CN114777865B - Roots flow metering device for industrial gas prepayment - Google Patents
Roots flow metering device for industrial gas prepayment Download PDFInfo
- Publication number
- CN114777865B CN114777865B CN202111522978.0A CN202111522978A CN114777865B CN 114777865 B CN114777865 B CN 114777865B CN 202111522978 A CN202111522978 A CN 202111522978A CN 114777865 B CN114777865 B CN 114777865B
- Authority
- CN
- China
- Prior art keywords
- flow
- pressure
- temperature
- roots
- vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F11/00—Apparatus requiring external operation adapted at each repeated and identical operation to measure and separate a predetermined volume of fluid or fluent solid material from a supply or container, without regard to weight, and to deliver it
- G01F11/28—Apparatus requiring external operation adapted at each repeated and identical operation to measure and separate a predetermined volume of fluid or fluent solid material from a supply or container, without regard to weight, and to deliver it with stationary measuring chambers having constant volume during measurement
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F15/00—Details of, or accessories for, apparatus of groups G01F1/00 - G01F13/00 insofar as such details or appliances are not adapted to particular types of such apparatus
- G01F15/005—Valves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F15/00—Details of, or accessories for, apparatus of groups G01F1/00 - G01F13/00 insofar as such details or appliances are not adapted to particular types of such apparatus
- G01F15/02—Compensating or correcting for variations in pressure, density or temperature
- G01F15/04—Compensating or correcting for variations in pressure, density or temperature of gases to be measured
- G01F15/043—Compensating or correcting for variations in pressure, density or temperature of gases to be measured using electrical means
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F15/00—Coin-freed apparatus with meter-controlled dispensing of liquid, gas or electricity
- G07F15/001—Coin-freed apparatus with meter-controlled dispensing of liquid, gas or electricity for gas
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F15/00—Coin-freed apparatus with meter-controlled dispensing of liquid, gas or electricity
- G07F15/06—Coin-freed apparatus with meter-controlled dispensing of liquid, gas or electricity with means for prepaying basic charges, e.g. rent for meters
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Fluid Mechanics (AREA)
- Details Of Flowmeters (AREA)
- Measuring Volume Flow (AREA)
Abstract
The application relates to the field of gas measurement, and it specifically discloses an industry gas prepayment roots flow metering device, and it includes roots base table, communicably connect in the intelligent volume correction appearance of roots base table, and be used for control the trip valve of roots base table and external intercommunication. The industrial gas prepayment Roots flow metering device can meet the requirement of a novel trade settlement management mode of 'purchasing gas first and then using gas' of a user.
Description
Technical Field
The invention relates to the field of gas metering, in particular to a Roots type flow metering device for industrial gas prepayment.
Background
With the rapid development of national economy and the further advance of urbanization construction, the number of users and the gas consumption demand of town civil gas and industrial gas are increased rapidly, so that the workload of gas metering and charging is increased.
In the field of gas metering, the existing flow meter only has a metering function, the metering mode is single, the principle is that the volume or the mass of gas passing through a pipeline is accumulated, the metering effect is further achieved, the measured gas quantity data are possibly inaccurate, and therefore the cost needed to be paid by a user is inaccurate.
Moreover, nowadays, the user can only pay the required fee according to the used gas quantity, so that the method is complex and complicated, and is not convenient for practical application. When the user wants to pre-pay the gas fee so as to reduce the number of subsequent payment, the user usually pre-pays a fixed fee, and the user deducts the corresponding fee according to the used gas amount next time, so that the pre-stored amount of money is possibly wasted or insufficient, and the user is inconvenient to use actually.
Therefore, in order to enable the gas flowmeter to accurately measure the total gas amount and meet the requirement of a novel trade settlement management mode of 'purchasing gas and then using gas' of a user, the industrial gas prepayment Roots flow metering device is expected.
Disclosure of Invention
The present application is proposed to solve the above-mentioned technical problems. The embodiment of the application provides an industry gas prepayment roots flow metering device, and it includes roots base table, communicably connect in the intelligence volume correction appearance of roots base table, and be used for control the trip valve of roots base table and external intercommunication. The industrial gas prepayment Roots flow metering device can meet the requirement of a novel trade settlement management mode of 'purchasing gas first and then using gas' of a user.
According to one aspect of the application, an industrial gas prepayment Roots flow metering device is provided and comprises:
roots base table, comprising: the device comprises a shell and a cover plate which are mutually buckled to form a metering chamber, two Roots wheels positioned in the metering chamber, two synchronous gears, a bearing, a rotor assembly, a flow sensor, a temperature sensor and a pressure sensor, wherein the two synchronous gears are respectively connected with the Roots wheels and are used for keeping the two Roots wheels to rotate at correct relative positions;
the intelligent volume corrector is connected with the Roots base meter in a communication mode; and
and the stop valve is used for controlling the Roots base meter to be communicated with the outside.
In the above mentioned industrial gas prepayment roots flow metering device, the intelligent volume corrector comprises a housing, a main board arranged in the housing, a display screen connected to the main board, a CPU card socket connected to the main board, a wireless module arranged in the main board, a power supply arranged in the main board, and a controller arranged in the main board, wherein a control program is arranged in the controller.
In the industrial gas pre-payment roots flow metering device, the controller is used for executing at least one of the following steps through a control program of the controller: performing automatic flow tracking supplement and compression factor operation; setting sampling modes of the temperature sensor and the pressure sensor; and receiving data collected by the temperature sensor and the pressure sensor.
In the industrial gas prepayment Roots flow metering device, the intelligent volume corrector comprises a wireless communication DTU module for monitoring malicious strong magnetic interference on site.
