Optimization method based on ultrasonic gas meter metering data

Abstract

Provided is an optimization method based on ultrasonic gas meter metering data, comprising: if a trend index obtained by analysis does not meet an expectation, calculating the degree of influence of a measurement condition on the trend index, and on the basis of the degree of influence, determining whether gas meter measurement data needs to be compensated for; constructing an initial compensation model for the gas meter measurement data, after optimization based on multiple variables, performing sensitivity analysis on an optimized compensation model, and by combining a compensation factor with real-time temperature and pressure data, completing correction of display data of a gas meter; and acquiring the characteristics of a fluid in a pipeline, according to the correspondence between the characteristics of the fluid and an optimization scheme, matching the corresponding optimization scheme for the gas meter from a pre-constructed gas meter optimization knowledge graph, executing the optimization scheme, and optimizing the gas meter.

Description

An optimization method based on ultrasonic gas meter measurement data Technical Field

[0001] The present invention relates to the technical field of metering data optimization, and in particular to an optimization method based on metering data of an ultrasonic gas meter. Background Art

[0002] An ultrasonic gas meter uses ultrasonic technology for measurement. Compared to traditional mechanical gas meters, ultrasonic gas meters offer higher measurement accuracy and reliability, and are less susceptible to mechanical wear and aging. The ultrasonic gas meter measures gas flow by exploiting the relationship between the speed of ultrasonic waves propagating through gas and the gas flow rate. As gas passes through the ultrasonic gas meter, an ultrasonic transmitter emits a beam of ultrasonic waves, which propagate through the gas. When the ultrasonic wave encounters obstacles in the gas (such as impurities or gas molecules), it is reflected and scattered. By measuring the time and speed of the ultrasonic wave's propagation through the gas, the gas flow rate can be calculated.

[0003] Chinese invention patent application publication number CN116295692A discloses a gas data processing method, system, device, and medium for a diaphragm gas meter. The compensation method obtains the meter's character length and character spacing length, and determines the meter's character center angle and character spacing center angle based on the character length and character spacing length; obtains the meter's rotational volume, and determines the meter's character spacing compensation based on the rotational volume and character spacing center angle; determines the meter's metering time and character wheel diameter; obtains the meter's boundary information and boundary distance based on the metering time; and determines the meter's compensated gas volume based on the character spacing compensation, character wheel diameter, rotational volume, and boundary distance.

[0004] The above compensation method can accurately measure the gas compensation amount of the diaphragm gas meter at the beginning or end, thereby improving the accuracy of gas metering. However, in addition to this, in the existing metering data optimization method, when the ultrasonic gas meter continuously outputs display data to the outside, the data quality is usually used as the starting point for optimization. When there are abnormalities in the output display data, the abnormal data is replaced or corrected, and finally the corrected display data is obtained.

[0005] However, although this method of optimizing data can reduce the frequency of abnormal data, its actual coverage is narrow and it can only screen out a number of abnormal points. When there are many abnormal points, they are usually resolved through alarms. Moreover, when the temperature and air pressure of the ultrasonic gas meter are variable, the state of the gas in the pipeline will also be affected. The degree of interference caused by temperature and air pressure changes to the gas meter display data is insufficient, and the displayed data after interference is difficult to be determined as abnormal data. This makes it difficult for the existing optimization method to play a practical role.

[0006] To this end, the present invention provides an optimization method based on ultrasonic gas meter measurement data.

[0007] Summary of the Invention

[0008] (1) Technical problems solved

[0009] In response to the shortcomings of the existing technology, the present invention provides an optimization method based on ultrasonic gas meter metering data. By calculating the degree of influence of measurement conditions on the trend index, the method determines whether the gas meter measurement data needs to be compensated based on the magnitude of the influence. An initial compensation model for the gas meter measurement data is constructed. After multivariable optimization, a sensitivity analysis is performed on the optimized compensation model. The compensation factor is combined with real-time temperature and pressure data to complete the correction of the gas meter display data, obtain the fluid characteristics in the pipeline, and match the gas meter with a corresponding optimization solution from a pre-constructed gas meter optimization knowledge graph based on the correspondence between the fluid characteristics and the optimization solution. The optimization solution is executed to optimize the gas meter. This method can eliminate the interference caused by temperature and pressure, reduce gas meter measurement errors, and improve the authenticity and reliability of the gas meter display data, thereby solving the technical problems described in the background technology.

[0010] (2) Technical solution

[0011] To achieve the above objectives, the present invention is implemented through the following technical solutions: an optimization method based on ultrasonic gas meter measurement data, comprising:

[0012] Obtaining measurement condition data of the gas meter in a pipeline connected to the gas meter, constructing a measurement condition set for the gas meter, generating a condition coefficient Wp(t,u) from the measurement condition set, and issuing a warning instruction if the condition coefficient Wp(t,u) exceeds a condition threshold;

[0013] After receiving the early warning instruction, the gas meter display error is analyzed. If the trend index obtained by the analysis does not meet the expectations, the degree of influence of the measurement conditions on the trend index is calculated. Based on the degree of influence, it is determined whether the gas meter measurement data needs to be compensated.

[0014] Construct an initial compensation model for gas meter measurement data. After multivariable optimization, perform a sensitivity analysis on the optimized compensation model. Determine the corresponding compensation factor based on the analysis results. Combine the compensation factor with real-time temperature and pressure data to optimize the gas meter display data.

[0015] If the accuracy of the corrected gas meter display data is lower than expected, obtain the fluid characteristics in the pipeline, and based on the correspondence between the fluid characteristics and the optimization plan, match the corresponding optimization plan for the gas meter from the pre-built gas meter optimization knowledge graph, execute the optimization plan, and optimize the gas meter.

[0016] Furthermore, a monitoring point is set up in the pipeline connected to it. In each monitoring cycle, the temperature and pressure in the pipeline are monitored to obtain the measured temperature Ct and measured pressure Cu when the gas meter is working. After several consecutive monitoring cycles, the data obtained from the monitoring are summarized to construct a measurement condition set for the gas meter.

[0017] Furthermore, the conditional coefficient Wp(t,u) is obtained as follows: linearly normalize the measured temperature Ct and the measured pressure Cu, and map the corresponding data values ​​to the interval [0, 1], and then use the following formula:

[0018] in, To measure the average temperature in each monitoring period, is the mean value of the measured pressure within the monitoring period; weight coefficient: 0≤β≤1, 0≤α≤1, and α+β=1, where i=1, 2,…n, n is the number within the monitoring period, which is a positive integer greater than 1.

[0019] Furthermore, the actual gas consumption is monitored in each monitoring cycle, and the measurement data is obtained. The difference between the measurement data and the gas meter display data is used as the display error. After obtaining the display error for several times in a row, an error set is constructed; a trend analysis is performed on the display error in the error set, and the corresponding trend index is obtained to determine whether the trend index in the current monitoring cycle falls within the preset interval. If not, a judgment instruction is issued.

[0020] Furthermore, after receiving the judgment instruction, the trend index and the corresponding condition coefficient Wp(t, u) within multiple monitoring periods are continuously obtained, and the measurement condition data corresponding to the condition coefficient Wp(t, u) is used as the independent variable, and the trend index within each monitoring period is used as the dependent variable to perform linear regression analysis and obtain the corresponding regression equation.

[0021] Furthermore, the regression coefficient corresponding to the measurement condition data in the regression equation is used as the influencing factor, and the influencing coefficient Yr(t,u) is constructed according to the following method;

[0022] in, is the influencing factor of the measured temperature Ct, is the influencing factor of the measured pressure Cu; the weight coefficient is 0≤ψ1≤1, 0≤ψ2≤1, and the weight coefficient can be obtained by referring to the hierarchical analysis method;

[0023] If the impact coefficient Yr(t,u) exceeds the impact threshold, a correction instruction is issued to the outside; if the impact coefficient Yr(t,u) does not exceed expectations, a reminder instruction is issued.

[0024] Furthermore, the gas flow rate is measured at different temperatures and pressures to complete data acquisition; based on the gas state equation, the influence of temperature and pressure on the gas density is analyzed, the degree to which the propagation speed of ultrasound in the gas is affected by temperature and pressure is determined, and the corresponding physical connection is obtained; based on the collected data and physical connection, an initial compensation model is constructed based on empirical nonlinear equations to describe the influence of temperature and pressure on the measurement data.

[0025] Furthermore, standard test data is obtained, and multiple linear regression analysis is used to optimize the model parameters of the initial compensation model so that the values ​​predicted by the model are consistent with the experimental data. Other variables are used to perform multivariate optimization and verification on the initial compensation model to obtain the optimized compensation model.

[0026] A sensitivity analysis is performed on the optimized compensation model, using temperature and pressure as analysis factors to obtain the degree of influence of the analysis factors on the measurement data. The corresponding compensation factor is determined based on the influence degree. The compensation factor is combined with real-time temperature and pressure data to dynamically adjust the gas meter display data.

[0027] Furthermore, the measured data is used as the gas meter display data to construct a data accuracy model, and the data accuracy Py of the gas meter display data before and after correction is calculated respectively, referring to the following method:

[0028] Among them, Yo i The value of the data at position i is displayed for the gas meter. Displays the mean value of the data for the gas meter;

[0029] The ratio of the data accuracy Py before and after compensation is used as the accuracy ratio Pb. If the accuracy ratio Pb exceeds the ratio threshold, a self-check instruction is issued to the outside.

[0030] Furthermore, after receiving the self-test instruction, the corresponding fluid data is collected in the pipeline, and based on the fluid data and its distribution status, a fluid data set is constructed after aggregation. After setting the feature standards, feature recognition is performed on the data in the fluid data set to obtain the corresponding fluid features; ultrasonic gas meter optimization is used as the target word, and an initial knowledge graph after training and optimization is constructed, which is used as the gas meter optimization knowledge graph.

[0031] (3) Beneficial effects

[0032] The present invention provides an optimization method based on ultrasonic gas meter measurement data, which has the following beneficial effects:

[0033] 1. By constructing the conditional coefficient Wp(t,u), a preliminary judgment is made on the degree of interference to the gas meter based on the conditional coefficient Wp(t,u). If the degree of interference is large, the authenticity of the data displayed by the gas meter is low. The working status of the gas meter can be predicted by the change of the conditional coefficient Wp(t,u).

[0034] 2. Through trend analysis, the degree of change of the displayed error is analyzed with the trend index, so as to judge whether the error generated by the gas meter will accumulate after long-term use, and then determine whether the gas meter needs to be repaired based on the judgment result. If the repair standard is met, the use of the gas meter can be suspended and entered into the repair state.

[0035] 3. The degree of influence of the measurement conditions of the gas meter on the trend of its display error change is judged based on the value of the influence coefficient Yr(t,u). If the degree of influence is large, a correction instruction is issued to the outside, and based on the correction instruction, the display data of the gas meter is corrected and compensated.

[0036] 4. Optimizing gas meter data eliminates the interference caused by temperature and pressure to a certain extent, reduces the error between the data and the actual data, and improves the authenticity and reliability of the data displayed by the gas meter. When this is used as a pricing standard, the economic losses incurred are relatively small. By building a compensation model, the number of times data is continuously optimized can be reduced, thereby improving optimization efficiency.

[0037] 5. By building a gas meter optimization knowledge graph, the corresponding optimization plan is matched from the gas meter optimization knowledge graph according to the fluid characteristics, and the gas meter is optimized in a targeted manner, so that the optimized gas meter is more compatible with the measurement conditions. When an abnormality occurs in the gas meter, it can be handled quickly and frequently to improve the optimization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] FIG1 is a flow chart of a method for optimizing measurement data of an ultrasonic gas meter according to the present invention;

[0039] FIG2 is a schematic diagram of the optimization system results of the ultrasonic gas meter measurement data of the present invention. DETAILED DESCRIPTION

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0041] Referring to FIG1 , the present invention provides an optimization method based on ultrasonic gas meter measurement data, comprising the following steps:

[0042] Step 1: Obtain the measurement condition data of the gas meter in the pipeline connected to the gas meter, construct a measurement condition set for the gas meter, and generate a condition coefficient Wp(t,u) from the measurement condition set. If the condition coefficient Wp(t,u) exceeds the condition threshold, issue a warning instruction;

[0043] The step 1 includes the following:

[0044] Step 101: After determining the location of the gas meter, a monitoring point is set in the pipeline connected to it, and a corresponding monitoring period is determined, such as 1 minute or 3 minutes. During each monitoring period, the temperature and pressure in the pipeline are monitored to obtain the measured temperature Ct and pressure Cu of the gas meter, that is, the ultrasonic gas meter during operation. After several consecutive monitoring periods, the monitored data is aggregated to construct a set of measurement conditions for the gas meter.

[0045] Step 102: Generate a condition coefficient Wp(t,u) from the measurement condition set. The condition coefficient Wp(t,u) is obtained as follows: linearly normalize the measured temperature Ct and the measured pressure Cu, and map the corresponding data values ​​to the interval [0, 1], and then use the following formula:

[0046] in, To measure the average temperature in each monitoring period, is the mean value of the measured pressure during the monitoring period; weight coefficient: 0≤β≤1, 0≤α≤1, and α+β=1, where the weight coefficient can be obtained by referring to the hierarchical analysis method;

[0047] Where i = 1, 2, ... n, n is the number of monitoring cycles, which is a positive integer greater than 1, Ct i To measure the temperature at position i, Cu i is the value of the measured pressure at position i;

[0048] Based on historical data and management expectations for gas meter quality, a condition threshold is pre-set. If the condition coefficient Wp(t,u) exceeds the pre-set condition threshold, it indicates that the temperature and pressure of the gas in the pipeline may be abnormal. In this case, when the gas meter is used to monitor the gas usage status, there may be a certain difference between the actual data and the measured data, and the authenticity and reliability are insufficient. In this case, an external warning instruction is issued;

[0049] Additional explanations are needed:

[0050] Ultrasonic gas meters calculate flow rate and flow by measuring the difference in the propagation time of ultrasonic signals in the gas medium. Temperature and pressure are the two main environmental factors that affect the measurement accuracy of ultrasonic gas meters. They interfere with the propagation characteristics of ultrasonic waves by changing the physical properties of the gas.

[0051] The speed of sound of a gas changes with temperature. As the temperature rises, molecular motion accelerates and the speed of sound increases. Conversely, when the temperature decreases, the speed of sound slows down. Temperature also affects the density of the gas. According to the ideal gas law, when the temperature rises, the volume of the gas will expand and the density will decrease without changing the pressure; when the temperature drops, the density increases. Changing the gas density will indirectly affect ultrasonic measurement because the measurement of sound wave propagation time usually assumes that the gas density is constant.

[0052] The density of a gas changes with pressure. As pressure increases, the gas molecules compress, increasing the density; as pressure decreases, the density decreases. Pressure affects the speed of sound, but this effect is generally minor in gases because they are more compressible than liquids. However, at high pressures, the effect of pressure on the speed of sound becomes more significant.

[0053] When using, combine the contents in steps 101 and 102:

[0054] When the ultrasonic gas meter is in use, temperature and pressure factors will have a certain impact on the fluid state in the pipeline, and ultimately cause certain interference to the gas meter measurement data, causing certain errors between the actual data and the displayed data. If it cannot be handled in time, it will cause certain economic losses. In this step, by constructing the conditional coefficient Wp(t,u), a preliminary judgment is made on the degree of interference to the gas meter based on the conditional coefficient Wp(t,u). If the degree of interference is large, the authenticity of the data displayed by the gas meter is low. At this time, timely processing is required. Otherwise, the state can be maintained. Therefore, the working state of the gas meter can be predicted through the change of the conditional coefficient Wp(t,u).

[0055] In the existing metering data optimization method, when the ultrasonic gas meter continuously outputs display data to the outside, data quality is usually used as the starting point for optimization. When there are abnormalities in the output display data, the abnormal data is replaced or corrected, and finally the corrected display data is obtained. However, although this method of optimizing data can reduce the frequency of abnormal data, its actual coverage is relatively narrow, and it can only screen out a number of abnormal points. When there are many abnormal points, they are usually resolved through alarms. Moreover, when the temperature and air pressure of the ultrasonic gas meter are changeable, the gas state in the pipeline will also be affected. The degree of interference caused by temperature and air pressure changes to the gas meter display data is insufficient, and the display data after interference is difficult to be determined as abnormal data. This makes it difficult for the existing optimization method to play a practical role.

[0056] Step 2: After receiving the warning instruction, perform a trend analysis on the display error of the gas meter. If the trend index obtained by the analysis does not meet expectations, calculate the degree of influence of the measurement conditions on the trend index. Based on the degree of influence, determine whether the gas meter measurement data needs to be compensated;

[0057] The second step includes the following:

[0058] Step 201: At a monitoring point in the pipeline, actual gas consumption is monitored during each monitoring cycle, and the measured data is obtained. The difference between the measured data and the data displayed on the gas meter is used as the display error. After obtaining the display error for a number of consecutive times, an error set is constructed. A trend analysis is performed on the display errors in the error set, and a corresponding trend index is obtained. It is determined whether the trend index in the current monitoring cycle falls within a preset range. If not, a determination instruction is issued.

[0059] Through trend analysis, the degree of change of the displayed error is analyzed with a trend index, so that it is possible to judge whether the errors generated by the gas meter will accumulate after long-term use, and then determine whether the gas meter needs to be repaired based on the judgment results. If the repair standards are met, the use of the gas meter can be suspended and put into repair state.

[0060] Step 202: After receiving the judgment instruction, continuously obtain the trend index and the corresponding condition coefficient Wp(t,u) within multiple monitoring periods, use the measurement condition data corresponding to the condition coefficient Wp(t,u) as the independent variable, and use the trend index within each monitoring period as the dependent variable to perform linear regression analysis and obtain the corresponding regression equation;

[0061] Step 203: Using the regression coefficient corresponding to the measurement condition data in the regression equation as an influencing factor, the influencing coefficient Yr(t,u) is constructed according to the following method;

[0062] in, is the influencing factor of the measured temperature Ct, is the influencing factor of the measured pressure Cu; the weight coefficient is 0≤ψ1≤1, 0≤ψ2≤1, and the weight coefficient can be obtained by referring to the hierarchical analysis method;

[0063] Based on historical data and expected usage of the gas meter, an impact threshold is pre-set. If the impact coefficient Yr(t,u) exceeds the impact threshold, it means that the two representative conditions of temperature and pressure in the pipeline have a cumulative impact on the gas meter display error. If not promptly addressed, the gas meter may be damaged. In this case, a correction instruction is issued to the external party.

[0064] If the impact coefficient Yr(t,u) does not exceed expectations, it means that the impact on the operation of the gas meter is stable, and a reminder instruction is issued at this time.

[0065] Among them, trend analysis can refer to the following:

[0066] Trend analysis is a statistical method used to detect the direction or path of movement of a series of data points (such as time series data) over a period of time. It uses historical data to predict future trends, helping to understand past behavior and attempt to anticipate potential future changes. Trend analysis is widely used in financial analysis, meteorology, market research, and various scientific studies. A trend index is typically used in trend analysis to measure the strength or direction of a trend. It refers to a metric that measures the degree to which a specific variable changes over time.

[0067] When using, combine the contents in steps 201 to 203:

[0068] After performing multiple regression analysis, the influence coefficient Yr(t,u) is constructed. Based on the value of the influence coefficient Yr(t,u), the degree of influence of the measurement conditions of the gas meter on the trend of its display error change is judged. If the degree of influence is large, a correction instruction is issued to the outside. Based on the correction instruction, the display data of the gas meter is corrected and compensated. At the same time, after several different regression analyses, factors other than temperature and air pressure can also be judged and analyzed.

[0069] Step 3: Construct an initial compensation model for the gas meter measurement data. After multivariable optimization, perform a sensitivity analysis on the optimized compensation model. Based on the analysis results, determine the corresponding compensation factor. Combine the compensation factor with the real-time temperature and pressure data to optimize the gas meter display data.

[0070] The step three includes the following:

[0071] Step 301: Measure gas flow at different temperatures and pressures to complete data acquisition; analyze the effects of temperature and pressure on gas density based on the gas state equation, determine the extent to which the propagation velocity of ultrasonic waves in the gas is affected by temperature and pressure, and obtain the corresponding physical connection;

[0072] According to the collected data and physical connections, an initial compensation model is constructed based on empirical nonlinear equations to describe the influence of temperature and pressure on the measurement data, thus completing the construction of the initial compensation model:

[0073] Step 302: Acquire standard test data. For example, conduct experiments using standard gas with known parameters (such as temperature, pressure, and flow), change the temperature and pressure conditions, and record the corresponding measurement data to obtain test data. Use multiple linear regression analysis to optimize the model parameters of the initial compensation model so that the model-predicted values ​​match the experimental data. Use other variables, such as gas type and humidity, to perform multivariate optimization and verification on the initial compensation model to obtain an optimized compensation model.

[0074] Step 303: Perform sensitivity analysis on the optimized compensation model, using temperature and pressure as analysis factors to obtain the degree of influence of the analysis factors on the measurement data, determine the corresponding compensation factor based on the influence degree, and dynamically adjust the gas meter display data based on the compensation factor combined with the real-time temperature and pressure data.

[0075] When using, combine the contents in steps 301 to 303:

[0076] After receiving the correction instruction, a compensation model is constructed, and the corresponding compensation factor is obtained after sensitivity analysis. Thus, based on the compensation factor and the current temperature and pressure data, the current display number of the gas meter is compensated and corrected. After correction and compensation, the gas meter data is optimized. Therefore, the optimized gas meter display data eliminates the interference caused by temperature and pressure to a certain extent, and the error between the data and the real data is smaller, thereby improving the authenticity and reliability of the gas meter display data. When this is used as a pricing standard, the economic loss generated is relatively small. By constructing a compensation model, the number of times the data is continuously optimized can be reduced, and the optimization efficiency can be improved.

[0077] Step 4: If the corrected gas meter display data accuracy is lower than expected, obtain the fluid characteristics in the pipeline, and based on the correspondence between the fluid characteristics and the optimization solution, match the gas meter with a corresponding optimization solution from the pre-built gas meter optimization knowledge graph, execute the optimization solution, and optimize the gas meter;

[0078] The step 4 includes the following contents:

[0079] Step 401: Use the measured data as the gas meter display data to construct a data accuracy model, and calculate the data accuracy Py of the gas meter display data before and after correction, respectively, as follows:

[0080] Among them, Yo i The value of the data at position i is displayed for the gas meter. Displays the mean value of the data for the gas meter;

[0081] The ratio of the data accuracy Py before and after compensation is used as the accuracy ratio Pb. Combined with historical data and management expectations for gas meter accuracy, a ratio threshold is pre-set. If the accuracy ratio Pb exceeds the ratio threshold, it means that after compensation and correction of the gas meter's measurement data, the accuracy of the data used is insufficient, and the gas meter may have certain operational faults. In this case, a self-test command is issued to the outside.

[0082] Step 402: After receiving the self-test instruction, corresponding fluid data, such as pressure, flow rate, density, and temperature, are collected in the pipeline. Based on the fluid data and its distribution, a fluid data set is constructed after aggregation. After setting feature standards, feature recognition is performed on the data in the fluid data set to obtain the corresponding fluid features.

[0083] Step 403: Using ultrasonic gas meter optimization as the target word, construct a gas meter optimization knowledge graph. The specific method can be found in the following content:

[0084] Using ultrasonic gas meter optimization as the target word, we collected relevant data sets, which may include literature, reports, news, databases, etc. We cleaned the collected data, removed irrelevant information, and standardized the data. We used natural language processing methods to segment the cleaned data text and extract keywords and phrases.

[0085] Use deep learning models, such as the BERT-based NER model, to identify key entities in data text, such as the environmental conditions, operating status, fluid characteristics, and optimization solutions of ultrasonic gas meters. Aggregate the above data to construct a knowledge graph data set.

[0086] Use relational extraction models to determine the relationships between entities in a knowledge graph data set, merge identical or similar entities in the knowledge graph, and use logical reasoning models or machine learning models to discover implicit knowledge relationships. Use the RDF data model to convert data into a knowledge graph representation, including identifying core entities, defining relationships and attributes between entities, and using a unified representation method.

[0087] Constructing an initial knowledge graph involves establishing the entity nodes and the relationship edges between them, selecting a graph database or graph storage system, and loading data into it. Based on verification and evaluation, the initial knowledge graph is iterated and optimized to expand its scope and depth, and increase the richness and accuracy of the data.

[0088] The trained and optimized initial knowledge graph is obtained and used as the gas meter optimization knowledge graph. Based on the correspondence between the fluid characteristics and the optimization scheme, the corresponding optimization scheme is matched for the gas meter from the gas meter optimization knowledge graph. The optimization scheme is executed and the gas meter is optimized.

[0089] When using, combine the contents in steps 401 to 403:

[0090] By detecting and identifying the fluid characteristics in the pipeline and building a gas meter optimization knowledge graph, when a self-test instruction is received and the current operating status of the gas meter needs to be self-tested, the corresponding optimization plan is matched from the gas meter optimization knowledge graph based on the fluid characteristics. Therefore, based on the matched optimization plan, the gas meter can be optimized in a targeted manner, so that the optimized gas meter is more compatible with the measurement conditions in which it is located. At the same time, by quickly matching the optimization plan, when the gas meter has an abnormality, it can also be handled quickly and frequently, shortening the duration that the gas meter cannot be used or is in poor condition, and improving optimization efficiency.

[0091] It should be noted that the AHP is an analytical method that combines qualitative and quantitative analysis. It can decompose complex problems into multiple levels. By comparing the importance of factors at each level, it can help decision makers make decisions on complex problems and determine the final decision plan. In this process, the AHP can be used to determine the weight coefficients of these indicators. The steps of the AHP are as follows:

[0092] Clarify the problem: First, you need to clarify the decision problem and determine the decision goals and alternatives;

[0093] Establish a hierarchical model: Based on the nature of the problem and the decision-making goal, the problem is decomposed into different levels, usually including the goal level, the criterion level, and the solution level. The goal level is the overall goal of the decision-making problem, the criterion level is the criteria used to evaluate alternative solutions, and the solution level is the alternative solutions.

[0094] Constructing a judgment matrix: By comparing the importance of elements in the same level relative to an element in the previous level, a judgment matrix is ​​constructed. The elements in the judgment matrix represent the ratio of the relative importance of two elements;

[0095] Hierarchical single sorting: Based on the judgment matrix, the relative importance ranking weight of elements in the same level relative to an element in the previous level is calculated. This process is called hierarchical single sorting.

[0096] Consistency test: Check the consistency of the judgment matrix, that is, check whether the judgment matrix meets the consistency conditions. If the consistency conditions are met, the hierarchical single sorting result is considered reasonable;

[0097] Total ranking of levels: Calculate the composite weight of each level element to the system goal and perform total ranking to determine the total ranking weight of each element at the bottom level of the hierarchical structure diagram;

[0098] Through the analytic hierarchy process, decision makers can break down complex decision-making problems into different levels and make decisions based on qualitative and quantitative analysis; this method can improve the accuracy and effectiveness of decision-making and is particularly suitable for complex problems that are difficult to solve with quantitative methods.

[0099] Please refer to FIG2 . The present invention provides an optimization system based on ultrasonic gas meter measurement data, comprising:

[0100] The early warning unit obtains the measurement condition data of the gas meter in the pipeline connected to the gas meter, constructs a measurement condition set of the gas meter, generates a condition coefficient from the measurement condition set, and issues an early warning instruction if the condition coefficient exceeds a condition threshold;

[0101] The analysis unit calculates the degree of influence of the measurement conditions on the trend index if the trend index obtained by the analysis does not meet expectations, and determines whether compensation of the gas meter measurement data is required based on the magnitude of the influence;

[0102] The correction unit constructs an initial compensation model for the gas meter measurement data. After multivariable optimization, it performs sensitivity analysis on the optimized compensation model. The compensation factor is combined with real-time temperature and pressure data to complete the correction of the gas meter display data.

[0103] The optimization unit obtains the fluid characteristics in the pipeline, matches the corresponding optimization solution for the gas meter from the pre-built gas meter optimization knowledge graph based on the correspondence between the fluid characteristics and the optimization solution, executes the optimization solution, and optimizes the gas meter.

[0104] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0105] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0106] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0107] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is only for some logical functions. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0108] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0109] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0110] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0111] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0112] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. An optimization method based on the measurement data of an ultrasonic gas meter, characterized in that: including Obtain the measurement condition data of the gas meter in the pipeline connected to the gas meter, construct the measurement condition set of the gas meter, generate the condition coefficient Wp(t,u) from the measurement condition set, and issue a warning instruction if the condition coefficient Wp(t,u) exceeds the condition threshold; After receiving the warning instruction, perform a trend analysis on the display error of the gas meter. If the trend index obtained from the analysis does not meet the expectation, calculate the influence degree of the measurement condition on the trend index, and determine whether it is necessary to compensate the gas meter measurement data according to the magnitude of the influence degree; Construct an initial compensation model for the gas meter measurement data. After multi-variable optimization, perform a sensitivity analysis on the optimized compensation model, determine the corresponding compensation factor according to the analysis result, and complete the optimization of the gas meter display data by combining the compensation factor with the real-time temperature and pressure data; If the accuracy of the corrected gas meter display data is less than expected, obtain the fluid characteristics in the pipeline, and match the corresponding optimization scheme for the gas meter from the pre-constructed gas meter optimization knowledge graph according to the correspondence between the fluid characteristics and the optimization scheme, and execute the optimization scheme to optimize the gas meter.

2. The optimization method for ultrasonic gas meter measurement data according to claim 1, characterized in that: Monitor the temperature and pressure in the pipeline within each monitoring period, respectively obtain the measurement temperature Ct and measurement pressure Cu when the gas meter is working, and after several consecutive monitoring periods, summarize the monitored data to construct the measurement condition set of the gas meter.

3. The optimization method for ultrasonic gas meter measurement data according to claim 2, characterized in that: The acquisition method of the conditional coefficient Wp(t, u) is as follows: linearly normalize the measured temperature Ct and the measured pressure Cu, map the corresponding data values within the interval [0, 1], and then according to the following formula: Among them, To measure the mean value of the temperature in each monitoring period, is the average value of the measurement pressure within the monitoring period; Weighting coefficients: 0≤β≤1, 0≤α≤1, and α + β = 1, where i = 1, 2,... n, n is the number of monitoring periods, and n is a positive integer greater than 1.

4. The optimization method for ultrasonic gas meter measurement data according to claim 1, characterized in that: Monitor the actual gas consumption within each monitoring period, obtain the measurement data, use the difference between it and the gas meter display data as the display error, and construct an error set after continuously obtaining several display errors; Perform a trend analysis on the display errors in the error set and obtain the corresponding trend index, and determine whether the trend index in the current monitoring period falls within a preset interval. If not, issue a judgment instruction.

5. The optimization method for ultrasonic gas meter measurement data according to claim 4, characterized in that: After receiving the judgment instruction, continuously obtain the trend index and the corresponding condition coefficient Wp(t,u) within multiple monitoring periods, use the measurement condition data corresponding to the condition coefficient Wp(t,u) as the independent variable, and use the trend index within each monitoring period as the dependent variable to perform linear regression analysis and obtain the corresponding regression equation.

6. The optimization method for ultrasonic gas meter measurement data according to claim 5, characterized in that: Taking the regression coefficient corresponding to the measurement condition data in the regression equation as the influencing factor, and then constructing the influence coefficient Yr(t,u) according to the following method; Among them, To measure the influencing factor of temperature Ct, To measure the influence factor of pressure Cu; the weight coefficients are 0 ≤ ψ1 ≤ 1, 0 ≤ ψ2 ≤ 1. If the influence coefficient Yr(t,u) exceeds the influence threshold, a correction instruction is sent externally; if the influence coefficient Yr(t,u) does not exceed the expectation, a reminder instruction is sent.

7. An optimization method based on ultrasonic gas meter measurement data according to claim 1, characterized in that: The gas flow rate is measured at different temperatures and pressures to complete data acquisition; according to the gas state equation, the influence of temperature and pressure on the gas density is analyzed, the degree of influence of temperature and pressure on the propagation speed of ultrasonic waves in the gas is determined, and the corresponding physical relationship is obtained; based on the collected data and physical relationship, an initial compensation model is constructed based on the empirical non-linear equation.

8. An optimization method based on ultrasonic gas meter measurement data according to claim 7, characterized in that: Standard test data is obtained, multiple linear regression analysis is used to optimize the model parameters of the initial compensation model to make the predicted value of the model fit the experimental data, and other variables are used to perform multivariate optimization and verification on the initial compensation model to obtain the optimized compensation model.

9. An optimization method based on ultrasonic gas meter measurement data according to claim 8, characterized in that: Taking the measurement data as the gas meter display data, a data accuracy model is constructed, and the data accuracy Py of the gas meter display data before and after correction is calculated respectively, referring to the following method: Among them, Yo i is the value of the gas meter display data at the i position, is the mean value of the data displayed by the gas meter; Taking the ratio of the data accuracy Py before and after compensation as the accuracy ratio Pb, if the accuracy ratio Pb exceeds the ratio threshold, a self-check instruction is sent externally.

10. An optimization method based on ultrasonic gas meter measurement data according to claim 9, characterized in that: After receiving the self-check instruction, the corresponding fluid data is collected in the pipeline. Based on the fluid data and its distribution state, a fluid data set is constructed after summarization. After setting the feature standard, feature recognition is performed on the data in the fluid data set to obtain the corresponding fluid features; Taking the optimization of the ultrasonic gas meter as the target word, an initial knowledge graph after training and optimization is constructed and used as the gas meter optimization knowledge graph.

Images