AU2020101900A4 - A method, device and equipment for detecting abnormal electric meter - Google Patents
A method, device and equipment for detecting abnormal electric meter Download PDFInfo
- Publication number
- AU2020101900A4 AU2020101900A4 AU2020101900A AU2020101900A AU2020101900A4 AU 2020101900 A4 AU2020101900 A4 AU 2020101900A4 AU 2020101900 A AU2020101900 A AU 2020101900A AU 2020101900 A AU2020101900 A AU 2020101900A AU 2020101900 A4 AU2020101900 A4 AU 2020101900A4
- Authority
- AU
- Australia
- Prior art keywords
- meter
- error
- layer
- abnormal
- prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R22/00—Arrangements for measuring time integral of electric power or current, e.g. electricity meters
- G01R22/06—Arrangements for measuring time integral of electric power or current, e.g. electricity meters by electronic methods
- G01R22/061—Details of electronic electricity meters
- G01R22/068—Arrangements for indicating or signaling faults
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, device and equipment for detecting abnormal electricity
meter, which belongs to the field of electric power technology. The method includes:
converting the data of each electric meter into an input data set suitable for time series
prediction, using at least two layers of long short-term memory network algorithm to predict
the error of the input data set to obtain the prediction error of the expected date; in the case that
there are abnormal meters according to the prediction error of the expected date, the
convolution neural network is used to detect the anomaly of each meter, and the abnormal
meter is obtained. The invention carries out error prediction through at least two layers of long
short-term memory network algorithm. In the case ofjudging the existence of abnormal meters,
the convolution neural network is used to detect the abnormal information of each meter
effectively and accurately, and the abnormal meter is screened out, so that the user can maintain
and replace the electric meter pertinently and the smart meters can be no longer limited by the
service life, saving economic costs and resources for the country and individuals.
1 /3
101: Convert the data of each electric meter into an input data set suitable for time
series prediction, and use at least two-layer long shcrt-term memory network
algorithm to predict the error of the input data set toobtain the prediction error of the
expected date.
102: In the case that there are abnornalw meters according to the prediction error of
the expected date, the convolution neural network is used to detect the anomaly of
each meter, and the abnormalmeter is obtained.
A flow chart of a method for detecting the abnormality of an electric meter provided
by an embodiment of the invention
FIG, 1
Description
1 /3
101: Convert the data of each electric meter into an input data set suitable for time
series prediction, and use at least two-layer long shcrt-term memory network
algorithm to predict the error of the input data set toobtain the prediction error of the
expected date.
102: In the case that there are abnornalwmeters according to the prediction error of
the expected date, the convolution neural network is used to detect the anomaly of
each meter, and the abnormalmeter is obtained.
A flow chart of a method for detecting the abnormality of an electric meter provided by an embodiment of the invention
FIG, 1
A method, device and equipment for detecting abnormal electric meter
[01] The embodiment of the invention relates to the field of electric power technology, in particular to a method, device and equipment for detecting abnormal electric meter.
[02] With the development of power technology, smart meter is the intelligent terminal and data entry of smart grid. In order to adapt to smart grid, smart meter has many application functions, such as bidirectional multi rate measurement, real-time control of user end, multiple data transmission mode, intelligent interaction and so on.
[03] With the development of smart grid technology, smart grid will cover 80% of the world's population. The construction of smart grid has brought a broad market demand for global smart meters and power consumption information acquisition and processing system products. The penetration rate of smart meters reaches 60%, and smart meters will play an increasingly important role in smart grid.
[04] In the existing technology, the state stipulates that the service life of smart meters is 8 years, but in fact, most smart meters can still be used normally after 8 years of use, and only replace smart meters according to their service life, resulting in high economic cost of replacing smart meters and waste of resources.
[05] Therefore, the embodiment of the invention provides a method, device and equipment for detecting the abnormality of an electric meter, so as to solve the problems in the prior art.
[06] In order to achieve the above purpose, the embodiment of the invention provides the following technical scheme.
[07] According to the first aspect of the embodiment of the invention, a method for detecting the abnormality of an electric meter is provided, including the data of each electric meter is converted into an input data set suitable for time series prediction. At least two layers of long short-term memory network algorithm is used to predict the error of the input data set, and the prediction error of the expected date is obtained.
[08] In the case of judging the existence of abnormal meters according to the prediction error of the expected date, the convolution neural network is used to detect the anomaly of each meter, and the abnormal meter is obtained.
[09] Further, the first layer of the long short-term memory network algorithm comprises 30 dimensions, and the second layer of the long short-term memory network algorithm comprises 30 dimensions.
[010] Furthermore, the activation function adopted by the convolution neural network is sigmoid function.
[011] Furthermore, the convolution neural network is used to detect the abnormality of each electric meter, and the abnormal electric meter is obtained, including:
[012] the first layer (input layer) of convolutional neural network which is used to receive the recursive graph converted according to each user's electricity consumption information; the features are extracted by the second layer and third layer of convolutional neural network; the fourth layer of convolutional neural network is the maximum pooling layer; the fifth layer of convolution neural network is the flat layer, which converts the multi-dimensional input into one-dimensional; according to the scalar given by the sixth and seventh layer of convolutional neural network, calculate and predicate the results, according to which the abnormal electricity meters are selected.
[013] Further, before converting each meter data into an input data set suitable for time series prediction, it includes to obtain the data of the meter, analyze the data and fit the characteristics to get the error distribution attribute. When the error distribution attribute is stable, the abnormal meter can be obtained according to the error distribution.
[014] In the second aspect of the present invention, a device for detecting the abnormality of an electric meter is provided, which comprises:
[015] the error detection module, which is used to convert the data of each electric meter into the input data set suitable for time series prediction and at least two layers of long short-term memory network algorithm is used to predict the error of the input data set to obtain the prediction error of the expected date; the abnormal meter detection module, which is connected with the error detection module and used to detect the abnormality of each meter by using the convolution neural network to obtain the abnormal meter when judging the existence of the abnormal meter according to the prediction error of the expected date.
[016] Further, the convolution neural network includes seven layers, in which the first layer is the input layer for receiving the recursive graph converted according to the electricity consumption information of each user; the second and third layers are the convolution layer for extracting features; the fourth layer is the maximum pooling layer; the fifth layer is the flat layer, which is used to convert the multi-dimensional input into one dimension; the sixth and seventh layers are the dense layers used to give scalars. According to the output results of the dense layer, the prediction results are calculated, and the abnormal electricity meters are selected according to the prediction results.
[017] Further, the device also includes a data analysis module connected with the error detection module.
[018] The data analysis module is used to obtain the data of the electric meter, conduct data analysis and feature fitting to obtain the error distribution attribute. When the error distribution attribute is stable, the abnormal meter is obtained according to the error distribution, and the error detection module is triggered when the error distribution attribute is unstable.
[019] In a third aspect of the present invention, an apparatus for detecting the abnormality of an electric meter is provided, which comprises a processor, which is used to convert the data of each electric meter into an input data set suitable for time series prediction, adopting at least two layers of long short-term memory network algorithm to predict the error of the input data set to obtain the prediction error of the expected date. In the case that there is an abnormal meter according to the prediction error of the expected date, the convolution neural network is used to detect the anomaly of each meter, and the abnormal meter is obtained.
[020] In a fourth aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores a program, which is used to realize the method for detecting the abnormality of an electric meter as described above.
[021] The embodiment of the invention has the following advantages.
[022] The embodiment of the invention converts the data of each electric meter into an input data set suitable for time series prediction, uses at least two-layer long short-term memory network algorithm to predict the error of the input data set to obtain the prediction error of the expected date, so as to determine the existence of abnormal electricity meters, and then uses convolution neural network to detect the abnormal electricity meter.
[023] This method can effectively and accurately mine the abnormal information of the user's electricity meter, and screen out the abnormal meter, so that the user can carry out targeted maintenance and replacement of the electricity meter, so as to the intelligent meter is no longer subject to the service life limit, which avoids the occurrence of batch replacement of meters when reaching the service life, and saves economic costs and resources for the country and individuals.
[024] In order to more clearly explain the embodiments of the invention or the technical solutions in the prior art, the following will briefly introduce the embodiments or the drawings needed in the description of the prior art. Obviously, the drawings in the following description are only illustrative. For those skilled in the art, other implementation drawings can be obtained from the provided drawings without paying creative labor.
[025] The structure, proportion, size, etc. shown in the specification are only used to match the contents disclosed in the specification for the understanding and reading of those who are familiar with the technology, and are not used to limit the implementation conditions of the invention, so they have no technical significance. Any change in the modification, proportion of the structure or adjustment in size, without affecting the efficacy and the purpose achieved by the invention, shall remain within the scope of the technical content disclosed by the invention,
[026] FIG. 1 is a flow chart of a method for detecting the abnormality of an electric meter provided by an embodiment of the invention;
[027] FIG. 2 is a flow chart of a method for detecting the abnormality of an electric meter provided by another embodiment of the invention;
[028] FIG. 3 shows the structure diagram of a device for detecting abnormal meter provided by another embodiment of the invention.
[029] In the figure, 301 is an error detection module, 302 is an abnormal meter detection module.
[030] In the following, the implementation mode of the invention is described by specific examples. People familiar with the technology can easily understand other advantages and effects of the invention from the contents disclosed in the specification. Obviously, the described embodiments are part of the invention embodiments, not all of them. Based on the embodiment of the invention, all other embodiments obtained by ordinary technical personnel in the art without creative labor belong to the scope of protection of the invention.
[031] In the first aspect of the invention, a method for detecting the abnormality of an electric meter is provided, as shown in FIG. 1, including:
[032] Step 101: convert the data of each electric meter into an input data set suitable for time series prediction, and use at least two-layer long short-term memory network algorithm to predict the error of the input data set to obtain the prediction error of the expected date.
[033] In the embodiment of the invention, the data of the electric meter is a group of time series data. The data of the electric meter is converted into the input data set suitable for time series prediction as the original data set, and at least two-layer long short-term memory network algorithm is used for error prediction of the input data set, wherein the long short-term memory network algorithm is LSTM ( Long Short-Term Memory) algorithm, which has at least two layers and the first and second layer both have 30 dimensions.
[034] In the embodiment of the invention, the activation function corresponding to the LSTM algorithm adopts the sigmoid function.
[035] Step 102: In the case that there are abnormal meters according to the prediction error of the expected date, the convolution neural network is used to detect the anomaly of each meter, and the abnormal meter is obtained.
[036] In the embodiment of the invention, a seven layers convolutional neural network (CNN) is adopted. The first layer of the convolutional neural network is the input layer, which receives the recursive graph converted according to each user's electricity consumption information; the second and third layer of it are used to extract features; the fourth layer of it is the maximum pooling layer; the fifth layer is the flat layer, which can transform multi-dimensional into multi-dimensional. According to the scalar given by the sixth and seventh layer of convolutional neural network, calculate and predicate the results, according to which the abnormal electricity meters are selected.
[037] Furthermore, seven layers of convolutional neural networks are as follows: the first layer is the input layer for receiving the recursive graph converted according to the electricity consumption information of each user; the second and third layers are the convolution layer for extracting features; the fourth layer is the maximum pooling layer; the fifth layer is the flat layer, which is used to convert the multi-dimensional input into one dimension; the sixth and seventh layers are the dense layers used to give scalars. According to the output results of the dense layer, the prediction results are calculated, and the abnormal electricity meters are selected according to the prediction results.
[038] In the second aspect of the invention, a method for detecting the abnormality of an electric meter is provided, as shown in FIG. 2, including:
[039] Step 201: obtain the meter data, conduct data analysis and feature fitting to obtain the error distribution attribute. When the error distribution attribute is stable, obtain the abnormal meter according to the error distribution.
[040] In the embodiment of the invention, the user meter power Wsub (with more user data) and the total neighborhood meter power Wsuper of every 24h are obtained respectively, according to which the error is calculated, and the error is recorded as E, using the formula:
[041] E = Wsuper- Wsu, k=1
[042] Furthermore, the error obtained is judged, the error value with negative error is deleted, and the missing value is replaced by the whole point current and voltage to complete the data cleaning.
[043] By drawing the general meter and sub meter, scatter diagram, absolute error curve and relative error curve, the relationship between error and electric quantity is analyzed. When the error distribution is stable, the abnormal situation of electric meter can be judged. When the error distribution is normal but the distribution is not fixed, it is impossible to determine the abnormal point by observing the distribution.
[044] Step 202: In the case of unstable error distribution attributes, using the method of deep learning and adopting the long short-term memory network algorithm to predict the error of the electricity meter data, and the prediction error of the expected date is obtained. In the case that there is an abnormal meter according to the prediction error of the expected date, the convolution neural network is used to detect the anomaly of each meter to obtain the abnormal meter.
[045] In the embodiment of the invention, the meter data is converted into an input data set suitable for time series prediction, and an error prediction of the input data set is carried out by using at least two-layer long short-term memory network algorithm, and the prediction error of the expected date is obtained.
[046] In the embodiment of the invention, the data of the electric meter is a group of time series data. The data of the electric meter is converted into the input data set suitable for time series prediction as the original data set, and at least two-layer long short-term memory network algorithm is used for error prediction of the input data set, wherein the long short-term memory network algorithm is LSTM (Long Short-Term Memory) algorithm, which has at least two layers, wherein the first layer has 30 dimensions, and the second layer also has 30 dimensions.
[047] In the embodiment of the invention, the activation function corresponding to the LSTM algorithm adopts the sigmoid function.
[048] In this embodiment, the seven layers convolution neural network is used to detect the anomaly of the electric meter. Further, the seven layers convolution neural network is respectively: the first layer which is the input layer for receiving the recursive graph converted according to the electricity consumption information of each user; the second and third layers which are the convolution layer for extracting features; the fourth layer is the maximum pooling layer; the fifth layer which is the flat layer and is used to convert the multi-dimensional input into one dimension; the sixth and seventh layers which are the dense layers used to give scalars. According to the output results of the dense layer, the prediction results are calculated, and the abnormal electricity meters are selected according to the prediction results.
[049] It should be noted that in the embodiment of the invention, the machine learning method can also be used to establish the model which using the SVM (Support Vector Machine) algorithm and the combination of SVM and EMD (Empirical Mode Decomposition) algorithm to detect abnormal electricity meters.
[050] In the third aspect of the invention, a device for detecting the abnormality of an electric meter is provided, as shown in FIG. 3, including:
[051] the error detection module 301, which is used to convert the data of each electric meter into an input data set suitable for time series prediction. The error prediction of the input data set is carried out by using at least two layers of long short term memory network algorithm, and the prediction error of the expected date is obtained;
[052] the abnormal meter detection module 302, which is connected with the error detection module 301, and is used to detect the abnormality of each meter by using the convolution neural network to obtain the abnormal meter when the existence of the abnormal meter is determined according to the prediction error of the expected date.
[053] Furthermore, the convolutional neural network includes seven layers, wherein the first layer is the input layer for receiving the recursive graph converted according to the electricity consumption information of each user; the second and third layers are the convolution layer for extracting features; the fourth layer is the maximum pooling layer; the fifth layer is the flat layer, which is used to convert the multi dimensional input into one dimension; the sixth and seventh layers are the dense layers used to give scalars. According to the output results of the dense layer, the prediction results are calculated, and the abnormal electricity meters are selected according to the prediction results.
[054] It should be noted that in the embodiment of the invention, the device also includes a data analysis module connected with the error detection module.
[055] The data analysis module is used to obtain the data of the meter, analyze the data and fit the characteristics to get the error distribution attribute. When the error distribution attribute is stable, the abnormal meter is obtained according to the error distribution, and the error detection module is triggered when the error distribution attribute is unstable.
[056] In a fourth aspect of the present invention, an apparatus for detecting the abnormality of an electric meter is provided, which comprises a processor which is used to convert the data of each electric meter into an input data set suitable for time series prediction, adopting at least two layers of long short-term memory network algorithm to predict the error of the input data set to obtain the prediction error of the expected date. In the case that there is an abnormal meter according to the prediction error of the expected date, the convolution neural network is used to detect the anomaly of each meter, and the abnormal meter is obtained.
[057] In the sixth aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores a program, which is used to realize the method for detecting the abnormality of the electric meter as described above.
[058] Although the present invention has been described in detail with general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made on the basis of the present invention. Therefore, these modifications or improvements made on the basis of not deviating from the spirit of the invention belong to the scope of protection required by the invention.
[059] The present invention and the described embodiments specifically include the best method known to the applicant of performing the invention. The present invention and the described preferred embodiments specifically include at least one feature that is industrially applicable
Claims (10)
1. The utility model relates to a method for detecting the abnormality of an electric meter is characterized in that the data of each electric meter is converted into an input data set suitable for time series prediction and at least two layers of long short term memory network algorithm is used to predict the error of the input data set to obtain the prediction error of the expected date.
According to the prediction error of the expected date, if there is an abnormal meter, the convolution neural network is used to detect the anomaly of each meter, and the abnormal meter is obtained.
2. The method according to claim 1 is characterized in that the first layer of the long short-term memory network algorithm comprises 30 dimensions, and the second layer of the long short-term memory network algorithm comprises 30 dimensions.
3. The method according to claim 1 is characterized in that the activation function adopted by the convolution neural network is sigmoid function.
4. The method according to claim 1 is characterized in that the convolution neural network is used to detect the abnormality of each electric meter, and the abnormal electric meter is obtained. The detect process includes that the first layer (input layer) of convolutional neural network is used to receive the recursive graph converted according to each user's electricity consumption information; the features are extracted by the second and the third layer of convolutional neural network; the fourth layer of convolutional neural network is the maximum pooling layer; the fifth layer of convolution neural network is the flat layer, which converts the multi-dimensional input into one-dimensional; according to the scalar given by the sixth and seventh layer of convolutional neural network, calculate and predicate the results, according to which the abnormal electricity meters are selected.
5. The method according to claim 1 is characterized in that before converting the data of each electric meter into an input data set suitable for time series prediction, the method also includes acquiring the data of the electric meter, analyzing the data and fitting the characteristics to obtain the error distribution attribute, and obtaining the abnormal meter according to the error distribution condition when the error distribution attribute is stable.
6. The utility model relates to a device for detecting the abnormality of an electric meter, which is characterized in including an error detection module which is used to convert the data of each electric meter into an input data set suitable for time series prediction, and a short-term and long-term memory network algorithm with at least two layers is used to predict the error of the input data set to obtain the prediction error of the expected date.
The abnormal meter detection module is connected with the error detection module, which is used to detect the abnormality of each meter by using the convolution neural network to obtain the abnormal meter when judging the existence of the abnormal meter according to the prediction error of the expected date.
7. The device according to claim 6 is characterized in that the convolution neural network includes seven layers, in which the first layer is the input layer for receiving the recursive graph converted according to the electricity consumption information of each user; the second and third layers are the convolution layer for extracting features; the fourth layer is the maximum pooling layer; the fifth layer is the flat layer, which is used to convert the multi-dimensional input into one dimension; the sixth and seventh layers are the dense layers used to give scalars. According to the output results of the dense layer, the prediction results are calculated, and the abnormal electricity meters are selected according to the prediction results.
8. The device according to claim 6 is characterized in that the device also includes a data analysis module connected with the error detection module; the data analysis module is used to obtain the data of the electric meter, conduct data analysis and feature fitting to obtain the error distribution attribute. When the error distribution attribute is stable, the abnormal meter is obtained according to the error distribution condition; when the error distribution attribute is unstable, the error detection module is triggered.
9. A device for detecting abnormal electric meter is characterized in that the processor is used to convert the data of each electric meter into an input data set suitable for time series prediction, adopting at least two layers of long short-term memory network algorithm to predict the error of the input data set to obtain the prediction error of the expected date. In the case that there is an abnormal meter according to the prediction error of the expected date, the convolution neural network is used to detect the anomaly of each meter, and the abnormal meter is obtained.
10. A computer-readable storage medium is characterized in that the computer readable storage medium stores a program for realizing the method for detecting abnormal meter according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2020101900A AU2020101900A4 (en) | 2020-08-21 | 2020-08-21 | A method, device and equipment for detecting abnormal electric meter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2020101900A AU2020101900A4 (en) | 2020-08-21 | 2020-08-21 | A method, device and equipment for detecting abnormal electric meter |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| AU2020101900A4 true AU2020101900A4 (en) | 2020-11-05 |
Family
ID=73016652
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2020101900A Active AU2020101900A4 (en) | 2020-08-21 | 2020-08-21 | A method, device and equipment for detecting abnormal electric meter |
Country Status (1)
| Country | Link |
|---|---|
| AU (1) | AU2020101900A4 (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112966432A (en) * | 2021-02-09 | 2021-06-15 | 东北电力大学 | Method and device for predicting remaining effective life of lithium ion battery |
| CN113281697A (en) * | 2021-05-20 | 2021-08-20 | 国网河南省电力公司营销服务中心 | Operation error online analysis method and system |
| CN113721094A (en) * | 2021-08-27 | 2021-11-30 | 北京市腾河电子技术有限公司 | Error analysis method, system, equipment and storage medium for low-voltage transformer area sampling system |
| CN113823075A (en) * | 2021-10-29 | 2021-12-21 | 长沙力合微智能科技有限公司 | Intelligent adjustment method and device for request waiting time delay of concentrator high-efficiency meter reading equipment |
| CN113985339A (en) * | 2021-09-22 | 2022-01-28 | 北京市腾河科技有限公司 | Error diagnosis method, system, equipment and storage medium for intelligent electric meter |
| CN114037171A (en) * | 2021-11-17 | 2022-02-11 | 国网天津市电力公司 | Power load prediction method based on recursive graph and convolutional neural network |
| CN114184996A (en) * | 2021-12-10 | 2022-03-15 | 广东电网有限责任公司 | Method, device and equipment for identifying metering abnormal behaviors of low-voltage transformer area intelligent electric meter and storage medium |
| CN114265001A (en) * | 2022-03-02 | 2022-04-01 | 华中科技大学 | Smart electric meter metering error evaluation method |
| CN114339477A (en) * | 2022-03-14 | 2022-04-12 | 浙江万胜智能科技股份有限公司 | Data acquisition management method and system based on multi-table integration |
| CN115049232A (en) * | 2022-05-31 | 2022-09-13 | 云南电网有限责任公司 | Method and system for judging station area abnormity |
| CN115061076A (en) * | 2022-05-31 | 2022-09-16 | 云南电网有限责任公司 | Ammeter error detection method based on light carrier area |
| CN115169613A (en) * | 2022-07-27 | 2022-10-11 | 云南电网有限责任公司 | Ammeter maintenance scheme determination method and device, electronic equipment and storage medium |
| CN115358347A (en) * | 2022-09-30 | 2022-11-18 | 山西虚拟现实产业技术研究院有限公司 | Method for predicting remaining life of intelligent electric meter under different subsystems |
| CN115840881A (en) * | 2023-02-15 | 2023-03-24 | 湖南红普创新科技发展有限公司 | Air data processing method and device and related equipment |
| CN116090637A (en) * | 2023-01-19 | 2023-05-09 | 国网江苏省电力有限公司苏州供电分公司 | Short-time electricity consumption prediction method and system |
| CN116205637A (en) * | 2023-05-04 | 2023-06-02 | 广东须臾科技有限公司 | Intelligent factory management system based on Internet of things and industrial big data |
| CN117556715A (en) * | 2024-01-12 | 2024-02-13 | 湖南大学 | Method and system for analyzing degradation of intelligent ammeter in typical environment based on information fusion |
-
2020
- 2020-08-21 AU AU2020101900A patent/AU2020101900A4/en active Active
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112966432A (en) * | 2021-02-09 | 2021-06-15 | 东北电力大学 | Method and device for predicting remaining effective life of lithium ion battery |
| CN113281697B (en) * | 2021-05-20 | 2023-04-18 | 国网河南省电力公司营销服务中心 | Operation error online analysis method and system |
| CN113281697A (en) * | 2021-05-20 | 2021-08-20 | 国网河南省电力公司营销服务中心 | Operation error online analysis method and system |
| CN113721094A (en) * | 2021-08-27 | 2021-11-30 | 北京市腾河电子技术有限公司 | Error analysis method, system, equipment and storage medium for low-voltage transformer area sampling system |
| CN113721094B (en) * | 2021-08-27 | 2024-03-22 | 北京市腾河电子技术有限公司 | Error analysis method and system for low-voltage station mining system, equipment and storage medium |
| CN113985339B (en) * | 2021-09-22 | 2023-11-24 | 北京市腾河科技有限公司 | Error diagnosis method and system for intelligent ammeter, equipment and storage medium |
| CN113985339A (en) * | 2021-09-22 | 2022-01-28 | 北京市腾河科技有限公司 | Error diagnosis method, system, equipment and storage medium for intelligent electric meter |
| CN113823075B (en) * | 2021-10-29 | 2022-07-05 | 深圳市力合微电子股份有限公司 | Intelligent adjustment method and device for request waiting time delay of concentrator high-efficiency meter reading equipment |
| CN113823075A (en) * | 2021-10-29 | 2021-12-21 | 长沙力合微智能科技有限公司 | Intelligent adjustment method and device for request waiting time delay of concentrator high-efficiency meter reading equipment |
| CN114037171A (en) * | 2021-11-17 | 2022-02-11 | 国网天津市电力公司 | Power load prediction method based on recursive graph and convolutional neural network |
| CN114184996A (en) * | 2021-12-10 | 2022-03-15 | 广东电网有限责任公司 | Method, device and equipment for identifying metering abnormal behaviors of low-voltage transformer area intelligent electric meter and storage medium |
| CN114184996B (en) * | 2021-12-10 | 2023-09-29 | 广东电网有限责任公司 | Metering abnormal behavior identification method and device for intelligent ammeter in low-voltage transformer area |
| CN114265001A (en) * | 2022-03-02 | 2022-04-01 | 华中科技大学 | Smart electric meter metering error evaluation method |
| CN114339477A (en) * | 2022-03-14 | 2022-04-12 | 浙江万胜智能科技股份有限公司 | Data acquisition management method and system based on multi-table integration |
| CN114339477B (en) * | 2022-03-14 | 2022-07-12 | 浙江万胜智能科技股份有限公司 | Data acquisition management method and system based on multi-table integration |
| CN115061076A (en) * | 2022-05-31 | 2022-09-16 | 云南电网有限责任公司 | Ammeter error detection method based on light carrier area |
| CN115049232A (en) * | 2022-05-31 | 2022-09-13 | 云南电网有限责任公司 | Method and system for judging station area abnormity |
| CN115169613A (en) * | 2022-07-27 | 2022-10-11 | 云南电网有限责任公司 | Ammeter maintenance scheme determination method and device, electronic equipment and storage medium |
| CN115358347A (en) * | 2022-09-30 | 2022-11-18 | 山西虚拟现实产业技术研究院有限公司 | Method for predicting remaining life of intelligent electric meter under different subsystems |
| CN116090637A (en) * | 2023-01-19 | 2023-05-09 | 国网江苏省电力有限公司苏州供电分公司 | Short-time electricity consumption prediction method and system |
| CN115840881A (en) * | 2023-02-15 | 2023-03-24 | 湖南红普创新科技发展有限公司 | Air data processing method and device and related equipment |
| CN116205637A (en) * | 2023-05-04 | 2023-06-02 | 广东须臾科技有限公司 | Intelligent factory management system based on Internet of things and industrial big data |
| CN117556715A (en) * | 2024-01-12 | 2024-02-13 | 湖南大学 | Method and system for analyzing degradation of intelligent ammeter in typical environment based on information fusion |
| CN117556715B (en) * | 2024-01-12 | 2024-03-26 | 湖南大学 | Method and system for analyzing degradation of intelligent ammeter in typical environment based on information fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2020101900A4 (en) | A method, device and equipment for detecting abnormal electric meter | |
| CN106709816B (en) | Non-parametric regression analysis-based power load abnormal data identification and correction method | |
| CN110807550B (en) | Distribution transformer overload recognition and early warning method based on neural network and terminal equipment | |
| CN111710150A (en) | Abnormal electricity consumption data detection method based on countermeasure self-coding network | |
| CN115170000B (en) | Remote monitoring method and system based on electric energy meter communication module | |
| CN107807860B (en) | Power failure analysis method and system based on matrix decomposition | |
| CN112434799B (en) | Non-invasive load identification method based on full convolution neural network | |
| CN112307003B (en) | Power grid data multidimensional auxiliary analysis method, system, terminal and readable storage medium | |
| CN111371188A (en) | Real-time early warning system for abnormal power consumption data | |
| CN114723285A (en) | Power grid equipment safety evaluation prediction method | |
| Shi et al. | Expected output calculation based on inverse distance weighting and its application in anomaly detection of distributed photovoltaic power stations | |
| CN111008726A (en) | Class image conversion method in power load prediction | |
| CN115664038B (en) | Intelligent power distribution operation and maintenance monitoring system for electrical safety management | |
| CN115313355A (en) | Automatic prediction method and system for big data of smart power grid in short-term load prediction | |
| CN103529337B (en) | The recognition methods of nonlinear correlation relation between equipment failure and electric quantity information | |
| CN107767037A (en) | A kind of user power utilization forms analytic method | |
| CN117713083A (en) | Power system short-term power load prediction system and method based on data management platform | |
| CN111506636A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm | |
| LU500121B1 (en) | A method, device and equipment for electric meter detecting | |
| CN112070379A (en) | Little electric wire netting risk monitoring early warning system | |
| CN114168662A (en) | Power distribution network problem combing and analyzing method and system based on multiple data sources | |
| CN111932138A (en) | System and method for analyzing residential electricity consumption behavior based on Gaussian mixture model and expectation maximization algorithm | |
| Li et al. | Research on Key Technology of State Evaluation and Replacement Acquisition System of Intelligent Electric Energy Meter Based on Smart Grid | |
| Li et al. | Research on Load State Identification Method Based on CNN-Transformer | |
| Zhang et al. | Smart Meter Fault Diagnosis Via Data Cleaning and SAMME-CART Algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| AMFD | Amendment of filing date |
Effective date: 20200821 |
|
| FGI | Letters patent sealed or granted (innovation patent) |