CN114298091A - SF6Gas flow measuring value correction method, device, equipment and storage medium - Google Patents

Abstract

The present application relates to a method, device, equipment and storage medium for correcting the measured value of SF ₆ gas flow. The method includes the following steps: obtaining the measured value of SF ₆ gas flow and the corresponding temperature value and air pressure value; Input into the trained correction value prediction model, the correction value prediction model includes a plurality of neural network models corresponding to the combination of different temperature segments and air pressure segments, and the correction value prediction model is based on the input temperature value and the temperature value to which the air pressure value belongs. segment and air pressure segment using the corresponding neural network model to predict and output the corresponding gas flow correction value; superimpose the SF ₆ gas flow measurement value and the gas flow correction value to obtain the corrected gas flow value. The temperature and air pressure are _segmented to obtain the neural network model corresponding to the combination of different temperature and air pressure segments.

Description

SF6 gas flow measurement value correction method, device, equipment and storage medium

technical field

The application relates to the field of gas flow measurement, and in particular to a method, device, equipment and storage medium for correcting the measurement value of SF ₆ gas flow.

Background technique

Sulfur hexafluoride (SF ₆ ) has good electrical insulation properties and excellent arc extinguishing properties. Its electric strength is 2.5 times that of nitrogen under the same pressure, its breakdown voltage is 2.5 times that of air, and its arc extinguishing ability is 100 times that of air. It is a new generation of ultra-high voltage insulating material superior to that between air and oil. Sulfur hexafluoride is widely used in electronic devices for its good insulating properties and arc extinguishing properties, such as circuit breakers, high-voltage transformers, gas-enclosed combined capacitors, high-voltage transmission lines, transformers, etc. The electrical industry uses its high dielectric strength and good arc extinguishing performance as an insulating material for high-voltage switches, large-capacity transformers, high-voltage cables and gases.

The flow of SF ₆ gas needs to be measured when it is applied. However, when measuring the flow of SF ₆ gas with a traditional gas flow meter, there is an error in the measured value due to the influence of temperature and air pressure. Therefore, it is necessary to provide a SF ₆ gas. Flow measurement value correction method.

SUMMARY OF THE INVENTION

The purpose of the embodiments of the present application is to provide a method, device and storage medium for correcting the measured value of SF ₆ gas flow, which are intended to solve the problem of errors existing in the measurement of SF ₆ gas flow by existing gas flow meters.

To achieve the above purpose, the application provides the following technical solutions:

In a first aspect, an embodiment of the present application provides a method for correcting the measured value of SF ₆ gas flow, including the following steps:

Obtain the SF ₆ gas flow measurement value and the corresponding temperature value and pressure value;

Input the above-mentioned temperature value and air pressure value into the trained correction value prediction model, the correction value prediction model includes a plurality of neural network models corresponding to the combination of different temperature segments and air pressure segments, and the correction value prediction model is based on the input temperature. The temperature segment and the pressure segment to which the value and air pressure value belong are predicted by the corresponding neural network model and output the corresponding gas flow correction value;

The corrected gas flow value is obtained by superimposing the SF ₆ gas flow measurement value and the gas flow correction value.

Further, the acquisition method of the trained correction value prediction model is as follows:

Obtain a plurality of characteristic sample data, each of which includes a temperature value, a pressure value and a corresponding SF ₆ gas flow measurement error value, and divide the plurality of characteristic sample data into multiple groups according to the combination of different temperature segments and pressure segments ;

Build a dual-input single-output neural network model;

Using each group of characteristic sample data respectively, with temperature value and pressure value as input, and SF ₆ gas flow measurement error value as output, the neural network model established above is trained, and a plurality of corresponding combinations of different temperature sections and pressure sections are obtained. The neural network model is the trained correction value prediction model.

Further, dividing the plurality of characteristic sample data into multiple groups according to the combination of different temperature segments and pressure segments specifically includes:

Divide a certain range of temperature and pressure into segments, and arrange and combine the segmented intervals, each combination includes a temperature interval and a pressure interval, and divide multiple characteristic sample data into multiple groups according to the above combinations.

Further, the establishment of a dual-input single-output neural network model specifically includes:

First, build the traditional BP neural network framework PSO algorithm framework, initialize the velocity and position vectors of the PSO algorithm particles, set the error interval threshold to be corrected, and calculate the mean square error function at the same time;

Then update the individual and global extreme values of the BP neural network, and update the particle velocity and position vector of the PSO algorithm;

Then, according to the calculated mean square error function value, it is judged whether the accuracy requirements are met. If the accuracy requirements are met, the particle velocity and position information are directly assigned to the BP neural network to complete the neural network optimization. If the accuracy requirements are not met, the number of iterations is increased. Until the mean square error function value meets the accuracy requirements, the establishment of the dual-input single-output neural network model is completed.

Further, the mean square error function is expressed as follows:

为神经网络输出层实际输出值。where n is the number of training samples of the neural network after optimization, Y _p (i) is the expected output value of the neural network,

The actual output value of the output layer of the neural network.

Further, the method also includes:

The model is further trained by using the gas flow correction value and the corresponding temperature value and air pressure value output by the trained correction value prediction model as feature samples.

In the second aspect, an embodiment of the present application provides a device for correcting the measured value of SF ₆ gas flow, including:

The data acquisition module is used to acquire the measured value of SF ₆ gas flow and the corresponding temperature value and pressure value;

A correction value acquisition module, used for inputting the above-mentioned temperature value and air pressure value into the trained correction value prediction model, the correction value prediction model including a plurality of neural network models corresponding to different combinations of temperature segments and air pressure segments, the correction value prediction model The value prediction model uses the corresponding neural network model to predict and output the corresponding gas flow correction value according to the temperature segment and the pressure segment to which the input temperature value and air pressure value belong;

An error correction module, configured to superimpose the SF ₆ gas flow measurement value and the gas flow correction value to obtain a corrected gas flow value.

In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, which is implemented when the processor executes the computer program The steps of the method as described above.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where a data processing program is stored on the computer-readable storage medium, and when the data processing program is executed by a processor, the steps of the above method are implemented.

Compared with the prior art, the beneficial effects of the present invention are:

The SF ₆ gas flow measurement value correction method, device, equipment and storage medium provided by the present invention firstly obtain the SF ₆ gas flow measurement value and the corresponding temperature value and air pressure value, and then input the above-mentioned temperature value and air pressure value into its In the trained correction value prediction model corresponding to the temperature segment and the air pressure segment, the model outputs the gas flow correction value corresponding to the temperature value and the air pressure value, and finally superimposes the _SF gas flow measurement value and the gas flow correction value Obtain the corrected gas flow value _; divide the temperature and air pressure into sections and obtain the neural network model corresponding to the combination of different temperature sections and pressure sections. Compensation for device measurement errors.

Description of drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that need to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, therefore It should not be regarded as a limitation of the scope. For those of ordinary skill in the art, other related drawings can also be obtained from these drawings without any creative effort.

₁ is a flowchart of a method for correcting the measured value of SF gas flow provided by an embodiment of the present invention;

FIG. 2 is a structural block diagram of a device for correcting the measured value of SF ₆ gas flow provided by an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application. It should be noted that like numerals and letters refer to like items in the following figures, so once an item is defined in one figure, it does not require further definition and explanation in subsequent figures.

The terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion such that a process, method, article or device comprising a list of elements includes not only those elements, but also other not expressly listed elements, or also include elements inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

The terms "first", "second", etc. are only used to distinguish one entity or operation from another, and should not be construed to indicate or imply relative importance, nor to require or imply such entities or operations. There is no such actual relationship or sequence between operations.

As shown in FIG. ₁ , an embodiment of the present invention provides a method for correcting the measured value of SF gas flow, including the following steps:

S101. Obtain the SF ₆ gas flow measurement value and the corresponding temperature value and air pressure value.

Wherein, the SF ₆ gas flow measurement value is measured by an SF ₆ gas flow measuring device such as an SF ₆ gas flow meter/SF ₆ gas flow sensor, and the corresponding temperature value and air pressure value can be measured by a temperature sensor and an air pressure sensor, SF 6 _6. The gas flow measuring device, the temperature sensor and the pressure sensor are arranged in series on the SF ₆ gas channel, that is, the SF ₆ gas passes through the above-mentioned measuring device in turn.

S102. Input the above temperature value and air pressure value into the trained correction value prediction model, where the correction value prediction model includes a plurality of neural network models corresponding to combinations of different temperature segments and air pressure segments, and the correction value prediction model is based on the input The temperature segment and the pressure segment to which the temperature value and air pressure value belong are predicted by the corresponding neural network model and output the corresponding gas flow correction value.

In the embodiment of the present invention, temperature and air pressure are segmented to obtain neural network models corresponding to the combination of different temperature segments and air pressure segments. Because the influences of SF ₆ gas temperature and air pressure on SF ₆ gas flow measurement under different temperature segments and air pressure segments are different , compared with only using a neural network model in the embodiment of the present invention, the model can output a higher-precision gas flow correction value, thereby obtaining a higher-precision gas flow value.

S103 , superimposing the SF ₆ gas flow measurement value and the gas flow correction value to obtain a corrected gas flow value.

Specifically, the gas flow correction value can be calculated in real time and the SF ₆ gas flow measurement value can be corrected in real time, and the high-precision gas flow value can be obtained and provided to the user, so as to realize the compensation of the measurement error of the SF ₆ gas flow measurement device.

Further, the acquisition method of the trained correction value prediction model is as follows:

(1) Acquiring a plurality of characteristic sample data, the characteristic sample data adopts standard data, each of the characteristic sample data includes a temperature value, a pressure value and a corresponding SF ₆ gas flow measurement error value, and the plurality of characteristic sample data Divide into multiple groups according to the combination of different temperature sections and pressure sections;

(2) Establish a neural network model with dual input and single output;

( ₃ ) Use each group of characteristic sample data respectively, take the temperature value and the pressure value as the input, and take the SF gas flow measurement error value as the output to train the neural network model established above, and obtain a plurality of corresponding different temperature sections and pressure values. The neural network model of the segment combination is the trained correction value prediction model.

Specifically, dividing the plurality of characteristic sample data into multiple groups according to the combination of different temperature segments and pressure segments specifically includes:

Divide a certain range of temperature and pressure into segments and arrange and combine the segmented intervals. Each combination includes a temperature interval and an air pressure interval. Multiple characteristic sample data are divided according to the interval to which their temperature and air pressure belong. Divide into multiple groups according to the above combination, each group contains multiple characteristic sample data, and the range of temperature and air pressure for segmentation and the segmentation method can be set based on actual needs, which is not limited in this embodiment.

When the initial weights and thresholds of the BP neural network are randomly generated, if the selection of the initial weights and thresholds is not appropriate, it is easy to cause problems such as slow network convergence and local minimum. The invention adopts the PSO algorithm to optimize the BP neural network, reduces the influence of the initial value on the prediction result of the BP neural network, and improves the convergence speed and prediction accuracy of the network. Preferably, the establishment of a dual-input single-output neural network model specifically includes:

First, build the traditional BP neural network framework PSO algorithm framework, initialize the speed and position vectors of the PSO algorithm particles, set the error interval threshold to be corrected, and calculate the mean square error function at the same time; then update the individual and global extreme values of the BP neural network, Update the particle velocity and position vector of the PSO algorithm; then judge whether the accuracy requirements are met according to the calculated mean square error function value. If the accuracy requirements are met, directly assign the particle velocity and position information to the BP neural network to complete the neural network optimization. If the accuracy requirements are met, the number of iterations is increased until the mean square error function value meets the accuracy requirements, and the establishment of a dual-input single-output neural network model is completed.

The mean squared error function is expressed as follows:

为神经网络输出层实际输出值。where n is the number of training samples of the neural network after optimization, Yp(i) is the expected output value of the neural network,

The actual output value of the output layer of the neural network.

Preferably, the method further includes: further training the model by using the gas flow correction value and the corresponding temperature value and air pressure value output by the trained correction value prediction model as feature samples, thereby further improving the accuracy of the model.

As shown in FIG. 2 , an embodiment of the present invention also provides a device for correcting the measured value of SF ₆ gas flow, including:

The data acquisition module 201 is used to acquire the SF gas flow measurement value and the corresponding temperature value and air pressure value _;

The correction value acquisition module 202 is used for inputting the above-mentioned temperature value and air pressure value into the trained correction value prediction model, and the correction value prediction model includes a plurality of neural network models corresponding to combinations of different temperature segments and air pressure segments. The correction value prediction model uses the corresponding neural network model to predict and output the corresponding gas flow correction value according to the temperature segment and the pressure segment to which the input temperature value and air pressure value belong;

The error correction module 203 is configured to superimpose the SF ₆ gas flow measurement value and the gas flow correction value to obtain a corrected gas flow value.

Embodiments of the present invention further provide an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements any of the above when executing the computer program steps of the method

An embodiment of the present invention further provides a computer-readable storage medium, where a data processing program is stored on the computer-readable storage medium, and when the data processing program is executed by a processor, the steps of any of the foregoing methods are implemented.

Since the principle of solving the problem in the above-mentioned embodiments of the apparatus, electronic device and computer-readable storage medium is similar to that of the above-mentioned method embodiments, reference may be made to the above-mentioned method embodiments for implementation thereof, and repeated descriptions will not be repeated.

As will be appreciated by those skilled in the art, the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

Memory may include non-persistent memory in computer readable media, random access memory (RAM) and/or non-volatile memory in the form of, for example, read only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media includes both persistent and non-permanent, removable and non-removable media, and storage of information may be implemented by any method or technology. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

The above descriptions are merely examples of the present application, and are not intended to limit the protection scope of the present application. For those skilled in the art, various modifications and changes may be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims (9)

1. a SF ₆ gas flow measurement value correction method, is characterized in that, comprises the following steps: Obtain the SF ₆ gas flow measurement value and the corresponding temperature value and pressure value; Input the above-mentioned temperature value and air pressure value into the trained correction value prediction model, the correction value prediction model includes a plurality of neural network models corresponding to the combination of different temperature segments and air pressure segments, and the correction value prediction model is based on the input temperature. The temperature segment and the pressure segment to which the value and air pressure value belong are predicted by the corresponding neural network model and output the corresponding gas flow correction value; The corrected gas flow value is obtained by superimposing the SF ₆ gas flow measurement value and the gas flow correction value. 2. a kind of SF gas flow measurement value correction method according to claim ₁ , is characterized in that, the acquisition method of described trained correction value prediction model is as follows: Obtain a plurality of characteristic sample data, each of which includes a temperature value, a pressure value and a corresponding SF ₆ gas flow measurement error value, and divide the plurality of characteristic sample data into multiple groups according to the combination of different temperature segments and pressure segments ; Build a dual-input single-output neural network model; Using each group of characteristic sample data respectively, with temperature value and pressure value as input, and SF ₆ gas flow measurement error value as output, the neural network model established above is trained, and a plurality of corresponding combinations of different temperature sections and pressure sections are obtained. The neural network model is the trained correction value prediction model. 3. A kind of SF ₆ gas flow measurement value correction method according to claim 2, it is characterized in that, described dividing a plurality of characteristic sample data into a plurality of groups according to the combination of different temperature sections and air pressure sections specifically comprises: Divide a certain range of temperature and pressure into segments, and arrange and combine the segmented intervals, each combination includes a temperature interval and a pressure interval, and divide multiple characteristic sample data into multiple groups according to the above combinations. 4. a kind of SF ₆ gas flow measurement value correction method according to claim 2, is characterized in that, described establishing the neural network model of double input and single output specifically comprises: First, build the traditional BP neural network framework PSO algorithm framework, initialize the velocity and position vectors of the PSO algorithm particles, set the error interval threshold to be corrected, and calculate the mean square error function at the same time; Then update the individual and global extreme values of the BP neural network, and update the particle velocity and position vector of the PSO algorithm; Then, according to the calculated mean square error function value, it is judged whether the accuracy requirements are met. If the accuracy requirements are met, the particle velocity and position information are directly assigned to the BP neural network to complete the neural network optimization. If the accuracy requirements are not met, the number of iterations is increased. Until the mean square error function value meets the accuracy requirements, the establishment of the dual-input single-output neural network model is completed. _5. a kind of SF gas flow measurement value correction method according to claim 4, is characterized in that, described mean square error function is expressed as follows:

where n is the number of training samples of the neural network after optimization, Y _p (i) is the expected output value of the neural network,

The actual output value of the output layer of the neural network. 6. The method for correcting the measured value of a SF ₆ gas flow rate according to claim 1, wherein the method further comprises: The model is further trained by using the gas flow correction value and the corresponding temperature value and air pressure value output by the trained correction value prediction model as feature samples. 7. A SF ₆ gas flow measurement value correction device, characterized in that, comprising: The data acquisition module is used to acquire the measured value of SF ₆ gas flow and the corresponding temperature value and pressure value; A correction value acquisition module, used for inputting the above-mentioned temperature value and air pressure value into the trained correction value prediction model, the correction value prediction model including a plurality of neural network models corresponding to different combinations of temperature segments and air pressure segments, the correction value prediction model The value prediction model uses the corresponding neural network model to predict and output the corresponding gas flow correction value according to the temperature segment and the pressure segment to which the input temperature value and air pressure value belong; An error correction module, configured to superimpose the SF ₆ gas flow measurement value and the gas flow correction value to obtain a corrected gas flow value. 8. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the computer program as claimed in the claims Steps of any one of the methods 1-6. 9. A computer-readable storage medium, wherein a data processing program is stored on the computer-readable storage medium, and when the data processing program is executed by a processor, the method according to any one of claims 1-6 is implemented A step of.

Images