Meter reading error judgment system

Abstract

The present invention relates to a meter reading error determination system, comprising: a content determination component for intelligently determining the meter reading flow error value corresponding to the current gas meter for a set time interval on a given day, using an echo state network model based on various associated information of the current gas meter and the respective meter reading flow error values ​​corresponding to the current gas meter for multiple set time intervals on a given day; and a value analysis component for analyzing the actual gas usage in the set time interval on that day, based on the meter reading flow error value and the number of gas meter readings for that day. The present invention enables intelligent determination of the meter reading flow error value corresponding to the current gas meter for the set time interval on that day using an artificial intelligence mechanism, and analysis of the actual gas usage in the set time interval on that day based on the meter reading flow error value and the number of gas meter readings for that day, thereby achieving reliable calibration of meter reading data.

Description

Technical Field

[0001] The present invention relates to the field of intelligent meter reading, and in particular to a meter reading error judgment system. Background Art

[0002] The intelligent meter reading system integrates household usage data with the management department's computer network center, fundamentally resolving current issues such as low automation, numerous intermediate links, and delayed payment for water, electricity, and gas usage. The system features multiple communication methods, flexible networking, and easy expansion, meeting diverse user needs from diverse perspectives and truly enabling scientific management of residential communities.

[0003] Typical smart meter reading systems utilize a distributed architecture, significantly improving system reliability and scalability. Communication between the data collector and the management center computer utilizes standard RS485 for long-distance data transmission. This unique and flexible networking approach is suitable for a variety of installation and use environments. However, smart meter reading is a remote technology, and there is a potential for data transmission discrepancies. Therefore, analysis of actual gas usage within a set time interval is necessary to determine the validity of the gas meter readings for that time period. Summary of the Invention

[0004] In order to solve the technical problems in the prior art, the present invention provides a meter reading error judgment system, which adopts an artificial intelligence mechanism to intelligently judge the meter reading flow error value corresponding to the current gas meter in the set time interval of the day, and analyzes the actual gas usage in the set time interval of the day based on the meter reading flow error value corresponding to the set time interval of the day and the gas meter reading quantity in the set time interval of the day. Specifically, the meter reading flow error value corresponding to the set time interval of the day and the gas meter reading quantity in the set time interval of the day are added to obtain a first reference value, and the meter reading flow error value corresponding to the set time interval of the day is subtracted from the gas meter reading quantity in the set time interval of the day to obtain a second reference value. The first reference value and the second reference value are used as two alternative values ​​for the actual gas usage in the set time interval of the day, thereby achieving reliable calibration of the meter reading data and taking into account the economic interests of users and suppliers.

[0005] The present invention has at least the following outstanding substantive features:

[0006] First, an artificial intelligence mechanism is used to intelligently determine the meter reading flow error value corresponding to the set time interval of the current gas meter on the day, and the actual gas usage in the set time interval on the day is analyzed based on the meter reading flow error value corresponding to the set time interval on the day and the gas meter reading quantity in the set time interval on the day. Specifically, the meter reading flow error value corresponding to the set time interval on the day and the gas meter reading quantity in the set time interval on the day are added together to obtain a first reference value, and the meter reading flow error value corresponding to the set time interval on the day is subtracted from the gas meter reading quantity in the set time interval on the day to obtain a second reference value. The first reference value and the second reference value are used as two alternative values ​​for the actual gas usage in the set time interval on the day, thereby achieving reliable calibration of the meter reading data and taking into account the economic interests of both users and suppliers.

[0007] Secondly, the artificial intelligence mechanism for performing intelligent judgment is based on an Echo State Network model. The Echo State Network model is the Echo State Network after completing multiple training actions. The number of training actions completed by the Echo State Network is monotonically positively correlated with the flow rate of the current gas meter, thereby enabling the customization of the Echo State Network model structure for different gas meters.

[0008] Again: obtain the meter reading flow error values ​​corresponding to the set time intervals of multiple historical days for the current gas meter, the position of the set time interval for each day on the time axis of that day is the same, and the meter reading flow error value corresponding to the set time interval for each day is the absolute value of the difference between the actual amount of gas used in the set time interval of that day and the gas meter reading amount in the set time interval of that day, and obtain the maximum set flow, minimum set flow, maximum working pressure, minimum working pressure, gas channel diameter and the number of gas appliances connected at the same time of the current gas meter as various related information of the current gas meter, so as to obtain comprehensive and sufficient basic information for intelligent judgment.

