CN114089257A - Electric energy meter burning online monitoring method, system and medium - Google Patents
Electric energy meter burning online monitoring method, system and medium Download PDFInfo
- Publication number
- CN114089257A CN114089257A CN202111258366.5A CN202111258366A CN114089257A CN 114089257 A CN114089257 A CN 114089257A CN 202111258366 A CN202111258366 A CN 202111258366A CN 114089257 A CN114089257 A CN 114089257A
- Authority
- CN
- China
- Prior art keywords
- electric energy
- energy meter
- burning
- characteristic data
- meter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/04—Testing or calibrating of apparatus covered by the other groups of this subclass of instruments for measuring time integral of power or current
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an electric energy meter burning online monitoring method, a system and a medium, and the electric energy meter burning online monitoring method comprises the following steps: 1) acquiring characteristic data of a monitored electric energy meter, wherein the characteristic data comprises electrical characteristic data, product characteristic data and environment characteristic data; 2) and inputting the characteristic data into a pre-trained machine learning model to obtain a probability evaluation result of the future burning of the monitored electric energy meter output by the machine learning model. According to the method, based on the mapping relation among the characteristic data including the electrical characteristic data, the product characteristic data, the environmental characteristic data and the probability evaluation result of the occurrence of meter burning, the probability of the occurrence of meter burning of the electric energy meter in the future can be monitored on line through the historical data of the electric energy meter, the problem that the appearance of the electric energy meter burning is difficult to monitor is solved, passive first-aid repair can be changed into active first-aid repair, the electricity utilization experience of customers is improved, the working efficiency of basic-level power supply service staff is improved, and the problem that the meter burning first-aid repair is not timely is solved.
Description
Technical Field
The invention relates to an electric energy meter online monitoring technology, in particular to an electric energy meter burning online monitoring method, a system and a medium, which can be used for online monitoring the probability of the electric energy meter burning in the future through historical data of the electric energy meter.
Background
The electric energy meter is an important electric power device for carrying out electric power transaction and settlement. The electric energy meter is generally installed behind user service entrance switch, before the consumer, therefore in case the electric energy meter breaks down, can lead to the user to have a power failure, then influences user's power consumption and experiences, then brings economy and loss of property for the user seriously. The burning meter is a common fault of the electric energy meter. The fault causes may be various, common causes include that a wiring terminal is not screwed down, contact is poor, load is too large, and the like, and because of lack of an online monitoring means, a power supply company generally processes the operation of burning the meter, such as field investigation and meter changing after receiving a contact call of a user, the processing period is long, the power consumption experience of the user is seriously affected, and meanwhile, a lot of temporary work is brought to power supply staff at a basic level.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: the invention can monitor the probability of the electric energy meter burning condition in the future on line through the historical data of the electric energy meter, solves the problem that the electric energy meter burning condition is difficult to monitor, can change passive rush repair into active rush repair, improves the electricity consumption experience of customers, improves the working efficiency of basic-level power supply service staff, and solves the problem that the burning condition is untimely.
In order to solve the technical problems, the invention adopts the technical scheme that:
an electric energy meter burning online monitoring method comprises the following steps:
1) acquiring characteristic data of a monitored electric energy meter, wherein the characteristic data comprises electrical characteristic data, product characteristic data and environment characteristic data;
2) and inputting the characteristic data into a pre-trained machine learning model to obtain a probability evaluation result of the future burning of the monitored electric energy meter output by the machine learning model.
Optionally, the electrical characteristic data includes part or all of the daily electricity consumption Q, the daily maximum voltage U, the daily maximum current I and the meter running number a of the monitored electric energy meter.
Optionally, the product characteristic data includes part or all of the manufacturer B of the monitored electric energy meter, the state C, the running time D, the year of installation E, the burning quantity F of the local area in the last two years, and the line loss G of the local area.
Optionally, the environmental characteristic data includes part or all of the ambient temperature T and the ambient humidity H of the monitored electric energy meter.