In the above industrial gas pre-payment roots flow metering device, the performing flow automatic tracking supplement and compression factor operation includes: acquiring temperature values, pressure values and flow values of a series of time points at preset intervals before the current time point; passing the temperature, pressure and flow values at a series of predetermined intervals of time prior to the current time through a context-based encoder model comprising an embedded layer to obtain a temperature, pressure and flow eigenvector, respectively; calculating a Gaussian density map between the temperature eigenvector and the pressure eigenvector
Wherein the value μ i of each position of the mean vector μ of the Gaussian density map is the mean of the eigenvalues of the ith position of the temperature eigenvector and the pressure eigenvector, and the covariance matrix Σ of the Gaussian density map is the covariance matrix between the temperature eigenvector and the pressure eigenvector; converting the characteristic value of each position in the flow characteristic vector into one-dimensional Gaussian distribution
Obtaining a one-dimensional Gaussian distribution vector, wherein σ i of the one-dimensional Gaussian distribution is the root mean square of the characteristic value of the corresponding position minus the square of the mean value of the characteristic values of all the positions in the flow characteristic vector; calculating a responsiveness density map of the Gaussian density map relative to the one-dimensional Gaussian distribution vector, wherein a value of each position of a mean vector of the responsiveness density map is μ i/μ 2i And the variance vector of the response density map is sigma/sigma; performing one-dimensional Gaussian discretization on each position of the responsiveness density map to obtain a classification matrix; and passing the classification matrix through a classifier to obtain a classification result, wherein the classification result is used for representing a regression flow compensation proportion and/or a compression factor.
In the above industrial gas prepaid roots flow rate metering device, the passing the temperature value, the pressure value and the flow rate value at a series of predetermined intervals of time points before the current time point through a context-based encoder model including an embedded layer to obtain a temperature characteristic vector, a pressure characteristic vector and a flow rate characteristic vector respectively includes: converting the temperature values of a series of time points at predetermined intervals before the current time point into temperature input vectors respectively through an embedded layer of the encoder model to obtain a sequence of temperature input vectors; passing the sequence of temperature input vectors through a Bert model of the encoder model to obtain the temperature feature vectors; converting pressure values at a series of predetermined intervals of time points before the current time point into pressure input vectors respectively through an embedded layer of the encoder model to obtain a sequence of pressure input vectors; passing the sequence of pressure input vectors through a Bert model of the encoder model to obtain the pressure feature vector; respectively converting flow values of a series of time points at preset intervals before the current time point into flow input vectors through an embedded layer of the encoder model to obtain a sequence of the flow input vectors; and passing the sequence of flow input vectors through a Bert model of the encoder model to obtain the flow feature vector.
In the above industrial gas pre-payment roots flow metering device, the gaussian density map between the temperature characteristic vector and the pressure characteristic vector is calculated
The method comprises the following steps: and passing the temperature characteristic vector and the pressure characteristic vector through a Sigmoid function to map characteristic values of various positions in the temperature characteristic vector and the pressure characteristic vector into a probability space.
In the above mentioned industrial gas prepayment roots flow metering device, the classification matrix is passed through a classifier to obtain a classification result, and the classification result is used for representing a regression flow compensation proportion and/or a compression factor, and includes: passing the classification matrix through a first classifier to obtain a first classification result, wherein the first classification result is used for representing a regression flow compensation proportion; and passing the classification matrix through a second classifier to obtain a second classification result, the second classification result being used for representing a compression factor; wherein the first classifier and the second classifier process the classification matrix to obtain the first classification result and the second classification result according to the following formula; wherein the formula is: softmax { (W) n ,Bn):…:(W 1 ,B 1 ) L Project (F) }, where Project (F) denotes the projection of the classification matrix as a vector, W 1 To W n As a weight matrix for each fully connected layer, B 1 To B n A bias matrix representing the fully connected layers of each layer.
Compared with the prior art, the utility model provides an industry gas prepayment roots flow metering device, it includes roots base table, communicably connect in the intelligence volume correction appearance of roots base table to and be used for control the trip valve of roots base table and external intercommunication. The industrial gas prepayment Roots flow metering device can meet the requirement of a novel trade settlement management mode of 'firstly purchasing gas and then using gas' of a user.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing in more detail embodiments of the present application with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings, like reference numbers generally represent like parts or steps.
FIG. 1A is a schematic structural diagram of an industrial gas prepayment Roots flow metering device according to an embodiment of the application;
FIG. 1B is a schematic diagram of the Roots-based meter in the pre-payment Roots-type flow metering device for industrial gas according to the embodiment of the application;
FIG. 1C is a schematic diagram of an intelligent volume corrector in an industrial gas pre-payment Roots flow metering device according to an embodiment of the application;
fig. 2 is a flowchart of steps executed by a controller through a control program in the industrial gas pre-payment roots flow metering device according to the embodiment of the application;
FIG. 3 is a flow chart of automatic flow tracking supplement and compression factor calculation in the Roots industrial gas prepayment flow metering device according to the embodiment of the present application;
FIG. 4 is a schematic view of an architecture for performing automatic flow tracking supplement and compression factor operation in the pre-paid Roots flow metering device for industrial gas according to the embodiment of the present application;
FIG. 5 is a block diagram of a step system executed by a control program of a controller in the industrial gas prepayment Roots flow metering device according to the embodiment of the application;
fig. 6 is a block diagram of a tracking operation unit in a step system executed by a control program of a controller of the industrial gas prepayment roots flow metering device according to an embodiment of the application.
In the figure: 1. roots base table; 2. an intelligent volume correction instrument; 3. and (6) cutting off the valve.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be understood that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and that the present application is not limited by the example embodiments described herein.
Exemplary metering device
As mentioned above, in order to enable the gas flowmeter to accurately measure the total gas amount, and to use a CPU card or a wireless communication module as a medium, the gas purchasing management system is combined with a gas selling management system or a cloud platform through the Internet of things to perform centralized management on gas purchasing, so that the requirement of a novel trade settlement management mode of 'purchasing gas and then using gas' of a user is met. Thereby providing an industrial gas prepayment Roots flow metering device.