[0009] According to the present invention, a meter reading error judgment system is provided, the system comprising:

[0010] a training mapping mechanism for performing multiple training actions on the echo state network to obtain an echo state network after completing the multiple training actions and outputting the network as an echo state network model, wherein the number of training actions completed by the echo state network is monotonically positively correlated with the flow range of the current gas meter;

[0011] The error analysis mechanism is used to obtain the flow error values ​​of each meter reading corresponding to the set time intervals of multiple historical days for the current gas meter, where the set time interval of each day has the same position on the time axis of that day, and the flow error value of the meter reading corresponding to the set time interval of each day is the absolute value of the difference between the actual gas usage amount in the set time interval of that day and the gas meter reading amount in the set time interval of that day;

[0012] An information extraction mechanism is used to output the maximum set flow rate, minimum set flow rate, maximum working pressure, minimum working pressure, gas channel diameter, and the number of gas appliances connected simultaneously of the current gas meter as various related information of the current gas meter;

[0013] a content judgment component, connected to the training mapping mechanism, the error analysis mechanism, and the information extraction mechanism, respectively, for using the echo state network model to intelligently judge the meter reading flow error value corresponding to the set time interval of the current gas meter on the current day based on various associated information of the current gas meter and the meter reading flow error values ​​corresponding to the set time intervals of multiple historical days;

[0014] a numerical analysis component connected to the content judgment component, configured to analyze the actual amount of gas used in the set time interval of the day based on the meter reading flow error value corresponding to the set time interval of the day and the gas meter reading amount in the set time interval of the day;

[0015] Among them, analyzing the actual amount of gas used in the set time interval of the day based on the meter reading flow error value corresponding to the set time interval of the day and the gas meter reading quantity in the set time interval of the day includes: adding the meter reading flow error value corresponding to the set time interval of the day and the gas meter reading quantity in the set time interval of the day to obtain a first reference value, subtracting the meter reading flow error value corresponding to the set time interval of the day from the gas meter reading quantity in the set time interval of the day to obtain a second reference value, and using the first reference value and the second reference value as two alternative values ​​for the actual amount of gas used in the set time interval of the day. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The embodiments of the present invention will be described below with reference to the accompanying drawings, in which:

[0017] Figure 1 FIG. 1 is a structural block diagram of a meter reading error judgment system according to embodiment A of the present invention.

[0018] Figure 2 FIG. 1 is a structural block diagram of a meter reading error judgment system according to embodiment B of the present invention.

[0019] Figure 3 FIG. 1 is a structural block diagram of a meter reading error judgment system according to embodiment C of the present invention. DETAILED DESCRIPTION

[0020] The following is a detailed description of an embodiment of the meter reading error judgment system of the present invention with reference to the accompanying drawings.

[0021] Figure 1This is a structural block diagram of a meter reading error judgment system according to embodiment A of the present invention, wherein the system comprises:

[0022] a training mapping mechanism for performing multiple training actions on the echo state network to obtain an echo state network after completing the multiple training actions and outputting the network as an echo state network model, wherein the number of training actions completed by the echo state network is monotonically positively correlated with the flow range of the current gas meter;

[0023] For example, the training mapping mechanism is configured to perform multiple training actions on an echo state network to obtain an echo state network after completing the multiple training actions and output the network as an echo state network model, wherein the number of training actions completed by the echo state network is monotonically positively correlated with the flow range of the current gas meter includes: using a signal conversion formula to represent a signal conversion relationship in which the number of training actions completed by the echo state network is monotonically positively correlated with the flow range of the current gas meter;

[0024] The error analysis mechanism is used to obtain the flow error values ​​of each meter reading corresponding to the set time intervals of multiple historical days for the current gas meter, where the set time interval of each day has the same position on the time axis of that day, and the flow error value of the meter reading corresponding to the set time interval of each day is the absolute value of the difference between the actual gas usage amount in the set time interval of that day and the gas meter reading amount in the set time interval of that day;

[0025] An information extraction mechanism is used to output the maximum set flow rate, minimum set flow rate, maximum working pressure, minimum working pressure, gas channel diameter, and the number of gas appliances connected simultaneously of the current gas meter as various related information of the current gas meter;

[0026] a content judgment component, connected to the training mapping mechanism, the error analysis mechanism, and the information extraction mechanism, respectively, for using the echo state network model to intelligently judge the meter reading flow error value corresponding to the set time interval of the current gas meter on the current day based on various associated information of the current gas meter and the meter reading flow error values ​​corresponding to the set time intervals of multiple historical days;

[0027] a numerical analysis component connected to the content judgment component, configured to analyze the actual amount of gas used in the set time interval of the day based on the meter reading flow error value corresponding to the set time interval of the day and the gas meter reading amount in the set time interval of the day;

[0028] The analyzing the actual gas usage in the set time interval based on the meter reading flow error value corresponding to the set time interval and the gas meter reading quantity in the set time interval includes: adding the meter reading flow error value corresponding to the set time interval and the gas meter reading quantity in the set time interval to obtain a first reference value, subtracting the meter reading flow error value corresponding to the set time interval from the gas meter reading quantity in the set time interval to obtain a second reference value, and using the first reference value and the second reference value as two alternative values ​​for the actual gas usage in the set time interval;

[0029] The method of obtaining the flow error values ​​of each meter reading corresponding to each set time interval of the current gas meter in the history of multiple days, wherein the position of the set time interval of each day on the time axis of the day is the same, and the flow error value of the meter reading corresponding to the set time interval of each day is the absolute value of the difference between the actual gas usage amount in the set time interval of the day and the gas meter reading amount in the set time interval of the day, includes: the historical multiple days are before the current day, and the number of days in the historical multiple days is proportional to the maximum set flow of the current gas meter;

[0030] And wherein, the training mapping device is used to perform multiple training actions on the echo state network to obtain the echo state network after completing the multiple training actions and output it as an echo state network model, and the number of training actions completed by the echo state network is monotonically positively correlated with the flow range of the current gas meter, including: the flow range of the current gas meter is the difference between the maximum set flow and the minimum set flow of the current gas meter.

[0031] Figure 2 FIG. 1 is a structural block diagram of a meter reading error judgment system according to embodiment B of the present invention.

[0032] Compared to embodiment A, the meter reading error judgment system shown in embodiment B of the present invention may further include:

[0033] a directional extraction component, disposed near the content determination component, the training mapping mechanism, the error analysis mechanism, and the information extraction mechanism and connected to the content determination component, the training mapping mechanism, the error analysis mechanism, and the information extraction mechanism, respectively;

[0034] Among them, the directional extraction component is arranged near the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism and is respectively connected to the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism, including: the directional extraction component is used to respectively realize on-site measurement of the current internal temperature of the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism.

[0035] Figure 3 FIG. 1 is a structural block diagram of a meter reading error judgment system according to embodiment C of the present invention.

[0036] Compared to implementation scheme A, the meter reading error judgment system shown in implementation scheme C of the present invention may further include:

[0037] a data acquisition component, disposed near the content determination component, the training mapping mechanism, the error analysis mechanism, and the information extraction mechanism and connected to the content determination component, the training mapping mechanism, the error analysis mechanism, and the information extraction mechanism, respectively;

[0038] Among them, the data acquisition component is arranged near the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism and is respectively connected to the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism, including: the data acquisition component is used to respectively realize on-site measurement of the current output power of the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism.

[0039] Next, the specific structure of the meter reading error judgment system of the present invention will be further described.

[0040] In the meter reading error judgment system according to various embodiments of the present invention:

[0041] Using a SOC chip to perform image data processing on the output data of the content determination component, the training mapping mechanism, the error analysis mechanism, and the information extraction mechanism to obtain output processed data corresponding to the content determination component, the training mapping mechanism, the error analysis mechanism, and the information extraction mechanism respectively;

[0042] The method of using a SOC chip to perform image data processing on the output data of the content judgment component, the training mapping mechanism, the error parsing mechanism, and the information extraction mechanism to obtain the output processed data corresponding to the content judgment component, the training mapping mechanism, the error parsing mechanism, and the information extraction mechanism includes: performing cache processing on the output data of the content judgment component, the training mapping mechanism, the error parsing mechanism, and the information extraction mechanism to obtain the cache data corresponding to the content judgment component, the training mapping mechanism, the error parsing mechanism, and the information extraction mechanism respectively;

[0043] wherein the SOC chip is used to perform image data processing on the output data of the content determination component, the training mapping mechanism, the error parsing mechanism, and the information extraction mechanism to obtain the output processed data corresponding to the content determination component, the training mapping mechanism, the error parsing mechanism, and the information extraction mechanism, respectively, including: the content determination component, the training mapping mechanism, the error parsing mechanism, and the information extraction mechanism are respectively connected to the SOC chip via different data interfaces;

[0044] The method of using an SOC chip to perform image data processing on output data of the content determination component, the training mapping mechanism, the error parsing mechanism, and the information extraction mechanism to obtain output processed data corresponding to the content determination component, the training mapping mechanism, the error parsing mechanism, and the information extraction mechanism includes: the content determination component, the training mapping mechanism, the error parsing mechanism, and the information extraction mechanism are respectively connected to an internal timing unit of the SOC chip;

[0045] And wherein, an SOC chip is used to perform image data processing on the output data of the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism to obtain the output processing data corresponding to the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism respectively, including: the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism are respectively connected to the internal registers of the SOC chip.

[0046] In addition, in the meter reading error judgment system, a training mapping device is used to perform multiple training actions on the echo state network to obtain an echo state network after completing the multiple training actions and output it as an echo state network model, and the number of training actions completed by the echo state network is monotonically positively correlated with the flow range of the current gas meter. The method also includes: using a numerical conversion formula to express the numerical conversion relationship of the monotonically positive correlation between the number of training actions completed by the echo state network and the flow range of the current gas meter.

[0047] The meter reading error judgment system of the present invention addresses the technical problem in the prior art of being unable to reliably calibrate remote meter reading data. By adopting an artificial intelligence mechanism to intelligently judge the meter reading flow error value corresponding to the current gas meter in the set time interval of the day, and based on the meter reading flow error value and the number of gas meter readings in the set time interval of the day, the actual amount of gas used in the set time interval of the day is analyzed, thereby solving the above technical problem.

[0048] Those skilled in the art will appreciate that various improvements may be made to the device disclosed herein without departing from the scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the contents of the appended claims.

Claims

1. A meter reading error judgment system, characterized in that: The system includes: a training mapping mechanism for performing multiple training actions on the echo state network to obtain an echo state network after completing the multiple training actions and outputting the network as an echo state network model, wherein the number of training actions completed by the echo state network is monotonically positively correlated with the flow rate of the current gas meter; The flow range of the current gas meter is the difference between the maximum set flow rate and the minimum set flow rate of the current gas meter; Among them, a numerical conversion formula is used to express the numerical conversion relationship of the number of training actions completed by the echo state network and the flow stroke of the current gas meter in a monotonically positive correlation; The error analysis mechanism is used to obtain the flow error values ​​of each meter reading corresponding to the set time intervals of multiple historical days for the current gas meter, where the set time interval of each day has the same position on the time axis of that day, and the flow error value of the meter reading corresponding to the set time interval of each day is the absolute value of the difference between the actual gas usage amount in the set time interval of that day and the gas meter reading amount in the set time interval of that day; Among them, the historical multiple days are before the current day, and the number of historical multiple days is proportional to the maximum set flow of the current gas meter; An information extraction mechanism is used to output the maximum set flow rate, minimum set flow rate, maximum working pressure, minimum working pressure, gas channel diameter, and the number of gas appliances connected simultaneously of the current gas meter as various related information of the current gas meter; The content judgment component is connected to the training mapping mechanism, the error analysis mechanism, and the information extraction mechanism, respectively, and is used to use the echo state network model to intelligently judge the meter reading flow error value corresponding to the set time interval of the current gas meter based on various related information of the current gas meter and the meter reading flow error values ​​corresponding to the set time intervals of multiple historical days; a numerical analysis component connected to the content judgment component, for analyzing the actual amount of gas used in the set time interval of the day based on the meter reading flow error value corresponding to the set time interval of the day and the gas meter reading amount in the set time interval of the day; Among them, the meter reading flow error value corresponding to the set time interval of the day and the gas meter reading quantity in the set time interval of the day are added to obtain a first reference value, and the meter reading flow error value corresponding to the set time interval of the day is subtracted from the gas meter reading quantity in the set time interval of the day to obtain a second reference value. The first reference value and the second reference value are used as two alternative values ​​for the actual amount of gas used in the set time interval of the day.

2. The meter reading error judgment system according to claim 1, wherein: The system further comprises: a directional extraction component, disposed near the content determination component, the training mapping mechanism, the error analysis mechanism, and the information extraction mechanism and connected to the content determination component, the training mapping mechanism, the error analysis mechanism, and the information extraction mechanism, respectively; The directional extraction component is used to respectively realize on-site measurement of the current internal temperature of the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism.

3. The meter reading error judgment system according to claim 1, wherein: The system further comprises: a data acquisition component, disposed near the content determination component, the training mapping mechanism, the error analysis mechanism, and the information extraction mechanism and connected to the content determination component, the training mapping mechanism, the error analysis mechanism, and the information extraction mechanism, respectively; The data acquisition component is used to respectively realize on-site measurement of the current output power of the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism.

4. The meter reading error judgment system according to any one of claims 1 to 3, characterized in that: An SOC chip is used to perform image data processing on the output data of the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism to obtain output processing data corresponding to the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism respectively.

5. The meter reading error judgment system according to claim 4, wherein: The output data of the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism are cached to obtain the cache data corresponding to the content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism respectively.

6. The meter reading error judgment system according to claim 4, wherein: The content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism are respectively connected to the SOC chip through different data interfaces.

7. The meter reading error judgment system according to claim 4, wherein: The content determination component, the training mapping mechanism, the error analysis mechanism, and the information extraction mechanism are respectively connected to an internal timing unit of the SOC chip.

8. The meter reading error judgment system according to claim 4, wherein: The content judgment component, the training mapping mechanism, the error analysis mechanism and the information extraction mechanism are respectively connected to the internal registers of the SOC chip.

Images