阅读说明：本技术 基于人工智能的电能表运行误差监测数据拟合方法及系统 (Electric energy meter operation error monitoring data fitting method and system based on artificial intelligence ) 是由 周玉 黄奇峰 邵雪松 蔡奇新 季欣荣 李悦 马云龙 徐鸣飞 崔高颖 于 2020-11-23 设计创作，主要内容包括：本申请实施例所提供的基于人工智能的电能表运行误差监测数据拟合方法及系统,首先获取电能表运行数据及其对应的误差监测数据集合,其次确定当前时刻监测数据以进行误差分析得到用电负荷节点数据的用电损耗误差数据,然后基于用电损耗误差数据对电能表运行数据对应的当前时刻监测数据进行误差拟合得到当前误差拟合数据并加入到对应的误差监测数据集合中。进而在误差监测数据集满足设定条件时得到待监测电能表的运行误差识别结果。如此,通过对待监测电能表的不同电能表运行数据进行运行误差的分析、拟合和迭代,能够得到待监测电能表的全局性和连续性的运行误差识别结果,从而为实现待监测电能表的误差校正提供精准可靠的校正依据。(The electric energy meter operation error monitoring data fitting method and system based on artificial intelligence provided by the embodiment of the application firstly obtain electric energy meter operation data and an error monitoring data set corresponding to the electric energy meter operation data, secondly determine current moment monitoring data to carry out error analysis to obtain power consumption loss error data of power consumption load node data, and then carry out error fitting on the current moment monitoring data corresponding to the electric energy meter operation data based on the power consumption loss error data to obtain current error fitting data and add the current error fitting data into the corresponding error monitoring data set. And then obtaining an operation error identification result of the electric energy meter to be monitored when the error monitoring data set meets the set condition. Therefore, the running error identification results of the globality and the continuity of the electric energy meter to be monitored can be obtained by analyzing, fitting and iterating the running errors of different electric energy meter running data of the electric energy meter to be monitored, and accurate and reliable correction basis is provided for realizing the error correction of the electric energy meter to be monitored.)

1. An electric energy meter operation error monitoring data fitting method based on artificial intelligence is characterized by comprising the following steps:

acquiring N groups of electric energy meter operation data and an error monitoring data set corresponding to each group of electric energy meter operation data, wherein each group of electric energy meter operation data comprises M different electric load node data, and N and M are positive integers greater than or equal to 1;

determining current moment monitoring data corresponding to the electric energy meter operation data in an error monitoring data set corresponding to the electric energy meter operation data;

performing error analysis by using current moment monitoring data corresponding to the electric energy meter operation data to obtain power consumption error data of each power consumption load node data in the electric energy meter operation data;

performing error fitting on current time monitoring data corresponding to the electric energy meter operation data based on the power consumption error data of each power load node data in N groups of electric energy meter operation data to obtain current error fitting data corresponding to the electric energy meter operation data;

adding current error fitting data corresponding to the electric energy meter operation data into an error monitoring data set corresponding to the electric energy meter operation data;

and returning and executing the step to determine the current moment monitoring data corresponding to the electric energy meter operation data in the error monitoring data set corresponding to the electric energy meter operation data until the error monitoring data set meets the set conditions, and obtaining the operation error identification result of the electric energy meter to be monitored corresponding to the electric energy meter operation data.

2. The method of claim 1, wherein the electric energy meter operation data includes a first target electric energy meter operation data and a second target electric energy meter operation data other than the first target electric energy meter operation data, and after obtaining an operation error identification result of the electric energy meter to be monitored corresponding to the electric energy meter operation data, the method further includes:

when power quality analysis between first target power meter operation data and second target power meter operation data is carried out in the peak period of power utilization, determining an operation error identification result of a target power meter to be monitored corresponding to the first target power meter operation data in operation error identification results of power meters to be monitored corresponding to the N groups of power meter operation data;

determining dynamic power consumption loss error data of each power consumption load node data in the first target electric energy meter operation data by adopting the operation error identification result of the target electric energy meter to be monitored;

and performing power quality analysis based on the power consumption load node data in the first target electric energy meter operation data, the dynamic power consumption loss error data and the power consumption load node data of the second target electric energy meter operation data in the power consumption peak period.

3. The method of claim 1, wherein determining the current-time monitoring data corresponding to the energy meter operating data in the set of error monitoring data corresponding to the energy meter operating data comprises:

determining an error monitoring data set and mechanical loss data at the last moment corresponding to the electric energy meter operation data, and mechanical loss data corresponding to a second target electric energy meter operation data;

comparing mechanical loss data corresponding to the electric energy meter operation data with mechanical loss data corresponding to second target electric energy meter operation data to obtain a dial plate loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data, wherein the second target electric energy meter operation data is all electric energy meter operation data including the electric energy meter operation data in N groups of electric energy meter operation data;

comparing mechanical loss data corresponding to the electric energy meter operation data with an error monitoring data set at the last moment corresponding to the electric energy meter operation data to obtain an electric energy quality loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data;

determining an error monitoring data set at the last moment corresponding to the running data of the electric energy meter or mechanical loss data corresponding to the running data of the electric energy meter as the monitoring data at the current moment corresponding to the running data of the electric energy meter based on the comparison result of the quality loss of the electric energy and the comparison result of the loss of the dial plate;

the determining of the mechanical loss data corresponding to the second target electric energy meter operation data includes: acquiring voltage and current fluctuation data corresponding to the second target electric energy meter operation data, and determining dial plate loss record at the last moment corresponding to the second target electric energy meter operation data; according to voltage and current fluctuation data corresponding to the second target electric energy meter operation data, determining mechanical loss data corresponding to the second target electric energy meter operation data in dial loss records at the last moment corresponding to the second target electric energy meter operation data;