Optionally, the daily electricity consumption Q, the daily maximum voltage U, the daily maximum current I, the number F of burning meters in the station area in the last two years, the line loss G of the station area, the ambient temperature T, and the ambient humidity H are original values based on a set unit, and the running number a and the running time D of the meter are normalized by the following formula:
x′＝log10(x)
in the above formula, x' is the result obtained by the normalization process, and x is the input before the normalization process; the manufacturer B, the state C and the year E are obtained by adopting One-hot coding processing.
Optionally, the machine learning model is an XGBoost-based machine learning model.
Optionally, step 1) is preceded by the step of training the machine learning model:
s1) acquiring characteristic data of the electric energy meter sample in a period of time before burning out, attaching a label for judging whether the electric energy meter sample is burnt or not to form a sample data set, and dividing the sample data set into a training set and a test set;
s2) training the XGboost-based machine learning model based on the training set;
s3) testing the XGboost-based machine learning model which completes the training of the current round based on a test set, and calculating the evaluation index of the test result by adopting a comprehensive evaluation index consisting of accuracy and recall rate as an evaluation index;
s4) judging whether the evaluation index of the test result meets the requirement, if so, taking the parameters of the current machine learning model based on the XGboost as the machine learning model based on the XGboost obtained by training, ending and exiting; otherwise, skipping to execute step S2) to continue training the XGBoost-based machine learning model.
Optionally, the functional expression of the comprehensive evaluation index composed of the accuracy and the recall in step S3) is:
in the above formula, F1 is a comprehensive evaluation index consisting of accuracy and recall, P is accuracy, and R is recall.
In addition, the invention also provides an electric energy meter burning online monitoring system which comprises a microprocessor and a memory which are connected with each other, wherein the microprocessor is programmed or configured to execute the steps of the electric energy meter burning online monitoring method.
In addition, the invention also provides a computer readable storage medium, wherein a computer program programmed or configured to execute the electric energy meter burning online monitoring method is stored in the computer readable storage medium.
Compared with the prior art, the invention has the following advantages:
1. according to the method, the electric data of the electric energy meter is utilized, the product characteristic data and the environment characteristic data are combined, the model for monitoring the burning of the electric energy meter on line is constructed, the state evaluation is carried out by predicting the future burning probability, the remote on-line evaluation can be carried out under the condition of not depending on manual site survey, and the problem that the burning of the electric energy meter is not timely repaired is solved.
2. The electric energy meter burning condition on-line monitoring method and the electric energy meter burning condition on-line monitoring system have the advantages that the electric data of the electric energy meter are utilized, the product characteristic data and the environment characteristic data are combined, the electric energy meter burning condition on-line monitoring model is constructed, the factors of the electric energy meter in the future and the burning expression condition of the electric energy meter in the future can be comprehensively mapped based on the electric data and the data of the product characteristic data and the environment characteristic data, and the accuracy of the electric energy meter in the future prediction of the burning expression condition can be effectively improved.
3. The invention can change passive first-aid repair into active first-aid repair, improve the electricity consumption experience of customers and improve the working efficiency of basic-level power supply service staff.
Drawings
FIG. 1 is a schematic diagram of the basic principle of the method according to the embodiment of the present invention.
Fig. 2 is a schematic diagram of a training process of a machine learning model according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a confusion matrix (confusion matrix) of actual values (true) and predicted values (predicted) in a test set according to an embodiment of the present invention.
Detailed Description
As shown in fig. 1, the method for monitoring the burning of the electric energy meter on line in the embodiment includes:
1) acquiring characteristic data of a monitored electric energy meter, wherein the characteristic data comprises electrical characteristic data, product characteristic data and environment characteristic data;
2) and inputting the characteristic data into a pre-trained machine learning model to obtain a probability evaluation result of the future burning of the monitored electric energy meter output by the machine learning model.
According to the electric energy meter burning online monitoring method, the electric data of the electric energy meter is utilized, the product characteristic data and the environment characteristic data are combined, a model for monitoring the electric energy meter burning online is built, the state evaluation is carried out by predicting the future meter burning probability, the remote online evaluation can be carried out under the condition of not depending on manual site survey, and the problem that the meter burning repair is not timely is solved. According to the method, the electric data of the electric energy meter are utilized, the product characteristic data and the environment characteristic data are combined, the model for monitoring the burning condition of the electric energy meter on line is constructed, based on the electric data and the data of the product characteristic data and the environment characteristic data, the factors of the electric energy meter under the future burning condition and the comprehensive mapping of the burning condition of the electric energy meter under the future burning condition can be realized, and the accuracy of predicting the burning condition of the electric energy meter under the future burning condition can be effectively improved. This embodiment can become to salvage passively and salvage for initiative, improves customer's power consumption and experiences, promotes basic unit power supply service staff's work efficiency.
In this embodiment, the electrical characteristic data includes a daily power consumption Q, a daily maximum voltage U, a daily maximum current I, and a meter running number a of the monitored electric energy meter. Through research, the causal relationship between each characteristic of the electrical characteristic data and a burning table is shown as follows: the change of the daily electricity consumption Q has certain relevance with the meter burning of the electric energy meter, the load of a meter burning user can be increased in a period of time before the meter burning occurs, and the daily electricity consumption is increased. And the load and daily electricity quantity change of the users in normal operation are relatively stable. The daily maximum voltage U and the daily maximum current A have certain relevance with the meter burning, and the voltage and the current of a meter burning user tend to increase before the meter burning occurs. The meter running terminal code A represents the accumulated electric energy value measured by the meter, the larger the A is, the longer the running time of the meter is or the load is larger at ordinary times, and the longer the running time is, the more serious the aging of the internal components of the meter is and the meter is more easily burnt out; if the load is large, the meter is in a heating state for a long time and is more easily burnt out.
In this embodiment, the product characteristic data includes a manufacturer B of the monitored electric energy meter, a state C of the monitored electric energy meter, an operation time D (days taken in this embodiment), an installation year E, a meter burning number F of the station area in two years, and a line loss G of the station area. Through research, the causal relationship between each characteristic of the product characteristic data and the burn table is found as follows: the manufacturer B has different technologies, components and parts adopted by each manufacturer, and statistics shows that the difference of the meter burning rate among different manufacturers is large, and meters produced by some manufacturers are easy to burn out. In the state C, the place where the electric energy meter operates is represented, and due to the difference between the technical levels of installation, operation and maintenance personnel and environmental conditions in different states, statistics shows that the electric energy meters in different states have larger difference in meter burning rate, and meters operating in some states are more easily burnt out. And the running time D is longer, which indicates that the internal components of the meter are more seriously aged and are more easily burnt out. In the installation year E, due to the influence of different batches of products of different manufacturers, components of batch products of certain manufacturers in certain years are more easily burnt out; the meter burning quantity F in the platform area in the last two years is larger, and the larger the value of F is, the meter burning is more easily caused by the local climate environment or the technical level of local installation operation and maintenance personnel. The line loss G of the local area shows a certain fluctuation in a short period due to the meter burning of individual users in the local area, and generally shows that the line loss is reduced and even becomes negative line loss.
In this embodiment, the environmental characteristic data includes an environmental temperature T and an environmental humidity H of the monitored electric energy meter. The environmental temperature T and the environmental humidity H represent the environmental conditions of the meter running place, according to the statistical conditions, the meter burning rates of different seasons and different months in the same place are greatly different, and the meter burning rates under certain environmental conditions are higher.
It should be noted that all or part of the electrical characteristic data, the product characteristic data and the environmental characteristic data may be used as needed.
In this embodiment, the daily power consumption Q, the daily maximum voltage U, the daily maximum current I, the number of meters burned in the distribution room in two years, F, the ambient temperature T, and the ambient humidity H are original values based on a setting unit, where the setting unit used by the daily power consumption Q is kWh, the setting unit used by the daily maximum voltage U is volt, the setting unit used by the daily maximum current I is ampere, the setting unit used by the number of meters burned in the distribution room in two years is only, the setting unit used by the ambient temperature T is celsius, and the setting unit used by the ambient humidity H is% RH.
In this embodiment, the meter running final code a and the running time D are the results obtained by the following normalization process:
x′＝log10(x)
in the above formula, x' is a result obtained by the normalization process, and x is an input before the normalization process.
