CN116701947A - Method and system for detecting electricity stealing behavior - Google Patents
Method and system for detecting electricity stealing behavior Download PDFInfo
- Publication number
- CN116701947A CN116701947A CN202310963438.9A CN202310963438A CN116701947A CN 116701947 A CN116701947 A CN 116701947A CN 202310963438 A CN202310963438 A CN 202310963438A CN 116701947 A CN116701947 A CN 116701947A
- Authority
- CN
- China
- Prior art keywords
- data
- preset period
- abnormal
- current
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 197
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000002159 abnormal effect Effects 0.000 claims abstract description 216
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 230000005856 abnormality Effects 0.000 claims description 19
- 238000003062 neural network model Methods 0.000 claims description 9
- 230000007547 defect Effects 0.000 claims description 6
- 230000006399 behavior Effects 0.000 abstract description 39
- 238000005070 sampling Methods 0.000 description 24
- 230000005612 types of electricity Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000007123 defense Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000005516 engineering 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
- 238000012545 processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R22/00—Arrangements for measuring time integral of electric power or current, e.g. electricity meters
- G01R22/06—Arrangements for measuring time integral of electric power or current, e.g. electricity meters by electronic methods
- G01R22/061—Details of electronic electricity meters
- G01R22/066—Arrangements for avoiding or indicating fraudulent use
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
Abstract
The application discloses a method and a system for detecting electricity stealing behavior, wherein the method comprises the following steps: obtaining abnormal data of a target platform area in a preset period, wherein the abnormal data comprise platform area line loss data, voltage abnormal data, current abnormal data, abnormal electricity consumption data and electric quantity abnormal data; inputting abnormal electricity consumption data into a parameter model, and obtaining the electricity stealing type output by the parameter model; inputting the line loss data, the voltage abnormal data, the current abnormal data and the electric quantity abnormal data of the transformer area into an identification model corresponding to the electricity stealing type; and judging whether the target station area has electricity stealing behaviors according to the output result of the identification model. According to the method and the system for detecting the electricity stealing behavior, through the technical scheme, when specific electricity stealing behavior detection is carried out, the possible electricity stealing type is judged, then the model corresponding to the electricity stealing type is selected for recognition, the recognition precision can be effectively improved, and the model training is more convenient.
Description
Technical Field
The application relates to the technical field of intelligent electric technology, in particular to a method and a system for detecting electricity stealing behavior.
Background
The electricity stealing behavior aims at illegally occupying electric energy and aims at not paying or less paying electricity fees, and adopts illegal means to do not measure or less measure electricity consumption. In the prior art, a Chinese patent with application number 201911313337.7 is disclosed, which discloses an anti-electricity-stealing method and system, the method comprises the following steps: screening out an electricity stealing sample, classifying the existing electricity stealing category, and marking the existing electricity stealing sample and a normal sample by category; removing normal samples to form a suspected electricity larceny sample set, and marking the class; constructing a suspected electricity larceny identification model based on a GRU algorithm aiming at the suspected electricity larceny sample set; inputting the data of the suspected electricity larceny sample set into a suspected electricity larceny identification model, and outputting a suspected electricity larceny sample and a suspected normal sample of two classifications; calculating the identification accuracy rate of the suspected electricity larceny identification model according to the output result of the suspected electricity larceny identification model and the class mark of the suspected electricity larceny sample set, and carrying out feedback adjustment on model parameters; determining an anti-electricity-stealing defense simulation model of the self-adaptive class identification according to the adjusted model parameters; and carrying out anti-electricity-theft detection on the user electricity utilization real-time data by using the anti-electricity-theft defense simulation model.
However, the electricity larceny behavior is various, and it is difficult to effectively distinguish whether the abnormality of the data is caused by electricity larceny or load variation by a single anti-electricity larceny defense simulation model.
Disclosure of Invention
In order to at least overcome the above-mentioned shortcomings in the prior art, the present application aims to provide a method and a system for detecting fraudulent use of electricity.
In a first aspect, an embodiment of the present application provides a method for detecting an electricity theft behavior, including:
obtaining abnormal data of a target platform region in a preset period, wherein the abnormal data comprise platform region line loss data, voltage abnormal data, current abnormal data, abnormal electricity consumption data and electric quantity abnormal data;
inputting the abnormal electricity consumption data into a parameter model, and obtaining the electricity stealing type output by the parameter model;
inputting the line loss data, the voltage abnormal data, the current abnormal data and the electric quantity abnormal data of the transformer area into an identification model corresponding to the electricity stealing type;
judging whether the target platform area has electricity stealing behavior according to the output result of the identification model.
When the embodiment of the application is implemented, the end equipment of the target platform area is configured to acquire the abnormal data, and sampling statistics is required to be carried out on the acquired abnormal data in a preset period; the inventor finds that the voltage abnormal data, the current abnormal data and the electric quantity abnormal data in the abnormal data have stronger correlation, the line loss data of the transformer area have stronger randomness, and the line loss data of the transformer area can influence the voltage abnormal data, the current abnormal data and the electric quantity abnormal data; the abnormal electricity utilization data mainly comprise an electric energy meter cover opening record, a metering door opening and closing condition, a constant magnetic field interference condition, an electric quantity differential abnormal condition and a power failure event condition, are independent of other abnormal data, and can cause the change of the abnormal electricity utilization data as long as the abnormal electricity utilization behavior is involved, so that in the embodiment of the application, the possible existing electricity utilization behavior is initially classified through a pre-trained parameter model based on the abnormal electricity utilization data, and then the further accurate identification is carried out based on other abnormal data through a model corresponding to the electricity utilization type, so that the accuracy of the identification of the electricity utilization behavior can be effectively improved.
Unlike the data statistics method of all data in the prior art, the embodiment of the application can accurately identify each type of electricity stealing behavior. By way of example, the electricity stealing behavior mentioned in the embodiments of the present application mainly includes: under-voltage electricity stealing, under-current electricity stealing, phase-shifting electricity stealing, spread spectrum electricity stealing and meter-less electricity stealing, which generally need to operate an ammeter box and the like, so that the possible types of electricity stealing behaviors can be effectively identified through abnormal electricity utilization data, namely the types of electricity stealing output according to a parameter model are under-voltage electricity stealing, under-current electricity stealing, phase-shifting electricity stealing, spread spectrum electricity stealing or meter-less electricity stealing, and then the identification model corresponding to the type of electricity stealing is selected to accurately identify the electricity stealing behavior. According to the technical scheme, when specific electricity stealing behavior detection is carried out, the possible electricity stealing type is judged, and then the model corresponding to the electricity stealing type is selected for recognition, so that the recognition accuracy can be effectively improved, and the model training is more convenient.