wherein, the determining the dial plate loss record of the last moment corresponding to the second target electric energy meter operation data includes: determining a power quality loss comparison result and a dial plate loss comparison result of each error monitoring data set in the error monitoring data set corresponding to the second target electric energy meter operation data; calculating a track fitting coefficient of each error distribution track data in an error monitoring data set corresponding to the second target electric energy meter operation data based on the electric energy quality loss comparison result and the dial plate loss comparison result; sorting each error distribution track data in the error monitoring data set corresponding to the second target electric energy meter operation data according to the track fitting coefficient, determining the error distribution track data sorted to be the optimal error distribution track data, and determining the error distribution track data sorted to be the suboptimal error distribution track data; and determining the suboptimal error distribution trajectory data as the dial plate loss record of the last moment corresponding to the second target electric energy meter operation data.

4. The method of claim 3, wherein obtaining a dial-loss comparison of the mechanical loss data corresponding to the power meter operating data by comparing the mechanical loss data corresponding to the power meter operating data with the mechanical loss data corresponding to the second target power meter operating data comprises:

determining loss time sequence weights of mechanical loss data corresponding to the electric energy meter operation data and loss time sequence weights of mechanical loss data corresponding to other electric energy meter operation data;

determining the loss time sequence weight difference between the mechanical loss data corresponding to the electric energy meter operation data and the mechanical loss data corresponding to other electric energy meter operation data according to the loss time sequence weight of the mechanical loss data corresponding to the electric energy meter operation data and the loss time sequence weight of the mechanical loss data corresponding to other electric energy meter operation data;

determining a loss time sequence weight index of the electric energy meter operation data based on the loss time sequence weight difference;

performing error analysis by using the mechanical loss data corresponding to the electric energy meter operation data to obtain an electric energy consumption error data set at the current moment corresponding to the electric energy meter operation data;

when the power quality analysis is carried out on the basis of the electric energy meter operation data, the current-time power consumption error data set corresponding to the electric energy meter operation data and second target electric energy meter operation data, the power distribution network server monitors operation stability information of the electric energy meter operation data fed back by early warning;

and determining a dial plate loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data based on the loss time sequence weight index of the electric energy meter operation data and the operation stability information.

5. The method of claim 3, wherein obtaining a dial-loss comparison of the mechanical loss data corresponding to the power meter operating data by comparing the mechanical loss data corresponding to the power meter operating data with the mechanical loss data corresponding to the second target power meter operating data comprises:

performing error analysis by using mechanical loss data corresponding to the electric energy meter operation data to obtain an electricity consumption loss error data set of the electric energy meter operation data at the current moment;

performing error analysis by using mechanical loss data corresponding to the second target electric energy meter operation data to obtain a power consumption loss error data set of the second target electric energy meter operation data at the current moment;

determining a loss factor of the power consumption error data of the electric energy meter operation data fed back by the power distribution network server monitoring early warning when the electric energy meter operation data adopts the power consumption error data set of the electric energy meter operation data at the current moment and the power consumption error data set of a second target electric energy meter operation data at the current moment to perform power quality analysis;

and determining a dial plate loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data based on the loss factor of the power consumption loss error data of the electric energy meter operation data fed back by the power distribution network server monitoring and early warning.

6. The method of claim 1, wherein performing error analysis using the current-time monitoring data corresponding to the power meter operating data to obtain power consumption error data of each power load node data in the power meter operating data comprises:

determining list description information of a monitoring data change list in current monitoring data corresponding to the electric energy meter operation data and time sequence characteristics of each electric load node data in the electric energy meter operation data;

determining whether an equipment loss list unit and a power transmission loss list unit exist in the monitoring data change list or not based on a list description weighted value corresponding to the list description information, and determining the feature correlation between the time sequence feature of each piece of power load node data under the power transmission loss list unit of the monitoring data change list and the time sequence feature of each piece of power load node data under the equipment loss list unit of the monitoring data change list according to the time sequence feature and the feature identification degree of the power load node data under the equipment loss list unit of the monitoring data change list on the premise that the equipment loss list unit and the power transmission loss list unit exist in the monitoring data change list;

transferring the time sequence characteristics of the electric load node data related to the time sequence characteristics of the electric load node data under the equipment loss list unit under the power transmission loss list unit of the monitoring data change list to the corresponding equipment loss list unit through the characteristic correlation degree; if the current power transmission loss list unit of the monitoring data change list contains time sequence characteristics of a plurality of pieces of power load node data, determining the characteristic correlation degree between the time sequence characteristics of the power load node data under the current power transmission loss list unit of the monitoring data change list based on the time sequence characteristics and the characteristic identification degree of the power load node data under the equipment loss list unit of the monitoring data change list, and screening the time sequence characteristics of the power load node data under the current power transmission loss list unit according to the characteristic correlation degree between the time sequence characteristics of the power load node data; setting a characteristic priority for the time sequence characteristics of each type of electric load node data obtained by screening according to the time sequence characteristics and the characteristic identification degree of the electric load node data under the equipment loss list unit of the monitoring data change list, and transferring the time sequence characteristics of each type of electric load node data to the equipment loss list unit corresponding to the characteristic priority; and calculating power consumption error data of each piece of power consumption load node data according to the power consumption load node data in the equipment loss list unit and the power consumption load node data in the power transmission loss list unit.

7. The method of claim 1, wherein performing error fitting on the current-time monitoring data corresponding to the electric energy meter operation data based on the electric energy consumption error data of each electric load node data in the N sets of electric energy meter operation data to obtain current error fitting data corresponding to the electric energy meter operation data comprises:

determining current power consumption error data; extracting error characteristic data from the current power consumption loss error data;

judging whether the loss percentage in the current power consumption loss error data is changed relative to the loss percentage in the last power consumption loss error data of the current power consumption loss error data;

if so, determining error characteristic data extracted from the current power consumption loss error data as effective error characteristic data of the current power consumption loss error data;

otherwise, carrying out fusion correction on error feature data extracted from the current power consumption error data and effective error feature data of a corresponding position in the last power consumption error data, and determining a fusion correction result as the effective error feature data of the current power consumption error data;

and performing error fitting on the current-time monitoring data according to the effective error characteristic data to obtain current error fitting data.

8. The method of claim 7, wherein adding the current error fit data corresponding to the power meter operating data to the error monitoring data set corresponding to the power meter operating data comprises:

converting the current error fitting data according to a data format corresponding to the error monitoring data set to obtain target fitting data;

adding the target fitting data to the error monitoring data set.

9. The method according to claim 1, wherein the setting condition is:

the error change curve corresponding to the error detection data set converges in a target time interval; and determining the target time period according to the accumulated service life of the electric energy meter corresponding to the electric energy meter operation data.

10. An electric energy meter operation error monitoring data fitting system based on artificial intelligence is characterized by comprising an artificial intelligence server and an electric energy meter to be monitored, wherein the artificial intelligence server and the electric energy meter are communicated with each other; wherein the artificial intelligence server is configured to:

acquiring N groups of electric energy meter operation data of the electric energy meter to be monitored and an error monitoring data set corresponding to each group of electric energy meter operation data, wherein each group of electric energy meter operation data comprises M different electric load node data, and N and M are positive integers greater than or equal to 1;

determining current moment monitoring data corresponding to the electric energy meter operation data in an error monitoring data set corresponding to the electric energy meter operation data;

performing error analysis by using current moment monitoring data corresponding to the electric energy meter operation data to obtain power consumption error data of each power consumption load node data in the electric energy meter operation data;

performing error fitting on current time monitoring data corresponding to the electric energy meter operation data based on the power consumption error data of each power load node data in N groups of electric energy meter operation data to obtain current error fitting data corresponding to the electric energy meter operation data;

adding current error fitting data corresponding to the electric energy meter operation data into an error monitoring data set corresponding to the electric energy meter operation data;

and returning and executing the step to determine the current moment monitoring data corresponding to the electric energy meter operation data in the error monitoring data set corresponding to the electric energy meter operation data until the error monitoring data set meets the set conditions, and obtaining the operation error identification result of the electric energy meter to be monitored corresponding to the electric energy meter operation data.

Technical Field

The application relates to the technical field of artificial intelligence, in particular to an electric energy meter operation error monitoring data fitting method and system based on artificial intelligence.

Background

An electric energy meter (electricity energy meter) is a meter for measuring electric energy, and the electric energy meter may also be called a watt-hour meter, a fire meter or a kilowatt-hour meter. The electric energy meter is capable of measuring an electrical quantity. At present, through the rapid development of the intelligent electric meters, the power grid industry can analyze the power consumption behaviors of users such as power consumption and power consumption time intervals based on the intelligent electric meters, so that flexible and effective power transmission and distribution scheduling is realized, and the safe and normal operation of the whole power grid is ensured.

However, the electric energy meter may have an operation error during the operation process, thereby affecting the normal metering accuracy. Therefore, how to correct the operation error of the electric energy meter is a technical problem which needs to be solved at present.

Disclosure of Invention

In view of this, the present application provides an electric energy meter operation error monitoring data fitting method and system based on artificial intelligence.

In a first aspect, a method for fitting operation error monitoring data of an electric energy meter based on artificial intelligence is provided, which includes:

acquiring N groups of electric energy meter operation data and an error monitoring data set corresponding to each group of electric energy meter operation data, wherein each group of electric energy meter operation data comprises M different electric load node data, and N and M are positive integers greater than or equal to 1;

determining current moment monitoring data corresponding to the electric energy meter operation data in an error monitoring data set corresponding to the electric energy meter operation data;

performing error analysis by using current moment monitoring data corresponding to the electric energy meter operation data to obtain power consumption error data of each power consumption load node data in the electric energy meter operation data;

performing error fitting on current time monitoring data corresponding to the electric energy meter operation data based on the power consumption error data of each power load node data in N groups of electric energy meter operation data to obtain current error fitting data corresponding to the electric energy meter operation data;

adding current error fitting data corresponding to the electric energy meter operation data into an error monitoring data set corresponding to the electric energy meter operation data;

and returning and executing the step to determine the current moment monitoring data corresponding to the electric energy meter operation data in the error monitoring data set corresponding to the electric energy meter operation data until the error monitoring data set meets the set conditions, and obtaining the operation error identification result of the electric energy meter to be monitored corresponding to the electric energy meter operation data.

Optionally, the electric energy meter operation data includes first target electric energy meter operation data and second target electric energy meter operation data other than the first target electric energy meter operation data, and after obtaining an operation error identification result of the electric energy meter to be monitored corresponding to the electric energy meter operation data, the method further includes: when power quality analysis between first target power meter operation data and second target power meter operation data is carried out in the peak period of power utilization, determining an operation error identification result of a target power meter to be monitored corresponding to the first target power meter operation data in operation error identification results of power meters to be monitored corresponding to the N groups of power meter operation data; determining dynamic power consumption loss error data of each power consumption load node data in the first target electric energy meter operation data by adopting the operation error identification result of the target electric energy meter to be monitored; and performing power quality analysis based on the power consumption load node data in the first target electric energy meter operation data, the dynamic power consumption loss error data and the power consumption load node data of the second target electric energy meter operation data in the power consumption peak period.

Optionally, the determining, in the error monitoring data set corresponding to the electric energy meter operation data, current time monitoring data corresponding to the electric energy meter operation data includes: determining an error monitoring data set and mechanical loss data at the last moment corresponding to the electric energy meter operation data, and mechanical loss data corresponding to a second target electric energy meter operation data; comparing mechanical loss data corresponding to the electric energy meter operation data with mechanical loss data corresponding to second target electric energy meter operation data to obtain a dial plate loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data, wherein the second target electric energy meter operation data is all electric energy meter operation data including the electric energy meter operation data in N groups of electric energy meter operation data; comparing mechanical loss data corresponding to the electric energy meter operation data with an error monitoring data set at the last moment corresponding to the electric energy meter operation data to obtain an electric energy quality loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data; determining an error monitoring data set at the last moment corresponding to the running data of the electric energy meter or mechanical loss data corresponding to the running data of the electric energy meter as the monitoring data at the current moment corresponding to the running data of the electric energy meter based on the comparison result of the quality loss of the electric energy and the comparison result of the loss of the dial plate;

the determining of the mechanical loss data corresponding to the second target electric energy meter operation data includes: acquiring voltage and current fluctuation data corresponding to the second target electric energy meter operation data, and determining dial plate loss record at the last moment corresponding to the second target electric energy meter operation data; according to voltage and current fluctuation data corresponding to the second target electric energy meter operation data, determining mechanical loss data corresponding to the second target electric energy meter operation data in dial loss records at the last moment corresponding to the second target electric energy meter operation data;

wherein, the determining the dial plate loss record of the last moment corresponding to the second target electric energy meter operation data includes: determining a power quality loss comparison result and a dial plate loss comparison result of each error monitoring data set in the error monitoring data set corresponding to the second target electric energy meter operation data; calculating a track fitting coefficient of each error distribution track data in an error monitoring data set corresponding to the second target electric energy meter operation data based on the electric energy quality loss comparison result and the dial plate loss comparison result; sorting each error distribution track data in the error monitoring data set corresponding to the second target electric energy meter operation data according to the track fitting coefficient, determining the error distribution track data sorted to be the optimal error distribution track data, and determining the error distribution track data sorted to be the suboptimal error distribution track data; and determining the suboptimal error distribution trajectory data as the dial plate loss record of the last moment corresponding to the second target electric energy meter operation data.

Optionally, the obtaining of the dial plate loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data by comparing the mechanical loss data corresponding to the electric energy meter operation data with the mechanical loss data corresponding to the second target electric energy meter operation data includes: determining loss time sequence weights of mechanical loss data corresponding to the electric energy meter operation data and loss time sequence weights of mechanical loss data corresponding to other electric energy meter operation data; determining the loss time sequence weight difference between the mechanical loss data corresponding to the electric energy meter operation data and the mechanical loss data corresponding to other electric energy meter operation data according to the loss time sequence weight of the mechanical loss data corresponding to the electric energy meter operation data and the loss time sequence weight of the mechanical loss data corresponding to other electric energy meter operation data; determining a loss time sequence weight index of the electric energy meter operation data based on the loss time sequence weight difference; performing error analysis by using the mechanical loss data corresponding to the electric energy meter operation data to obtain an electric energy consumption error data set at the current moment corresponding to the electric energy meter operation data; when the power quality analysis is carried out on the basis of the electric energy meter operation data, the current-time power consumption error data set corresponding to the electric energy meter operation data and second target electric energy meter operation data, the power distribution network server monitors operation stability information of the electric energy meter operation data fed back by early warning; and determining a dial plate loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data based on the loss time sequence weight index of the electric energy meter operation data and the operation stability information.

Optionally, the obtaining of the dial plate loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data by comparing the mechanical loss data corresponding to the electric energy meter operation data with the mechanical loss data corresponding to the second target electric energy meter operation data includes: performing error analysis by using mechanical loss data corresponding to the electric energy meter operation data to obtain an electricity consumption loss error data set of the electric energy meter operation data at the current moment; performing error analysis by using mechanical loss data corresponding to the second target electric energy meter operation data to obtain a power consumption loss error data set of the second target electric energy meter operation data at the current moment; determining a loss factor of the power consumption error data of the electric energy meter operation data fed back by the power distribution network server monitoring early warning when the electric energy meter operation data adopts the power consumption error data set of the electric energy meter operation data at the current moment and the power consumption error data set of a second target electric energy meter operation data at the current moment to perform power quality analysis; and determining a dial plate loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data based on the loss factor of the power consumption loss error data of the electric energy meter operation data fed back by the power distribution network server monitoring and early warning.

Optionally, performing error analysis on the current-time monitoring data corresponding to the electric energy meter operating data to obtain power consumption error data of each power consumption load node data in the electric energy meter operating data, where the error data includes:

determining list description information of a monitoring data change list in current monitoring data corresponding to the electric energy meter operation data and time sequence characteristics of each electric load node data in the electric energy meter operation data;

determining whether an equipment loss list unit and a power transmission loss list unit exist in the monitoring data change list or not based on a list description weighted value corresponding to the list description information, and determining the feature correlation between the time sequence feature of each piece of power load node data under the power transmission loss list unit of the monitoring data change list and the time sequence feature of each piece of power load node data under the equipment loss list unit of the monitoring data change list according to the time sequence feature and the feature identification degree of the power load node data under the equipment loss list unit of the monitoring data change list on the premise that the equipment loss list unit and the power transmission loss list unit exist in the monitoring data change list;

transferring the time sequence characteristics of the electric load node data related to the time sequence characteristics of the electric load node data under the equipment loss list unit under the power transmission loss list unit of the monitoring data change list to the corresponding equipment loss list unit through the characteristic correlation degree; if the current power transmission loss list unit of the monitoring data change list contains time sequence characteristics of a plurality of pieces of power load node data, determining the characteristic correlation degree between the time sequence characteristics of the power load node data under the current power transmission loss list unit of the monitoring data change list based on the time sequence characteristics and the characteristic identification degree of the power load node data under the equipment loss list unit of the monitoring data change list, and screening the time sequence characteristics of the power load node data under the current power transmission loss list unit according to the characteristic correlation degree between the time sequence characteristics of the power load node data; setting a characteristic priority for the time sequence characteristics of each type of electric load node data obtained by screening according to the time sequence characteristics and the characteristic identification degree of the electric load node data under the equipment loss list unit of the monitoring data change list, and transferring the time sequence characteristics of each type of electric load node data to the equipment loss list unit corresponding to the characteristic priority; and calculating power consumption error data of each piece of power consumption load node data according to the power consumption load node data in the equipment loss list unit and the power consumption load node data in the power transmission loss list unit.

Optionally, based on power consumption error data of each power consumption load node data in N sets of electric energy meter operation data, performing error fitting on current time monitoring data corresponding to the electric energy meter operation data to obtain current error fitting data corresponding to the electric energy meter operation data, including:

determining current power consumption error data; extracting error characteristic data from the current power consumption loss error data;

judging whether the loss percentage in the current power consumption loss error data is changed relative to the loss percentage in the last power consumption loss error data of the current power consumption loss error data;

if so, determining error characteristic data extracted from the current power consumption loss error data as effective error characteristic data of the current power consumption loss error data;

otherwise, carrying out fusion correction on error feature data extracted from the current power consumption error data and effective error feature data of a corresponding position in the last power consumption error data, and determining a fusion correction result as the effective error feature data of the current power consumption error data;

and performing error fitting on the current-time monitoring data according to the effective error characteristic data to obtain current error fitting data.

Optionally, adding the current error fitting data corresponding to the electric energy meter operation data to the error monitoring data set corresponding to the electric energy meter operation data includes:

converting the current error fitting data according to a data format corresponding to the error monitoring data set to obtain target fitting data;

adding the target fitting data to the error monitoring data set.

Optionally, the setting conditions are:

the error change curve corresponding to the error detection data set converges in a target time interval; and determining the target time period according to the accumulated service life of the electric energy meter corresponding to the electric energy meter operation data.

In a second aspect, an electric energy meter operation error monitoring data fitting system based on artificial intelligence is provided, which comprises an artificial intelligence server and an electric energy meter to be monitored, wherein the artificial intelligence server and the electric energy meter are communicated with each other; wherein the artificial intelligence server is configured to:

acquiring N groups of electric energy meter operation data of the electric energy meter to be monitored and an error monitoring data set corresponding to each group of electric energy meter operation data, wherein each group of electric energy meter operation data comprises M different electric load node data, and N and M are positive integers greater than or equal to 1;

determining current moment monitoring data corresponding to the electric energy meter operation data in an error monitoring data set corresponding to the electric energy meter operation data;

performing error analysis by using current moment monitoring data corresponding to the electric energy meter operation data to obtain power consumption error data of each power consumption load node data in the electric energy meter operation data;

performing error fitting on current time monitoring data corresponding to the electric energy meter operation data based on the power consumption error data of each power load node data in N groups of electric energy meter operation data to obtain current error fitting data corresponding to the electric energy meter operation data;

adding current error fitting data corresponding to the electric energy meter operation data into an error monitoring data set corresponding to the electric energy meter operation data;

and returning and executing the step to determine the current moment monitoring data corresponding to the electric energy meter operation data in the error monitoring data set corresponding to the electric energy meter operation data until the error monitoring data set meets the set conditions, and obtaining the operation error identification result of the electric energy meter to be monitored corresponding to the electric energy meter operation data. .

The electric energy meter operation error monitoring data fitting method and system based on artificial intelligence provided by the embodiment of the application firstly obtain electric energy meter operation data and an error monitoring data set corresponding to the electric energy meter operation data, secondly determine current moment monitoring data to carry out error analysis to obtain power consumption loss error data of power consumption load node data, and then carry out error fitting on the current moment monitoring data corresponding to the electric energy meter operation data based on the power consumption loss error data to obtain current error fitting data and add the current error fitting data into the corresponding error monitoring data set. And then obtaining an operation error identification result of the electric energy meter to be monitored when the error monitoring data set meets the set condition. Therefore, the running error identification results of the globality and the continuity of the electric energy meter to be monitored can be obtained by analyzing, fitting and iterating the running errors of the different electric energy meter running data of the electric energy meter to be monitored, and the running error identification results can represent the actual running condition of the electric energy meter to be monitored, so that accurate and reliable correction basis is provided for realizing the error correction of the electric energy meter to be monitored.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.

FIG. 1 is a flow chart illustrating a method for fitting operational error monitoring data of an artificial intelligence based electric energy meter according to an exemplary embodiment of the present application.

Fig. 2 is a communication architecture diagram of an artificial intelligence based electric energy meter operation error monitoring data fitting system according to an exemplary embodiment of the present application.

FIG. 3 is a diagram illustrating a hardware configuration of an artificial intelligence server according to an exemplary embodiment of the present application.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of systems and methods consistent with certain aspects of the present application, as detailed in the appended claims.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.

In order to correct the operation error of the electric energy meter, the embodiment of the invention provides an electric energy meter operation error monitoring data fitting method and system based on artificial intelligence.

To achieve the above object, referring to fig. 1, a flow chart of a method for fitting operation error monitoring data of an artificial intelligence-based electric energy meter is shown, wherein the method may include the following steps S11-S16.

And step S11, acquiring N groups of electric energy meter operation data and an error monitoring data set corresponding to each group of electric energy meter operation data.

For example, each set of electric energy meter operation data includes M different electric load node data, N and M are positive integers greater than or equal to 1, the electric load node data is used for representing electric load data of electric equipment in different electric power utilization states or in different electric power utilization periods, and the error monitoring data set is used for representing a metering error state of the electric energy meter to be monitored corresponding to the electric energy meter operation data.

Step S12, determining current time monitoring data corresponding to the electric energy meter operation data in the error monitoring data set corresponding to the electric energy meter operation data.

For example, the current time monitoring data is used for representing the operation state monitoring data corresponding to the electric energy meter operation data.

And step S13, performing error analysis by using the current-time monitoring data corresponding to the electric energy meter operation data to obtain the power consumption error data of each power consumption load node data in the electric energy meter operation data.

For example, the power consumption error data corresponds to an error in the operation data of the electric energy meter due to the power consumption.

And step S14, performing error fitting on the current-time monitoring data corresponding to the electric energy meter operation data based on the power consumption error data of each power consumption load node data in the N groups of electric energy meter operation data to obtain current error fitting data corresponding to the electric energy meter operation data.

For example, the current error fit data is continuously varying data.

And step S15, adding the current error fitting data corresponding to the electric energy meter operation data into the error monitoring data set corresponding to the electric energy meter operation data.

And step S16, returning to and executing the step, determining the current moment monitoring data corresponding to the electric energy meter operation data in the error monitoring data set corresponding to the electric energy meter operation data until the error monitoring data set meets the set conditions, and obtaining the operation error identification result of the electric energy meter to be monitored corresponding to the electric energy meter operation data.

For example, the operation error identification result is used for representing a continuous and complete metering error state of the electric energy meter to be monitored, and the metering error of the electric energy meter to be monitored can be accurately and reliably corrected through the operation error identification result, so that the normal operation of the electric energy meter to be monitored is ensured.

It can be understood that, by executing the above steps S11-S16, firstly, the operation data of the electric energy meter and the corresponding error monitoring data set thereof are obtained, secondly, the current time monitoring data are determined to perform error analysis to obtain the power consumption error data of the power consumption load node data, and then, the current time monitoring data corresponding to the operation data of the electric energy meter are subjected to error fitting based on the power consumption error data to obtain current error fitting data, and the current error fitting data are added to the corresponding error monitoring data set. And then obtaining an operation error identification result of the electric energy meter to be monitored when the error monitoring data set meets the set condition.

Therefore, the running error identification results of the globality and the continuity of the electric energy meter to be monitored can be obtained by analyzing, fitting and iterating the running errors of the different electric energy meter running data of the electric energy meter to be monitored, and the running error identification results can represent the actual running condition of the electric energy meter to be monitored, so that accurate and reliable correction basis is provided for realizing the error correction of the electric energy meter to be monitored.

In an alternative embodiment, the electric energy meter operation data includes a first target electric energy meter operation data and a second target electric energy meter operation data other than the first target electric energy meter operation data. Further, after obtaining the operation error identification result of the electric energy meter to be monitored corresponding to the electric energy meter operation data as described in the step S16, the following steps S17 to S19 may be included.

Step S17, when power quality analysis between first target power meter operation data and second target power meter operation data is carried out in the peak period of power utilization, determining the operation error identification result of the target power meter to be monitored corresponding to the first target power meter operation data in the operation error identification results of the power meters to be monitored corresponding to the N groups of power meter operation data.

And step S18, determining dynamic electricity consumption loss error data of each electricity consumption load node data in the first target electric energy meter operation data by using the operation error identification result of the target to-be-monitored electric energy meter.

Step S19, performing power quality analysis based on the power consumption load node data in the first target power meter operation data, the dynamic power consumption loss error data, and the power consumption load node data of the second target power meter operation data in the power consumption peak period.

Through the contents described in the steps S17 to S19, the power quality analysis can be performed on the power load node data, so that the reason of the running error of the electric energy meter to be monitored can be further analyzed, the error of the electric energy meter to be monitored can be comprehensively analyzed, and the metering error of the electric energy meter to be monitored can be further improved.

In some examples, the determining of the current-time monitoring data corresponding to the electric energy meter operation data in the error monitoring data set corresponding to the electric energy meter operation data, which is described in step S12, may include the following steps S121 to S124.

Step S121, determining an error monitoring data set at the last moment corresponding to the electric energy meter operation data, mechanical loss data and mechanical loss data corresponding to the second target electric energy meter operation data.

Step S122, comparing the mechanical loss data corresponding to the electric energy meter operation data with the mechanical loss data corresponding to second target electric energy meter operation data to obtain a dial plate loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data, wherein the second target electric energy meter operation data is all electric energy meter operation data including the electric energy meter operation data in the N groups of electric energy meter operation data.

Step S123, comparing the mechanical loss data corresponding to the electric energy meter operation data with the last-time error monitoring data set corresponding to the electric energy meter operation data to obtain an electric energy quality loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data.

Step S124, based on the power quality loss comparison result and the dial loss comparison result, determining the last-time error monitoring data set corresponding to the power meter operation data or the mechanical loss data corresponding to the power meter operation data as the current-time monitoring data corresponding to the power meter operation data.

Therefore, by applying the steps S121 to S124, the error monitoring data set and the mechanical loss data of the electric energy meter operation data at the last moment and the mechanical loss data corresponding to the second target electric energy meter operation data can be analyzed and compared, so that the current-moment monitoring data corresponding to the electric energy meter operation data can be completely and accurately determined.

Further, the determining of the mechanical loss data corresponding to the second target electric energy meter operation data in step S121 includes: step S1211, obtaining voltage and current fluctuation data corresponding to the second target electric energy meter operation data, and determining a dial loss record of a previous time corresponding to the second target electric energy meter operation data; step S1212, according to the voltage and current fluctuation data corresponding to the second target electric energy meter operation data, determining mechanical loss data corresponding to the second target electric energy meter operation data in the dial loss record at the previous time corresponding to the second target electric energy meter operation data. In this way, the time series continuity of the mechanical loss data can be ensured.

Further, in step S1211, the determining a dial plate loss record of a previous time corresponding to the second target electric energy meter operation data includes: determining a power quality loss comparison result and a dial plate loss comparison result of each error monitoring data set in the error monitoring data set corresponding to the second target electric energy meter operation data; calculating a track fitting coefficient of each error distribution track data in an error monitoring data set corresponding to the second target electric energy meter operation data based on the electric energy quality loss comparison result and the dial plate loss comparison result; sorting each error distribution track data in the error monitoring data set corresponding to the second target electric energy meter operation data according to the track fitting coefficient, determining the error distribution track data sorted to be the optimal error distribution track data, and determining the error distribution track data sorted to be the suboptimal error distribution track data; and determining the suboptimal error distribution trajectory data as the dial plate loss record of the last moment corresponding to the second target electric energy meter operation data. This ensures continuous and uninterrupted recording of the dial wear.

In some examples, the comparing the mechanical loss data corresponding to the operation data of the electric energy meter with the mechanical loss data corresponding to the operation data of the second target electric energy meter in step S122 to obtain the dial loss comparison result of the mechanical loss data corresponding to the operation data of the electric energy meter may further include the following steps S1221 to S1226.

Step S1221, determining a loss time sequence weight of the mechanical loss data corresponding to the electric energy meter operation data, and a loss time sequence weight of the mechanical loss data corresponding to the other electric energy meter operation data.

Step S1222 determines a loss time sequence weight difference between the mechanical loss data corresponding to the electric energy meter operation data and the mechanical loss data corresponding to the other electric energy meter operation data according to the loss time sequence weight of the mechanical loss data corresponding to the electric energy meter operation data and the loss time sequence weight of the mechanical loss data corresponding to the other electric energy meter operation data.

And step S1223, determining a loss time sequence weight index of the electric energy meter operation data based on the loss time sequence weight difference.

And step S1224, performing error analysis by using the mechanical loss data corresponding to the electric energy meter operation data to obtain an electric energy consumption error data set at the current moment corresponding to the electric energy meter operation data.

Step S1225, when determining that the power quality analysis is performed based on the power consumption error data set of the power meter at the current moment corresponding to the power meter operation data and the second target power meter operation data, the power distribution network server monitors operation stability information of the power meter operation data fed back by the early warning.

And S1226, determining a dial plate loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data based on the loss time sequence weight index of the electric energy meter operation data and the operation stability information.

It can be understood that, by executing the steps S1221 to S1226, the mechanical loss data can be compared in real time and accurately in combination with the power distribution network server, so that the reliability of the dial loss comparison result is improved.

Optionally, the step S122 of comparing the mechanical loss data corresponding to the electric energy meter operation data with the mechanical loss data corresponding to the second target electric energy meter operation data to obtain a dial plate loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data may further include: performing error analysis by using mechanical loss data corresponding to the electric energy meter operation data to obtain an electricity consumption loss error data set of the electric energy meter operation data at the current moment; performing error analysis by using mechanical loss data corresponding to the second target electric energy meter operation data to obtain a power consumption loss error data set of the second target electric energy meter operation data at the current moment; determining a loss factor of the power consumption error data of the electric energy meter operation data fed back by the power distribution network server monitoring early warning when the electric energy meter operation data adopts the power consumption error data set of the electric energy meter operation data at the current moment and the power consumption error data set of a second target electric energy meter operation data at the current moment to perform power quality analysis; and determining a dial plate loss comparison result of the mechanical loss data corresponding to the electric energy meter operation data based on the loss factor of the power consumption loss error data of the electric energy meter operation data fed back by the power distribution network server monitoring and early warning.

In practical applications, the inventor finds that, when determining the power consumption error data of the power load node data, there are often more redundant data in the power consumption error data, and to improve the technical problem, the step S13 may further include the following steps S131 to S133 by performing error analysis on the current-time monitoring data corresponding to the power meter operating data to obtain the power consumption error data of each power load node data in the power meter operating data.

Step S131, determining list description information of a monitoring data change list in the current monitoring data corresponding to the electric energy meter operation data and time sequence characteristics of each electric load node data in the electric energy meter operation data.

Step S132, based on the list description weighted value corresponding to the list description information, determines whether an equipment loss list unit and a transmission loss list unit exist in the monitoring data change list, and determines, according to the time sequence characteristics and the characteristic identification degrees of the electrical load node data in the equipment loss list unit of the monitoring data change list, a characteristic correlation between the time sequence characteristics of each electrical load node data in the transmission loss list unit of the monitoring data change list and the time sequence characteristics of each electrical load node data in the equipment loss list unit of the monitoring data change list on the premise that the equipment loss list unit and the transmission loss list unit exist in the monitoring data change list.

Step S133, transferring the time series characteristics of the electrical load node data related to the time series characteristics of the electrical load node data in the equipment loss list unit in the transmission loss list unit of the monitoring data change list to the corresponding equipment loss list unit according to the characteristic correlation degree; if the current power transmission loss list unit of the monitoring data change list contains time sequence characteristics of a plurality of pieces of power load node data, determining the characteristic correlation degree between the time sequence characteristics of the power load node data under the current power transmission loss list unit of the monitoring data change list based on the time sequence characteristics and the characteristic identification degree of the power load node data under the equipment loss list unit of the monitoring data change list, and screening the time sequence characteristics of the power load node data under the current power transmission loss list unit according to the characteristic correlation degree between the time sequence characteristics of the power load node data; setting a characteristic priority for the time sequence characteristics of each type of electric load node data obtained by screening according to the time sequence characteristics and the characteristic identification degree of the electric load node data under the equipment loss list unit of the monitoring data change list, and transferring the time sequence characteristics of each type of electric load node data to the equipment loss list unit corresponding to the characteristic priority; and calculating power consumption error data of each piece of power consumption load node data according to the power consumption load node data in the equipment loss list unit and the power consumption load node data in the power transmission loss list unit.

By implementing the content described in the above steps S131 to S133, correlation analysis can be performed on the power consumption load node data under the device loss list unit and the power transmission loss list unit of the monitoring data change list, and local adjustment of the power consumption load node data is implemented to update the device loss list unit and the power transmission loss list unit, so that redundant data can be effectively filtered out, and therefore, it is ensured that no redundant data exists in the calculated power consumption error data, and simplification of the power consumption error data is implemented.

In some examples, the step S14 may further include performing error fitting on the current time monitoring data corresponding to the power meter operation data based on the power consumption error data of each power load node data in the N sets of power meter operation data to obtain current error fitting data corresponding to the power meter operation data, which is described in the following steps S141 to S145.

Step S141, determining current power consumption error data; and extracting error characteristic data from the current power consumption loss error data.

Step S142, determining whether the loss percentage in the current power consumption loss error data is changed relative to the loss percentage in the last power consumption loss error data of the current power consumption loss error data.

Step S143, if yes, determining the error feature data extracted from the current power consumption loss error data as effective error feature data of the current power consumption loss error data.

And step S144, otherwise, carrying out fusion correction on the error feature data extracted from the current power consumption loss error data and the effective error feature data of the corresponding position in the last power consumption loss error data, and determining the fusion correction result as the effective error feature data of the current power consumption loss error data.

And S145, performing error fitting on the current-time monitoring data according to the effective error characteristic data to obtain current error fitting data.

Therefore, refined fitting of the monitoring data at the current moment can be achieved, excessive mutation nodes of the current error fitting data are avoided, and smoothness of the current error fitting data is guaranteed.

Further, the step S15 of adding the current error fitting data corresponding to the electric energy meter operation data into the error monitoring data set corresponding to the electric energy meter operation data includes: converting the current error fitting data according to a data format corresponding to the error monitoring data set to obtain target fitting data; adding the target fitting data to the error monitoring data set. This ensures data structure consistency of the data in the error-monitoring data set.

In an alternative embodiment, the setting conditions are: the error change curve corresponding to the error detection data set converges in a target time interval; and determining the target time period according to the accumulated use duration of the electric energy meter to be monitored corresponding to the electric energy meter operation data.

Based on the same inventive concept, there is also provided an artificial intelligence based electric energy meter operation error monitoring data fitting system 100 as shown in fig. 2, which comprises an artificial intelligence server 200 and an electric energy meter 300 to be monitored, which are communicated with each other; wherein the artificial intelligence server 200 is configured to:

acquiring N groups of electric energy meter operation data of the electric energy meter to be monitored and an error monitoring data set corresponding to each group of electric energy meter operation data, wherein each group of electric energy meter operation data comprises M different electric load node data, and N and M are positive integers greater than or equal to 1;

determining current moment monitoring data corresponding to the electric energy meter operation data in an error monitoring data set corresponding to the electric energy meter operation data;

performing error analysis by using current moment monitoring data corresponding to the electric energy meter operation data to obtain power consumption error data of each power consumption load node data in the electric energy meter operation data;

performing error fitting on current time monitoring data corresponding to the electric energy meter operation data based on the power consumption error data of each power load node data in N groups of electric energy meter operation data to obtain current error fitting data corresponding to the electric energy meter operation data;

adding current error fitting data corresponding to the electric energy meter operation data into an error monitoring data set corresponding to the electric energy meter operation data;

and returning and executing the step to determine the current moment monitoring data corresponding to the electric energy meter operation data in the error monitoring data set corresponding to the electric energy meter operation data until the error monitoring data set meets the set conditions, and obtaining the operation error identification result of the electric energy meter to be monitored corresponding to the electric energy meter operation data.

The implementation process of the functions and actions of each module (or device) in the system is specifically described in the implementation process of the corresponding step in the method, and is not described herein again.

For the system embodiment, since it basically corresponds to the method embodiment, reference may be made to the partial description of the method embodiment for relevant points. The above-described system embodiments are merely illustrative, wherein the modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.

On the basis of the above, there is also provided an artificial intelligence server 200 as shown in fig. 3, including: a processor 210, and a memory 220 and a network interface 230 connected to the processor 210; the network interface 230 is connected with a non-volatile memory 240 in the artificial intelligence server; the processor 210 retrieves a computer program from the non-volatile memory 240 via the network interface 230 and runs the computer program via the memory 220 to perform the method shown in fig. 1.

Further, a readable storage medium applied to a computer is provided, the readable storage medium is burned with a computer program, and the computer program realizes the method shown in fig. 1 when running in the memory of the artificial intelligence server.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.