Correspondingly, the industrial gas prepayment roots flow metering device mainly comprises three parts, namely a roots meter 1, an intelligent volume corrector 2 and a cut-off valve 3. Specifically, the roots table 1 includes: the device comprises a shell and a cover plate which are mutually buckled to form a metering chamber, two Roots wheels positioned in the metering chamber, two synchronous gears, a bearing, a rotor assembly, a flow sensor, a temperature sensor and a pressure sensor, wherein the two synchronous gears are respectively connected with the Roots wheels and are used for keeping the two Roots wheels to rotate at correct relative positions. The intelligent volume correction instrument is implemented as a WEVC flow correction instrument and is connected with the Roots base table 1 in a communication mode. The stop valve 3 is used for controlling the Roots base meter 1 to be communicated with the outside.
More specifically, intelligence volume correction appearance includes the shell, set up in mainboard in the shell, connect in the display screen of mainboard, connect in the CPU card socket of mainboard, set up in the wireless module of mainboard, set up in the power of mainboard and, set up in the controller of mainboard, be equipped with control program in the controller. And the intelligent volume correction instrument comprises a wireless communication DTU module for monitoring the malicious strong magnetic interference on the site.
The structural schematic diagram of the industrial gas prepayment Roots flow metering device is shown in FIG. 1A.
1. Roots base table 1:
a fixed metering cavity is formed among a shell, two Roots wheels and a cover plate, when gas enters a flow meter, a pressure difference (P in > P out) is generated between an inlet and an outlet and acts on the Roots wheels, and the Roots wheels are always kept in correct relative position rotation through driving of two high-precision machined synchronous gears (connected to the Roots wheels). Constant gaps are kept among the Roots wheels, between the Roots wheels and the shell, and between the Roots wheels and the cover plate, so that continuous non-contact rotation is realized. Four times the metering chamber gas (one revolution volume) is discharged per revolution of the roots wheel, the number of revolutions of the roots wheel being proportional to the amount of gas volume passing through the flow meter. As shown in fig. 1B.
The flow sensor detects the flow pulse signal of the base meter, the pressure sensor detects the pressure value of the gas, and the temperature detects the gas temperature value. The Roots basic meter 1 has the advantages of high metering accuracy, high reliability, no influence of pressure and flow change, high-precision machining and repeated positioning technology, good universality and interchangeability among parts, good repeatability and long service life.
2. Intelligent volume correction appearance 2:
the intelligent volume corrector 2 is composed of flow, temperature and pressure detection channels, microprocessor power supply conversion and other auxiliary circuits, and is provided with an external output signal interface, after conversion processing, multi-channel signals sent by each sensor are calculated by the microprocessor according to a gas equation, the gas flow under the working condition is converted into the flow and the total amount under the standard state, meanwhile, a CP card or a wireless DTU module is used as a medium, the accumulated residual gas quantity of the gas purchasing quantity and the standard condition residual quantity are calculated and processed, and a control valve is controlled to be opened or closed according to the residual gas quantity, so that the prepayment management is realized. The principle of the intelligent volume corrector 2 is shown in fig. 1C.
It has the following advantages: the flow compensation operation, the IC card operation and the control are integrated, the structure is compact, no signal transmission error exists, the reliability is high, the micro-power-consumption technical design is adopted, the power consumption of the whole machine is low, and the built-in battery can be used for more than five years; the high-performance microprocessor and the modern digital filtering technology are adopted, the software has powerful functions, the performance is excellent, the temperature, the pressure and the flow of the detected gas can be detected, and automatic tracking compensation and compression factor operation of the flow are carried out; the sampling mode of temperature and pressure can be set, or the set values of temperature and pressure in the meter can be directly selected; the remote data acquisition system is provided with an RS485 interface, and is convenient to be matched with various acquisition instruments to form a remote data acquisition system; the built-in 2G, 4G, NB-IOT wireless communication DTU modules can be selected to monitor malicious strong magnetic interference on site in real time, close the valve and store event records, have a data storage function and can prevent data loss during battery replacement or sudden power failure. The realization of the functions of prepayment and automatic charging supports the charging of the use amount (yuan) or the gas amount (m 3). In the dollar amount mode, the price can be adjusted using cards or communications, supporting the use of regular gas prices, tiered gas prices, or long duration gas prices. The intelligent CPU card which conforms to the financial card specification (I07816 standard) of the people's bank of China is adopted, and an advanced encryption technology key management system is combined, so that the legal rights and interests of users are ensured. The management system can issue a user card, an acquisition card, an application transfer card, a valve opening card, a valve closing card, a zero clearing card, a price adjusting card and the like, and is convenient to manage and use. And a system background charging mode is supported, and the flow meter receives and displays information such as residual amount, price and the like issued after settlement of the wireless system.
3. A shut-off valve 3:
the stop valve 3 mainly comprises a valve body, a ball body, a speed reduction executing mechanism and a control main board. The stop valve 3 adopts a zero-pressure-loss ball valve structure, hard anode oxidation treatment is carried out on the surface of the valve body, a micro-motor executing mechanism is adopted, the micro-motor executing mechanism is adopted, large-torque transmission is realized, the power consumption is low, and the service life of a battery is long. And the potential safety hazard of the electric valve is avoided by adopting an explosion-proof electric explosion-proof design.
As described above, the intelligent volume corrector 2 has the functions of automatic flow rate tracking compensation and compression factor calculation, that is, the preset program of the intelligent volume corrector 2 can perform the functions of automatic flow rate tracking compensation and compression factor calculation when being executed.