In one possible implementation manner, obtaining the station line loss data of the target station in the preset period includes:
acquiring three-phase ammeter data of the target station area; the three-phase ammeter data comprise three-phase ammeter voltage data, three-phase ammeter current data and three-phase ammeter apparent power data;
in the preset period, adding one line loss parameter when any one of the three-phase meter voltage data, the three-phase meter current data and the three-phase meter apparent power data exceeds a corresponding threshold value of the target station area master station; the line loss parameter returns to zero when the preset period starts;
and taking the line loss parameter at the end of the preset period as the station area line loss data of the target station area in the preset period.
In one possible implementation manner, acquiring the voltage anomaly data of the target station area in the preset period includes:
acquiring the voltage phase failure condition, the voltage out-of-limit condition and the voltage balance condition of the target platform area;
in the preset period, when the voltage phase failure, voltage out-of-limit or voltage unbalance occurs in the target platform area, adding one voltage parameter; the voltage parameter returns to zero when the preset period starts;
and taking the voltage parameter at the end of the preset period as voltage abnormal data of the target platform area in the preset period.
In one possible implementation manner, obtaining current anomaly data of the target station area in a preset period includes:
acquiring the current loss condition, the current reverse condition and the current balance condition of the target station area;
in the preset period, when the current loss flow, the current direction or the current imbalance occurs in the target station area, adding one to the current parameter; the current parameter returns to zero when the preset period starts;
and taking the current parameter at the end of the preset period as current abnormal data of the target area in the preset period.
In one possible implementation manner, acquiring abnormal electricity utilization data of the target platform area in a preset period includes:
acquiring an electric energy meter cover opening record, a metering door opening and closing condition, a constant magnetic field interference condition, an electric quantity differential abnormal condition and a power failure event condition of the target platform area;
in the preset period, when the target platform area is abnormal in terms of electric energy meter uncovering, metering gate opening, constant magnetic field interference, electric quantity differential motion or power failure event, adding one to the electricity consumption parameter; the electricity consumption parameter returns to zero when the preset period starts;
and taking the electricity consumption parameter at the end of the preset period as abnormal electricity consumption data of the target station area in the preset period.
In one possible implementation manner, acquiring the abnormal data of the electric quantity of the target platform area in the preset period includes:
acquiring the requirement capacity exceeding condition, the load capacity exceeding condition, the current overcurrent condition, the load continuous lower limit exceeding condition and the power factor abnormality condition of the target station area;
in the preset period, when the target area has the defects of excessive capacity of the required quantity, excessive capacity of the load, overcurrent of the current, continuous exceeding of the lower limit of the load and abnormal power factor, adding one to the electric quantity parameter; the electric quantity parameter returns to zero when the preset period starts;
and taking the electric quantity parameter at the end of the preset period as electric quantity abnormal data of the target platform area in the preset period.
In one possible implementation manner, the construction of the parametric model and the identification model includes:
obtaining an abnormal data sample; the abnormal data samples are used for acquiring a plurality of platform area line loss data, voltage abnormal data, current abnormal data, abnormal electricity consumption data and electric quantity abnormal data of the preset period under different electricity stealing types;
constructing different neural network models for each electricity stealing type, and carrying out data association training on the abnormal electricity utilization data in the abnormal data sample and the corresponding electricity stealing condition to form a parameter model; the data input of the parameter model is abnormal electricity utilization data, and the data output of the parameter model is an electricity larceny type corresponding to possible electricity larceny behavior;
training the neural network model by taking the line loss data, the voltage abnormal data, the current abnormal data and the electric quantity abnormal data of the transformer area in the abnormal data sample as input data of the neural network model corresponding to the electricity stealing type to generate a plurality of judgment models; each judgment model corresponds to one electricity stealing type, the input data of the judgment models are data of line loss of a transformer area, voltage abnormal data, current abnormal data and electric quantity abnormal data, and the data output of the judgment models are in accordance or not in accordance;
and forming a plurality of judgment model forming model groups as the identification models.
In a second aspect, an embodiment of the present application further provides a system for detecting electricity theft behavior, including:
an acquisition unit configured to acquire abnormal data of a target station area within a preset period, the abnormal data including station area line loss data, voltage abnormal data, current abnormal data, abnormal electricity consumption data and electric quantity abnormal data;
the model selecting unit is configured to input the abnormal electricity consumption data into a parametric model and acquire the electricity stealing type output by the parametric model;
the identification unit is configured to input the transformer area line loss data, the voltage abnormality data, the current abnormality data and the electric quantity abnormality data into an identification model corresponding to the electricity stealing type;
and the judging unit is configured to judge whether the electricity stealing behavior exists in the target platform region according to the output result of the identification model.
In one possible implementation, the acquisition unit is further configured to:
acquiring three-phase ammeter data of the target station area; the three-phase ammeter data comprise three-phase ammeter voltage data, three-phase ammeter current data and three-phase ammeter apparent power data;
in the preset period, adding one line loss parameter when any one of the three-phase meter voltage data, the three-phase meter current data and the three-phase meter apparent power data exceeds a corresponding threshold value of the target station area master station; the line loss parameter returns to zero when the preset period starts;
taking the line loss parameter at the end of the preset period as the station area line loss data of the target station area in the preset period;
acquiring the voltage phase failure condition, the voltage out-of-limit condition and the voltage balance condition of the target platform area;
in the preset period, when the voltage phase failure, voltage out-of-limit or voltage unbalance occurs in the target platform area, adding one voltage parameter; the voltage parameter returns to zero when the preset period starts;
and taking the voltage parameter at the end of the preset period as voltage abnormal data of the target platform area in the preset period.
In one possible implementation, the acquisition unit is further configured to:
acquiring the current loss condition, the current reverse condition and the current balance condition of the target station area;
in the preset period, when the current loss flow, the current direction or the current imbalance occurs in the target station area, adding one to the current parameter; the current parameter returns to zero when the preset period starts;
taking the current parameter at the end of the preset period as current abnormal data of the target station area in the preset period;
acquiring an electric energy meter cover opening record, a metering door opening and closing condition, a constant magnetic field interference condition, an electric quantity differential abnormal condition and a power failure event condition of the target platform area;
in the preset period, when the target platform area is abnormal in terms of electric energy meter uncovering, metering gate opening, constant magnetic field interference, electric quantity differential motion or power failure event, adding one to the electricity consumption parameter; the electricity consumption parameter returns to zero when the preset period starts;
taking the electricity consumption parameter at the end of the preset period as abnormal electricity consumption data of the target station area in the preset period;
acquiring the requirement capacity exceeding condition, the load capacity exceeding condition, the current overcurrent condition, the load continuous lower limit exceeding condition and the power factor abnormality condition of the target station area;
in the preset period, when the target area has the defects of excessive capacity of the required quantity, excessive capacity of the load, overcurrent of the current, continuous exceeding of the lower limit of the load and abnormal power factor, adding one to the electric quantity parameter; the electric quantity parameter returns to zero when the preset period starts;
and taking the electric quantity parameter at the end of the preset period as electric quantity abnormal data of the target platform area in the preset period.
Compared with the prior art, the application has the following advantages and beneficial effects:
according to the method and the system for detecting the electricity stealing behavior, through the technical scheme, when specific electricity stealing behavior detection is carried out, the possible electricity stealing type is judged, then the model corresponding to the electricity stealing type is selected for recognition, the recognition precision can be effectively improved, and the model training is more convenient.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings:
FIG. 1 is a flow chart of steps of a method according to an embodiment of the present application;
fig. 2 is a schematic diagram of a system architecture according to an embodiment of the application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for the purpose of illustration and description only and are not intended to limit the scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this disclosure, illustrates operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Furthermore, one or more other operations may be added to or removed from the flow diagrams by those skilled in the art under the direction of the present disclosure.
In addition, the described embodiments are only some, but not all, embodiments of the application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
Referring to fig. 1 in combination, a flow chart of a method for detecting electricity theft behavior according to an embodiment of the present application may be applied to an electricity theft behavior detection system in fig. 2, and further, the method for detecting electricity theft behavior may specifically include the following descriptions of steps S1 to S4.
S1: obtaining abnormal data of a target platform region in a preset period, wherein the abnormal data comprise platform region line loss data, voltage abnormal data, current abnormal data, abnormal electricity consumption data and electric quantity abnormal data;
s2: inputting the abnormal electricity consumption data into a parameter model, and obtaining the electricity stealing type output by the parameter model;
s3: inputting the line loss data, the voltage abnormal data, the current abnormal data and the electric quantity abnormal data of the transformer area into an identification model corresponding to the electricity stealing type;
s4: judging whether the target platform area has electricity stealing behavior according to the output result of the identification model.
When the embodiment of the application is implemented, the end equipment of the target platform area is configured to acquire the abnormal data, and sampling statistics is required to be carried out on the acquired abnormal data in a preset period; the inventor finds that the voltage abnormal data, the current abnormal data and the electric quantity abnormal data in the abnormal data have stronger correlation, the line loss data of the transformer area have stronger randomness, and the line loss data of the transformer area can influence the voltage abnormal data, the current abnormal data and the electric quantity abnormal data; the abnormal electricity utilization data mainly comprise an electric energy meter cover opening record, a metering door opening and closing condition, a constant magnetic field interference condition, an electric quantity differential abnormal condition and a power failure event condition, are independent of other abnormal data, and can cause the change of the abnormal electricity utilization data as long as the abnormal electricity utilization behavior is involved, so that in the embodiment of the application, the possible existing electricity utilization behavior is initially classified through a pre-trained parameter model based on the abnormal electricity utilization data, and then the further accurate identification is carried out based on other abnormal data through a model corresponding to the electricity utilization type, so that the accuracy of the identification of the electricity utilization behavior can be effectively improved.
Unlike the data statistics method of all data in the prior art, the embodiment of the application can accurately identify each type of electricity stealing behavior. By way of example, the electricity stealing behavior mentioned in the embodiments of the present application mainly includes: under-voltage electricity stealing, under-current electricity stealing, phase-shifting electricity stealing, spread spectrum electricity stealing and meter-less electricity stealing, which generally need to operate an ammeter box and the like, so that the possible types of electricity stealing behaviors can be effectively identified through abnormal electricity utilization data, namely the types of electricity stealing output according to a parameter model are under-voltage electricity stealing, under-current electricity stealing, phase-shifting electricity stealing, spread spectrum electricity stealing or meter-less electricity stealing, and then the identification model corresponding to the type of electricity stealing is selected to accurately identify the electricity stealing behavior. According to the technical scheme, when specific electricity stealing behavior detection is carried out, the possible electricity stealing type is judged, and then the model corresponding to the electricity stealing type is selected for recognition, so that the recognition accuracy can be effectively improved, and the model training is more convenient.
In one possible implementation manner, obtaining the station line loss data of the target station in the preset period includes:
acquiring three-phase ammeter data of the target station area; the three-phase ammeter data comprise three-phase ammeter voltage data, three-phase ammeter current data and three-phase ammeter apparent power data;
in the preset period, adding one line loss parameter when any one of the three-phase meter voltage data, the three-phase meter current data and the three-phase meter apparent power data exceeds a corresponding threshold value of the target station area master station; the line loss parameter returns to zero when the preset period starts;
and taking the line loss parameter at the end of the preset period as the station area line loss data of the target station area in the preset period.
When the embodiment of the application is implemented, three-phase meter voltage data, three-phase meter current data and three-phase meter apparent power data are acquired, the sampling frequency of 1 minute can be adopted, and when the three-phase meter voltage data exceeds the corresponding threshold value of the main station of the target station area during each sampling, the line loss parameter is increased by 1; similarly, when the current data of the three-phase meter exceeds the corresponding threshold value of the master station of the target area, the line loss parameter is increased by 1, and when the apparent power data of the three-phase meter exceeds the corresponding threshold value of the master station of the target area, the line loss parameter is increased by 1; the above data did not exceed 0, and both the uncalculated and uncaptured were noted 0.
In one possible implementation manner, acquiring the voltage anomaly data of the target station area in the preset period includes:
acquiring the voltage phase failure condition, the voltage out-of-limit condition and the voltage balance condition of the target platform area;
in the preset period, when the voltage phase failure, voltage out-of-limit or voltage unbalance occurs in the target platform area, adding one voltage parameter; the voltage parameter returns to zero when the preset period starts;
and taking the voltage parameter at the end of the preset period as voltage abnormal data of the target platform area in the preset period.
When the embodiment of the application is implemented, the sampling frequency of 15 minutes can be adopted for obtaining the voltage open-phase condition, the voltage out-of-limit condition and the voltage balance condition, and when sampling is carried out each time, if the voltage open-phase occurs, the voltage parameter is added with 1, and the accumulation is not carried out before the end of the current voltage open-phase; similarly, if the voltage is out of limit during each sampling, the voltage parameter is added with 1, and no accumulation is carried out before the end of the current voltage out of limit; the voltage variable is incremented by 1 and accumulated for each sampling if a voltage imbalance occurs. The above data did not exceed 0, and both the uncalculated and uncaptured were noted 0.
In one possible implementation manner, obtaining current anomaly data of the target station area in a preset period includes:
acquiring the current loss condition, the current reverse condition and the current balance condition of the target station area;
in the preset period, when the current loss flow, the current direction or the current imbalance occurs in the target station area, adding one to the current parameter; the current parameter returns to zero when the preset period starts;
and taking the current parameter at the end of the preset period as current abnormal data of the target area in the preset period.
When the embodiment of the application is implemented, the sampling frequency of 15 minutes can be adopted for acquiring the current loss condition, the current reversal condition and the current balance condition, and when each sampling is carried out, the current parameter is added with 1 if the current loss occurs, and the current loss is not accumulated before the current loss is ended; likewise, the current parameter is incremented by 1 and accumulated if a current reversal occurs at each sampling; the current parameter is incremented by 1 and accumulated for each sampling if a current imbalance occurs. The above data did not exceed 0, and both the uncalculated and uncaptured were noted 0.
In one possible implementation manner, acquiring abnormal electricity utilization data of the target platform area in a preset period includes:
acquiring an electric energy meter cover opening record, a metering door opening and closing condition, a constant magnetic field interference condition, an electric quantity differential abnormal condition and a power failure event condition of the target platform area;
in the preset period, when the target platform area is abnormal in terms of electric energy meter uncovering, metering gate opening, constant magnetic field interference, electric quantity differential motion or power failure event, adding one to the electricity consumption parameter; the electricity consumption parameter returns to zero when the preset period starts;
and taking the electricity consumption parameter at the end of the preset period as abnormal electricity consumption data of the target station area in the preset period.
When the embodiment of the application is implemented, the sampling frequency of 15 minutes can be adopted for acquiring the electric energy meter uncapping record, the metering door opening and closing condition, the constant magnetic field interference condition, the electric quantity differential abnormal condition and the power failure event condition of the target platform area, and the electricity consumption parameter is added by 1 and accumulated if the electric energy meter uncapping occurs during each sampling; when sampling is carried out each time, if a metering gate is opened or closed, the electricity consumption parameter is added with 1 and accumulated; adding 1 to the electricity parameters if constant magnetic field interference occurs during each sampling, and accumulating; if the electric quantity differential abnormality occurs during each sampling, the electricity consumption parameter is added with 1 and accumulated; the power consumption parameter is incremented by 1 and accumulated if a power outage event occurs at each sampling. It can be seen from this embodiment that the abnormal electricity usage data mentioned in the embodiment of the present application may cover most of the behaviors that may be involved in electricity theft.
In one possible implementation manner, acquiring the abnormal data of the electric quantity of the target platform area in the preset period includes:
acquiring the requirement capacity exceeding condition, the load capacity exceeding condition, the current overcurrent condition, the load continuous lower limit exceeding condition and the power factor abnormality condition of the target station area;
in the preset period, when the target area has the defects of excessive capacity of the required quantity, excessive capacity of the load, overcurrent of the current, continuous exceeding of the lower limit of the load and abnormal power factor, adding one to the electric quantity parameter; the electric quantity parameter returns to zero when the preset period starts;
and taking the electric quantity parameter at the end of the preset period as electric quantity abnormal data of the target platform area in the preset period.
When the embodiment of the application is implemented, the sampling frequency of 15 minutes can be adopted for obtaining the condition of the excess capacity of the required quantity, the condition of the excess capacity of the load, the condition of the overcurrent of the current, the condition of the continuous excess lower limit of the load and the abnormal condition of the power factor, and the electric quantity parameter is added by 1 and accumulated if the excess capacity of the required quantity occurs during each sampling; when sampling is performed each time, if the load exceeds capacity, the electric quantity parameter is added with 1, and accumulation is not performed before the current load exceeds capacity; when sampling is carried out each time, if current flowing occurs, the electric quantity parameter is added with 1, and the current flowing is not accumulated before the current flowing is finished; when the load continuously exceeds the lower limit during each sampling, the electric quantity parameter is added with 1 and accumulated; the power parameter is incremented by 1 and accumulated if a power factor abnormality occurs at each sampling.
In the embodiment, the method for acquiring each abnormal data is provided, each abnormal data can be acquired through one type of acquisition module, all abnormal conditions are dataized, and meanwhile, in the embodiment of the application, all data only have abnormal and normal state increment, so that the final data can effectively represent the abnormal conditions, and cannot have strong complexity, thereby being beneficial to the design of an identification model.
In one possible implementation manner, the construction of the parametric model and the identification model includes:
obtaining an abnormal data sample; the abnormal data samples are used for acquiring a plurality of platform area line loss data, voltage abnormal data, current abnormal data, abnormal electricity consumption data and electric quantity abnormal data of the preset period under different electricity stealing types;
constructing different neural network models for each electricity stealing type, and carrying out data association training on the abnormal electricity utilization data in the abnormal data sample and the corresponding electricity stealing condition to form a parameter model; the data input of the parameter model is abnormal electricity utilization data, and the data output of the parameter model is an electricity larceny type corresponding to possible electricity larceny behavior;
training the neural network model by taking the line loss data, the voltage abnormal data, the current abnormal data and the electric quantity abnormal data of the transformer area in the abnormal data sample as input data of the neural network model corresponding to the electricity stealing type to generate a plurality of judgment models; each judgment model corresponds to one electricity stealing type, the input data of the judgment models are data of line loss of a transformer area, voltage abnormal data, current abnormal data and electric quantity abnormal data, and the data output of the judgment models are in accordance or not in accordance;
and forming a plurality of judgment model forming model groups as the identification models.
When the embodiment of the application is implemented, the abnormal electricity consumption data is a natural number larger than 0, so the parameter model is actually a numerical value-based segmentation model, namely each segmentation corresponds to an electricity stealing condition, and under the condition that the preset period is 24 hours, the abnormal electricity consumption data corresponds to an unoccupied electricity stealing value larger than 25, and corresponds to a spread electricity stealing value larger than 17 and smaller than or equal to 25, so that the possible electricity stealing type can be roughly detected.
In the embodiment of the application, when training a judgment model, in order to reduce the training dimension of the model, the correlation between the line loss data of the platform area and the voltage abnormal data is calculated by a correlation algorithm to be used as a first correlation parameter, the correlation between the line loss data of the platform area and the current abnormal data is calculated to be used as a second correlation parameter, and the correlation between the line loss data of the platform area and the electric quantity abnormal data is calculated to be used as a third correlation parameter;
calculating the line loss data of the transformer area into voltage abnormal data according to the first related parameters, calculating the line loss data of the transformer area into current abnormal data according to the second related parameters, and calculating the line loss data of the transformer area into electric quantity abnormal data according to the third related parameters; and training a judgment model according to the converted voltage abnormal data, current abnormal data and electric quantity abnormal data.
When the method is used, the judgment model can calculate the input line loss data of the transformer area into voltage abnormal data, current abnormal data and electric quantity abnormal data according to the first related parameter, the second related parameter and the third related parameter, and then output calculation which accords with or does not accord with the voltage abnormal data, the current abnormal data and the electric quantity abnormal data is carried out. By the method, the dimension of input data can be further reduced, the overfitting of the judgment model in training is reduced, and the detection precision is improved.
Based on the same inventive concept, referring to fig. 2, there is shown an electricity theft behavior detection system including:
an acquisition unit configured to acquire abnormal data of a target station area within a preset period, the abnormal data including station area line loss data, voltage abnormal data, current abnormal data, abnormal electricity consumption data and electric quantity abnormal data;
the model selecting unit is configured to input the abnormal electricity consumption data into a parametric model and acquire the electricity stealing type output by the parametric model;
the identification unit is configured to input the transformer area line loss data, the voltage abnormality data, the current abnormality data and the electric quantity abnormality data into an identification model corresponding to the electricity stealing type;
and the judging unit is configured to judge whether the electricity stealing behavior exists in the target platform region according to the output result of the identification model.
When the embodiment of the application is implemented, the model selection unit, the identification unit and the judgment unit can be configured at the remote server, and the acquisition unit is configured at the platform area to acquire the related data.
In one possible implementation, the acquisition unit is further configured to:
acquiring three-phase ammeter data of the target station area; the three-phase ammeter data comprise three-phase ammeter voltage data, three-phase ammeter current data and three-phase ammeter apparent power data;
in the preset period, adding one line loss parameter when any one of the three-phase meter voltage data, the three-phase meter current data and the three-phase meter apparent power data exceeds a corresponding threshold value of the target station area master station; the line loss parameter returns to zero when the preset period starts;
taking the line loss parameter at the end of the preset period as the station area line loss data of the target station area in the preset period;
acquiring the voltage phase failure condition, the voltage out-of-limit condition and the voltage balance condition of the target platform area;
in the preset period, when the voltage phase failure, voltage out-of-limit or voltage unbalance occurs in the target platform area, adding one voltage parameter; the voltage parameter returns to zero when the preset period starts;
and taking the voltage parameter at the end of the preset period as voltage abnormal data of the target platform area in the preset period.
In one possible implementation, the acquisition unit is further configured to:
acquiring the current loss condition, the current reverse condition and the current balance condition of the target station area;
in the preset period, when the current loss flow, the current direction or the current imbalance occurs in the target station area, adding one to the current parameter; the current parameter returns to zero when the preset period starts;
taking the current parameter at the end of the preset period as current abnormal data of the target station area in the preset period;
acquiring an electric energy meter cover opening record, a metering door opening and closing condition, a constant magnetic field interference condition, an electric quantity differential abnormal condition and a power failure event condition of the target platform area;
in the preset period, when the target platform area is abnormal in terms of electric energy meter uncovering, metering gate opening, constant magnetic field interference, electric quantity differential motion or power failure event, adding one to the electricity consumption parameter; the electricity consumption parameter returns to zero when the preset period starts;
taking the electricity consumption parameter at the end of the preset period as abnormal electricity consumption data of the target station area in the preset period;
acquiring the requirement capacity exceeding condition, the load capacity exceeding condition, the current overcurrent condition, the load continuous lower limit exceeding condition and the power factor abnormality condition of the target station area;
in the preset period, when the target area has the defects of excessive capacity of the required quantity, excessive capacity of the load, overcurrent of the current, continuous exceeding of the lower limit of the load and abnormal power factor, adding one to the electric quantity parameter; the electric quantity parameter returns to zero when the preset period starts;
and taking the electric quantity parameter at the end of the preset period as electric quantity abnormal data of the target platform area in the preset period.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or elements, or may be an electrical, mechanical, or other form of connection.
The elements described as separate components may or may not be physically separate, and it will be apparent to those skilled in the art that elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the elements and steps of the examples have been generally described functionally in the foregoing description so as to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a grid device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the application, and is not meant to limit the scope of the application, but to limit the application to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the application are intended to be included within the scope of the application.
Claims (10)
1. A method of detecting fraudulent use of electricity, comprising:
obtaining abnormal data of a target platform region in a preset period, wherein the abnormal data comprise platform region line loss data, voltage abnormal data, current abnormal data, abnormal electricity consumption data and electric quantity abnormal data;
inputting the abnormal electricity consumption data into a parameter model, and obtaining the electricity stealing type output by the parameter model;
inputting the line loss data, the voltage abnormal data, the current abnormal data and the electric quantity abnormal data of the transformer area into an identification model corresponding to the electricity stealing type;
judging whether the target platform area has electricity stealing behavior according to the output result of the identification model.
2. The method for detecting electricity theft behavior according to claim 1, wherein obtaining the station line loss data of the target station in the preset period includes:
acquiring three-phase ammeter data of the target station area; the three-phase ammeter data comprise three-phase ammeter voltage data, three-phase ammeter current data and three-phase ammeter apparent power data;
in the preset period, adding one line loss parameter when any one of the three-phase meter voltage data, the three-phase meter current data and the three-phase meter apparent power data exceeds a corresponding threshold value of the target station area master station; the line loss parameter returns to zero when the preset period starts;
and taking the line loss parameter at the end of the preset period as the station area line loss data of the target station area in the preset period.
3. The method for detecting electricity theft behavior according to claim 1, wherein obtaining voltage abnormality data of the target station area in a preset period includes:
acquiring the voltage phase failure condition, the voltage out-of-limit condition and the voltage balance condition of the target platform area;
in the preset period, when the voltage phase failure, voltage out-of-limit or voltage unbalance occurs in the target platform area, adding one voltage parameter; the voltage parameter returns to zero when the preset period starts;
and taking the voltage parameter at the end of the preset period as voltage abnormal data of the target platform area in the preset period.
4. The method for detecting electricity theft behavior according to claim 1, wherein obtaining current anomaly data of the target station area within a preset period includes:
acquiring the current loss condition, the current reverse condition and the current balance condition of the target station area;
in the preset period, when the current loss flow, the current direction or the current imbalance occurs in the target station area, adding one to the current parameter; the current parameter returns to zero when the preset period starts;
and taking the current parameter at the end of the preset period as current abnormal data of the target area in the preset period.
5. The method for detecting electricity theft behavior according to claim 1, wherein obtaining abnormal electricity usage data of the target station area in a preset period includes:
acquiring an electric energy meter cover opening record, a metering door opening and closing condition, a constant magnetic field interference condition, an electric quantity differential abnormal condition and a power failure event condition of the target platform area;
in the preset period, when the target platform area is abnormal in terms of electric energy meter uncovering, metering gate opening, constant magnetic field interference, electric quantity differential motion or power failure event, adding one to the electricity consumption parameter; the electricity consumption parameter returns to zero when the preset period starts;
and taking the electricity consumption parameter at the end of the preset period as abnormal electricity consumption data of the target station area in the preset period.
6. The method for detecting electricity theft behavior according to claim 1, wherein obtaining abnormal data of an electric quantity of the target station area in a preset period includes:
acquiring the requirement capacity exceeding condition, the load capacity exceeding condition, the current overcurrent condition, the load continuous lower limit exceeding condition and the power factor abnormality condition of the target station area;
in the preset period, when the target area has the defects of excessive capacity of the required quantity, excessive capacity of the load, overcurrent of the current, continuous exceeding of the lower limit of the load and abnormal power factor, adding one to the electric quantity parameter; the electric quantity parameter returns to zero when the preset period starts;
and taking the electric quantity parameter at the end of the preset period as electric quantity abnormal data of the target platform area in the preset period.
7. The method for detecting electricity theft behavior according to claim 1, wherein the constructing of the parametric model and the identification model includes:
obtaining an abnormal data sample; the abnormal data samples are used for acquiring a plurality of platform area line loss data, voltage abnormal data, current abnormal data, abnormal electricity consumption data and electric quantity abnormal data of the preset period under different electricity stealing types;
constructing different neural network models for each electricity stealing type, and carrying out data association training on the abnormal electricity utilization data in the abnormal data sample and the corresponding electricity stealing condition to form a parameter model; the data input of the parameter model is abnormal electricity utilization data, and the data output of the parameter model is an electricity larceny type corresponding to possible electricity larceny behavior;
training the neural network model by taking the line loss data, the voltage abnormal data, the current abnormal data and the electric quantity abnormal data of the transformer area in the abnormal data sample as input data of the neural network model corresponding to the electricity stealing type to generate a plurality of judgment models; each judgment model corresponds to one electricity stealing type, the input data of the judgment models are data of line loss of a transformer area, voltage abnormal data, current abnormal data and electric quantity abnormal data, and the data output of the judgment models are in accordance or not in accordance;
and forming a plurality of judgment model forming model groups as the identification models.
8. A system for detecting fraudulent use of electricity using the method of any of claims 1 to 7, comprising:
an acquisition unit configured to acquire abnormal data of a target station area within a preset period, the abnormal data including station area line loss data, voltage abnormal data, current abnormal data, abnormal electricity consumption data and electric quantity abnormal data;
the model selecting unit is configured to input the abnormal electricity consumption data into a parametric model and acquire the electricity stealing type output by the parametric model;
the identification unit is configured to input the transformer area line loss data, the voltage abnormality data, the current abnormality data and the electric quantity abnormality data into an identification model corresponding to the electricity stealing type;
and the judging unit is configured to judge whether the electricity stealing behavior exists in the target platform region according to the output result of the identification model.
9. The electricity theft behavior detection system of claim 8, wherein the acquisition unit is further configured to:
acquiring three-phase ammeter data of the target station area; the three-phase ammeter data comprise three-phase ammeter voltage data, three-phase ammeter current data and three-phase ammeter apparent power data;
in the preset period, adding one line loss parameter when any one of the three-phase meter voltage data, the three-phase meter current data and the three-phase meter apparent power data exceeds a corresponding threshold value of the target station area master station; the line loss parameter returns to zero when the preset period starts;
taking the line loss parameter at the end of the preset period as the station area line loss data of the target station area in the preset period;
acquiring the voltage phase failure condition, the voltage out-of-limit condition and the voltage balance condition of the target platform area;
in the preset period, when the voltage phase failure, voltage out-of-limit or voltage unbalance occurs in the target platform area, adding one voltage parameter; the voltage parameter returns to zero when the preset period starts;
and taking the voltage parameter at the end of the preset period as voltage abnormal data of the target platform area in the preset period.
10. The electricity theft behavior detection system of claim 8, wherein the acquisition unit is further configured to:
acquiring the current loss condition, the current reverse condition and the current balance condition of the target station area;
in the preset period, when the current loss flow, the current direction or the current imbalance occurs in the target station area, adding one to the current parameter; the current parameter returns to zero when the preset period starts;
taking the current parameter at the end of the preset period as current abnormal data of the target station area in the preset period;
acquiring an electric energy meter cover opening record, a metering door opening and closing condition, a constant magnetic field interference condition, an electric quantity differential abnormal condition and a power failure event condition of the target platform area;
in the preset period, when the target platform area is abnormal in terms of electric energy meter uncovering, metering gate opening, constant magnetic field interference, electric quantity differential motion or power failure event, adding one to the electricity consumption parameter; the electricity consumption parameter returns to zero when the preset period starts;
taking the electricity consumption parameter at the end of the preset period as abnormal electricity consumption data of the target station area in the preset period;
acquiring the requirement capacity exceeding condition, the load capacity exceeding condition, the current overcurrent condition, the load continuous lower limit exceeding condition and the power factor abnormality condition of the target station area;
in the preset period, when the target area has the defects of excessive capacity of the required quantity, excessive capacity of the load, overcurrent of the current, continuous exceeding of the lower limit of the load and abnormal power factor, adding one to the electric quantity parameter; the electric quantity parameter returns to zero when the preset period starts;
and taking the electric quantity parameter at the end of the preset period as electric quantity abnormal data of the target platform area in the preset period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310963438.9A CN116701947B (en) | 2023-08-02 | 2023-08-02 | Method and system for detecting electricity stealing behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310963438.9A CN116701947B (en) | 2023-08-02 | 2023-08-02 | Method and system for detecting electricity stealing behavior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116701947A true CN116701947A (en) | 2023-09-05 |
| CN116701947B CN116701947B (en) | 2023-11-03 |
Family
ID=87824231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310963438.9A Active CN116701947B (en) | 2023-08-02 | 2023-08-02 | Method and system for detecting electricity stealing behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116701947B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116930595A (en) * | 2023-09-18 | 2023-10-24 | 法拉迪电气有限公司 | Accurate data metering method for new energy grid-connected voltage regulation |
Citations (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106291253A (en) * | 2016-09-23 | 2017-01-04 | 国网天津市电力公司 | A kind of anti-electricity-theft early warning analysis method |
| CN109446193A (en) * | 2018-11-13 | 2019-03-08 | 国网宁夏电力有限公司电力科学研究院 | It opposes electricity-stealing model generating method and device |
| CN110097297A (en) * | 2019-05-21 | 2019-08-06 | 国网湖南省电力有限公司 | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium |
| CN110246054A (en) * | 2019-04-28 | 2019-09-17 | 国网内蒙古东部电力有限公司电力科学研究院 | A kind of intelligent electricity anti-theft total management system and method |
| CN110264015A (en) * | 2019-06-28 | 2019-09-20 | 国网河南省电力公司电力科学研究院 | It opposes electricity-stealing and checks monitoring method and platform |
| CN110824270A (en) * | 2019-10-09 | 2020-02-21 | 中国电力科学研究院有限公司 | Electricity stealing user identification method and device combining transformer area line loss and abnormal events |
| CN111126820A (en) * | 2019-12-17 | 2020-05-08 | 国网山东省电力公司电力科学研究院 | Electricity stealing prevention method and system |
| CN111507611A (en) * | 2020-04-15 | 2020-08-07 | 北京中电普华信息技术有限公司 | Method and system for determining electricity stealing suspected user |
| CN112131441A (en) * | 2020-09-27 | 2020-12-25 | 国网内蒙古东部电力有限公司 | Method and system for rapidly identifying abnormal behavior of power utilization |
| CN112733456A (en) * | 2021-03-17 | 2021-04-30 | 国网河南省电力公司营销服务中心 | Electricity stealing prevention behavior identification method and system |
| CN112749465A (en) * | 2021-01-19 | 2021-05-04 | 深圳智芯微电子科技有限公司 | Method, processor, storage medium, and detection system for detecting electricity theft |
| CN113111053A (en) * | 2021-04-13 | 2021-07-13 | 国网冀北电力有限公司技能培训中心 | Line loss diagnosis and electricity stealing prevention system, method and model based on big data |
| CN113452145A (en) * | 2021-08-30 | 2021-09-28 | 广东电网有限责任公司中山供电局 | Method and system for monitoring power utilization condition of low-voltage transformer area user |
| CN114002469A (en) * | 2021-11-03 | 2022-02-01 | 国网四川省电力公司成都供电公司 | Electricity stealing detection method and device and electricity stealing detector |
| CN114239725A (en) * | 2021-12-17 | 2022-03-25 | 四川大学 | Electricity stealing detection method oriented to data virus throwing attack |
| CN114266676A (en) * | 2021-12-28 | 2022-04-01 | 华东交通大学 | Abnormal electricity utilization detection method of genetic optimization Bagging heterogeneous integration model |
| CN114722722A (en) * | 2022-04-24 | 2022-07-08 | 深圳微言科技有限责任公司 | Power consumption data anomaly detection method and system based on big data analysis |
| CN114742405A (en) * | 2022-04-11 | 2022-07-12 | 国网江苏省电力有限公司营销服务中心 | Electricity stealing identification method and system based on line loss multi-dimensional correlation analysis |
| CN114881665A (en) * | 2021-09-30 | 2022-08-09 | 中国电力科学研究院有限公司 | Method and system for identifying electricity stealing suspected user based on target identification algorithm |
| US20220322300A1 (en) * | 2021-03-05 | 2022-10-06 | Lg Electronics Inc. | Method of operating a ue related to transmittable data for each sidelink grant in a wireless communication system |
| CN115293257A (en) * | 2022-08-02 | 2022-11-04 | 电子科技大学 | Detection method and system for abnormal electricity utilization user |
| CN115510781A (en) * | 2022-08-09 | 2022-12-23 | 中国电力科学研究院有限公司 | Anti-electricity-stealing early warning model verification method based on anti-electricity-stealing simulation experiment platform |
| CN116089838A (en) * | 2023-03-01 | 2023-05-09 | 中南大学 | Training method and recognition method for intelligent recognition model of electricity stealing user |
| WO2023105510A1 (en) * | 2021-12-06 | 2023-06-15 | Ben David Shimon | Alert method and systems analyzing household behavior |
| WO2023109527A1 (en) * | 2021-12-17 | 2023-06-22 | 广东电网有限责任公司东莞供电局 | Electricity theft behavior detection method and apparatus, computer device and storage medium |
-
2023
- 2023-08-02 CN CN202310963438.9A patent/CN116701947B/en active Active
Patent Citations (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106291253A (en) * | 2016-09-23 | 2017-01-04 | 国网天津市电力公司 | A kind of anti-electricity-theft early warning analysis method |
| CN109446193A (en) * | 2018-11-13 | 2019-03-08 | 国网宁夏电力有限公司电力科学研究院 | It opposes electricity-stealing model generating method and device |
| CN110246054A (en) * | 2019-04-28 | 2019-09-17 | 国网内蒙古东部电力有限公司电力科学研究院 | A kind of intelligent electricity anti-theft total management system and method |
| CN110097297A (en) * | 2019-05-21 | 2019-08-06 | 国网湖南省电力有限公司 | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium |
| CN110264015A (en) * | 2019-06-28 | 2019-09-20 | 国网河南省电力公司电力科学研究院 | It opposes electricity-stealing and checks monitoring method and platform |
| CN110824270A (en) * | 2019-10-09 | 2020-02-21 | 中国电力科学研究院有限公司 | Electricity stealing user identification method and device combining transformer area line loss and abnormal events |
| CN111126820A (en) * | 2019-12-17 | 2020-05-08 | 国网山东省电力公司电力科学研究院 | Electricity stealing prevention method and system |
| CN111507611A (en) * | 2020-04-15 | 2020-08-07 | 北京中电普华信息技术有限公司 | Method and system for determining electricity stealing suspected user |
| CN112131441A (en) * | 2020-09-27 | 2020-12-25 | 国网内蒙古东部电力有限公司 | Method and system for rapidly identifying abnormal behavior of power utilization |
| CN112749465A (en) * | 2021-01-19 | 2021-05-04 | 深圳智芯微电子科技有限公司 | Method, processor, storage medium, and detection system for detecting electricity theft |
| US20220322300A1 (en) * | 2021-03-05 | 2022-10-06 | Lg Electronics Inc. | Method of operating a ue related to transmittable data for each sidelink grant in a wireless communication system |
| CN112733456A (en) * | 2021-03-17 | 2021-04-30 | 国网河南省电力公司营销服务中心 | Electricity stealing prevention behavior identification method and system |
| CN113111053A (en) * | 2021-04-13 | 2021-07-13 | 国网冀北电力有限公司技能培训中心 | Line loss diagnosis and electricity stealing prevention system, method and model based on big data |
| CN113452145A (en) * | 2021-08-30 | 2021-09-28 | 广东电网有限责任公司中山供电局 | Method and system for monitoring power utilization condition of low-voltage transformer area user |
| CN114881665A (en) * | 2021-09-30 | 2022-08-09 | 中国电力科学研究院有限公司 | Method and system for identifying electricity stealing suspected user based on target identification algorithm |
| CN114002469A (en) * | 2021-11-03 | 2022-02-01 | 国网四川省电力公司成都供电公司 | Electricity stealing detection method and device and electricity stealing detector |
| WO2023105510A1 (en) * | 2021-12-06 | 2023-06-15 | Ben David Shimon | Alert method and systems analyzing household behavior |
| CN114239725A (en) * | 2021-12-17 | 2022-03-25 | 四川大学 | Electricity stealing detection method oriented to data virus throwing attack |
| WO2023109527A1 (en) * | 2021-12-17 | 2023-06-22 | 广东电网有限责任公司东莞供电局 | Electricity theft behavior detection method and apparatus, computer device and storage medium |
| CN114266676A (en) * | 2021-12-28 | 2022-04-01 | 华东交通大学 | Abnormal electricity utilization detection method of genetic optimization Bagging heterogeneous integration model |
| CN114742405A (en) * | 2022-04-11 | 2022-07-12 | 国网江苏省电力有限公司营销服务中心 | Electricity stealing identification method and system based on line loss multi-dimensional correlation analysis |
| CN114722722A (en) * | 2022-04-24 | 2022-07-08 | 深圳微言科技有限责任公司 | Power consumption data anomaly detection method and system based on big data analysis |
| CN115293257A (en) * | 2022-08-02 | 2022-11-04 | 电子科技大学 | Detection method and system for abnormal electricity utilization user |
| CN115510781A (en) * | 2022-08-09 | 2022-12-23 | 中国电力科学研究院有限公司 | Anti-electricity-stealing early warning model verification method based on anti-electricity-stealing simulation experiment platform |
| CN116089838A (en) * | 2023-03-01 | 2023-05-09 | 中南大学 | Training method and recognition method for intelligent recognition model of electricity stealing user |
Non-Patent Citations (3)
| Title |
|---|
| LIU, S等: "Identification of stealing electricity based on big data analysis", 《ENERGY REPORTS》, vol. 6, pages 731 - 738 * |
| 万龙等: "基于用电特征分析的窃电行为识别方法", 《电工材料》, no. 1, pages 64 - 67 * |
| 闫西慧等: "基于自编码神经网络和随机森林的窃电识别算法", 《电力大数据》, vol. 24, no. 6, pages 44 - 51 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116930595A (en) * | 2023-09-18 | 2023-10-24 | 法拉迪电气有限公司 | Accurate data metering method for new energy grid-connected voltage regulation |
| CN116930595B (en) * | 2023-09-18 | 2023-11-24 | 法拉迪电气有限公司 | Accurate data metering method for new energy grid-connected voltage regulation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116701947B (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| Jiang et al. | Wavelet based feature extraction and multiple classifiers for electricity fraud detection | |
| CN116701947B (en) | Method and system for detecting electricity stealing behavior | |
| Xia et al. | Detection methods in smart meters for electricity thefts: A survey | |
| Nizar et al. | Power utility nontechnical loss analysis with extreme learning machine method | |
| Biswas et al. | Electricity theft pinpointing through correlation analysis of master and individual meter readings | |
| Munshi et al. | Unsupervised nonintrusive extraction of electrical vehicle charging load patterns | |
| Venkatesan et al. | A real-time hardware fault detector using an artificial neural network for distance protection | |
| CN110389269A (en) | Low-voltage platform area topological relation recognition methods and its device based on electric current Optimized Matching | |
| CN107589391B (en) | Method, device and system for detecting integral error of electric energy metering device | |
| CN107292501A (en) | A kind of method and apparatus for assessing the effluent monitoring quality of data | |
| CN109889512A (en) | A kind of method for detecting abnormality and device of charging pile CAN message | |
| CN113922412B (en) | New energy multi-station short-circuit ratio panoramic evaluation method, system, storage medium and computing equipment | |
| CN114290960A (en) | Method and device for acquiring battery health degree of power battery and vehicle | |
| Veerakumar et al. | PMU-based real-time distribution system state estimation considering anomaly detection, discrimination and identification | |
| CN115293257A (en) | Detection method and system for abnormal electricity utilization user | |
| Hucker et al. | Requirements of automated PD diagnosis systems for fault identification in noisy conditions | |
| CN111612149A (en) | Main network line state detection method, system and medium based on decision tree | |
| CN109743224A (en) | Electrically-charging equipment data processing method and device | |
| CN106501703B (en) | BMS equilibrium metal-oxide-semiconductor detection method and device | |
| CN108845285A (en) | Electric energy metering device detection method and system | |
| CN115685045B (en) | Online evaluation method for voltage transformer | |
| US20090101469A1 (en) | Coin sensor | |
| CN116128690B (en) | Carbon emission cost value calculation method, device, equipment and medium | |
| Abbasy et al. | Power system state estimation: ANN application to bad data detection and identification |
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 |