In this example, the manufacturer B, the state C and the year of installation E are results obtained by One-hot encoding. The One-hot encoding method is a process that converts class variables into a form that is readily utilized by machine learning algorithms. Suppose that there are n classes for feature x, x ═ x1,x2,…,xn]A certain set of features x is:
| serial number | Categories |
| 1 | x1 |
| 2 | x2 |
| … | … |
| n | xn |
After One-hot encoding processing is adopted, the set form of the feature x becomes:
as can be seen from the foregoing, in the present embodiment, different normalization processing methods are adopted for different feature data: for the meter running word final code A and the running time D (days), because the numerical span ranges of A and D of different meters are too large, in order to reduce the complexity of the model as much as possible and reduce the computation amount of the model, the log function standardization processing is carried out on the model. For the manufacturer B, the state C and the year E, since the three characteristics are all category variables, a one-hot coding mode is adopted in order to directly apply the three characteristics to the model classifier. For other characteristics, the numerical range of the characteristics is concentrated, and in order to keep the original characteristics of the data as much as possible and reduce the operation amount of data preprocessing, the original values are adopted for operation.
In this embodiment, the machine learning model is an XGBoost-based machine learning model, and in addition, other machine learning models may be adopted as needed.
As shown in fig. 2, step 1) in this embodiment further includes a step of training a machine learning model:
s1) acquiring characteristic data of the electric energy meter sample in a period of time before burning out, attaching a label for judging whether the electric energy meter sample is burnt or not to form a sample data set, and dividing the sample data set into a training set and a test set; for example, in this embodiment, a cross validation function built in a program is used, and 80% of the cross validation function is divided into a training set and 20% of the cross validation function is divided into a validation set.
S2) training the XGboost-based machine learning model based on the training set;
s3) testing the XGboost-based machine learning model which completes the training of the current round based on a test set, and calculating the evaluation index of the test result by adopting a comprehensive evaluation index consisting of accuracy and recall rate as an evaluation index;
s4) judging whether the evaluation index of the test result meets the requirement, if so, taking the parameters of the current machine learning model based on the XGboost as the machine learning model based on the XGboost obtained by training, ending and exiting; otherwise, skipping to execute step S2) to continue training the XGBoost-based machine learning model.
Parameters of the XGBoost-based machine learning model may be divided into three types, a general parameter, an enhanced parameter, and a learning objective parameter. The problem of burning the electric energy meter and monitoring the electric energy meter on line in the embodiment belongs to a classification problem, and a softmax function is selected as a target function of the constructed XGboost model. In this embodiment, the parameters of the XGBoost-based machine learning model include a maximum depth (max _ depth), iteration times (n _ estimators), a contraction step length (eta), a gamma parameter, a lambda regularization coefficient, and a learning rate (learning _ rate) of the XGBoost-based machine learning model, and for the parameters, parameters need to be adjusted in the training process, and other parameters adopt default values.
In this embodiment, the input characteristic variable data set is input into the trained model to obtain the probability of meter burning of the electric energy meter, the probability is greater than 50% and is recorded as meter burning, the label is 1, otherwise, the label is 0 when the electric energy meter is in normal operation. Comparing with the real label data, and adopting the precision rate, the recall rate and the comprehensive evaluation index (F1-Measure) as the evaluation index, in the embodiment, the functional expression of the comprehensive evaluation index formed by the precision rate and the recall rate in the step S3) is as follows:
in the above formula, F1 is a comprehensive evaluation index consisting of accuracy and recall, P is accuracy, and R is recall.
Wherein, the function expression of the precision ratio P (precision) is as follows:
wherein, the function expression of the recall ratio R (Recall) is as follows:
wherein True Positive (TP) indicates the number of positive examples samples marked as positive (1 marked as 1), False Positive (FP) indicates the number of false examples samples marked as positive (0 marked as 1), True Negative (TN) indicates the number of false examples samples marked as false (0 marked as 0), and False Negative (FN) indicates the number of positive examples samples marked as false (1 marked as 0). Fig. 3 is a schematic diagram of a confusion matrix (mixing matrix) of actual values (true) and predicted values (predicted) in a test set according to an embodiment of the present invention, where the number of samples in the test set is 29464, the diagram shows deviations of actual values and predicted values of a burn-in table and an unburnt table in the test set, an upper left corner number of the matrix indicates that the actual meter is unburnt, the number of the predicted meter is 26338, an upper right corner number indicates that the actual meter is unburnt, the number of the predicted meter is 258, a lower left corner number indicates that the actual meter is burned, the number of the predicted meter is 927, a lower right corner number indicates that the actual meter is burned, and the number of the predicted meter is 1941. The corresponding evaluation index P was 88.3%, R67.7%, and F1 was 76.6%. Therefore, the on-line monitoring method for the burning of the electric energy meter can accurately evaluate the probability of the burning of the electric energy meter running on the site. After the XGboost-based machine learning model is trained, the XGboost-based machine learning model is input with the characteristic data of the electric energy meter in operation, so that the probability of meter burning of the electric energy meter in operation can be obtained through the XGboost-based machine learning model, and thus, basic-level workers are guided to initiatively repair and eliminate defects.
In addition, the present embodiment also provides an online monitoring system for a burning meter of an electric energy meter, which includes a microprocessor and a memory connected to each other, wherein the microprocessor is programmed or configured to execute the steps of the online monitoring method for the burning meter of the electric energy meter.
In addition, the present embodiment also provides a computer readable storage medium, in which a computer program programmed or configured to execute the foregoing electric energy meter burning online monitoring method is stored.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may occur to those skilled in the art without departing from the principle of the invention, and are considered to be within the scope of the invention.
Claims (10)
1. An electric energy meter burning online monitoring method is characterized by comprising the following steps:
1) acquiring characteristic data of a monitored electric energy meter, wherein the characteristic data comprises electrical characteristic data, product characteristic data and environment characteristic data;
2) and inputting the characteristic data into a pre-trained machine learning model to obtain a probability evaluation result of the future burning of the monitored electric energy meter output by the machine learning model.
2. The method for monitoring the combustion of the electric energy meter according to claim 1, wherein the electrical characteristic data comprises part or all of daily electricity consumption Q, daily maximum voltage U, daily maximum current I and meter running number A of the monitored electric energy meter.
3. The method for monitoring the burning of the electric energy meter according to claim 2, wherein the product characteristic data comprises part or all of a manufacturer B of the monitored electric energy meter, a state C of the city, a running time D, an installation year E, the burning quantity F of the station in the last two years and the line loss G of the station.
4. The method for monitoring the burning of the electric energy meter according to the claim 3, characterized in that the environmental characteristic data comprises part or all of the environmental temperature T and the environmental humidity H of the monitored electric energy meter.
5. The method for monitoring the electric energy meter burning online according to claim 4, wherein the daily electric energy consumption Q, the daily maximum voltage U, the daily maximum current I, the burning number F of the meter in the station area in the last two years, the line loss G of the station area, the ambient temperature T and the ambient humidity H are original numerical values based on set units, and the meter running number A and the running time D are the results obtained by adopting the following standardized processing:
x′＝log10(x)
in the above formula, x' is the result obtained by the normalization process, and x is the input before the normalization process; the manufacturer B, the state C and the year E are obtained by adopting One-hot coding processing.
6. The electric energy meter burning online monitoring method according to claim 5, wherein the machine learning model is an XGboost-based machine learning model.
7. The method for monitoring the combustion of the electric energy meter on line according to claim 6, characterized in that the step 1) is preceded by a step of training a machine learning model:
s1) acquiring characteristic data of the electric energy meter sample in a period of time before burning out, attaching a label for judging whether the electric energy meter sample is burnt or not to form a sample data set, and dividing the sample data set into a training set and a test set;
s2) training the XGboost-based machine learning model based on the training set;
s3) testing the XGboost-based machine learning model which completes the training of the current round based on a test set, and calculating the evaluation index of the test result by adopting a comprehensive evaluation index consisting of accuracy and recall rate as an evaluation index;
s4) judging whether the evaluation index of the test result meets the requirement, if so, taking the parameters of the current machine learning model based on the XGboost as the machine learning model based on the XGboost obtained by training, ending and exiting; otherwise, skipping to execute step S2) to continue training the XGBoost-based machine learning model.
8. The method for on-line monitoring of the burning of the electric energy meter according to claim 7, wherein the function expression of the comprehensive evaluation index consisting of the accuracy and the recall rate in the step S3) is as follows:
in the above formula, F1 is a comprehensive evaluation index consisting of accuracy and recall, P is accuracy, and R is recall.
9. An on-line monitoring system for burning electric energy meters, which comprises a microprocessor and a memory which are connected with each other, and is characterized in that the microprocessor is programmed or configured to execute the steps of the on-line monitoring method for burning electric energy meters in any one of claims 1-8.
10. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, the computer program being programmed or configured to perform the online monitoring method for electric energy meter burning according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111258366.5A CN114089257B (en) | 2021-10-27 | 2021-10-27 | Electric energy meter burning on-line monitoring method, system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111258366.5A CN114089257B (en) | 2021-10-27 | 2021-10-27 | Electric energy meter burning on-line monitoring method, system and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114089257A true CN114089257A (en) | 2022-02-25 |
| CN114089257B CN114089257B (en) | 2023-08-18 |
Family
ID=80297916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111258366.5A Active CN114089257B (en) | 2021-10-27 | 2021-10-27 | Electric energy meter burning on-line monitoring method, system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114089257B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104880690A (en) * | 2015-06-15 | 2015-09-02 | 国网上海市电力公司 | Method for evaluating operation of electric energy meter |
| CN104991223A (en) * | 2015-07-27 | 2015-10-21 | 国网重庆市电力公司电力科学研究院 | Watt-hour meter state assessment index selection and quantization method |
| CN109492783A (en) * | 2018-11-14 | 2019-03-19 | 中国电力科学研究院有限公司 | A kind of Application of Power Metering Instruments failure risk prediction technique based on GBDT |
| CN109633518A (en) * | 2019-01-29 | 2019-04-16 | 国网湖南省电力有限公司 | A kind of intelligent electric energy meter comprehensive performance evaluation method, apparatus |
| CN109839535A (en) * | 2019-03-23 | 2019-06-04 | 深圳市江机实业有限公司 | Scene damage single-phase intelligent electric energy meter electricity data extraction element and its operating method |
| CN110222991A (en) * | 2019-06-10 | 2019-09-10 | 国网江苏省电力有限公司常州供电分公司 | Metering device method for diagnosing faults based on RF-GBDT |
| CN110794360A (en) * | 2019-10-22 | 2020-02-14 | 中国电力科学研究院有限公司 | Method and system for predicting fault of intelligent electric energy meter based on machine learning |
| CN111025081A (en) * | 2019-11-07 | 2020-04-17 | 广州南方电力集团科技发展有限公司 | Residential voltage monitoring method for power distribution area |
| CN112487046A (en) * | 2020-10-30 | 2021-03-12 | 深圳供电局有限公司 | Power utilization information analysis method, device, system, computer equipment and storage medium |
| WO2021098246A1 (en) * | 2019-11-19 | 2021-05-27 | 河南许继仪表有限公司 | Electric energy meter service life prediction method and apparatus, and storage medium |
| CN113409166A (en) * | 2021-08-19 | 2021-09-17 | 国网江西综合能源服务有限公司 | XGboost model-based method and device for detecting abnormal electricity consumption behavior of user |
-
2021
- 2021-10-27 CN CN202111258366.5A patent/CN114089257B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104880690A (en) * | 2015-06-15 | 2015-09-02 | 国网上海市电力公司 | Method for evaluating operation of electric energy meter |
| CN104991223A (en) * | 2015-07-27 | 2015-10-21 | 国网重庆市电力公司电力科学研究院 | Watt-hour meter state assessment index selection and quantization method |
| CN109492783A (en) * | 2018-11-14 | 2019-03-19 | 中国电力科学研究院有限公司 | A kind of Application of Power Metering Instruments failure risk prediction technique based on GBDT |
| CN109633518A (en) * | 2019-01-29 | 2019-04-16 | 国网湖南省电力有限公司 | A kind of intelligent electric energy meter comprehensive performance evaluation method, apparatus |
| CN109839535A (en) * | 2019-03-23 | 2019-06-04 | 深圳市江机实业有限公司 | Scene damage single-phase intelligent electric energy meter electricity data extraction element and its operating method |
| CN110222991A (en) * | 2019-06-10 | 2019-09-10 | 国网江苏省电力有限公司常州供电分公司 | Metering device method for diagnosing faults based on RF-GBDT |
| CN110794360A (en) * | 2019-10-22 | 2020-02-14 | 中国电力科学研究院有限公司 | Method and system for predicting fault of intelligent electric energy meter based on machine learning |
| CN111025081A (en) * | 2019-11-07 | 2020-04-17 | 广州南方电力集团科技发展有限公司 | Residential voltage monitoring method for power distribution area |
| WO2021098246A1 (en) * | 2019-11-19 | 2021-05-27 | 河南许继仪表有限公司 | Electric energy meter service life prediction method and apparatus, and storage medium |
| CN112487046A (en) * | 2020-10-30 | 2021-03-12 | 深圳供电局有限公司 | Power utilization information analysis method, device, system, computer equipment and storage medium |
| CN113409166A (en) * | 2021-08-19 | 2021-09-17 | 国网江西综合能源服务有限公司 | XGboost model-based method and device for detecting abnormal electricity consumption behavior of user |
Non-Patent Citations (4)
| Title |
|---|
| BAOFENG LI 等: "《Smart Meters Fault Prediction Technology Based on Cost-sensitive XGBoost Algorithm for Imbalanced Dat》", 《2019 3RD INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION SCIENCES (ICRAS)》, pages 189 - 195 * |
| 张璨辉 等: "电能表故障预测的代价敏感模型研究", 《电测与仪表》, vol. 58, no. 3, pages 180 - 184 * |
| 蔡慧 等: "基于信息融合的低压智能电能表动态评价模型", 《电力***自动化》, vol. 44, no. 11, pages 206 - 215 * |
| 薛阳 等: "电能表故障与地域气候、行业负荷关系研究", 《中国电力》, no. 08, pages 103 - 110 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114089257B (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108375715B (en) | Power distribution network line fault risk day prediction method and system | |
| CN110320892B (en) | Sewage treatment equipment fault diagnosis system and method based on L asso regression | |
| CN110097297A (en) | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium | |
| CN100416438C (en) | Method and device for monitoring a technical installation comprising several systems, in particular an electric power station | |
| CN110533299B (en) | Calculation method, equipment and medium for on-line monitoring of ammeter misalignment rate | |
| CN111639783A (en) | Line loss prediction method and system based on LSTM neural network | |
| CN113095953B (en) | Enterprise environment-friendly monitoring method based on electricity consumption data | |
| CN113988711B (en) | Pollution discharge enterprise stop or limit production monitoring method based on electricity consumption data in control state | |
| CN117742224B (en) | PAD terminal real-time abnormality monitoring and intelligent processing method | |
| CN111723085B (en) | Method and system for cleaning electric energy consumption data of public building air conditioner | |
| CN114254806A (en) | Power distribution network heavy overload early warning method and device, computer equipment and storage medium | |
| CN114879619A (en) | Digital workshop energy optimization method and system | |
| CN110781206A (en) | Method for predicting whether electric energy meter in operation fails or not by learning meter-dismantling and returning failure characteristic rule | |
| CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence | |
| CN117808456A (en) | Equipment fault early warning method and device based on intelligent operation management | |
| CN115907033A (en) | Method and system for predicting hourly power consumption based on machine learning algorithm | |
| CN114089257A (en) | Electric energy meter burning online monitoring method, system and medium | |
| CN116432524A (en) | Transformer oil temperature prediction method, device, equipment and storage medium | |
| CN115809805A (en) | Power grid multi-source data processing method based on edge calculation | |
| CN115146715A (en) | Power utilization potential safety hazard diagnosis method, device, equipment and storage medium | |
| CN111445036B (en) | Dynamic adjustment method for cleaning frequency of photovoltaic power station and storage medium | |
| CN106447521A (en) | Minitype breaker asset life prediction method | |
| CN111080068A (en) | Method and device for evaluating running state of electric energy meter | |
| CN118246912B (en) | Electric meter prepayment method and system based on artificial intelligence | |
| CN117871771B (en) | Big data-based gas energy monitoring method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |