advantages: According to this disclosure, a predetermined propagation constraint is obtained by analyzing preset control indicators; a first historical record is extracted from the historical control records of similar valve products of the target pressure regulating valve, the first historical record including a first historical control indicator parameter set and a first historical valve flow rate; supervised training is performed on the first historical control indicator parameter set and the first historical valve flow rate based on neural network principles to obtain an intelligent flow prediction model; first control data is randomly acquired, and propagation is performed on the first control data in conjunction with the predetermined propagation constraint to obtain a first propagation set, the first propagation set including multiple propagation control data; the multiple propagation control data are analyzed sequentially through the intelligent flow prediction model to obtain... Multiple propagation-regulated flow prediction values ​​are obtained; the propagation-regulated flow prediction value with the smallest deviation from the preset valve flow rate among the multiple propagation-regulated flow prediction values ​​obtained by reverse matching is taken as the optimal regulation parameter; iterative optimization is performed until a predetermined iteration threshold is reached, and the optimal regulation parameter obtained at that time is taken as the first target regulation parameter. The first target regulation parameter is used to perform initial regulation settings on the target pressure regulating valve. This solves the technical problems of low reliability in determining valve flow rate solely through valve characteristic curves and the accuracy of predicting flow coefficient changes under different operating conditions and different types of gas conditions in the prior art. It achieves the technical effect of targeted calculation and determination of valve flow rate during natural gas pipeline commissioning operations, and improves the fitting degree between the calculation results and the valve flow rate during on-site natural gas pipeline commissioning operations.

[0010] It should be understood that the description in this section is not intended to highlight key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0012] Figure 1 A flowchart illustrating a valve control method based on back-calculation of flow rate of pressure regulating valves during natural gas pipeline commissioning is provided for embodiments of this disclosure.

[0013] Figure 2 This is a logical diagram illustrating the device relationships in a valve control method based on back-calculation of flow rate from a pressure regulating valve during natural gas pipeline commissioning, according to an embodiment of this disclosure.

[0014] Figure 3 A schematic diagram of a valve control system based on flow back calculation of pressure regulating valves during natural gas pipeline commissioning, provided in an embodiment of this disclosure;

[0015] Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of this disclosure.

[0016] Explanation of reference numerals in the attached figures: Module 11 for obtaining predetermined breeding constraints, Module 12 for obtaining first historical records, Module 13 for obtaining intelligent flow prediction model, Module 14 for obtaining first breeding set, Module 15 for obtaining multiple breeding regulation flow prediction values, Module 16 for obtaining optimal regulation parameters, Module 17 for obtaining first target regulation parameters, Computer device 100, Processor 101, Memory 102, Bus 103. Detailed Implementation

[0017] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0018] Example 1

[0019] The valve control method based on flow back calculation of pressure regulating valves during natural gas pipeline commissioning provided in this disclosure embodiment is referred to below. Figure 1 and Figure 2 As explained, the method includes:

[0020] The method provided in this disclosure includes:

[0021] Analysis of preset control indicators yields predetermined reproduction constraints;

[0022] Specifically, preset control indicators for natural gas pipelines are obtained through big data retrieval or historical control records. Correspondingly, threshold values ​​for multiple indicators within these preset control indicators are obtained through big data retrieval or historical control records. These threshold values ​​serve as predetermined propagation constraints for each preset control indicator. These predetermined propagation constraints are the conditions for automatic propagation.

[0023] Extract the first historical record from the historical control records of similar valve products of the target pressure regulating valve. The first historical record includes the first historical control index parameter set and the first historical valve flow.

[0024] Specifically, the target pressure regulating valve is a natural gas pipeline valve whose pressure is to be regulated. Based on big data retrieval, historical control records of similar valve products for the target pressure regulating valve are obtained. A set of historical records is randomly extracted from the collected historical control records of similar valve products for the target pressure regulating valve as the first historical record. For example, the similar valve products for the target pressure regulating valve are natural gas pipeline valves that were regulated at the same time and in the same batch as the target pressure regulating valve, or natural gas pipeline valves of the same material and model from a historical batch. Further, the first historical record includes a first historical control indicator parameter set and a first historical valve flow rate. The first historical record is accessed sequentially based on preset control indicators to obtain the first historical control indicator parameter set.

[0025] Based on the principle of neural networks, the first historical control index parameter set and the first historical valve flow are subjected to supervised training to obtain an intelligent flow prediction model.

[0026] Specifically, an intelligent flow prediction model is constructed based on a BP neural network. This model is a neural network model that can be iteratively optimized in machine learning. The first historical control index parameter set and the first historical valve flow rate are used as the training dataset, and supervised training is performed using this dataset. The sample dataset is divided into a training set and a validation set according to a preset data partitioning rule. The preset partitioning ratio can be customized by those skilled in the art based on actual conditions, for example, 85% or 15%. The intelligent flow prediction model is then trained under supervised conditions using the training set. When the output result of the intelligent flow prediction model tends to converge, the accuracy of the output result is verified using the validation set to obtain a preset validation accuracy index. This preset validation accuracy index can be customized by those skilled in the art based on actual conditions, for example, 95%. When the accuracy of the intelligent flow prediction model's output result is greater than or equal to the preset validation accuracy index, the intelligent flow prediction model is obtained.

[0027] Randomly obtain first regulation data, and combine it with the predetermined reproduction constraint to reproduce the first regulation data to obtain a first reproduction set, which includes multiple reproduction regulation data.

[0028] Specifically, first control data is randomly acquired, which represents any achievable opening degree of the target control valve. For example, the first control data can be acquired based on historical valve control records. Further, the first control data is propagated using predetermined propagation constraints to obtain a first propagation set, which includes multiple propagation control data sets. For example, the propagation method can be optimized using an invasive weed method. The predetermined propagation constraints are constraints on the control thresholds of valve opening data, valve characteristic data, valve flow gas characteristics, valve operating conditions, and valve operating environment control indicators.

[0029] The intelligent flow prediction model is used to analyze the multiple reproductive regulation data in sequence and obtain multiple reproductive regulation flow prediction values.

[0030] Specifically, multiple reproductive regulation data points are input into an intelligent flow prediction model. The model then analyzes these data points sequentially to obtain multiple predicted flow rates. For example, the multiple reproductive regulation data points might represent multiple aperture values, which are then used by the intelligent flow prediction model to output multiple predicted gas flow rates.

[0031] The optimal control parameter is the reproductive control data corresponding to the reproductive control flow prediction value with the smallest deviation from the preset valve flow rate among the multiple reproductive control flow prediction values ​​obtained by reverse matching.

[0032] Specifically, the optimal control parameter is the propagation control data corresponding to the propagation control flow prediction value with the smallest deviation from the preset valve flow rate among multiple propagation control flow prediction values ​​obtained through reverse matching. For example, multiple predicted gas flow rates obtained through multiple valve opening values ​​are compared sequentially with the preset valve flow rate to obtain multiple comparison deviations. Further, the multiple comparison deviations are serialized according to the deviation values ​​from smallest to largest, and the deviation value with the largest ranking is obtained as the value with the smallest deviation obtained from the comparison. The valve opening value corresponding to the predicted gas flow rate with the smallest deviation from the preset valve flow rate is taken as the optimal control parameter.

[0033] The process iterates until a predetermined iteration threshold is reached, and the optimal control parameter obtained at that time is used as the first target control parameter. The first target control parameter is used to perform initial control settings on the target pressure regulating valve.

[0034] Specifically, the propagation control data is iteratively optimized and compared with the preset valve flow deviation. The optimization is iterated until a predetermined iteration threshold is reached. The optimal control parameter obtained at that time is used as the first target control parameter, which is used to initially control the target pressure regulating valve. The predetermined iteration threshold can be customized by those skilled in the art according to the actual situation.

[0035] This embodiment addresses the technical problems of low reliability in determining valve flow rate solely through valve characteristic curves and the accuracy of predicting flow coefficient changes under different operating conditions and gas types in existing technologies. It achieves the technical effect of targeted calculation and determination of valve flow rate during natural gas pipeline commissioning operations, improving the fit between the calculation results and the valve flow rate during on-site natural gas pipeline commissioning operations.

[0036] The method provided in this disclosure also includes:

[0037] The preset control indicators are obtained, including valve opening data, valve characteristic data, valve gas flow characteristics, valve operating conditions, and valve operating environment.

[0038] The valve opening data, valve characteristic data, valve flow gas characteristics, valve operating conditions, and valve operating environment are acquired sequentially.

[0039] The first threshold, the second threshold, the third threshold, the fourth threshold, and the fifth threshold are used as the predetermined reproductive constraints.

[0040] Specifically, based on big data retrieval, preset control indicators for natural gas pipeline pressure regulating valves are obtained. These preset control indicators are set within a reasonable range to obtain predetermined constraints. Further, the preset control indicators include valve opening data, valve characteristic data, valve flow gas characteristics, valve operating conditions, and valve operating environment. Valve opening data is percentage data; for example, 0 degrees indicates the valve is fully closed, and 90 degrees indicates the valve is fully open. Valve characteristic data includes valve type and structural parameters. Valve flow gas characteristics refer to gas composition and other gas-distinguishing features. Valve operating conditions refer to the valve's operational status. The valve operating environment refers to the natural gas pipeline environment.

[0041] Furthermore, thresholds are sequentially acquired for the target objects in the preset control indicators, namely, the first threshold for valve opening data, the second threshold for valve characteristic data, the third threshold for valve flow gas characteristics, the fourth threshold for valve operating conditions, and the fifth threshold for valve operating environment.

[0042] Furthermore, the first threshold, second threshold, third threshold, fourth threshold, and fifth threshold are used as predetermined reproductive constraints. Under the state conditions of the predetermined reproductive constraints, the predetermined control data is automatically reproduced to obtain reproductive data.

[0043] Among them, the predetermined reproduction constraints obtained by analyzing the preset control indicators can be used to precisely control the preset indicators.

[0044] The method provided in this disclosure also includes:

[0045] Obtain the target valve type and target valve structure of the target pressure regulating valve;

[0046] The gas flowing through the target pressure regulating valve is detected by the multifunctional gas detector to obtain the real-time characteristics of the gas flowing through the valve.

[0047] The operating environment of the target pressure regulating valve is detected by the environmental detector to obtain the real-time valve operating environment;

[0048] The real-time valve operating condition of the target pressure regulating valve is obtained, and real-time input information is obtained by combining the target valve type, the target valve structure, the real-time valve flow gas characteristics, and the real-time valve operating environment.

[0049] The real-time input information is analyzed by the intelligent traffic prediction model to obtain the real-time traffic prediction value;

[0050] When the real-time flow prediction value is not at the preset flow deviation threshold, a control warning command is issued. The preset flow deviation threshold is a deviation threshold set based on the preset valve flow.

[0051] The first target control parameter is adjusted based on the control and early warning command.

[0052] Specifically, the valve control method based on the back calculation of the flow rate of the pressure regulating valves during the commissioning of natural gas pipelines is applied to the valve control system based on the back calculation of the flow rate of the pressure regulating valves during the commissioning of natural gas pipelines. The system is communicatively connected to a multi-functional gas detector and an environmental detector.

[0053] Furthermore, the target valve type and structure of the target pressure regulating valve are obtained. The target valve type is a piston valve, safety valve, or other application type, and the target valve structure is the valve shape, size, and other structural features.

[0054] Furthermore, the gas flowing through the target pressure regulating valve is detected using a multifunctional gas detector to obtain real-time gas flow characteristics. These real-time gas flow characteristics are the characteristics observed over a given gas flow time, including gas density and volume.

[0055] Furthermore, the operating environment of the target pressure regulating valve is detected by an environmental detector to obtain the real-time valve operating environment. The real-time valve operating environment refers to the real-time characteristics of the gas flow space when gas is flowing, including features such as humidity or dryness.

[0056] Furthermore, by combining the target valve type, target valve structure, real-time valve flow gas characteristics, and real-time valve operating environment, the real-time valve operating condition of the target pressure regulating valve is obtained, thus acquiring real-time input information. Further, an intelligent flow prediction model is used to analyze the real-time valve operating condition of the target pressure regulating valve based on the real-time input information, and under the conditions of the target valve type, target valve structure, real-time valve flow gas characteristics, and real-time valve operating environment, a real-time flow prediction value is obtained.

[0057] Furthermore, a control warning command is issued when the real-time flow prediction value is not within the preset flow deviation threshold. The preset flow deviation threshold is a deviation threshold set based on the preset valve flow rate. The preset valve flow rate is determined according to the target valve type and structure. Depending on actual environmental conditions, the preset valve flow rate has an error range, which serves as the preset flow deviation threshold.

[0058] Furthermore, based on the control and early warning instructions, the control parameters of the first target are adjusted to the preset flow deviation threshold.

[0059] Among these methods, dynamically adjusting the first target control parameter based on actual conditions can improve the accuracy of valve control.

[0060] The method provided in this disclosure also includes:

[0061] Based on the target valve type and the target valve structure, match the target flow characteristic curve of the target pressure regulating valve in the natural gas regulating valve database;

[0062] The opening degree of the target pressure regulating valve when the preset valve flow rate is reached, as determined according to the target flow characteristic curve, is recorded as the second target control parameter.

[0063] Specifically, a natural gas regulating valve database is constructed based on big data retrieval. The database includes multiple regulating valves with valve information identifiers. Each regulating valve with a valve information identifier corresponds to a valve information entry, which includes a valve type, a valve structure, and a valve flow characteristic curve.

[0064] Furthermore, the target pressure regulating valve has a target valve type and a target valve structure, and the target flow characteristic curve corresponding to the target pressure regulating valve is matched in the natural gas regulating valve database based on the target valve type and target valve structure.

[0065] Furthermore, the opening degree of the target pressure regulating valve when the preset valve flow rate is reached, as determined based on the target flow characteristic curve, is recorded as the second target control parameter. The preset valve flow rate is a custom setting obtained by those skilled in the art based on actual conditions.

[0066] Among these, obtaining the second target control parameter can improve the efficiency of valve control.

[0067] The method provided in this disclosure also includes:

[0068] A natural gas regulating valve database is constructed based on big data, and the natural gas regulating valve database includes multiple regulating valves with valve information identification;

[0069] Specifically, a first regulating valve is randomly extracted from the plurality of regulating valves with valve information identifiers, and the first regulating valve corresponds to first valve information, which includes the first valve type, the first valve structure, and the first valve flow characteristic curve of the first regulating valve.

[0070] Specifically, a natural gas regulating valve database is constructed based on big data retrieval. This database includes multiple regulating valves with valve information identifiers. From these identified valves, one regulating valve is randomly selected as the first regulating valve. This first regulating valve corresponds to first valve information, which includes its first valve type, first valve structure, and first valve flow characteristic curve. Furthermore, the first valve flow characteristic curve can be obtained by combining its first valve type and first valve structure.

[0071] Among them, obtaining the correspondence between the first valve type, the first valve structure, and the first valve flow characteristic curve can improve the efficiency of valve control.

[0072] The method provided in this disclosure also includes:

[0073] A set of principles for calculating flow coefficients is established, which includes the inlet density method, outlet density method, average density method, compressibility coefficient method, critical flow coefficient method, sine method, polynomial method, and expansion coefficient method.

[0074] The eight flow coefficient calculation channels respectively obtain eight opening values ​​based on the various calculation principles in the set of flow coefficient calculation principles;

[0075] The average value of the eight opening values ​​is used as the third target control parameter.

[0076] Specifically, a set of flow coefficient calculation principles is established, including the pre-valve density method, post-valve density method, average density method, compressibility coefficient method, critical flow coefficient method, sine method, polynomial method, and expansion coefficient method. Further, eight flow coefficient calculation channels obtain eight opening values ​​based on various calculation principles within the set. Each calculation principle is used to calculate the opening of the target control valve when the target valve flow rate is reached, resulting in eight opening values.

[0077] Furthermore, the sum of the eight opening values ​​is calculated, and the sum of the eight opening values ​​is divided by eight to obtain the calculation result. The average value of the eight opening values ​​is used as the third target control parameter.

[0078] Among them, obtaining eight opening values ​​through eight flow coefficient calculation channels can improve the accuracy of obtaining the third target control parameter.

[0079] The method provided in this disclosure also includes:

[0080] Obtain the weighted value of the second target control parameter and the third target control parameter;

[0081] The first target control parameter is adjusted using the weighted value.

[0082] Specifically, weights are assigned to the second and third target control parameters, for example, in a weight ratio of 6:4. Further, the sum of the products of the weights of the second and third target control parameters, and the sum of the products of the weights of the two third target control parameters are calculated. The sum of these two sums is then used to obtain the weighted value of the second and third target control parameters. This weighted value is then used to adjust the first target control parameter of the target control valve.

[0083] Among them, the weighted second target control parameter and the third target control parameter, and adjusting the first target control parameter can improve the accuracy of valve control.

[0084] Example 2

[0085] Based on the same inventive concept as the valve control method for back-calculating the flow rate of the pressure regulating valve based on the commissioning of a natural gas pipeline in the foregoing embodiments, the following is referred to Figure 3 As an explanation, this disclosure also provides a valve control system based on the back-calculation of flow rate from pressure regulating valves during natural gas pipeline commissioning, the system comprising:

[0086] The predetermined reproduction constraint acquisition module 11 is used to analyze preset control indicators to obtain predetermined reproduction constraints.

[0087] First historical record acquisition module 12 is used to extract the first historical record from the historical control records of similar valve products of the target pressure regulating valve. The first historical record includes a first historical control index parameter set and a first historical valve flow rate.

[0088] The intelligent flow prediction model acquisition module 13 is used to perform supervised training on the first historical control index parameter set and the first historical valve flow based on the neural network principle to obtain the intelligent flow prediction model.

[0089] The first breeding set acquisition module 14 is used to randomly acquire first regulation data and combine it with the predetermined breeding constraints to breed the first regulation data to obtain a first breeding set, which includes multiple breeding regulation data.

[0090] The module 15 for obtaining multiple breeding regulation flow prediction values ​​is used to analyze the multiple breeding regulation data sequentially through the intelligent flow prediction model and obtain multiple breeding regulation flow prediction values.

[0091] The optimal control parameter acquisition module 16 is used to take the breeding control data corresponding to the breeding control flow prediction value with the smallest deviation from the preset valve flow rate among the multiple breeding control flow prediction values ​​obtained by reverse matching as the optimal control parameter.

[0092] The first target control parameter acquisition module 17 is used to iteratively optimize until a predetermined iteration threshold is reached, and the optimal control parameter obtained at that time is used as the first target control parameter. The first target control parameter is used to perform initial control settings on the target pressure regulating valve.

[0093] Furthermore, the system also includes:

[0094] A preset control index acquisition module is used to acquire the preset control index, which includes valve opening data, valve characteristic data, valve flow gas characteristics, valve operating conditions, and valve operating environment.

[0095] A valve opening data acquisition module is used to sequentially acquire a first threshold of the valve opening data, a second threshold of the valve characteristic data, a third threshold of the valve flow gas characteristics, a fourth threshold of the valve operating conditions, and a fifth threshold of the valve operating environment.

[0096] A predetermined reproduction constraint acquisition module is used to use the first threshold, the second threshold, the third threshold, the fourth threshold, and the fifth threshold as the predetermined reproduction constraint.

[0097] Furthermore, the system also includes:

[0098] A target valve type acquisition module is used to acquire the target valve type and target valve structure of the target pressure regulating valve.

[0099] A real-time valve flow gas characteristic acquisition module is used to detect the flow gas of the target pressure regulating valve through the multi-functional gas detector to obtain the real-time valve flow gas characteristics.

[0100] A real-time valve operating environment acquisition module is used to detect the operating environment of the target pressure regulating valve through the environment detector to obtain the real-time valve operating environment.

[0101] The real-time input information acquisition module is used to acquire the real-time valve operating conditions of the target pressure regulating valve, and combine the target valve type, the target valve structure, the real-time valve flow gas characteristics, and the real-time valve operating environment to obtain real-time input information;

[0102] A real-time traffic prediction value acquisition module is used to analyze the real-time input information through the intelligent traffic prediction model to obtain real-time traffic prediction values.

[0103] A control and early warning command acquisition module is used to issue a control and early warning command when the real-time flow prediction value is not at a preset flow deviation threshold, wherein the preset flow deviation threshold is a deviation threshold set based on the preset valve flow.

[0104] The first target control parameter adjustment module is used to adjust the first target control parameter based on the control warning command.

[0105] Furthermore, the system also includes:

[0106] A target flow characteristic curve matching module is used to match the target flow characteristic curve of the target pressure regulating valve in a natural gas regulating valve database based on the target valve type and the target valve structure.

[0107] The second target control parameter acquisition module is used to record the opening degree of the target pressure regulating valve when the preset valve flow rate is reached, as determined according to the target flow characteristic curve, as the second target control parameter.

[0108] Furthermore, the system also includes:

[0109] A natural gas regulating valve database construction module is used to construct a natural gas regulating valve database based on big data. The natural gas regulating valve database includes multiple regulating valves with valve information identifiers.

[0110] The first regulating valve acquisition module is used to randomly extract a first regulating valve from the plurality of regulating valves with valve information identifiers, and the first regulating valve corresponds to first valve information, which includes the first valve type, the first valve structure and the first valve flow characteristic curve of the first regulating valve.

[0111] Furthermore, the system also includes:

[0112] A flow coefficient calculation principle set acquisition module is used to construct a flow coefficient calculation principle set, which includes the inlet density method, outlet density method, average density method, compressibility coefficient method, critical flow coefficient method, sine method, polynomial method, and expansion coefficient method.

[0113] Eight opening value acquisition modules are used to obtain eight opening values ​​for the eight flow coefficient calculation channels based on various calculation principles in the flow coefficient calculation principle set.

[0114] The third target control parameter acquisition module is used to obtain the average value of the eight opening values ​​as the third target control parameter.

[0115] Furthermore, the system also includes:

[0116] A weighted value acquisition module is used to obtain the weighted value of the second target control parameter and the third target control parameter;

[0117] A weighted value processing module is used to adjust the first target control parameter using the weighted value.

[0118] The specific example of the valve control method based on the back-calculation of the flow rate of the pressure regulating valve during natural gas pipeline commissioning in Embodiment 1 is also applicable to the valve control system based on the back-calculation of the flow rate of the pressure regulating valve during natural gas pipeline commissioning in this embodiment. Through the foregoing detailed description of the valve control method based on the back-calculation of the flow rate of the pressure regulating valve during natural gas pipeline commissioning, those skilled in the art can clearly understand the valve control system based on the back-calculation of the flow rate of the pressure regulating valve during natural gas pipeline commissioning in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here. As for the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant details can be found in the method section.

[0119] Example 3

[0120] Figure 4 This is a schematic diagram based on the third embodiment of the present disclosure, as shown below. Figure 4 As shown, the computer device 100 in this disclosure may include a processor 101 and a memory 102.

[0121] Memory 102 is used to store programs. Memory 102 may include volatile memory, such as random-access memory (RAM), such as static random-access memory (SRAM), double data rate synchronous dynamic random-access memory (DDR SDRAM), etc.; memory may also include non-volatile memory, such as flash memory. Memory 102 is used to store computer programs (such as application programs, functional modules, etc. that implement the above methods), computer instructions, etc. The computer programs, computer instructions, etc., can be partitioned and stored in one or more memories 102. Furthermore, the computer programs, computer instructions, data, etc., can be accessed by processor 101.

[0122] The aforementioned computer programs and instructions can be stored in one or more partitions of memory 102. Furthermore, the aforementioned computer programs and instructions can be invoked by processor 101.

[0123] The processor 101 is configured to execute the computer program stored in the memory 102 to implement the various steps in the methods described in the above embodiments.

[0124] For details, please refer to the relevant descriptions in the preceding method embodiments.

[0125] The processor 101 and the memory 102 can be independent structures or integrated structures. When the processor 101 and the memory 102 are independent structures, the memory 102 and the processor 101 can be coupled together via the bus 103.

[0126] The computer device in this embodiment can execute the technical solution in the above method. Its specific implementation process and technical principles are the same, and will not be repeated here.

[0127] According to embodiments of the present disclosure, the present disclosure also provides a computer-readable storage medium storing a computer program that, when executed, implements the steps provided in any of the above embodiments.

[0128] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0129] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A valve control method based on back-calculation of flow rate of pressure regulating valves during natural gas pipeline commissioning, characterized in that, The method includes: Analysis of preset control indicators yields predetermined reproduction constraints; Extract the first historical record from the historical control records of similar valve products of the target pressure regulating valve. The first historical record includes the first historical control index parameter set and the first historical valve flow. Based on the principle of neural networks, the first historical control index parameter set and the first historical valve flow are subjected to supervised training to obtain an intelligent flow prediction model. Randomly obtain first regulation data, and combine it with the predetermined reproduction constraint to reproduce the first regulation data to obtain a first reproduction set, which includes multiple reproduction regulation data. The intelligent flow prediction model is used to analyze the multiple reproductive regulation data in sequence and obtain multiple reproductive regulation flow prediction values. The optimal control parameter is the reproductive control data corresponding to the reproductive control flow prediction value with the smallest deviation from the preset valve flow rate among the multiple reproductive control flow prediction values ​​obtained by reverse matching. The process iterates until a predetermined iteration threshold is reached, and the optimal control parameter obtained at that time is used as the first target control parameter. The first target control parameter is used to perform initial control settings on the target pressure regulating valve.

2. The method according to claim 1, characterized in that, The analysis pre-sets the control indicators to obtain predetermined reproduction constraints, including: The preset control indicators are obtained, including valve opening data, valve characteristic data, valve gas flow characteristics, valve operating conditions, and valve operating environment. The valve opening data, valve characteristic data, valve flow gas characteristics, valve operating conditions, and valve operating environment are acquired sequentially. The first threshold, the second threshold, the third threshold, the fourth threshold, and the fifth threshold are used as the predetermined reproductive constraints.

3. The method according to claim 1, characterized in that, Also includes: Obtain the target valve type and target valve structure of the target pressure regulating valve; The gas flowing through the target pressure regulating valve is detected by a multi-functional gas detector to obtain the real-time characteristics of the gas flowing through the valve. The operating environment of the target pressure regulating valve is detected by an environmental detector to obtain the real-time valve operating environment; The real-time valve operating condition of the target pressure regulating valve is obtained, and real-time input information is obtained by combining the target valve type, the target valve structure, the real-time valve flow gas characteristics, and the real-time valve operating environment. The real-time input information is analyzed by the intelligent traffic prediction model to obtain the real-time traffic prediction value; When the real-time flow prediction value is not at the preset flow deviation threshold, a control warning command is issued. The preset flow deviation threshold is a deviation threshold set based on the preset valve flow. The first target control parameter is adjusted based on the control and early warning command.

4. The method according to claim 3, characterized in that, After obtaining the target valve type and target valve structure of the target pressure regulating valve, the method further includes: Based on the target valve type and the target valve structure, match the target flow characteristic curve of the target pressure regulating valve in the natural gas regulating valve database; The opening degree of the target pressure regulating valve when the preset valve flow rate is reached, as determined according to the target flow characteristic curve, is recorded as the second target control parameter.

5. The method according to claim 4, characterized in that, Before matching the target flow characteristic curve of the target pressure regulating valve in the natural gas regulating valve database based on the target valve type and the target valve structure, the process includes: A natural gas regulating valve database is constructed based on big data, and the natural gas regulating valve database includes multiple regulating valves with valve information identification; Specifically, a first regulating valve is randomly extracted from the plurality of regulating valves with valve information identifiers, and the first regulating valve corresponds to first valve information, which includes the first valve type, the first valve structure, and the first valve flow characteristic curve of the first regulating valve.

6. The method according to claim 4, characterized in that, The method includes a flow coefficient analysis model, wherein the flow coefficient analysis model includes eight flow coefficient calculation channels, and the method includes: A set of principles for calculating flow coefficients is established, which includes the in-valve density method, the out-of-valve density method, the average density method, the compressibility coefficient method, the critical flow coefficient method, the sine method, the polynomial method, and the expansion coefficient method. The eight flow coefficient calculation channels respectively obtain eight opening values ​​based on the various calculation principles in the set of flow coefficient calculation principles; The average value of the eight opening values ​​is used as the third target control parameter.

7. The method according to claim 6, characterized in that, The method further includes: Obtain the weighted value of the second target control parameter and the third target control parameter; The first target control parameter is adjusted using the weighted value.

8. A valve control system based on back-calculation of flow rate of pressure regulating valves during natural gas pipeline commissioning, characterized in that, The system is used to implement the valve control method based on the back calculation of flow rate of pressure regulating valves during natural gas pipeline commissioning, as described in any one of claims 1-7, and the system comprises: A predetermined reproduction constraint acquisition module is used to analyze preset control indicators to obtain predetermined reproduction constraints. The first historical record acquisition module is used to extract the first historical record from the historical control records of similar valve products of the target pressure regulating valve. The first historical record includes a first historical control index parameter set and a first historical valve flow rate. The intelligent flow prediction model acquisition module is used to perform supervised training on the first historical control index parameter set and the first historical valve flow based on the neural network principle to obtain the intelligent flow prediction model. The first breeding set acquisition module is used to randomly acquire first regulation data and combine it with the predetermined breeding constraints to breed the first regulation data to obtain a first breeding set, which includes multiple breeding regulation data. A module for obtaining multiple breeding regulation flow prediction values ​​is used to analyze the multiple breeding regulation data sequentially through the intelligent flow prediction model and obtain multiple breeding regulation flow prediction values. The optimal control parameter acquisition module is used to take the reproductive control data corresponding to the reproductive control flow prediction value with the smallest deviation from the preset valve flow rate among the multiple reproductive control flow prediction values ​​obtained by reverse matching as the optimal control parameter. The first target control parameter acquisition module is used to iteratively optimize until a predetermined iteration threshold is reached, and the optimal control parameter obtained at that time is used as the first target control parameter. The first target control parameter is used to perform initial control settings on the target pressure regulating valve.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images