CN109635950B - Electric energy meter running state monitoring method based on genetic algorithm and community clustering - Google Patents
Electric energy meter running state monitoring method based on genetic algorithm and community clustering Download PDFInfo
- Publication number
- CN109635950B CN109635950B CN201811457030.XA CN201811457030A CN109635950B CN 109635950 B CN109635950 B CN 109635950B CN 201811457030 A CN201811457030 A CN 201811457030A CN 109635950 B CN109635950 B CN 109635950B
- Authority
- CN
- China
- Prior art keywords
- electric energy
- energy meter
- electricity utilization
- state
- genetic algorithm
- 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
- 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
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Genetics & Genomics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an electric energy meter running state monitoring method based on a genetic algorithm and community clustering, which comprises the following steps: 1) Basic data of the electric energy meter to be measured are obtained, and electricity utilization characteristic parameters of the electric energy meter to be measured are extracted; 2) Based on the electricity utilization characteristic parameters, acquiring the running state of the electric energy meter to be tested by adopting an electric energy meter state evaluation model based on a genetic algorithm and a polynary neural network; the electricity utilization characteristic parameters are selected according to electric energy meter operation state association factors, and the electric energy meter operation state association factors are determined based on a community clustering algorithm. Compared with the prior art, the invention has the advantages of promoting the state rotation rationalization and intellectualization of the electric energy meter, timely finding out the fault meter and the electric energy meter with hidden quality trouble, ensuring the operation quality level of the electric energy meter, and the like.
Description
Technical Field
The invention relates to a method for monitoring the state of an electric energy meter, in particular to a method for monitoring the running state of the electric energy meter based on a genetic algorithm and community clustering.
Background
As the electric energy meter of legal metering appliances, the electric energy meter bears the tasks of measuring, storing and transmitting important information such as voltage, current, electric energy and the like, and the electric energy metering and information transmission are accurate and timely related to the quality and efficiency of electric charge settlement between an electric company and a customer. For millions of running electric energy meters with larger metering electric quantity, the running state of the running electric energy meters is monitored by adopting a regular field inspection mode at present. The input amount in traffic and manpower is huge, and the management direction of the current enterprise personnel reduction and synergy is difficult to meet. Meanwhile, with technological progress and improvement of product quality, the field operation failure rate of the electric energy meter is lower and lower, and frequent field inspection lacks practical significance.
The operation condition of the whole batch of electric energy meters is judged through the sampling detection result, and the whole batch rotation of the electric energy meters or the continuous use sampling detection supervision method is determined according to the operation condition, so that the method is a commonly adopted electric energy operation condition evaluation and operation exchange method at present, but is more troublesome.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide an electric energy meter state monitoring method based on a genetic algorithm and community clustering.
The aim of the invention can be achieved by the following technical scheme:
a method for monitoring the running state of an electric energy meter based on a genetic algorithm and community clustering comprises the following steps:
1) Basic data of the electric energy meter to be measured are obtained, and electricity utilization characteristic parameters of the electric energy meter to be measured are extracted;
2) Based on the electricity utilization characteristic parameters, acquiring the running state of the electric energy meter to be tested by adopting an electric energy meter state evaluation model based on a genetic algorithm and a polynary neural network;
the electricity utilization characteristic parameters are selected according to electric energy meter operation state association factors, and the electric energy meter operation state association factors are determined based on a community clustering algorithm.
Further, different electricity utilization characteristic parameters are extracted for different electric energy meters to be tested by taking a time dimension as a sequence.
Further, the base data is acquired based on an electricity consumption information acquisition system, an SG186 marketing business system and an MDS production scheduling platform.
Further, when the electric energy meter state evaluation model is trained, a typical and accurate initial sample database is established through laboratory tests and screening and refining of the existing data of typical events to perform initial setting and initial training on the model.
Further, the electric energy meter state evaluation model is dynamically corrected and updated based on the electricity utilization characteristic parameter database.
Furthermore, in the process of determining the operation state association factors of the electric energy meter, the community clustering technology is utilized to realize division according to electricity utilization characteristics and installation environments, and intelligent clustering is realized according to the similarity of key influence factors of the electric energy meter.
Further, the method further comprises:
and grading the electric energy meter to be tested based on the operation state of the electric energy meter to be tested obtained in the step 2).
Further, a grading result of the electric energy meter to be measured is obtained by adopting a clustering qualitative combination risk grading mode, and intelligent division of batches of the electric energy meter is achieved.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, differential schemes are formulated for different types of electric energy meters to be analyzed, the dimension of the state parameters of the electric energy meters in the state inspection mode is expanded, the consideration of the environmental factors and the user characteristics of the electric energy meters is enhanced, and the universal applicability and the demand pertinence of the monitoring results to various intelligent electric energy meters in the network are ensured.
2. The invention adopts the customer electricity utilization characteristic sequence extraction technology in the time dimension to realize the deep mining of the existing data of the customer and the expansion application of the service system function, solves the problem of fuzzy electricity utilization characteristics of the customer, expands the application range and analysis dimension of the existing state inspection system, and provides a data basis for the state evaluation and state rotation of the electric energy meter.
3. Aiming at the problem of influence of human factors on evaluation conclusion in expert scoring mode, the invention adopts the electric energy meter state evaluation model based on genetic algorithm and polynary neural network to obtain the running state of the electric energy meter to be tested, adopts the mode of sample training and machine learning, and avoids the interference of artificial links such as weight setting, expert scoring and the like.
4. According to the invention, a mode of qualitatively combining clustering and risk rating is adopted, a state evaluation conclusion and a state evaluation certainty reference conclusion are given in a targeted manner, and model self-optimization is carried out by combining an analysis result feedback mechanism, so that state evaluation analysis of the electric energy meter is realized.
5. The invention can automatically and intelligently locate and judge the running states of a large number of electric energy meters in operation, realize fault early warning and hidden trouble investigation of a large number of common electric energy meters, provide basis and reference for intelligent rotation of the electric energy meters, and promote rationalization and intellectualization of the state rotation of the electric energy meters.
6. The invention realizes the intelligent division of the batches of the electric energy meter, identifies possible faults in the batches in advance, and improves the state rotation management level.
7. The electric energy meter state evaluation model is dynamically corrected and updated based on the power utilization characteristic parameter database, the automation and intelligent level of state evaluation is improved, the electric energy meter state evaluation and subsequent analysis and early warning functions are realized, and the problems that the electric energy meter state is difficult to acquire, rotate and early warning excessively depends on experience are solved.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples. The present embodiment is implemented on the premise of the technical scheme of the present invention, and a detailed implementation manner and a specific operation process are given, but the protection scope of the present invention is not limited to the following examples.
As shown in fig. 1, the invention provides a method for monitoring the running state of an electric energy meter based on a genetic algorithm and community clustering, which comprises the following steps:
1) Basic data of the electric energy meter to be measured is obtained, data screening and cleaning are carried out, electricity utilization characteristic parameters of the electric energy meter to be measured are extracted, the electricity utilization characteristic parameters are selected according to electric energy meter operation state association factors, and the electric energy meter operation state association factors are determined based on a community clustering algorithm;
2) Based on the electricity utilization characteristic parameters, acquiring the running state of the electric energy meter to be tested by adopting an electric energy meter state evaluation model based on a genetic algorithm and a polynary neural network;
according to the method, the key characteristics of representing the state of the electric energy meter are extracted by utilizing a time sequence analysis method, a state evaluation model based on artificial intelligence is established, batch division of the electric energy meter in site operation is realized, the traditional expert system is replaced by an artificial intelligence method based on multidimensional data analysis to objectively and reasonably evaluate the operation state of the intelligent electric energy meter, early identification and scientific judgment of faults of the electric energy meter are realized, the accuracy of state evaluation of the electric energy meter and the intelligent level of rotation management are effectively improved, resource waste is reduced, the electric energy meter with hidden quality hazards is found in time, and the operation quality level of the electric energy meter is ensured.
1. Electrical feature extraction
And extracting different electricity utilization characteristic parameters of different electric energy meters to be detected by taking the time dimension as a sequence. The method is characterized in that the type, the characteristics and the customer difference condition of the metering device in the network are considered, the electricity information acquisition system, the SG186 marketing service system, the MDS production scheduling platform and the PMS2.0 system data information are synthesized, the time dimension is used as a sequence to select related data items for representing the electricity characteristics of the user, the time dimension is used for extracting the electricity characteristics of the customer, the deep mining of the existing data of the customer and the expansion application of the service system function are realized, the problem of the fuzzy electricity characteristics of the user is solved, the application range and the analysis dimension of the existing state inspection system are expanded, and a data basis is provided for the state evaluation and the state rotation of the electric energy meter.
In the process of determining the operation state association factors of the electric energy meter, the community clustering technology is utilized to realize division according to electricity utilization characteristics and installation environments, and intelligent clustering is realized according to the similarity of key influence factors of the electric energy meter.
2. Smart meter status assessment
The invention can be applied to the evaluation of the states of the single-phase intelligent meter and the three-phase intelligent meter.
The invention compares the corresponding electricity utilization characteristics of various electric energy meters, takes electricity utilization information acquisition data as a core, takes a production scheduling platform and a marketing business system as supplements, pays attention to comprehensive application of original data and electricity utilization characteristic information, adopts a machine learning thought, comprehensive genetic algorithm, community cluster analysis and other various big data analysis application means, researches an electric energy meter state evaluation analysis model based on a polynary neural network, realizes automatic optimization and automatic updating of a sample library by the analysis model, expands the dimension of a state evaluation result by the advantage of cluster analysis, comprehensively considers factors such as manufacturers, operation years, installation environment and the like to study on-network electric energy meter state batch division methods, develops cluster trend prediction and hidden danger early warning rules of the state evaluation analysis model, strengthens the self-adaptability and versatility of the state evaluation analysis model, improves the automation and intelligent level of state evaluation, realizes the state evaluation and subsequent analysis early warning functions of the electric energy meter, and solves the problems that the state of the electric energy meter is difficult to acquire, rotate and early warning excessively depend on experience.
When the electric energy meter state evaluation model is trained, a typical and accurate initial sample database is established through laboratory tests and screening and refining of the existing data of typical events, and the model is initially set and trained. The electric energy meter state evaluation model is dynamically corrected and updated based on the electricity utilization characteristic parameter database.
In some embodiments, the method further comprises rating the electrical energy meter to be tested based on the obtained operational status of the electrical energy meter to be tested. And a grading result of the electric energy meter to be measured is obtained by adopting a clustering qualitative combination risk grading mode, so that the intelligent division of batches of the electric energy meter is realized.
The foregoing describes in detail preferred embodiments of the present invention. It should be understood that numerous modifications and variations can be made in accordance with the concepts of the invention by one of ordinary skill in the art without undue burden. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or limited experiments based on the prior art by the person skilled in the art according to the inventive concept shall be within the scope of protection defined by the claims.
Claims (3)
1. The electric energy meter running state monitoring method based on the genetic algorithm and the community clustering is characterized by comprising the following steps of:
1) Basic data of the electric energy meter to be measured are obtained, and electricity utilization characteristic parameters of the electric energy meter to be measured are extracted;
2) Based on the electricity utilization characteristic parameters, acquiring the running state of the electric energy meter to be tested by adopting an electric energy meter state evaluation model based on a genetic algorithm and a polynary neural network;
the electricity utilization characteristic parameters are selected according to electric energy meter operation state association factors, and the electric energy meter operation state association factors are determined based on a community clustering algorithm;
when the electric energy meter state evaluation model is trained, a typical and accurate initial sample database is established through laboratory tests and screening and refining of the existing data of typical events, and initial setting and initial training are carried out on the model;
in the process of determining the operation state association factors of the electric energy meter, a community clustering technology is utilized to realize division according to electricity utilization characteristics and installation environments, and intelligent clustering is realized according to the similarity of key influence factors of the electric energy meter;
extracting different electricity utilization characteristic parameters of different electric energy meters to be detected by taking a time dimension as a sequence;
the basic data are acquired based on an electricity consumption information acquisition system, an SG186 marketing business system and an MDS production scheduling platform;
and the electric energy meter state evaluation model is dynamically corrected and updated based on the electricity utilization characteristic parameter database.
2. The method for monitoring the operation state of an electric energy meter based on a genetic algorithm and a community cluster according to claim 1, further comprising:
and grading the electric energy meter to be tested based on the operation state of the electric energy meter to be tested obtained in the step 2).
3. The electric energy meter running state monitoring method based on the genetic algorithm and the community clustering according to claim 2 is characterized in that a clustering qualitative combination risk rating mode is adopted to obtain a rating result of the electric energy meter to be tested, and intelligent division of electric energy meter batches is achieved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811457030.XA CN109635950B (en) | 2018-11-30 | 2018-11-30 | Electric energy meter running state monitoring method based on genetic algorithm and community clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811457030.XA CN109635950B (en) | 2018-11-30 | 2018-11-30 | Electric energy meter running state monitoring method based on genetic algorithm and community clustering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109635950A CN109635950A (en) | 2019-04-16 |
| CN109635950B true CN109635950B (en) | 2023-09-15 |
Family
ID=66070202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811457030.XA Active CN109635950B (en) | 2018-11-30 | 2018-11-30 | Electric energy meter running state monitoring method based on genetic algorithm and community clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109635950B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110866074B (en) * | 2019-07-02 | 2022-11-04 | 黑龙江省电工仪器仪表工程技术研究中心有限公司 | Electric energy meter improved K-means classification method based on regional characteristics |
| CN110297207A (en) * | 2019-07-08 | 2019-10-01 | 国网上海市电力公司 | Method for diagnosing faults, system and the electronic device of intelligent electric meter |
| CN110837946A (en) * | 2019-10-09 | 2020-02-25 | 国网天津市电力公司电力科学研究院 | Electric energy meter state evaluation method based on genetic algorithm |
| CN114137472A (en) * | 2021-11-16 | 2022-03-04 | 国网江苏省电力有限公司营销服务中心 | Intelligent electric energy meter state evaluation system with data sharing and service fusion functions |
| CN117909770B (en) * | 2024-03-20 | 2024-05-24 | 山东德源电力科技股份有限公司 | Intelligent settlement data storage method for single-phase fee-controlled electric energy meter |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10379146B2 (en) * | 2015-09-23 | 2019-08-13 | International Business Machines Corporation | Detecting non-technical losses in electrical networks based on multi-layered statistical techniques from smart meter data |
| CN105608638B (en) * | 2015-12-21 | 2019-10-22 | 深圳供电局有限公司 | A kind of method and its system of the table code data synchronous regime determining intelligent terminal and electric energy meter |
| CN106022664A (en) * | 2016-07-08 | 2016-10-12 | 大连大学 | Big data analysis based network intelligent power saving monitoring method |
| CN106251034A (en) * | 2016-07-08 | 2016-12-21 | 大连大学 | Wisdom energy saving electric meter monitoring system based on cloud computing technology |
| WO2018027180A1 (en) * | 2016-08-05 | 2018-02-08 | The Regents Of The University Of California | Phase identification in power distribution systems |
| CN106779069A (en) * | 2016-12-08 | 2017-05-31 | 国家电网公司 | A kind of abnormal electricity consumption detection method based on neutral net |
| CN107609783B (en) * | 2017-09-22 | 2021-11-26 | 中国电力科学研究院 | Method and system for evaluating comprehensive performance of intelligent electric energy meter based on data mining |
| CN107831465A (en) * | 2017-10-31 | 2018-03-23 | 国网黑龙江省电力有限公司电力科学研究院 | A kind of intelligent electric energy meter fault judgment method based on BP neural network |
-
2018
- 2018-11-30 CN CN201811457030.XA patent/CN109635950B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109635950A (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109635950B (en) | Electric energy meter running state monitoring method based on genetic algorithm and community clustering | |
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| CN106154209B (en) | Electrical energy meter fault prediction technique based on decision Tree algorithms | |
| CN110516837B (en) | AI-based intelligent diagnosis method, system and device | |
| CN109597014A (en) | A kind of electric energy meter error diagnostic method based on artificial intelligence technology | |
| CN110927654B (en) | Batch running state evaluation method for intelligent electric energy meters | |
| CN110727662A (en) | Low-voltage transformer area user phase identification method and system based on correlation analysis | |
| CN105426980B (en) | Power distribution network health index assessment engineering application system | |
| CN105022019A (en) | Method of comprehensively estimating reliability of single-phase intelligent electric energy meter | |
| CN110928866A (en) | Line topology checking method and system based on power failure information big data analysis | |
| CN111506618B (en) | Abnormal electricity consumption behavior analysis method combined with lightgbm-stacking algorithm | |
| CN111586729A (en) | Three-network signal detection method and system based on metering terminal communication | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN115423009A (en) | Cloud edge coordination-oriented power equipment fault identification method and system | |
| US20200393501A1 (en) | Systems and methods to analyze waveforms from multiple devices in power systems | |
| CN117406026A (en) | Power distribution network fault detection method suitable for distributed power supply | |
| CN105139287A (en) | Comprehensive electric energy metering device state assessment method integrating safety domain | |
| CN115293257A (en) | Detection method and system for abnormal electricity utilization user | |
| CN111612019A (en) | Method for identifying and analyzing fault abnormality of intelligent electric meter based on big data model | |
| CN115267575A (en) | Energy storage battery life prediction algorithm based on Transformer | |
| CN111999695A (en) | State evaluation and abnormity diagnosis method for metering device of transformer substation | |
| CN112232625A (en) | Power transmission and transformation project cost evaluation method based on space-time big data | |
| CN113176530A (en) | On-service electric energy meter batch fault diagnosis method based on meter-dismantling operation characteristics | |
| CN104166902A (en) | City lighting energy efficiency management system based on internet of things technology | |
| CN117031201A (en) | Multi-scene topology anomaly identification method and system for power distribution network |
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 |