CN110968703B - Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm - Google Patents
Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm Download PDFInfo
- Publication number
- CN110968703B CN110968703B CN201911238633.5A CN201911238633A CN110968703B CN 110968703 B CN110968703 B CN 110968703B CN 201911238633 A CN201911238633 A CN 201911238633A CN 110968703 B CN110968703 B CN 110968703B
- Authority
- CN
- China
- Prior art keywords
- metering point
- information
- abnormal
- knowledge base
- knowledge
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 122
- 238000000605 extraction Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 11
- 230000005611 electricity Effects 0.000 claims abstract description 58
- 238000012549 training Methods 0.000 claims abstract description 8
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 7
- 230000008014 freezing Effects 0.000 claims description 30
- 238000007710 freezing Methods 0.000 claims description 30
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000009411 base construction Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 238000000819 phase cycle Methods 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 abstract description 11
- 238000012423 maintenance Methods 0.000 abstract description 3
- 238000003745 diagnosis Methods 0.000 description 12
- 238000004458 analytical method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000009412 basement excavation Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000012098 association analyses Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention relates to a method for constructing an abnormal metering point knowledge base based on an LSTM end-to-end extraction algorithm, which is characterized by comprising the following steps of: the method comprises the following steps: (1) Extracting abnormal metering point information in an electricity consumption information acquisition system; (2) Based on the abnormal metering point information, calculating the knowledge information probability of the abnormal metering point through an LSTM network unit model to form a multidimensional knowledge tag; (3) And extracting the formed multidimensional knowledge labels based on the bidirectional LSTM training network, establishing an abnormal metering point knowledge identification label aiming at the knowledge characteristic value with the maximum probability, and outputting a multidimensional abnormal metering point knowledge base. According to the invention, the metering abnormality is identified through the matching of the knowledge base, so that the problem electric energy meter is screened out, and accurate guidance is provided for maintenance, service life and the like of the electric energy meter.
Description
Technical Field
The invention belongs to the field of electric energy meter metering error analysis, and particularly relates to a method and a system for constructing an abnormal metering point knowledge base based on an LSTM end-to-end extraction algorithm.
Background
In 2009, the national grid company has drastically built electricity consumption information acquisition systems, and currently has realized the operation of 4.5 hundred million electricity meters in the universe. The system is operated for many years, and massive electricity utilization data is accumulated. Through data analysis, effective electricity utilization information such as an electric energy meter operation error, an electricity utilization behavior mode of a user and the like is excavated, so that the potential of massive data can be developed, the operation cost can be greatly reduced, and decision support is provided for power grid companies.
However, in the mass data acquired by the electricity consumption information acquisition system, a large amount of various data are acquired from the real world, the quality of the original data is influenced by diversity, uncertainty and complexity, so that the acquired actual data are messy, have phenomena such as missing and abnormality, and do not meet the standard requirements of knowledge acquisition of a data mining tool in many cases. The traditional knowledge base triplet extraction model is limited by the sample scale, and the effect on the long-tail relation is difficult to meet the requirements of practical application and the requirements of low-voltage area management refinement.
Therefore, a knowledge base is required to be established for the related abnormal conditions so as to guide the maintenance, service life and the like of the electric energy meter, clean, concise and accurate data are provided, the excavation process is more effective and easier, and the excavation efficiency and accuracy are improved.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an abnormal metering point knowledge base construction method and system based on an LSTM end-to-end extraction algorithm.
The invention solves the technical problems by adopting the following technical scheme:
an abnormal metering point knowledge base construction method based on an LSTM end-to-end extraction algorithm comprises the following steps:
(1) Extracting abnormal metering point information in an electricity consumption information acquisition system;
(2) Based on the abnormal metering point information, calculating the knowledge information probability of the abnormal metering point through an LSTM network unit model to form a multidimensional knowledge tag;
(3) And extracting the formed multidimensional knowledge labels based on the bidirectional LSTM training network, establishing an abnormal metering point knowledge identification label aiming at the knowledge characteristic value with the maximum probability, and outputting a multidimensional abnormal metering point knowledge base.
And the abnormal metering point information comprises instantaneous oversrange metering point information, stable oversrange metering point information, suspected electricity stealing metering point information, wiring error metering point information, acquisition abnormal metering point information, clock error metering point information, transformer overload metering point information, user change relation error metering point information, transformer light load metering point information and acquisition abnormal information.
The instantaneous oversrange metering point information comprises field checking information and electricity user file information, the stable oversrange metering point information comprises field checking information and electricity user file information, the suspected electricity stealing metering point information comprises field checking information, operation error calculation information, voltage current information and power factor information, the wiring error metering point information comprises information such as reverse trend, abnormal phase sequence, reverse electric quantity and the like, the abnormal metering point information comprises daily freezing data, abnormal event information and 96 high-frequency acquisition 96 point voltage current data information, the clock error metering point information comprises daily freezing data and abnormal event information, the overload metering point information of the transformer comprises 96 point voltage current data, daily freezing data and electric energy meter specification data, the household transformation relation error metering point information comprises information such as load environment, electricity consumption curve, geographical position and the like, the mutual inductor light load metering point information comprises 96 point voltage current data, daily freezing data and electric energy meter specification data, the collector abnormal information comprises daily freezing data, 96 point voltage current data and electric energy meter file specification information.
Moreover, the LSTM network element model is
Where P (wj) represents the predictive probability of the j-th knowledge point.
The multidimensional abnormal metering point knowledge base comprises an instantaneous overscan metering point knowledge base, a stable overscan metering point knowledge base, a suspected electricity stealing metering point knowledge base, a wiring error metering point knowledge base, an abnormal metering point knowledge base, a clock error metering point knowledge base, a transformer overload metering point knowledge base, a user variable relation error metering point knowledge base, a transformer light load metering point knowledge base and a collector abnormal knowledge base.
An abnormal metering point knowledge base construction system based on LSTM end-to-end extraction algorithm comprises
The abnormal metering point information extraction module is used for extracting abnormal metering point information in the electricity consumption information acquisition system;
the abnormal metering point knowledge information probability calculation module is used for calculating the abnormal metering point knowledge information probability through the LSTM network unit model based on the abnormal metering point information to form a multidimensional knowledge tag;
the multidimensional abnormal metering point knowledge base construction module is used for extracting the formed multidimensional knowledge labels based on the bidirectional LSTM training network, establishing an abnormal metering point knowledge identification label aiming at the knowledge characteristic value with the maximum probability, and outputting the multidimensional abnormal metering point knowledge base.
And the abnormal metering point information comprises instantaneous oversrange metering point information, stable oversrange metering point information, suspected electricity stealing metering point information, wiring error metering point information, acquisition abnormal metering point information, clock error metering point information, transformer overload metering point information, user change relation error metering point information, transformer light load metering point information and acquisition abnormal information.
The instantaneous oversrange metering point information comprises field checking information and electricity user file information, the stable oversrange metering point information comprises field checking information and electricity user file information, the suspected electricity stealing metering point information comprises field checking information, operation error calculation information, voltage current information and power factor information, the wiring error metering point information comprises information such as reverse trend, abnormal phase sequence, reverse electric quantity and the like, the abnormal metering point information comprises daily freezing data, abnormal event information and 96 high-frequency acquisition 96 point voltage current data information, the clock error metering point information comprises daily freezing data and abnormal event information, the overload metering point information of the transformer comprises 96 point voltage current data, daily freezing data and electric energy meter specification data, the household transformation relation error metering point information comprises information such as load environment, electricity consumption curve, geographical position and the like, the mutual inductor light load metering point information comprises 96 point voltage current data, daily freezing data and electric energy meter specification data, the collector abnormal information comprises daily freezing data, 96 point voltage current data and electric energy meter file specification information.
Moreover, the LSTM network element model is
Where P (wj) represents the predictive probability of the j-th knowledge point.
The multidimensional abnormal metering point knowledge base comprises an instantaneous overscan metering point knowledge base, a stable overscan metering point knowledge base, a suspected electricity stealing metering point knowledge base, a wiring error metering point knowledge base, an abnormal metering point knowledge base, a clock error metering point knowledge base, a transformer overload metering point knowledge base, a user variable relation error metering point knowledge base, a transformer light load metering point knowledge base and a collector abnormal knowledge base.
The invention has the advantages and positive effects that:
according to the system for constructing the abnormal metering point knowledge base based on the LSTM end-to-end extraction algorithm, the traditional triplet knowledge extraction model is improved, the abnormal metering information of the long tail relation is extracted accurately based on the LSTM end-to-end extraction algorithm, information contained in rich samples of the head relation is effectively utilized, ten knowledge bases in the aspects of instantaneous oversrange, stable oversrange, suspected electricity larceny, wiring errors, abnormal collection, clock errors, transformer overload, household change relation errors, transformer light load, collector abnormality and the like are formed, the abnormality of metering points of the electric energy meter is effectively identified and calculated, and the power assistance makes accurate guidance on maintenance, service life and the like of the electric energy meter.
Drawings
FIG. 1 is a schematic block diagram of the present invention;
FIG. 2 is a schematic diagram of the LSTM knowledge probability computation model of the invention (where "< S >" and "</S >" represent the beginning and end of a sentence, respectively).
Detailed Description
Embodiments of the invention are described in further detail below with reference to the attached drawing figures:
step one: exception metering point information collection
And extracting abnormal metering point information in the electricity consumption information acquisition system.
Step two: based on the abnormal metering point information, calculating the knowledge information probability of the abnormal metering point through the LSTM network element model to form a multidimensional knowledge tag.
The LSTM language model uses previous word sequences to predict the probability of current outlier metric knowledge. After the input abnormal metering point information is mapped to the pre-trained word vector with fixed dimension (the word vector of "_NE_" is initially zero vector, but the word vector is updated in the training process), the abnormal metering point information is input into the LSTM model. The output of each LSTM unit is sent to a softmax classifier, and finally the knowledge point distribution of each piece of information in the current position word list is output:
wherein P (wj) represents the predictive probability of the j-th knowledge point in the question. The smaller LP (S) the higher the probability that statement S is satisfactory.
Further, aiming at the knowledge characteristic value with the maximum probability, an abnormal metering point knowledge identification tag is established, and a multidimensional abnormal metering knowledge point is output.
Step three: knowledge label extraction is carried out based on a bidirectional LSTM training network to form a multidimensional abnormal metering point knowledge base
Knowledge extraction is carried out on abnormal metering points of long-tail relations through a bidirectional LSTM training network, information contained in rich samples of head relations is effectively utilized, triples are extracted from unstructured texts, and annotation data are automatically constructed for each relation by utilizing weak supervision annotation ideas to form an abnormal metering point knowledge base.
1. Constructing instantaneous overscan metering point knowledge base
Based on the electric energy meter instantaneous oversrange abnormity diagnosis model, site check information fed back by a work order and electricity user file information, an instantaneous oversrange expert knowledge base is established, according to calculation data of the diagnosis model and instantaneous oversrange electricity utilization rules and characteristics, user electricity utilization behaviors are analyzed, users with suspected instantaneous oversrange abnormity are diagnosed, and electricity utilization time periods with suspected instantaneous oversrange of the electricity users are given. Meanwhile, the knowledge base is continuously perfected, enriched and optimized according to the field information fed back by the work order.
2. Construction of a stable overscan metering point knowledge base
And establishing a stable overscan expert knowledge base based on the electric energy meter stable overscan abnormality diagnosis model, the site check information fed back by the work order and the electricity user file information. And analyzing the electricity consumption behavior of the user according to the data calculated by the diagnosis model and the electricity consumption characteristics and rules of the stable overscan, and diagnosing the abnormal user suspected to be stable overscan.
One possible determination method is that the average value of the current is larger than Imax, and the absolute value of the calculation error of the electric energy meter exceeds a limit value, and then the electric energy meter is determined to be of a stable overscan abnormality type.
Meanwhile, the knowledge base is continuously perfected and optimized according to the field information fed back by the work order.
3. Construction of suspected electricity larceny metering point knowledge base
A knowledge base is established based on the verification information, the operation error calculation information, the voltage and current information, the power factor information and the like of the site. The knowledge base of suspected electricity theft is based on comprehensive analysis of various information, such as:
(1) Abnormal electric quantity:
when a user has a value which is not 0 for a long time, the user has negative growth, zero growth or abnormal growth, and the situation is possibly caused by electricity stealing;
(2) Line loss anomaly:
the line loss of the station area exceeds a threshold value or is compared with the line loss of the same period in the past year, and whether electricity theft possibly exists in the station area is judged in a combined mode;
(3) Three-phase imbalance analysis:
the fluctuation of the three-phase unbalance rate can also be characterized as an electricity stealing phenomenon;
(4) Abnormal event analysis:
based on the obtained abnormal events of the metering point, such as the opening of the cover of the electric energy meter and the opening and closing of the metering door, the abnormal events related to the electricity stealing report that the electricity stealing is possible.
And according to the conditions and the error analysis result, establishing a suspected electricity stealing expert knowledge base. And a diagnosis basis is provided for the suspected electricity larceny conclusion.
4. Construction of a knowledge base of wiring error metering points
According to theoretical deduction in the electrical aspect, the influence on the metering of the ammeter under different wiring conditions is obtained, meanwhile, abnormal events reported by wiring error metering points, such as reverse flow, abnormal phase sequence, abnormal reverse electric quantity and the like, are recorded, and can be used for association analysis of the abnormal events in the later period, so that the error wiring judgment accuracy is improved. And (3) sorting the related content into a wiring error metering point knowledge base, and diagnosing whether wiring errors exist or not through input given by a wiring error abnormality diagnosis model.
5. Constructing a knowledge base for acquiring abnormal metering points
Based on daily freezing data, abnormal event information and high-frequency acquisition 96-point voltage and current data information of the electric energy meter, an expert knowledge base for acquiring abnormal metering points is constructed. The phenomenon that the electricity consumption data cannot be reported occurs at the abnormal collecting metering point, the phenomenon is reflected in the daily freezing and voltage and current data, the data of some data points are null values, the statistical analysis that the data points are null values is carried out on the ammeter, the collecting success rate of the ammeter is calculated, and therefore the abnormal collecting metering point is found. In addition, the method can also carry out comprehensive judgment by means of the collected abnormal information provided by the abnormal event so as to improve the success rate of diagnosis.
After the diagnosis result is given, the diagnosis logic for collecting the abnormality can be continuously perfected and optimized according to the result of on-site check feedback.
6. Construction of knowledge base of clock error metering point
Based on the daily freezing data and abnormal event information of the electric energy meter, a clock error metering point expert knowledge base is established. On the one hand, the knowledge base can diagnose whether the clock error occurs by utilizing the abnormality reported by the electric energy meter when the clock error occurs, and on the other hand, when the clock error occurs, the daily freezing data can shift, the electricity consumption of a certain table can be tried to be translated, and whether the line loss is greatly improved or not is detected, so that the clock error is diagnosed.
The knowledge base stores metering points where problems occur and meters error information for the invocation of the error analysis module.
7. Constructing an overload metering point knowledge base of a transformer
And (3) high-frequency acquisition of 96-point voltage and current data and daily freezing data based on the electric energy meter and specification data of the electric energy meter are used for constructing a transformer overload metering point knowledge base. And estimating daily average working current based on the daily freezing data and the 96-point current data, and judging that the transformer is overloaded if the average current is larger than the maximum current of the electric energy meter.
And the site checking work order feeds back abnormal results to be classified and put in storage so as to facilitate later automatic comparison and discrimination.
8. Construction of user variable relation error metering point knowledge base
The disorder of the change relation of the station area causes line loss abnormality, influences error calculation and analysis, and is unfavorable for the data management work of the station area. The information of load environment, electricity consumption curve, geographical position and the like of the metering points with wrong user variable relations is recorded, a user variable relation metering point knowledge base is built, relevant judging indexes can be introduced during the analysis of the platform region errors, the data are preprocessed firstly, and the calculation precision of the model errors is greatly improved. Meanwhile, according to the user variable relation error metering point knowledge base, a comparison basis can be provided for user variable relation diagnosis and treatment of similar metering points.
9. Constructing a knowledge base of light-load metering points of a transformer
And (3) high-frequency acquisition of 96-point voltage and current data and daily freezing data based on the electric energy meter and specification data of the electric energy meter are used for constructing a transformer light-load metering point knowledge base. And estimating daily average working current based on daily freezing data and 96-point current data, setting a light load threshold value, and judging that the transformer is light load if the average current is smaller than the rated current setting threshold value of the electric energy meter.
And the site checking work order feeds back abnormal results to be classified and put in storage so as to facilitate later automatic comparison and discrimination.
10. Constructing an abnormal knowledge base of a collector
And constructing an abnormal expert knowledge base of the collector based on daily freezing data of the electric energy meter, high-frequency collection of 96-point voltage and current data information and ammeter file information. The abnormal situation of the collector can lead to the phenomenon that electricity consumption data of the electric meters in batches cannot be reported, the phenomenon that data of data points of a plurality of meters are null appears in daily freezing and voltage current data is reflected, statistical analysis of the null data points of adjacent electric meters under a platform area is carried out, and the acquisition success rate of the electric meters under the area is calculated, so that the abnormal situation of the collector is found.
After the diagnosis result is given, the diagnosis logic of the collector abnormality can be continuously perfected and optimized according to the result of on-site check feedback.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (2)
1. A method for constructing an abnormal metering point knowledge base based on an LSTM end-to-end extraction algorithm is characterized by comprising the following steps: the method comprises the following steps:
(1) Extracting abnormal metering point information in an electricity consumption information acquisition system;
(2) Based on the abnormal metering point information, calculating the knowledge information probability of the abnormal metering point through an LSTM network unit model to form a multidimensional knowledge tag;
(3) Extracting the formed multidimensional knowledge labels based on a bidirectional LSTM training network, establishing an abnormal metering point knowledge identification label aiming at the knowledge characteristic value with the maximum probability, and outputting a multidimensional abnormal metering point knowledge base;
the abnormal metering point information comprises instantaneous oversrange metering point information, stable oversrange metering point information, suspected electricity stealing metering point information, wiring error metering point information, acquisition abnormal metering point information, clock error metering point information, transformer overload metering point information, household change relation error metering point information, transformer light load metering point information and acquisition device abnormal information;
the instantaneous overscan metering point information comprises field checking information and electricity user file information, the stable overscan metering point information comprises field checking information and electricity user file information, the suspected electricity stealing metering point information comprises field checking information, operation error calculation information, voltage current information and power factor information, the wiring error metering point information comprises information such as reverse trend, abnormal phase sequence, reverse electric quantity and the like, the abnormal metering point collecting information comprises daily freezing data, abnormal event information and 96-point high-frequency voltage current collecting data information, the clock error metering point information comprises daily freezing data and abnormal event information, the transformer overload metering point information comprises 96-point voltage current data, daily freezing data and electric energy meter specification data, the household variable relation error metering point information comprises information such as load environment, electricity consumption curve, geographical position and the like, the transformer light load metering point information comprises 96-point voltage current data, daily freezing data and electric energy meter specification data, and the collector abnormal information comprises daily freezing data, 96-point voltage current data and electric energy meter specification data;
the LSTM network element model is
Wherein P (wj) represents the predictive probability of the jth knowledge point;
the multidimensional abnormal metering point knowledge base comprises an instantaneous oversrange metering point knowledge base, a stable oversrange metering point knowledge base, a suspected electricity stealing metering point knowledge base, a wiring error metering point knowledge base, an abnormal metering point knowledge base, a clock error metering point knowledge base, a transformer overload metering point knowledge base, a user variable relation error metering point knowledge base, a transformer light load metering point knowledge base and a collector abnormal knowledge base.
2. An abnormal metering point knowledge base construction system based on an LSTM end-to-end extraction algorithm is characterized in that: comprising
The abnormal metering point information extraction module is used for extracting abnormal metering point information in the electricity consumption information acquisition system;
the abnormal metering point knowledge information probability calculation module is used for calculating the abnormal metering point knowledge information probability through the LSTM network unit model based on the abnormal metering point information to form a multidimensional knowledge tag;
the multidimensional abnormal metering point knowledge base construction module is used for extracting the formed multidimensional knowledge labels based on the bidirectional LSTM training network, establishing an abnormal metering point knowledge identification label aiming at the knowledge characteristic value with the maximum probability, and outputting a multidimensional abnormal metering point knowledge base;
the abnormal metering point information comprises instantaneous oversrange metering point information, stable oversrange metering point information, suspected electricity stealing metering point information, wiring error metering point information, acquisition abnormal metering point information, clock error metering point information, transformer overload metering point information, household change relation error metering point information, transformer light load metering point information and acquisition device abnormal information;
the instantaneous overscan metering point information comprises field checking information and electricity user file information, the stable overscan metering point information comprises field checking information and electricity user file information, the suspected electricity stealing metering point information comprises field checking information, operation error calculation information, voltage current information and power factor information, the wiring error metering point information comprises information such as reverse trend, abnormal phase sequence, reverse electric quantity and the like, the abnormal metering point collecting information comprises daily freezing data, abnormal event information and 96-point high-frequency voltage current collecting data information, the clock error metering point information comprises daily freezing data and abnormal event information, the transformer overload metering point information comprises 96-point voltage current data, daily freezing data and electric energy meter specification data, the household variable relation error metering point information comprises information such as load environment, electricity consumption curve, geographical position and the like, the transformer light load metering point information comprises 96-point voltage current data, daily freezing data and electric energy meter specification data, and the collector abnormal information comprises daily freezing data, 96-point voltage current data and electric energy meter specification data;
the LSTM network element model is
Wherein P (wj) represents the predictive probability of the jth knowledge point;
the multidimensional abnormal metering point knowledge base comprises an instantaneous oversrange metering point knowledge base, a stable oversrange metering point knowledge base, a suspected electricity stealing metering point knowledge base, a wiring error metering point knowledge base, an abnormal metering point knowledge base, a clock error metering point knowledge base, a transformer overload metering point knowledge base, a user variable relation error metering point knowledge base, a transformer light load metering point knowledge base and a collector abnormal knowledge base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911238633.5A CN110968703B (en) | 2019-12-06 | 2019-12-06 | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911238633.5A CN110968703B (en) | 2019-12-06 | 2019-12-06 | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110968703A CN110968703A (en) | 2020-04-07 |
| CN110968703B true CN110968703B (en) | 2024-01-02 |
Family
ID=70033120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911238633.5A Active CN110968703B (en) | 2019-12-06 | 2019-12-06 | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110968703B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113469253A (en) * | 2021-07-02 | 2021-10-01 | 河海大学 | Electricity stealing detection method based on triple twin network |
| CN115292387B (en) * | 2022-08-18 | 2023-05-23 | 北京志翔科技股份有限公司 | Multi-dimensional data analysis-based energy source overscan use monitoring method |
| CN115358347B (en) * | 2022-09-30 | 2023-01-31 | 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 |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105915398A (en) * | 2016-06-24 | 2016-08-31 | 广西电网有限责任公司南宁供电局 | Rapid fault detection and power recovery system based on rural power network, and concentrator detection method thereof |
| CN106161138A (en) * | 2016-06-17 | 2016-11-23 | 贵州电网有限责任公司贵阳供电局 | A kind of intelligence automatic gauge method and device |
| CN106199494A (en) * | 2016-07-25 | 2016-12-07 | 国网上海市电力公司 | A kind of intelligent diagnosis system based on metering device fault |
| CN106772205A (en) * | 2016-11-30 | 2017-05-31 | 广东电网有限责任公司电力科学研究院 | A kind of automatic power-measuring system terminal unit exception monitoring method and device |
| CN107703383A (en) * | 2017-09-21 | 2018-02-16 | 国网上海市电力公司 | A kind of method for building up of information acquisition system fault diagnosis knowledge base |
| CN108336725A (en) * | 2016-12-16 | 2018-07-27 | 泰豪软件股份有限公司 | The management of dispatching of power netwoks monitoring of tools and intelligent analysis system |
| CN109858679A (en) * | 2018-12-30 | 2019-06-07 | 国网浙江省电力有限公司 | A kind of opposing electricity-stealing for the man-machine object of combination checks monitoring system and its working method |
| CN109886475A (en) * | 2019-01-24 | 2019-06-14 | 广西电网有限责任公司电力科学研究院 | The information security Situation Awareness System of metering automation system based on AI |
| CN109934337A (en) * | 2019-03-14 | 2019-06-25 | 哈尔滨工业大学 | A kind of detection method of the spacecraft telemetry exception based on integrated LSTM |
| CN110009525A (en) * | 2019-04-02 | 2019-07-12 | 国网新疆电力有限公司电力科学研究院 | Power information acquisition system and application method |
| CN110046145A (en) * | 2019-04-02 | 2019-07-23 | 国网安徽省电力有限公司 | Expert intelligence Analysis Service platform based on electric flux big data research |
| CN110109771A (en) * | 2019-05-07 | 2019-08-09 | 北京恒泰实达科技股份有限公司 | The abnormal key diagnostic method of a kind of area's line loss |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8473065B2 (en) * | 2007-05-17 | 2013-06-25 | Jeffrey A. Matos | Implantable medical device which may be controlled from central station |
-
2019
- 2019-12-06 CN CN201911238633.5A patent/CN110968703B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106161138A (en) * | 2016-06-17 | 2016-11-23 | 贵州电网有限责任公司贵阳供电局 | A kind of intelligence automatic gauge method and device |
| CN105915398A (en) * | 2016-06-24 | 2016-08-31 | 广西电网有限责任公司南宁供电局 | Rapid fault detection and power recovery system based on rural power network, and concentrator detection method thereof |
| CN106199494A (en) * | 2016-07-25 | 2016-12-07 | 国网上海市电力公司 | A kind of intelligent diagnosis system based on metering device fault |
| CN106772205A (en) * | 2016-11-30 | 2017-05-31 | 广东电网有限责任公司电力科学研究院 | A kind of automatic power-measuring system terminal unit exception monitoring method and device |
| CN108336725A (en) * | 2016-12-16 | 2018-07-27 | 泰豪软件股份有限公司 | The management of dispatching of power netwoks monitoring of tools and intelligent analysis system |
| CN107703383A (en) * | 2017-09-21 | 2018-02-16 | 国网上海市电力公司 | A kind of method for building up of information acquisition system fault diagnosis knowledge base |
| CN109858679A (en) * | 2018-12-30 | 2019-06-07 | 国网浙江省电力有限公司 | A kind of opposing electricity-stealing for the man-machine object of combination checks monitoring system and its working method |
| CN109886475A (en) * | 2019-01-24 | 2019-06-14 | 广西电网有限责任公司电力科学研究院 | The information security Situation Awareness System of metering automation system based on AI |
| CN109934337A (en) * | 2019-03-14 | 2019-06-25 | 哈尔滨工业大学 | A kind of detection method of the spacecraft telemetry exception based on integrated LSTM |
| CN110009525A (en) * | 2019-04-02 | 2019-07-12 | 国网新疆电力有限公司电力科学研究院 | Power information acquisition system and application method |
| CN110046145A (en) * | 2019-04-02 | 2019-07-23 | 国网安徽省电力有限公司 | Expert intelligence Analysis Service platform based on electric flux big data research |
| CN110109771A (en) * | 2019-05-07 | 2019-08-09 | 北京恒泰实达科技股份有限公司 | The abnormal key diagnostic method of a kind of area's line loss |
Non-Patent Citations (1)
| Title |
|---|
| 罗慧，刘梅招，周钰山.基于长短期记忆网络的智能用电数据甄别方法.广东电力.2019,第32卷(第2期),第47-54. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110968703A (en) | 2020-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108375715B (en) | Power distribution network line fault risk day prediction method and system | |
| Zhu et al. | Time series shapelet classification based online short-term voltage stability assessment | |
| CN106054104B (en) | A kind of intelligent electric meter failure real-time predicting method based on decision tree | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN105677791B (en) | For analyzing the method and system of the operation data of wind power generating set | |
| Kang et al. | Big data analytics in China's electric power industry: modern information, communication technologies, and millions of smart meters | |
| CN111103565B (en) | Data transformation method and system based on intelligent electric energy meter metering error analysis | |
| CN108537394B (en) | Real-time safety early warning method and device for smart power grid | |
| CN110727662A (en) | Low-voltage transformer area user phase identification method and system based on correlation analysis | |
| CN111259947A (en) | Power system fault early warning method and system based on multi-mode learning | |
| CN105759201A (en) | High voltage circuit breaker self-diagnosis method based on abnormal sample identification | |
| CN109635950B (en) | Electric energy meter running state monitoring method based on genetic algorithm and community clustering | |
| CN111612149A (en) | Main network line state detection method, system and medium based on decision tree | |
| CN111612019A (en) | Method for identifying and analyzing fault abnormality of intelligent electric meter based on big data model | |
| CN112508254B (en) | Method for determining investment prediction data of transformer substation engineering project | |
| CN112418662A (en) | Power distribution network operation reliability analysis method using artificial neural network | |
| CN116879672A (en) | Intelligent identification method for total fault of area based on time convolution network | |
| CN115186935B (en) | Electromechanical device nonlinear fault prediction method and system | |
| CN115470854A (en) | Information system fault classification method and classification system | |
| CN114139408A (en) | Power transformer health state assessment method | |
| CN113537770A (en) | Decision tree configuration life prediction method and system based on cloud computing | |
| CN109871998B (en) | Power distribution network line loss rate prediction method and device based on expert sample library | |
| CN112560908A (en) | Cloud-end cooperative load identification system and method | |
| CN110261693A (en) | A kind of online thermal test method and system based on stable state sampling technique | |
| CN113872200B (en) | Medium-voltage distribution network power failure event diagnosis and identification method, system and storage medium |
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 |