CN112710979B - Intelligent electric energy meter operation monitoring management system and method based on deep learning - Google Patents
Intelligent electric energy meter operation monitoring management system and method based on deep learning Download PDFInfo
- Publication number
- CN112710979B CN112710979B CN202011451317.9A CN202011451317A CN112710979B CN 112710979 B CN112710979 B CN 112710979B CN 202011451317 A CN202011451317 A CN 202011451317A CN 112710979 B CN112710979 B CN 112710979B
- Authority
- CN
- China
- Prior art keywords
- electric energy
- energy meter
- clock
- accumulated deviation
- level
- 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
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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses an intelligent ammeter operation monitoring management system and method based on deep learning, wherein the system comprises an ammeter monitoring unit, a network management unit and a network management unit, wherein the ammeter monitoring unit monitors an ammeter which is already connected to acquire information of the ammeter which is already connected to the network management unit; the electric energy meter management control unit presets a clock accumulated deviation level corresponding to different electric energy meter information aiming at the electric energy meter which has established connection; and the electric energy meter management control unit is used for controlling according to the clock accumulated deviation level of the electric energy meter which is already connected and a control mode corresponding to the information of the electric energy meter which is connected with the electric energy meter monitoring unit. According to the invention, the triple clock accumulated deviation analysis is carried out on the clock data of the online electric energy meter, so that the effectiveness of the online electric energy meter is ensured, different abnormal defect elimination processing modes are arranged on the electric energy meter based on different clock accumulated deviation grades, the operation management level of the electric energy meter is improved, and the fine management of the electric energy meter is realized.
Description
Technical Field
The invention relates to the technical field of power grid metering operation monitoring, in particular to an intelligent electric energy meter operation monitoring management system and method based on deep learning.
Background
In a power supply system, the number of the electric energy meters monitored on line is exponentially increased. The access of a large number of electric energy meters is related to the problems of the operation states of the large number of electric energy meters, and the like, the traditional system cannot meet the requirements of real-time control, unreliable control, effective operation and timely problem treatment, and the problems cannot be guaranteed.
How to monitor the operation condition of the online electric energy meter and analyze the corresponding operation state according to the data deviation of the online electric energy meter, and give out the corresponding processing decision is a problem to be solved urgently.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides an intelligent electric energy meter operation monitoring management system and method based on deep learning, which are used for carrying out triple clock accumulated deviation analysis on an online electric energy meter and ensuring the effectiveness of the online electric energy meter.
The aim of the invention is realized by the following technical scheme: intelligent ammeter operation monitoring management system based on deep learning includes
The electric energy meter monitoring unit monitors the electric energy meter which is already connected to acquire information of the electric energy meter which is already connected to the electric energy meter; and
the electric energy meter management control unit is used for presetting a clock accumulated deviation level corresponding to different electric energy meter information aiming at the electric energy meter which has established connection;
the electric energy meter management control unit controls according to the clock accumulated deviation level of the electric energy meter which is already connected and the control mode corresponding to the information of the electric energy meter which is connected with the electric energy meter monitoring unit.
Further, the electric energy meter monitoring unit is provided with an electric energy meter clock data acquisition unit, and the electric energy meter clock data acquisition unit acquires time data of a calendar clock of the electric energy meter in real time.
Further, the electric energy meter management control unit is provided with an accumulated deviation calculating unit, and the accumulated deviation calculating unit calculates accumulated deviation of the clock of the electric energy meter which is connected.
Further, the electric energy meter management control unit is provided with an accumulated deviation prediction unit, and the accumulated deviation prediction unit predicts accumulated deviation of the clock of the electric energy meter which is connected.
Further, the electric energy meter management control unit is provided with an accumulated deviation grade analysis unit, and the accumulated deviation grade analysis unit performs grade analysis and judgment according to the clock accumulated deviation calculated value of the electric energy meter which is already connected;
when the current accumulated deviation level of the electric energy meter which is already connected does not exceed the first clock accumulated deviation level, the electric energy meter management control unit enters into the level analysis judgment of the clock accumulated deviation predicted value when the clock accumulated deviation does not exceed the first clock accumulated deviation threshold corresponding to the first clock accumulated deviation level, and when the clock accumulated deviation predicted value level of the electric energy meter which is already connected does not exceed the first clock accumulated deviation level, the electric energy meter management control unit outputs the clock data normal reminding information when the clock accumulated deviation predicted value does not exceed the first clock accumulated deviation threshold corresponding to the first clock accumulated deviation level.
Further, the clock accumulated deviation level includes a first clock accumulated deviation level corresponding to the clock data,
when the accumulated deviation level of the electric energy meter which is connected exceeds the first clock accumulated deviation level, the electric energy meter management control unit enters the second clock accumulated deviation analysis judgment when the clock accumulated deviation exceeds the first clock accumulated deviation threshold corresponding to the first clock accumulated deviation level.
Further, the clock accumulated deviation level includes a second clock accumulated deviation level corresponding to the clock data,
the second clock accumulated deviation analysis and judgment, the electric energy meter management control unit judges whether the clock accumulated deviation exceeds a second clock accumulated deviation threshold corresponding to the second clock accumulated deviation level,
under the condition that the accumulated deviation level of the electric energy meter which is connected is not over the second clock accumulated deviation level, the electric energy meter management control unit enters a daily average deviation calculation module to calculate the daily average deviation of clock data of the corresponding electric energy meter under the condition that the clock accumulated deviation is not over the second clock accumulated deviation threshold corresponding to the second clock accumulated deviation level.
Further, the clock accumulated deviation level includes a third clock accumulated deviation level corresponding to the clock data,
when the accumulated deviation level of the electric energy meter which is connected exceeds the second clock accumulated deviation level, the electric energy meter management control unit enters a third clock accumulated deviation analysis judgment when the clock accumulated deviation exceeds the clock accumulated deviation threshold corresponding to the second clock accumulated deviation level.
Further, the third clock accumulated deviation analysis judges that the electric energy meter management control unit judges whether the clock accumulated deviation exceeds a third clock accumulated deviation threshold corresponding to the third clock accumulated deviation level,
under the condition that the accumulated deviation level of the electric energy meter which is connected already exceeds the third clock accumulated deviation level, the electric energy meter management control unit enters an electric energy meter replacement execution reminding module to remind the electric energy meter to be replaced under the condition that the clock accumulated deviation exceeds a third clock accumulated deviation threshold corresponding to the third clock accumulated deviation level.
Further, the third clock accumulated deviation analysis judges: under the condition that the accumulated deviation level of the electric energy meter which is connected is not over the third clock accumulated deviation level, the electric energy meter management control unit enters the electric energy meter timing reminding module to remind the electric energy meter to perform timing under the condition that the clock accumulated deviation is not over the third clock accumulated deviation threshold corresponding to the third clock accumulated deviation level.
The invention also provides an intelligent electric energy meter operation monitoring management method based on deep learning, which comprises the following steps:
a step of monitoring the electric energy meter, wherein the electric energy meter which is already connected is monitored, and information of the electric energy meter which is already connected is obtained; and
a step of electric energy meter management control, in which a clock accumulated deviation level corresponding to different electric energy meter information is preset for the electric energy meter which has established connection; and controlling according to a control mode corresponding to the information of the electric energy meter connected with the electric energy meter.
Compared with the prior art, the invention has the following technical effects:
(1) The intelligent ammeter operation monitoring management system based on deep learning performs triple clock accumulation deviation analysis on the online ammeter, ensures the effectiveness of the online ammeter, and simultaneously sets different abnormal defect elimination treatment modes on the ammeter based on different clock accumulation deviation grades, thereby improving the ammeter operation management level and realizing the fine management of the ammeter.
(2) According to the invention, triple grade judgment is carried out on the current clock accumulated deviation and the future clock accumulated deviation prediction at the same time, and when the clock accumulated deviation at the current moment is in a normal state, clock accumulated deviation analysis is carried out based on the future clock accumulated deviation prediction value, so that real-time analysis on the clock accumulated deviation of the electric energy meter and trend prediction on the clock accumulated deviation of the electric energy meter are realized, and out-of-tolerance early warning of the electric energy meter and optimization of the clock deviation inspection time period of the electric energy meter are realized.
(3) And the accumulated deviation prediction of the future electric energy meter is decomposed into a plurality of components by adopting an error time sequence, the components are predicted respectively, and the prediction results of the error components are overlapped, so that the accuracy of the accumulated deviation prediction of the electric energy meter is improved.
Drawings
FIG. 1 is a block diagram of an intelligent ammeter operation monitoring management system based on deep learning;
FIG. 2 is a flow chart of a monitoring and managing method of the intelligent ammeter operation monitoring and managing system based on deep learning;
fig. 3 is a flow chart of an analysis method of the clock accumulated deviation level analysis unit in the intelligent electric energy meter operation monitoring management system based on deep learning.
Detailed Description
The present invention will be further described in detail with reference to the accompanying drawings, for the purpose of making the objects, technical solutions and advantages of the present invention more apparent, and the described embodiments should not be construed as limiting the present invention, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present invention.
The intelligent ammeter operation monitoring management system based on deep learning that this embodiment provided includes:
the electric energy meter monitoring unit monitors the electric energy meter which is already connected to acquire information of the electric energy meter which is already connected to the electric energy meter; and
the electric energy meter management control unit is used for presetting a clock accumulated deviation level corresponding to different electric energy meter information aiming at the electric energy meter which has established connection;
the electric energy meter management control unit controls according to the clock accumulated deviation level of the electric energy meter which is already connected and the control mode corresponding to the information of the electric energy meter which is connected with the electric energy meter monitoring unit.
In this embodiment, based on different clock data, the clock accumulated deviation grade matching judgment is performed, and based on the grade judgment result, different management methods are performed on the electric energy meter, so that on-line real-time monitoring and management of clock abnormality of the electric energy meter are realized, the defect of a field inspection mode of the metering device is avoided, and the operation management level of the metering device is improved.
Further, the electric energy meter monitoring unit is provided with an electric energy meter clock data acquisition unit, and the electric energy meter clock data acquisition unit acquires time data of a calendar clock of the electric energy meter in real time.
Meanwhile, the electric energy meter management control unit has an accumulated deviation calculating unit, and the accumulated deviation calculating unit calculates accumulated deviation of a clock of the electric energy meter which is connected, for example, the calculating method may be:
the ratio of Ts to Tm+Tt2/2 is equal to the standard time; tm is the calendar clock of the electric energy meter; tt2 is the communication delay time of the master station pair meter.
The electric energy meter management control unit has an accumulated deviation prediction unit, the accumulated deviation prediction unit predicts the accumulated deviation of the clock of the electric energy meter which is established with connection, and the accumulated deviation prediction unit comprises:
an error sequence decomposition subunit, which is used for gradually decomposing the historical accumulated deviation time sequence to obtain a plurality of components;
and the component deviation prediction subunit adopts a BP neural network to perform deviation prediction on each component, and fuses the component deviation predicted values to output an accumulated deviation predicted result.
Specifically, the prediction method of the accumulated deviation prediction unit is as follows:
decomposing a historical accumulated deviation time sequence, wherein the sequence adopts the change data of clock accumulated deviation between every two adjacent automatic inspection pairs of an electric energy meter, firstly obtains the time Tk (k=1, 2..m) corresponding to all local extremum points of the time sequence x (t), then extracts a baseline signal between two adjacent extremum points, and introduces an extraction operator L into an extraction formula, wherein the provision formula is as follows:
wherein L is a piecewise linear baseline extraction operator; alpha epsilon [0,1] is a constant coefficient.
Based on the baseline signal extraction formula, for T 2 ～T m-1 Extracting baseline signals from extreme points at moment, respectively taking five points from two end points to the middle, and obtaining the baseline signals from the two end points according to a cubic polynomial fitting;
fitting all lks (k=1, 2, … M) using a cubic spline function to obtain a baseline L1;
subtracting the extracted basis from the time series x (t)The 1 st rotation component x can be obtained after line L1 R1 (t) =x (t) -L1, repeating the above steps with L1 as a new time sequence x (t), and gradually decomposing to obtain a plurality of baseline components and rotation components until the residual signal can be approximated as a monotone signal or a constant signal.
Based on the obtained components, the components are input into a trained BP neural network to obtain component deviation predicted values, and the fused predicted values obtained by adding the deviation predicted values of the components are used as final clock accumulated deviation predicted values of the electric energy meter.
In the process of training the BP neural network, in order to shorten the training time and accelerate the convergence of the training model, the embodiment adopts a genetic algorithm to update the network model parameters in the training process in a optimizing and iterating way, and specifically, the training process comprises the following steps:
firstly, establishing an initial BP neural network, wherein the initial BP neural network comprises the steps of determining the number of neurons of an input layer, an output layer and a hidden layer of the network, the number of hidden layer layers, an activation function and the like;
based on a large number of change sequence data of clock accumulated deviation between every two adjacent automatic pairs of inspection of the electric energy meter, acquiring a plurality of components based on the decomposition method;
based on the component data as network model training input data, encoding the weight and the threshold value of the BP neural network to obtain an initial population, wherein each weight and each threshold value are used as an individual of a genetic algorithm;
iterative individual screening is carried out based on the inverse of the difference between the output predicted value and the actual output value of an individual input neural network as an adaptability function of an algorithm;
removing individuals which do not meet the fitness value, and copying, crossing and mutating the individuals which meet the fitness requirement to generate new individuals;
checking whether the generated new individual is an optimal individual, if so, decoding the finally obtained optimal individual to be respectively used as a weight and a threshold value of the BP neural network, and if not, carrying out a genetic algorithm again;
and training the BP neural network based on the weight and the threshold of the BP neural network obtained by decoding the optimal individual until the error precision requirement or the upper limit of iteration times is reached, and obtaining the BP neural network after training.
The electric energy meter management control unit is provided with an accumulated deviation grade analysis unit, wherein the accumulated deviation grade analysis unit carries out grade analysis judgment according to a clock accumulated deviation calculated value of the electric energy meter which is already connected, specifically, the accumulated deviation grade comprises a first clock accumulated deviation grade and a second clock accumulated deviation grade and a third clock accumulated deviation grade, wherein the upper limit threshold value of the first clock accumulated deviation grade, namely the first clock accumulated deviation threshold value, is set to be 1min, the upper limit threshold value of the second clock accumulated deviation grade, namely the second clock accumulated deviation threshold value, is recorded as K1, in practice, K1 can be 3min, and the upper limit threshold value of the third clock accumulated deviation grade, namely the third clock accumulated deviation threshold value, is set to be 5min; the accumulated deviation grade analysis unit carries out grade analysis on the current accumulated deviation calculated value, when the current accumulated deviation calculated value is in the first clock accumulated deviation grade, the time correction and the electric energy meter replacement processing of the electric energy meter are not carried out, in order to reduce the possibility of clock out deviation of the accumulated deviation of the electric energy meter, the grade analysis is continuously carried out on the future accumulated deviation predicted value on the basis, if the future accumulated deviation predicted value is also in the first clock accumulated deviation grade (namely, normal grade), the situation that the clock deviation data of the electric energy meter is in the normal allowable range and the clock accumulated deviation is not too large in the future is indicated, and the abnormal defect elimination processing flow of the electric energy meter is not needed.
Specifically, the process flow of the accumulated deviation level analysis unit is as follows:
when the current accumulated deviation level of the electric energy meter which is already connected does not exceed the first clock accumulated deviation level, the electric energy meter management control unit enters into the level analysis judgment of the clock accumulated deviation predicted value when the clock accumulated deviation does not exceed the first clock accumulated deviation threshold corresponding to the first clock accumulated deviation level, and when the clock accumulated deviation predicted value level of the electric energy meter which is already connected does not exceed the first clock accumulated deviation level, the electric energy meter management control unit outputs the clock data normal reminding information when the clock accumulated deviation predicted value does not exceed the first clock accumulated deviation threshold corresponding to the first clock accumulated deviation level.
The clock accumulated deviation level comprises a first clock accumulated deviation level corresponding to clock data, and when the accumulated deviation level of the electric energy meter which is connected exceeds the first clock accumulated deviation level, the electric energy meter management control unit enters the second clock accumulated deviation analysis judgment when the clock accumulated deviation exceeds a first clock accumulated deviation threshold corresponding to the first clock accumulated deviation level.
The clock accumulated deviation level comprises a second clock accumulated deviation level corresponding to clock data, and the second clock accumulated deviation analysis judgment refers to that the electric energy meter management control unit judges whether the clock accumulated deviation exceeds a second clock accumulated deviation threshold corresponding to the second clock accumulated deviation level;
under the condition that the accumulated deviation level of the electric energy meter which is connected is not over the second clock accumulated deviation level, the electric energy meter management control unit enters a daily average deviation calculation module to calculate the daily average deviation of clock data of the corresponding electric energy meter under the condition that the clock accumulated deviation is not over the second clock accumulated deviation threshold corresponding to the second clock accumulated deviation level.
The clock accumulated deviation level includes a third clock accumulated deviation level corresponding to the clock data, and the electric energy meter management control unit enters the third clock accumulated deviation analysis and judgment when the clock accumulated deviation exceeds the clock accumulated deviation threshold corresponding to the second clock accumulated deviation level when the accumulated deviation level of the electric energy meter which has established connection exceeds the second clock accumulated deviation level.
The third clock accumulated deviation analysis and judgment means that the electric energy meter management control unit judges whether the clock accumulated deviation exceeds a third clock accumulated deviation threshold corresponding to the third clock accumulated deviation level;
under the condition that the accumulated deviation level of the electric energy meter which is connected already exceeds the third clock accumulated deviation level, the electric energy meter management control unit enters an electric energy meter replacement execution reminding module to remind the electric energy meter to be replaced under the condition that the clock accumulated deviation exceeds a third clock accumulated deviation threshold corresponding to the third clock accumulated deviation level.
Under the condition that the accumulated deviation level of the electric energy meter which is connected is not over the third clock accumulated deviation level, the electric energy meter management control unit enters the electric energy meter timing reminding module to remind the electric energy meter to perform timing under the condition that the clock accumulated deviation is not over the third clock accumulated deviation threshold corresponding to the third clock accumulated deviation level.
The daily average deviation calculation module calculates the daily average deviation of the clock data of the corresponding electric energy meter, if the daily average deviation of the clock data of the corresponding electric energy meter exceeds the corresponding daily average deviation threshold of the clock data, the daily average deviation threshold of the clock data is recorded as k2min, and the conventional 0.5min/24h can be adopted in the embodiment, and the clock data enters the electric energy meter replacement execution reminding module to remind of replacing the electric energy meter;
if the average daily deviation of the clock data of the corresponding electric energy meter does not exceed the average daily deviation threshold of the corresponding clock data, the operation monitoring of the electric energy meter is finished, and the abnormal defect elimination of the electric energy meter is finished.
The embodiment also provides an intelligent electric energy meter operation monitoring management method based on deep learning, which comprises the following steps:
a step of monitoring the electric energy meter, wherein the electric energy meter which is already connected is monitored, and information of the electric energy meter which is already connected is obtained; and
a step of electric energy meter management control, in which a clock accumulated deviation level corresponding to different electric energy meter information is preset for the electric energy meter which has established connection; and controlling according to a control mode corresponding to the information of the electric energy meter connected with the electric energy meter.
The specific limitation of the intelligent electric energy meter operation monitoring management method can be referred to the limitation of the intelligent electric energy meter operation monitoring management system, and the description is omitted here.
The embodiment also provides an electronic device, including:
a memory for storing executable instructions;
and the processor is used for realizing the intelligent electric energy meter operation monitoring management system based on the deep learning when the executable instructions stored in the memory are operated.
The embodiment also provides a computer readable storage medium, which stores executable instructions, wherein the executable instructions realize the intelligent electric energy meter operation monitoring management system based on deep learning when being executed by a processor.
The electronic device may be a server comprising a processor, a memory and a network interface connected by a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic device includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the electronic device is used for storing clock data of the electric energy meter, related threshold data and the like. The network interface of the electronic device is used for communicating with an external terminal through a network connection. The computer program is executed by the processor to realize the monitoring management method of the intelligent ammeter operation monitoring management system based on deep learning.
The present invention is not limited to the above-described specific embodiments, and various modifications may be made by those skilled in the art without inventive effort from the above-described concepts, and are within the scope of the present invention.
Claims (5)
1. Intelligent ammeter operation monitoring management system based on deep learning, its characterized in that: comprising
The electric energy meter monitoring unit monitors the electric energy meter which is already connected to acquire information of the electric energy meter which is already connected to the electric energy meter; and
the electric energy meter management control unit is used for presetting a clock accumulated deviation level corresponding to different electric energy meter information aiming at the electric energy meter which has established connection;
the electric energy meter management control unit controls according to the clock accumulated deviation level of the electric energy meter which is already connected and the control mode corresponding to the information of the electric energy meter which is connected with the electric energy meter monitoring unit;
the electric energy meter management control unit is provided with an accumulated deviation grade analysis unit which performs grade analysis and judgment according to the clock accumulated deviation calculated value of the electric energy meter which is already connected;
when the current accumulated deviation level of the electric energy meter which is already connected does not exceed the first clock accumulated deviation level, the electric energy meter management control unit enters into the level analysis judgment of the clock accumulated deviation predicted value when the clock accumulated deviation does not exceed the first clock accumulated deviation threshold corresponding to the first clock accumulated deviation level, and when the clock accumulated deviation predicted value level of the electric energy meter which is already connected does not exceed the first clock accumulated deviation level, the electric energy meter management control unit outputs the clock data normal reminding information when the clock accumulated deviation predicted value does not exceed the first clock accumulated deviation threshold corresponding to the first clock accumulated deviation level;
the clock accumulated bias level includes a first clock accumulated bias level corresponding to clock data,
under the condition that the accumulated deviation level of the electric energy meter which is connected already exceeds the first clock accumulated deviation level, the electric energy meter management control unit enters a second clock accumulated deviation analysis judgment under the condition that the clock accumulated deviation exceeds a first clock accumulated deviation threshold corresponding to the first clock accumulated deviation level;
the clock accumulated bias level includes a second clock accumulated bias level corresponding to clock data,
the second clock accumulated deviation analysis and judgment, the electric energy meter management control unit judges whether the clock accumulated deviation exceeds a second clock accumulated deviation threshold corresponding to the second clock accumulated deviation level,
under the condition that the accumulated deviation level of the electric energy meter which is connected is not over the second clock accumulated deviation level, the electric energy meter management control unit enters a daily average deviation calculation module to calculate the daily average deviation of clock data of the corresponding electric energy meter under the condition that the clock accumulated deviation is not over the second clock accumulated deviation threshold corresponding to the second clock accumulated deviation level;
the clock accumulated bias level includes a third clock accumulated bias level corresponding to clock data,
when the accumulated deviation level of the electric energy meter which is connected with the electric energy meter exceeds the second clock accumulated deviation level, the electric energy meter management control unit enters a third clock accumulated deviation analysis judgment when the clock accumulated deviation exceeds the clock accumulated deviation threshold corresponding to the second clock accumulated deviation level;
the third clock accumulated deviation analysis and judgment unit judges whether the clock accumulated deviation exceeds a third clock accumulated deviation threshold corresponding to the third clock accumulated deviation level,
under the condition that the accumulated deviation level of the electric energy meter which is connected already exceeds the third clock accumulated deviation level, the electric energy meter management control unit enters an electric energy meter replacement execution reminding module to remind the electric energy meter to be replaced under the condition that the clock accumulated deviation exceeds a third clock accumulated deviation threshold corresponding to the third clock accumulated deviation level.
2. The deep learning-based intelligent ammeter operation monitoring management system of claim 1, further comprising: the electric energy meter monitoring unit is provided with an electric energy meter clock data acquisition unit, and the electric energy meter clock data acquisition unit acquires time data of a calendar clock of the electric energy meter in real time.
3. The deep learning-based intelligent ammeter operation monitoring management system of claim 1, further comprising: the electric energy meter management control unit is provided with an accumulated deviation calculating unit which calculates accumulated deviation of clocks of the electric energy meters which are connected.
4. The deep learning-based intelligent ammeter operation monitoring management system of claim 1, further comprising: the electric energy meter management control unit is provided with an accumulated deviation prediction unit, and the accumulated deviation prediction unit predicts the accumulated deviation of the clock of the electric energy meter which is connected.
5. The intelligent ammeter operation monitoring management system based on deep learning as claimed in claim 1, wherein:
and (3) analyzing and judging the accumulated deviation of the third clock: under the condition that the accumulated deviation level of the electric energy meter which is connected is not over the third clock accumulated deviation level, the electric energy meter management control unit enters the electric energy meter timing reminding module to remind the electric energy meter to perform timing under the condition that the clock accumulated deviation is not over the third clock accumulated deviation threshold corresponding to the third clock accumulated deviation level.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011451317.9A CN112710979B (en) | 2020-12-10 | 2020-12-10 | Intelligent electric energy meter operation monitoring management system and method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011451317.9A CN112710979B (en) | 2020-12-10 | 2020-12-10 | Intelligent electric energy meter operation monitoring management system and method based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112710979A CN112710979A (en) | 2021-04-27 |
| CN112710979B true CN112710979B (en) | 2023-06-27 |
Family
ID=75541750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011451317.9A Active CN112710979B (en) | 2020-12-10 | 2020-12-10 | Intelligent electric energy meter operation monitoring management system and method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112710979B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115291157B (en) * | 2022-07-14 | 2023-09-22 | 国网山东省电力公司营销服务中心(计量中心) | Electric energy meter residual life prediction method and system based on clock deviation |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105446122A (en) * | 2016-01-13 | 2016-03-30 | 国家电网公司 | Electric energy meter clock calibration method |
| CN106054104A (en) * | 2016-05-20 | 2016-10-26 | 国网新疆电力公司电力科学研究院 | Intelligent ammeter fault real time prediction method based on decision-making tree |
| CN106254022A (en) * | 2016-07-28 | 2016-12-21 | 国网内蒙古东部电力有限公司 | Time supervision based on clock synchronization apparatus and time delay query software system platform |
| CN109407040A (en) * | 2018-12-07 | 2019-03-01 | 广东电网有限责任公司 | A kind of intelligent electric energy meter calibration method, device, equipment and storage medium |
| CN110059845A (en) * | 2019-02-01 | 2019-07-26 | 国网浙江省电力有限公司温州供电公司 | Metering device clocking error trend forecasting method based on timing evolved genes model |
| CN110320791A (en) * | 2019-06-20 | 2019-10-11 | 国网湖南省电力有限公司 | A kind of power information acquisition system clock management method and device |
| CN111045319A (en) * | 2019-12-12 | 2020-04-21 | 广西电网有限责任公司 | Method for automatically correcting clock differentiation of electric energy meter |
| CN111596253A (en) * | 2019-08-24 | 2020-08-28 | 青岛鼎信通讯股份有限公司 | Method for governing clock error through broadcast time synchronization on 09 standard intelligent meter |
-
2020
- 2020-12-10 CN CN202011451317.9A patent/CN112710979B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105446122A (en) * | 2016-01-13 | 2016-03-30 | 国家电网公司 | Electric energy meter clock calibration method |
| CN106054104A (en) * | 2016-05-20 | 2016-10-26 | 国网新疆电力公司电力科学研究院 | Intelligent ammeter fault real time prediction method based on decision-making tree |
| CN106254022A (en) * | 2016-07-28 | 2016-12-21 | 国网内蒙古东部电力有限公司 | Time supervision based on clock synchronization apparatus and time delay query software system platform |
| CN109407040A (en) * | 2018-12-07 | 2019-03-01 | 广东电网有限责任公司 | A kind of intelligent electric energy meter calibration method, device, equipment and storage medium |
| CN110059845A (en) * | 2019-02-01 | 2019-07-26 | 国网浙江省电力有限公司温州供电公司 | Metering device clocking error trend forecasting method based on timing evolved genes model |
| CN110320791A (en) * | 2019-06-20 | 2019-10-11 | 国网湖南省电力有限公司 | A kind of power information acquisition system clock management method and device |
| CN111596253A (en) * | 2019-08-24 | 2020-08-28 | 青岛鼎信通讯股份有限公司 | Method for governing clock error through broadcast time synchronization on 09 standard intelligent meter |
| CN111045319A (en) * | 2019-12-12 | 2020-04-21 | 广西电网有限责任公司 | Method for automatically correcting clock differentiation of electric energy meter |
Non-Patent Citations (1)
| Title |
|---|
| 用电信息采集系统大数据在电能表时钟管理研究中的应用;王玮 等;《电力大数据》;20171231;第20卷(第12期);第8-12页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112710979A (en) | 2021-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023130776A1 (en) | Method and system for predicting working condition health status of battery in energy storage power station | |
| WO2021138925A1 (en) | Lithium battery capacity estimation method based on improved convolution-long short term memory neural network | |
| CN108445435B (en) | Online error evaluation method for electric energy meter calibrating device | |
| CN112232447B (en) | Construction method of complete sample set of power equipment state monitoring data | |
| CN112734128A (en) | 7-day power load peak value prediction method based on optimized RBF | |
| CN112710979B (en) | Intelligent electric energy meter operation monitoring management system and method based on deep learning | |
| CN113114529B (en) | KPI (Key Performance indicator) anomaly detection method and device based on condition variation automatic encoder and computer storage medium | |
| CN111458661A (en) | Power distribution network line variation relation diagnosis method, device and system | |
| CN113239132A (en) | Online out-of-tolerance identification method for voltage transformer | |
| CN114781184A (en) | Digital energy consumption online safety monitoring management method and system | |
| CN111680398B (en) | Single machine performance degradation prediction method based on Holt-windows model | |
| CN115587673A (en) | Voltage transformer error state prediction method and system | |
| CN106325258B (en) | Relay protection device state evaluation method based on online monitoring information | |
| CN117454771A (en) | Mechanical equipment dynamic maintenance decision-making method based on evaluation and prediction information | |
| CN117154263A (en) | Lithium battery cascade utilization charging and discharging system and control method | |
| CN116736130A (en) | Lithium battery residual service life prediction method and system | |
| CN113459897B (en) | Electric vehicle charging big data-based state of charge correction and prediction method | |
| CN115577927A (en) | Important power consumer electricity utilization safety assessment method and device based on rough set | |
| CN111611117B (en) | Hard disk fault prediction method, device, equipment and computer readable storage medium | |
| CN114201825A (en) | Method and system for evaluating equipment performance degradation state based on combination characteristics | |
| CN109033569A (en) | A method of optimize for carrier-borne aircraft sensing system prophylactic repair threshold intensity and number | |
| CN110866652B (en) | Online PMU data error correction method and system based on LSTM model | |
| CN114330775A (en) | Monte Carlo simulation-based visual maintenance strategy optimization method for accelerated degradation equipment | |
| CN112001073A (en) | Reliability analysis research method of traction power supply system | |
| CN117216673B (en) | Current transformer monitoring evaluation overhauls platform |
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 |