Considering that the flow value is not only related to the flow but also related to the temperature and the pressure of the industrial gas prepayment Roots flow metering device, that is, if the currently detected flow value can be corrected through the sensor data of the temperature and the pressure, the accuracy of automatic flow tracking compensation and the accuracy of compression factor calculation can be improved.
Fig. 2 is a flow chart of steps executed by the controller through a control program in the industrial gas prepayment roots flow metering device according to the embodiment of the application. As shown in fig. 2, in the industrial gas pre-payment roots flow metering device according to the embodiment of the application, the controller executes the steps through the control program thereof, including: s110, performing automatic flow tracking supplement and compression factor operation; s120, setting sampling modes of the temperature sensor and the pressure sensor; and S130, receiving data collected by the temperature sensor and the pressure sensor.
Fig. 3 is a flow chart of automatic flow tracking and supplementing and compression factor operation in the industrial gas prepayment roots flow metering device according to the embodiment of the application. As shown in fig. 3, the flow automatic tracking supplement and compression factor operation is performed, which includes the steps of: s210, acquiring temperature values, pressure values and flow values of a series of time points at preset intervals before the current time point; s220, respectively passing the temperature value, the pressure value and the flow value of a series of time points at preset intervals before the current time point through a context-based encoder model comprising an embedded layer to obtain a temperature characteristic vector, a pressure characteristic vector and a flow characteristic vector; s230, calculating a Gaussian density map between the temperature characteristic vector and the pressure characteristic vector
Wherein the value μ i of each position of the mean vector μ of the Gaussian density map is the mean of the eigenvalues of the ith position of the temperature eigenvector and the pressure eigenvector, and the covariance matrix Σ of the Gaussian density map is the covariance matrix between the temperature eigenvector and the pressure eigenvector; s240, converting the characteristic value of each position in the flow characteristic vector into one-dimensional Gaussian distribution
To obtain a one-dimensional Gaussian distribution vector, wherein the σ i of the one-dimensional Gaussian distribution is the average of the characteristic values of the corresponding positionsSquare root of the square of the mean value of the eigenvalues of all positions in the flow eigenvector is subtracted; s250, calculating a responsiveness density map of the Gaussian density map relative to the one-dimensional Gaussian distribution vector, wherein the value of each position of a mean vector of the responsiveness density map is mui/mui 2i And the variance vector of the response density map is sigma/sigma; s260, performing one-dimensional Gaussian discretization on each position of the responsiveness density map to obtain a classification matrix; s270, enabling the classification matrix to pass through a classifier to obtain a classification result, wherein the classification result is used for expressing a regression flow compensation proportion and/or a compression factor.
Fig. 4 is a schematic diagram illustrating an architecture of automatic flow tracking supplement and compression factor operation in an industrial gas prepayment roots flow metering device according to an embodiment of the application. As shown in fig. 4, in the network architecture of the industrial gas pre-payment roots flow metering device for performing flow automatic tracking supplement and compression factor operation, first, the acquired temperature value (e.g., P1 as illustrated in fig. 4), pressure value (e.g., P2 as illustrated in fig. 4) and flow value (e.g., P3 as illustrated in fig. 4) at a series of time points at predetermined intervals before the current time point are respectively passed through a context-based encoder model (e.g., E as illustrated in fig. 4) including an embedded layer to obtain a temperature feature vector (e.g., VF1 as illustrated in fig. 4), a pressure feature vector (e.g., VF2 as illustrated in fig. 4) and a flow feature vector (e.g., VF3 as illustrated in fig. 4); then, a Gaussian density map between the temperature eigenvector and the pressure eigenvector is calculated
(e.g., GD as illustrated in fig. 4); then, converting the characteristic value of each position in the flow characteristic vector into one-dimensional Gaussian distribution
To obtain a one-dimensional gaussian distribution vector (e.g., VGs as illustrated in fig. 4); then, calculating the Gaussian density map relative to the one-dimensional heightA responsivity density map of the gaussian distribution vector (e.g., F as illustrated in fig. 4); then, performing one-dimensional gaussian discretization on each position of the response density map to obtain a classification matrix (e.g., M as illustrated in fig. 4); finally, the classification matrix is passed through a classifier (e.g., a classifier as illustrated in fig. 4) to obtain a classification result, which is used to represent a regression flow compensation proportion and/or a compression factor.
In steps S210 and S220, the temperature value, the pressure value, and the flow value at a series of predetermined intervals before the current time point are obtained, and the temperature value, the pressure value, and the flow value at a series of predetermined intervals before the current time point are respectively passed through a context-based encoder model including an embedded layer to obtain a temperature eigenvector, a pressure eigenvector, and a flow eigenvector. It should be understood that the technical solution of the present application expects to correct the currently detected flow value by the sensor values of temperature and pressure, thereby determining more accurate flow compensation and compression factor values. Therefore, in the technical scheme of the application, firstly, the temperature value, the pressure value and the flow value of a series of time points with preset intervals before the current time point are obtained through the temperature sensor, the pressure sensor and the flow sensor respectively; then, the temperature value, the pressure value and the flow value of a series of time points at preset intervals before the current time point are respectively subjected to encoding processing in a context-based encoder model containing an embedded layer so as to map the temperature characteristic, the pressure characteristic and the flow characteristic into a high-dimensional space, and thus a temperature characteristic vector, a pressure characteristic vector and a flow characteristic vector are obtained.
Specifically, in this embodiment, the process of passing the temperature value, the pressure value, and the flow value at a series of predetermined intervals of time points before the current time point through a context-based encoder model including an embedded layer to obtain a temperature feature vector, a pressure feature vector, and a flow feature vector includes: firstly, respectively converting temperature values of a series of time points at preset intervals before the current time point into temperature input vectors through an embedded layer of the encoder model to obtain a sequence of the temperature input vectors; then, passing the sequence of the temperature input vectors through a Bert model of the encoder model to obtain the temperature feature vectors; then, converting the pressure values at a series of time points at predetermined intervals before the current time point into pressure input vectors respectively through an embedded layer of the encoder model to obtain a sequence of pressure input vectors; then, passing the sequence of pressure input vectors through a Bert model of the encoder model to obtain the pressure feature vector; then, respectively converting the flow numerical values of a series of time points at preset intervals before the current time point into flow input vectors through an embedded layer of the encoder model so as to obtain a sequence of the flow input vectors; finally, the sequence of flow input vectors is passed through a Bert model of the encoder model to obtain the flow feature vector.
In step S230, a Gaussian density map between the temperature eigenvector and the pressure eigenvector is calculated
Wherein the value μ for each position of the mean vector μ of the Gaussian density map i Is the mean of the eigenvalues of the ith position of the temperature eigenvector and the pressure eigenvector, and the covariance matrix sigma of the gaussian density map is the covariance matrix between the temperature eigenvector and the pressure eigenvector. It should be understood that, considering that the gas flow may generate disturbance due to temperature and pressure, in the technical solution of the present application, it is necessary to calculate the responsiveness of the flow characteristic with respect to the temperature characteristic and the pressure characteristic, and considering that when the feature vector is fused by the gaussian density map, since the gaussian density is widely used as the learning target of the convolutional neural network-based method, it implements effective fusion of the features in the high-dimensional feature space under the convolutional neural network mapping, so that this can be implemented by the gaussian probability density map within the feature space.
That is, accordingly, in one particular exampleFirst, the temperature feature vector and the pressure feature vector are passed through a Sigmoid function to map feature values of respective positions in the temperature feature vector and the pressure feature vector into a probability space, thereby facilitating subsequent calculation processing. Then, based on the correlation between the temperature and the pressure, a Gaussian density map between the temperature feature vector and the pressure feature vector is calculated
I.e. the value mu for each position of the mean vector mu i Is the mean of the eigenvalues of the ith position of the temperature eigenvector and the pressure eigenvector, and the covariance matrix sigma is the covariance matrix between the temperature eigenvector and the pressure eigenvector.
In step S240 and step S250, the eigenvalue of each position in the flow eigenvector is converted into a one-dimensional gaussian distribution
To obtain a one-dimensional Gaussian distribution vector, wherein σ of the one-dimensional Gaussian distribution i Subtracting the root mean square of the mean value of the feature values of all the positions in the flow feature vector from the square of the feature value of the corresponding position, and calculating a responsiveness density map of the Gaussian density map relative to the one-dimensional Gaussian distribution vector, wherein the value of each position of the mean value vector of the responsiveness density map is mu i /μ 2i And the variance vector of the responsive density map is sigma/sigma. That is, in the technical solution of the present application, in order to correct the currently detected flow value by the sensor values of temperature and pressure to determine the more accurate flow compensation and compression factor value, the flow eigenvector itself needs to be gaussian probability densified, that is, the eigenvalue of each position is converted into one-dimensional gaussian distribution
Wherein
Thereby obtaining a one-dimensional gaussian distribution vector.
Then, calculating the responsiveness density map of the Gaussian density map relative to the one-dimensional Gaussian distribution vector, namely obtaining the responsiveness density map
That is, in one particular example, the value for each position of the mean vector of the responsive density map is μ i /μ 2i And its variance vector is sigma/sigma, i.e.
Representing a matrix multiplication. It should be understood that, since the gas flow may generate disturbance due to temperature and pressure, and both the temperature characteristic and the pressure characteristic can be regarded as response characteristics for the gas flow characteristic in a high-dimensional space, in the technical solution of the present application, calculating the responsiveness of the flow characteristic relative to the temperature characteristic and the pressure characteristic can effectively unify the temperature characteristic and the pressure characteristic on the basis of a high-dimensional characteristic distribution of the flow characteristic, so as to improve the accuracy of subsequent classification.
In steps S260 and S270, performing one-dimensional gaussian discretization on each position of the response density map to obtain a classification matrix, and passing the classification matrix through a classifier to obtain a classification result, wherein the classification result is used for representing a regression flow compensation proportion and/or a compression factor. That is, in the technical solution of the present application, after the response density map is obtained, each position of the response density map is further subjected to one-dimensional gaussian discretization to obtain a classification matrix. It should be understood that, through the one-bit gaussian discretization process, no information loss is generated during the augmentation fusion, and thus the accuracy of classification can be improved. And finally, inputting the classification matrix into a classifier to obtain a classification result for expressing the regression flow compensation proportion and/or the compression factor.
Specifically, in the embodiment of the present application, the classification matrix is passed through a classifier to obtain a classification resultThe classification result is used for representing the regression flow compensation proportion and/or the compression factor, and the classification result comprises the following steps: firstly, enabling the classification matrix to pass through a first classifier to obtain a first classification result, wherein the first classification result is used for expressing a regression flow compensation proportion; then, the classification matrix is passed through a second classifier to obtain a second classification result, wherein the second classification result is used for representing a compression factor; wherein the first classifier and the second classifier process the classification matrix to obtain the first classification result and the second classification result according to the following formulas; wherein the formula is: softmax { (W) n ,B n ):…:(W 1 ,B 1 ) Project (F), where Project (F) represents projecting the classification matrix as a vector, W 1 To W n As a weight matrix for each fully connected layer, B 1 To B n A bias matrix representing the layers of the fully connected layer.
To sum up, the industry gas prepayment roots flow metering device of this application embodiment is elucidated, and it passes through roots base table 1, communicably connect in the intelligence volume correction appearance of roots base table 1 to and be used for control the roots base table 1 constitutes industry gas prepayment roots flow metering device jointly with external trip valve 3 that communicates. And the current detected flow value is corrected through the sensor values of the temperature and the pressure, so that more accurate flow compensation and compression factor values are determined. Therefore, the gas flowmeter can accurately measure the total gas amount and meet the requirement of a novel trade settlement management mode of 'firstly purchasing gas and then using gas' of a user.
Exemplary System
FIG. 5 illustrates a block diagram of a controller in an industrial gas pre-paid Roots flow metering device according to an embodiment of the present application. As shown in fig. 5, the controller 500 according to the embodiment of the present application includes: a tracking operation unit 510, configured to perform automatic flow tracking supplement and compression factor operation; a sampling manner setting unit 520 for setting a sampling manner of the temperature sensor and the pressure sensor; and a data receiving unit 530 for receiving data collected by the temperature sensor and the pressure sensor.
Fig. 6 illustrates a block diagram of the tracking operation unit in the controller of the industrial gas prepayment roots flow metering device according to the embodiment of the application. As shown in fig. 6, the tracking operation unit 510 according to the embodiment of the present application includes: a value acquiring subunit 511, configured to acquire temperature values, pressure values, and flow values at a series of time points at predetermined intervals before a current time point; an encoding subunit 512, configured to pass the temperature value, the pressure value, and the flow value at a series of time points at predetermined intervals before the current time point, which are obtained by the value obtaining subunit 511, through a context-based encoder model including an embedded layer to obtain a temperature feature vector, a pressure feature vector, and a flow feature vector, respectively; a Gaussian density map calculation subunit 513 configured to calculate a Gaussian density map between the temperature feature vector obtained by the encoding subunit 512 and the pressure feature vector obtained by the encoding subunit 512
Wherein the value μ for each position of the mean vector μ of the Gaussian density map i Is the mean of the eigenvalues of the ith position of the temperature eigenvector and the pressure eigenvector, and the covariance matrix sigma of the gaussian density map is the covariance matrix between the temperature eigenvector and the pressure eigenvector; a gaussian distribution vector transformation unit 514, configured to transform the feature value of each position in the flow feature vector obtained by the coding subunit 512 into a one-dimensional gaussian distribution
To obtain a one-dimensional Gaussian distribution vector, wherein σ of the one-dimensional Gaussian distribution i A root mean square obtained by subtracting a square of a mean value of the eigenvalues of all the positions in the flow eigenvector from a square of the eigenvalue of the corresponding position; a responsiveness density map calculation subunit 515, configured to calculate the gaussian density map obtained by the gaussian density map calculation subunit 513 with respect to the gaussian distribution vector transformed singlesElement 514, wherein each position of the mean vector of the response density map has a value of μ i /μ 2i And the variance vector of the responsive density map is sigma/sigma; a classification matrix generation subunit 516, configured to perform one-dimensional gaussian discretization on each position of the responsiveness density map obtained by the responsiveness density map calculation subunit 515 to obtain a classification matrix; a classification subunit 517, configured to pass the classification matrix obtained by the classification matrix generation subunit 516 through a classifier to obtain a classification result, where the classification result is used to indicate a regression flow compensation proportion and/or a compression factor.
In an example, in the tracking operation unit 510, the encoding sub-unit 512 is further configured to: converting the temperature values of a series of time points at predetermined intervals before the current time point into temperature input vectors respectively through an embedded layer of the encoder model to obtain a sequence of temperature input vectors; passing the sequence of temperature input vectors through a Bert model of the encoder model to obtain the temperature feature vectors; converting pressure values at a series of predetermined intervals of time points before the current time point into pressure input vectors respectively through an embedded layer of the encoder model to obtain a sequence of pressure input vectors; passing the sequence of pressure input vectors through a Bert model of the encoder model to obtain the pressure feature vector; respectively converting the flow numerical values of a series of time points at preset intervals before the current time point into flow input vectors through an embedded layer of the encoder model to obtain a sequence of the flow input vectors; and passing the sequence of flow input vectors through a Bert model of the encoder model to obtain the flow feature vector.
In an example, in the tracking operation unit 510, the gaussian density map calculation subunit 513 is further configured to: and passing the temperature characteristic vector and the pressure characteristic vector through a Sigmoid function to map characteristic values of various positions in the temperature characteristic vector and the pressure characteristic vector into a probability space.
In an example, in the tracking operation unit 510, the classification subunit 517 is further configured to: passing the classification matrix through a first classifier to obtain a first classification result, wherein the first classification result is used for representing a regression flow compensation proportion; and passing the classification matrix through a second classifier to obtain a second classification result, the second classification result being used for representing a compression factor; wherein the first classifier and the second classifier process the classification matrix to obtain the first classification result and the second classification result according to the following formulas; wherein the formula is: softmax { (W) n ,B n ):…:(W 1 ,B 1 ) L Project (F) }, where Project (F) denotes the projection of the classification matrix as a vector, W 1 To W n As a weight matrix for each fully connected layer, B 1 To B n A bias matrix representing the layers of the fully connected layer.
Here, it will be understood by those skilled in the art that the specific functions and operations of the respective sub-units and modules in the above-described trace arithmetic unit 510 have been described in detail in the above description of the method of performing the traffic auto-trace supplement and compression factor arithmetic with reference to fig. 1 to 4, and thus, a repetitive description thereof will be omitted.
As described above, the tracking operation unit 510 according to the embodiment of the present application may be implemented in various terminal devices, such as a server of a tracking operation algorithm, and the like. In one example, the tracking operation unit 510 according to the embodiment of the present application may be integrated into the terminal device as a software module and/or a hardware module. For example, the tracking calculation unit 510 may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the tracking calculation unit 510 can also be one of many hardware modules of the terminal device.
Alternatively, in another example, the tracking operation unit 510 and the terminal device may be separate devices, and the tracking operation unit 510 may be connected to the terminal device through a wired and/or wireless network and transmit the interaction information according to an agreed data format.
The foregoing describes the general principles of the present application in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present application are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present application. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the foregoing disclosure is not intended to be exhaustive or to limit the disclosure to the precise details disclosed.
The block diagrams of devices, apparatuses, systems referred to in this application are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
It should also be noted that in the devices, apparatuses, and methods of the present application, the components or steps may be decomposed and/or recombined. These decompositions and/or recombinations are to be considered as equivalents of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the application to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.
Claims (5)
1. The utility model provides an industry gas prepayment roots flow metering device which characterized in that includes:
roots base table, comprising: the device comprises a shell, a cover plate, two Roots wheels, two synchronous gears, a bearing, a rotor assembly, a flow sensor, a temperature sensor and a pressure sensor, wherein the shell and the cover plate are mutually buckled to form a metering chamber between the shell and the cover plate;
the intelligent volume corrector is connected with the Roots base meter in a communication mode; and
the stop valve is used for controlling the Roots base meter to be communicated with the outside;
the intelligent volume correction instrument comprises a shell, a mainboard arranged in the shell, a display screen connected to the mainboard, a CPU card socket connected to the mainboard, a wireless module arranged on the mainboard, a power supply arranged on the mainboard and a controller arranged on the mainboard, wherein a control program is arranged in the controller;
wherein, the controller is used for executing at least one of the following steps through the control program of the controller:
performing automatic flow tracking supplement and compression factor operation;
setting sampling modes of the temperature sensor and the pressure sensor; and
receiving data collected by the temperature sensor and the pressure sensor;
wherein, the performing of the flow automatic tracking supplement and the compression factor operation comprises:
acquiring temperature values, pressure values and flow values of a series of time points at preset intervals before the current time point;
passing the temperature, pressure and flow values at a series of predetermined intervals of time prior to the current time through a context-based encoder model comprising an embedded layer to obtain a temperature, pressure and flow eigenvector, respectively;
calculating a Gaussian density map between the temperature eigenvector and the pressure eigenvector
Wherein the value μ of each position of the mean vector μ of the Gaussian density map i Is the mean of the eigenvalues of the ith position of the temperature eigenvector and the pressure eigenvector, and the covariance matrix sigma of the gaussian density map is the covariance matrix between the temperature eigenvector and the pressure eigenvector;
converting the characteristic value of each position in the flow characteristic vector into one-dimensional Gaussian distribution
To obtain a one-dimensional Gaussian distribution vector, wherein σ of the one-dimensional Gaussian distribution i A root mean square obtained by subtracting a square of a mean value of the eigenvalues of all the positions in the flow eigenvector from a square of the eigenvalue of the corresponding position;
calculating a responsiveness density map of the Gaussian density map relative to the one-dimensional Gaussian distribution vector, wherein each position of a mean vector of the responsiveness density map has a value of μ i /μ 2i And the variance vector of the response density map is sigma/sigma;
performing one-dimensional Gaussian discretization on each position of the responsiveness density map to obtain a classification matrix;
and passing the classification matrix through a classifier to obtain a classification result, wherein the classification result is used for representing a regression flow compensation proportion and/or a compression factor.
2. The industrial gas pre-paid Roots flow metering device of claim 1, wherein the intelligent volume corrector comprises a wireless communication DTU module for monitoring malicious strong magnetic interference in the field.
3. The industrial gas pre-paid Roots flow metering device according to claim 2, wherein the passing the temperature, pressure and flow values at a series of predetermined intervals of time points before the current time point through a context based encoder model containing an embedded layer to obtain a temperature, pressure and flow eigenvector, respectively, comprises:
converting the temperature values of a series of time points at predetermined intervals before the current time point into temperature input vectors respectively through an embedded layer of the encoder model to obtain a sequence of temperature input vectors;
passing the sequence of temperature input vectors through a Bert model of the encoder model to obtain the temperature feature vectors;
converting pressure values at a series of predetermined intervals of time points before the current time point into pressure input vectors respectively through an embedded layer of the encoder model to obtain a sequence of pressure input vectors;
passing the sequence of pressure input vectors through a Bert model of the encoder model to obtain the pressure feature vector;
respectively converting the flow numerical values of a series of time points at preset intervals before the current time point into flow input vectors through an embedded layer of the encoder model to obtain a sequence of the flow input vectors; and
passing the sequence of flow input vectors through a Bert model of the encoder model to obtain the flow feature vector.
4. The industrial gas pre-paid Roots flow metering device of claim 3, wherein the calculating a Gaussian density map between the temperature eigenvector and the pressure eigenvector
The method comprises the following steps:
and passing the temperature characteristic vector and the pressure characteristic vector through a Sigmoid function to map characteristic values of various positions in the temperature characteristic vector and the pressure characteristic vector into a probability space.
5. The industrial gas pre-paid Roots flow metering device according to claim 4, wherein the passing the classification matrix through a classifier to obtain a classification result, the classification result being indicative of a regression flow compensation ratio and/or a compression factor, comprises:
passing the classification matrix through a first classifier to obtain a first classification result, wherein the first classification result is used for representing a regression flow compensation proportion; and
passing the classification matrix through a second classifier to obtain a second classification result, wherein the second classification result is used for representing a compression factor;
wherein the first classifier and the second classifier process the classification matrix to obtain the first classification result and the second classification result according to the following formula;
wherein the formula is: softmax { (W) n ,B n ):…:(W 1 ,B 1 ) L Project (F) }, where Project (F) denotes the projection of the classification matrix as a vector, W 1 To W n As a weight matrix for each fully connected layer, B 1 To B n A bias matrix representing the layers of the fully connected layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111522978.0A CN114777865B (en) | 2021-12-13 | 2021-12-13 | Roots flow metering device for industrial gas prepayment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111522978.0A CN114777865B (en) | 2021-12-13 | 2021-12-13 | Roots flow metering device for industrial gas prepayment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114777865A CN114777865A (en) | 2022-07-22 |
| CN114777865B true CN114777865B (en) | 2023-01-31 |
Family
ID=82423129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111522978.0A Active CN114777865B (en) | 2021-12-13 | 2021-12-13 | Roots flow metering device for industrial gas prepayment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114777865B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201163202Y (en) * | 2008-02-29 | 2008-12-10 | 陕西航天动力高科技股份有限公司 | Roots type flowmeter |
| CN201974202U (en) * | 2010-12-15 | 2011-09-14 | 陕西航天动力高科技股份有限公司 | Split type dual-display Roots flowmeter |
| CN102538893A (en) * | 2010-12-15 | 2012-07-04 | 陕西航天动力高科技股份有限公司 | Mechanical electronic dual-display roots flowmeter |
| CN103206997A (en) * | 2013-02-07 | 2013-07-17 | 浙江苍南仪表厂 | Gas Roots flow measuring device and flow correction method for same |
| CN203177911U (en) * | 2013-02-07 | 2013-09-04 | 浙江苍南仪表厂 | Gas Roots flow measuring device |
| JP2014071006A (en) * | 2012-09-28 | 2014-04-21 | Tokiko Techno Kk | Flow rate correction device |
| CN108827413A (en) * | 2018-06-22 | 2018-11-16 | 上海功尊仪表有限公司 | A kind of Roots type flowmeter |
| CN209841108U (en) * | 2019-06-17 | 2019-12-24 | 天信仪表集团有限公司 | Integrated intelligent anti-theft gas flowmeter |
| CN213041298U (en) * | 2020-08-25 | 2021-04-23 | 新天科技股份有限公司 | Roots flowmeter controller |
| CN113654608A (en) * | 2021-08-31 | 2021-11-16 | 浙江裕顺仪表有限公司 | Anti-vibration double-helix Roots wheel gas Roots flowmeter with temperature and pressure compensation |
-
2021
- 2021-12-13 CN CN202111522978.0A patent/CN114777865B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201163202Y (en) * | 2008-02-29 | 2008-12-10 | 陕西航天动力高科技股份有限公司 | Roots type flowmeter |
| CN201974202U (en) * | 2010-12-15 | 2011-09-14 | 陕西航天动力高科技股份有限公司 | Split type dual-display Roots flowmeter |
| CN102538893A (en) * | 2010-12-15 | 2012-07-04 | 陕西航天动力高科技股份有限公司 | Mechanical electronic dual-display roots flowmeter |
| JP2014071006A (en) * | 2012-09-28 | 2014-04-21 | Tokiko Techno Kk | Flow rate correction device |
| CN103206997A (en) * | 2013-02-07 | 2013-07-17 | 浙江苍南仪表厂 | Gas Roots flow measuring device and flow correction method for same |
| CN203177911U (en) * | 2013-02-07 | 2013-09-04 | 浙江苍南仪表厂 | Gas Roots flow measuring device |
| CN108827413A (en) * | 2018-06-22 | 2018-11-16 | 上海功尊仪表有限公司 | A kind of Roots type flowmeter |
| CN209841108U (en) * | 2019-06-17 | 2019-12-24 | 天信仪表集团有限公司 | Integrated intelligent anti-theft gas flowmeter |
| CN213041298U (en) * | 2020-08-25 | 2021-04-23 | 新天科技股份有限公司 | Roots flowmeter controller |
| CN113654608A (en) * | 2021-08-31 | 2021-11-16 | 浙江裕顺仪表有限公司 | Anti-vibration double-helix Roots wheel gas Roots flowmeter with temperature and pressure compensation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114777865A (en) | 2022-07-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101876693B (en) | Electric energy metering chip-based terminal calibration system | |
| CN104700506B (en) | Safety cut-off type remote-control intelligent mass flow gas meter, flow meter and its management system | |
| CN203489925U (en) | Passive intelligent water meter | |
| CN107831448B (en) | A kind of state-of-charge estimation method of parallel connection type battery system | |
| US20180128662A1 (en) | Method and apparatus for determining the mass of a fluid flowing through a flow rate meter in a consumption time interval | |
| KR102167912B1 (en) | Metering Data Collection Unit with Battery Energy Calculator and Ultrasonic Meter and Remote Data Collectioin System Having the Same | |
| CN101256086A (en) | Charging method and charging device for fixed air-quantity temperature difference type central air-conditioning | |
| RU2337320C1 (en) | Water meter | |
| CN114777865B (en) | Roots flow metering device for industrial gas prepayment | |
| CN108871484A (en) | A kind of remote transmitting water meter device and fare payment system | |
| CN103278218B (en) | A kind of flow monitoring device for mechanical water meter | |
| CN102944268B (en) | A kind of intelligent gas meter with temperature compensation | |
| CN110400423A (en) | A kind of multi-functional flowmeter of integral type Internet of Things and control method | |
| CN108961576B (en) | Real-time recharging system and method for NB-IOT prepayment meter | |
| CN202075342U (en) | Three-phase SOC (system-on-chip) intelligent power meter | |
| CN113655304A (en) | Online detection system and method for metering performance of electric vehicle charger | |
| CN202305666U (en) | Direct current electric energy meter | |
| CN114969402B (en) | Vector geographic information acquisition method based on remote sensing image | |
| Móczár et al. | Distributed measurement system for heat metering and control | |
| CN108305454A (en) | A kind of intelligent acquisition system for table tool information | |
| CN115685048A (en) | Online calibration method and system for communication module of intelligent electric meter | |
| CN201583294U (en) | Natural gas integrated intelligent differential pressure type flowmeter | |
| CN201259704Y (en) | CPU card three phase electronic type electrical energy meter | |
| CN104751570B (en) | IC-card intelligent quality flow gas table and its management system | |
| CN211627658U (en) | Intelligent meter fee control self-checking device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |