CN113311379B - Low-voltage electricity larceny intelligent diagnosis method based on big data - Google Patents
Low-voltage electricity larceny intelligent diagnosis method based on big data Download PDFInfo
- Publication number
- CN113311379B CN113311379B CN202110582683.6A CN202110582683A CN113311379B CN 113311379 B CN113311379 B CN 113311379B CN 202110582683 A CN202110582683 A CN 202110582683A CN 113311379 B CN113311379 B CN 113311379B
- Authority
- CN
- China
- Prior art keywords
- electricity
- users
- data
- suspected
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/04—Testing or calibrating of apparatus covered by the other groups of this subclass of instruments for measuring time integral of power or current
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
一种基于大数据的低压窃电智能诊断方法，首先采集基于电能表的关联数据并建立基于多维度的多种低压窃电智能诊断模型，然后从建立的模型中选择一个没有使用过的模型进行疑似窃电用户判定，如判定为疑似窃电用户，输出疑似窃电用户，并进行现场核查；如判定为非疑似窃电用户，则继续从建立的模型中选择一个没有使用过的模型进行疑似窃电用户判定直到所有模型的判定结果都为非疑似窃电用户，则输出非疑似窃电用户，结束本方法。本发明中的模型以及所设定阈值能够高效且准确的判断出安装遥控窃电装置、更换电能表内部元器件、短接电能表接线柱、短接电能表内部计量回路这几种窃电类型的疑似窃电用户，为现场核查提供技术支持以及理论依据。
A low-voltage electricity theft intelligent diagnosis method based on big data, first collects related data based on electric energy meters and establishes multiple low-voltage electricity theft intelligent diagnosis models based on multiple dimensions, then selects an unused model from the established models to determine suspected electricity theft users, if determined to be suspected electricity theft users, outputs the suspected electricity theft users, and conducts on-site verification; if determined to be non-suspected electricity theft users, then continues to select an unused model from the established models to determine suspected electricity theft users until the determination results of all models are non-suspected electricity theft users, then outputs non-suspected electricity theft users, and ends the method. The model and the set threshold in the present invention can efficiently and accurately determine suspected electricity theft users of several types of electricity theft, such as installing remote control electricity theft devices, replacing internal components of electric energy meters, short-circuiting electric energy meter terminals, and short-circuiting internal metering circuits of electric energy meters, providing technical support and theoretical basis for on-site verification.
Description
Technical Field
The invention relates to a low-voltage electricity larceny intelligent diagnosis method based on big data, and belongs to the technical field of electric energy metering detection.
Background
The resident user is used as an electricity main body, has the characteristics of large body quantity, wide range, quick diffusion, difficult investigation and the like, and is the content of key research on how to effectively utilize massive electricity consumption acquisition data to accurately lock abnormal users.
Disclosure of Invention
In order to solve the defects in the prior art, the invention aims to provide a low-voltage electricity larceny intelligent diagnosis method based on big data.
The invention adopts the following technical scheme:
The low-voltage electricity larceny intelligent diagnosis method based on big data comprises the following steps:
Step 1, acquiring associated data of an electric energy meter, wherein the associated data comprises current data, uncap event information, electric quantity data, business expansion flow information and station area line loss data;
step 2, cleaning the data acquired in the step 1, and removing invalid data;
Step 3, based on the electric energy meter associated data processed in the step 2, establishing various low-voltage electricity stealing intelligent diagnosis models;
Step 4, selecting one model which is not used from the models established in the step 3 to judge the suspected electricity larceny user, outputting the suspected electricity larceny user if the model is judged to be the suspected electricity larceny user, and entering the step 5;
and 5, performing field checking work according to the judging result in the step 4.
In step 1, the electric energy meter has a current measurement function, and the power consumption information acquisition system can acquire phase line current and zero line current operation parameters in real time.
In step 1, the current data refers to the real-time phase line current obtained by the electric energy meterAnd real-time zero line current;
The uncovering event information comprises uncovering times and uncovering starting timeEnd time of uncapping;
For users with the uncovering event, the electric quantity data refers to the electric energy meter before the uncovering event occursHeaven and backPower consumption data for each day, and if the uncovering record event occurs on the nth day,For the nth day power, beforeThe power consumption data of the day isAnd then (b) backThe power consumption data of the day is;
For users without the cover event, the electric quantity data refer to the electric quantity data of each month from the date of the meter loading;
the business expansion flow information refers to fault rush repair information so as to distinguish abnormal uncapping events caused by normal operation;
The station area line loss data comprise station area power supply quantity, station area sales quantity and station area line loss rate;
in step 2, the invalid data includes data of failed acquisition, null data and messy code data.
In step 3, the low-voltage electricity larceny intelligent diagnosis model is a current analysis model, an event analysis model, an electric quantity analysis model and a line loss analysis model.
The current analysis model calculates and analyzes the difference between the phase current and the zero line current, and the user corresponding to the electric energy meter with the difference value larger than the difference value threshold and the phase error value and the zero line error value exceeding the error threshold is a suspected electricity larceny user, and the phase current and the zero line current have different valuesTo satisfy the following relation:
phase, zero line current error The following relation is satisfied:
Such as AndThen a suspected fraudulent user is determined.
The difference threshold is 0.5A and the error threshold is 30%.
The event analysis model calculates the duration of uncovering irrelevant to the business expansion flow information in the uncovering abnormal event, screens suspected electricity larceny users according to whether the duration meets a set uncovering threshold value, and judges specific electricity larceny types.
The threshold of uncapping is [2,50] min, namely uncapping timeA user of [2,50] minutes is determined to be a suspected fraudulent user;
the method for judging the electricity stealing type is as follows:
if it is Judging that the suspected short circuit electric energy meter binding post and the internal metering loop of the short circuit electric energy meter steal electricity;
if it is Judging that the internal components of the replacement electric energy meter steal electricity;
if it is And judging that the remote control electricity larceny device is installed.
The electric quantity analysis model is used for respectively analyzing users with and without the abnormal event of uncovering;
If the abnormal event of the uncovering of the user is irrelevant to the business expansion flow information, calculating the uncovering record event of the electric energy meter of the user before the occurrence Tianhe and thenDaily average daily electricity as beforeTianhe and thenWhen the average daily electricity consumption is larger than the electricity consumption difference threshold, the user is considered to be a suspected electricity larceny user;
For users without abnormal events of uncovering, calculating the electric quantity deviation of every two adjacent months from the date of loading, and screening out that the users with the electric quantity difference exceeding the electric quantity threshold value of two adjacent months before and after the user is suspected electricity larceny users.
The electric quantity difference threshold value and the electric quantity consumption threshold value are both 30 percent, the saidAnd (3) withAnd are all 7.
The line loss analysis model judges the users meeting the following relation as suspected electricity larceny users:
Wherein, if the suspected electricity stealing day of the user is D, the electricity consumption of the previous day of the user is The power supply amount of the first day of the platform area isThe daily sales electricity quantity before the station area isThe power consumption of the user on the day of suspected electricity larceny isSuspected fraudulent use of electricity the power supply quantity of the balcony area isThe suspected electricity stealing is that the electricity selling quantity of the sky plot is。
The line loss analysis threshold was 5%.
The invention has the advantages that the existing diagnosis method is single diagnosis, the electricity stealing method has the remarkable characteristics of equipment intellectualization, behavior concealment and the like, the means of clearing events in the meter, simulating electric energy meter current and the like are known at present, and the traditional single diagnosis can not identify the electricity stealing behavior of a user. According to the invention, through monitoring self-power data and associated data of the electric energy meter, a multi-model diagnosis method based on big data is established from four dimensions of current comparison, event analysis, electric quantity comparison and station area line loss matching, comprehensive research and judgment are carried out on suspected electricity larceny users, and a research and judgment model is flexibly configured in an independent or combined mode, so that the low-voltage electricity larceny intelligent diagnosis method based on big data is realized, the electricity larceny users are accurately and rapidly locked, and technical support is provided for field investigation work. The set threshold value is an optimal value obtained through a large number of case analysis, so that the model can efficiently and accurately judge suspected electricity larceny users of several electricity larceny types, such as installation of remote control electricity larceny devices, replacement of internal components of the electric energy meter, short-circuit of the electric energy meter binding post and short-circuit of the electric energy meter.
Drawings
FIG. 1 is an overall flow chart of a low voltage electricity theft intelligent diagnosis method based on big data.
Detailed Description
The application is further described below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present application, and are not intended to limit the scope of the present application.
A low-voltage electricity larceny intelligent diagnosis method based on big data comprises the following steps:
step 1, collecting associated data of an electric energy meter;
the associated data comprises current data, uncap event information, electric quantity data, business expansion flow information and station area line loss data.
The electric energy meter has a current measurement function, and the power consumption information acquisition system can acquire phase line current and zero line current operation parameters in real time, so that current data refer to real-time phase line current of the electric energy meterAnd real-time zero line currentThe uncapping event information comprises the number of uncapping abnormal events and the uncapping starting timeEnd time of uncapping;
For users with uncovering events, the electric quantity data refers to the electric energy meter before the uncovering event occursHeaven and backPower consumption data for each day, and if the uncovering record event occurs on the nth day,For the nth day power, beforeThe power consumption data of the day isAnd then (b) backThe power consumption data of the day is。
For users without the cover event, the electric quantity data refer to the electric quantity data of each month from the date of the meter loading;
In the present embodiment of the present invention, in the present embodiment, And (3) withAnd are all 7.
The business expansion flow information refers to fault rush repair information, and aims to distinguish uncapping abnormal events caused by normal operation;
The station area line loss data comprise station area power supply quantity, station area sales quantity and station area line loss rate;
step 2, cleaning the data acquired in the step 1, and removing invalid data;
the invalid data comprises data of acquisition failure, null data and messy code data.
Step 3, based on the electric energy meter associated data processed in the step 2, establishing various low-voltage electricity stealing intelligent diagnosis models;
the electricity stealing type which can be used for diagnosis by the model established in the embodiment comprises the steps of installing a remote control electricity stealing device, replacing internal components of the electric energy meter, shorting an electric energy meter binding post and shorting an internal metering loop of the electric energy meter;
the low-voltage electricity larceny intelligent diagnosis model is built from several latitudes of electricity quantity, electricity flow, event record and line loss, and comprises an electricity flow analysis model, an event analysis model, an electricity quantity analysis model and a line loss analysis model.
The amperometric model comprises the following:
Under the normal wiring condition, current flows into the metering unit of the electric energy meter through the phase line, flows through the load and then returns to the electric energy meter through the zero line, so that a complete closed loop is formed, and the phase line current and the zero line current flowing through the electric energy meter are the same current, and the amplitude values are basically equal. If electricity stealing occurs, the phase and zero line currents of the electric energy meter are necessarily different.
The electric energy meter has a current measurement function, and the electricity consumption information acquisition system can acquire phase and zero line current operation parameters in real time, and can preliminarily judge suspected electricity stealing users by comparing the phase and zero line current differences detected.
And (3) detecting the difference between the phase line current and the zero line current in the step (1), screening the object meeting the phase line current and zero line current difference judgment logic, and accordingly intelligently identifying the suspected electricity larceny electric energy meter, wherein the specific matching rule is as follows, the difference between the phase line current and the zero line current is calculated and analyzed, and the electric energy meter with the difference value being larger than a difference value threshold and the phase line error value and the zero line error value exceeding an error threshold is screened. After the electricity stealing behavior occurs, the phase current and the zero line current of the electric energy meter are necessarily different, and the difference value is in direct proportion to the load. By analyzing the case under inspection, the user is using the difference statistics of the electrical phase and zero line, the difference threshold is preferably 0.5A and the error threshold is preferably 30%.
Phase, zero line current differenceExpressed by the following formula:
phase, zero line current error Expressed by the following formula:
Such as AndThen a suspected fraudulent user is determined.
The event analysis model includes the following:
Under the normal electricity consumption condition of a user, the electric energy meter runs stably and reliably, and besides normal overhaul and few false alarm conditions, the electric energy meter can not actively report an abnormal event of the cover opening. Aiming at the electric energy meter reporting the abnormal event of uncovering, analyzing whether a work order for urgent repair or fault treatment exists during uncovering, if no related business expansion flow information exists, calculating whether the duration of uncovering meets a set uncovering threshold value, eliminating the situation of false alarm, and screening suspected electricity stealing users.
The electric energy meter has the active event reporting function, the marketing system and the electricity consumption information acquisition system can acquire business expansion flow information and uncapping event information in real time, and the suspected electricity stealing users can be screened and suspected electricity stealing methods can be given by matching the uncapping recording time of the electric energy meter and the time required by the known electricity stealing scheme.
Aiming at the behavior of opening the electric energy meter to steal electricity in the electric energy meter, the uncapping event record of the electric energy meter can be triggered, the electric energy meter is counted in the current main stream of the electric energy meter, namely, the remote control electricity stealing device is installed, the internal components and parts of the electric energy meter are replaced, the binding post of the electric energy meter is short-circuited, the internal metering loop of the electric energy meter is short-circuited, and the like, the uncapping duration of the electric energy meter is found to be within the range of 2-50 minutes, so that users with the uncapping duration within the range of 2-50 minutes are judged to be suspected electricity stealing users, and the specific matching rules are as follows:
if it is Judging that the suspected short circuit electric energy meter binding post and the internal metering loop of the short circuit electric energy meter steal electricity;
if it is Judging that the internal components of the replacement electric energy meter steal electricity;
if it is And judging that the remote control electricity larceny device is installed.
The electrical quantity analysis model comprises the following contents:
The electricity consumption of the normal users can fluctuate in a certain range along with factors such as workdays, rest days, holidays and the like, and the electricity consumption of the normal low-voltage resident users is relatively stable and smaller, so that the situation of continuous and large fluctuation of the electricity can not occur. If the user has electricity stealing behavior, the electric quantity before and after electricity stealing can be greatly different. The average electric quantity data in a certain time period before and after the occurrence time of the uncovering event can be calculated, whether the electric quantity in the two time periods has obvious difference and accords with a set electric quantity difference threshold value can be analyzed, and therefore a suspected electricity stealing user can be judged. For the behavior of stealing electricity without uncapping, calculating the data of the electricity quantity of the adjacent months since the date of the dress, and analyzing whether the electricity quantity of the two time periods has obvious difference and exceeds the electricity consumption threshold of the adjacent two months, thereby judging the suspected electricity stealing users. Through statistics of the checked cases, in this embodiment, the power difference threshold and the power consumption threshold are both 30%. The specific calculation method is as follows:
for the user with the abnormal event of uncovering and the abnormal event of uncovering is irrelevant to the business expansion flow information, before the abnormal event of uncovering of the electric energy meter of the user occurs, the user is calculated Tianhe and thenAverage daily electricity quantity;
Front of it Daily average daily electrical quantity:
Rear part (S) Daily average daily electrical quantity:
In the present embodiment of the present invention, in the present embodiment, And (3) withAnd are all 7.
When (when)And (3) withAnd when the difference ratio of the power supply is larger than the power difference threshold value, the user is considered to be a suspected electricity larceny user.
For the users without abnormal event of uncovering, calculating the deviation of the electric quantity of every two adjacent months from the date of loading the meter,
And screening out the users with the electricity consumption difference exceeding the electricity consumption threshold value of two adjacent months before and after the electricity consumption is suspected electricity stealing users.
Such asThe user is considered to be a suspected electricity larceny user.
Wherein, For the power deviation every two months in the neighborhood,For the electricity consumption of the first month of two adjacent months,Is the electricity consumption of the second month in two adjacent months.
The line loss analysis model comprises the following contents:
When a certain user under the transformer area has electricity stealing behavior, the line loss can be affected to different degrees according to factors such as the electricity consumption of the user and the electricity stealing proportion, and meanwhile, the electricity loss of the transformer area and the electricity consumption of the electricity stealing user can be in a certain proportion relation before and after the line loss rate changes. And matching the lost electric quantity before and after the line loss change of the transformer area with the daily electric quantity of the user, and screening out that the difference value between the daily electric quantity before and after the user and the lost electric quantity of the transformer area are within a line loss analysis threshold value and are suspected abnormal users. In this embodiment, the line loss analysis threshold is 5%.
Setting the suspected electricity stealing day of the user as D, and setting the electricity consumption of the user in the previous day asThe power supply amount of the first day of the platform area isThe daily sales electricity quantity before the station area isThe power consumption of the user on the day of suspected electricity larceny isSuspected fraudulent use of electricity the power supply quantity of the balcony area isThe suspected electricity stealing is that the electricity selling quantity of the sky plot is。
The user who meets the following conditions is a suspected electricity larceny user:
And 4, selecting one model which is not used from the models established in the step 3 to judge the suspected electricity larceny user, outputting the suspected electricity larceny user if the model is judged to be the suspected electricity larceny user, and entering the step 5, repeating the step if the model is judged to be the non-suspected electricity larceny user, and outputting the non-suspected electricity larceny user if all the models are used and the judgment result is the non-suspected electricity larceny user, and ending the method.
And 5, performing corresponding field checking work according to the judging result in the step 4.
In the embodiment, the user type is a single-phase electric energy meter user capable of reading phase and zero line current.
According to the low-voltage electricity larceny intelligent diagnosis method based on big data, through constructing current, event records, electric quantity and platform area line loss models, the suspected electricity larceny behaviors of low-voltage users can be independently and intelligently diagnosed in a combined mode, the problems that traditional low-voltage electricity larceny analysis is difficult, the workload is large, the checking is difficult and the like are solved, and the conversion from low-voltage electricity larceny operation to intelligent operation is realized.
While the applicant has described and illustrated the embodiments of the present invention in detail with reference to the drawings, it should be understood by those skilled in the art that the above embodiments are only preferred embodiments of the present invention, and the detailed description is only for the purpose of helping the reader to better understand the spirit of the present invention, and not to limit the scope of the present invention, but any improvements or modifications based on the spirit of the present invention should fall within the scope of the present invention.
Claims (7)
1. The low-voltage electricity larceny intelligent diagnosis method based on big data is characterized by comprising the following steps of:
Step 1, acquiring associated data of an electric energy meter, wherein the associated data comprises current data, uncap event information, electric quantity data, business expansion flow information and station area line loss data;
The current data refer to a real-time phase line current I L and a real-time zero line current I N which are acquired by the electric energy meter;
The uncovering event information comprises uncovering times, uncovering start time T Start to and uncovering end time T Ending ;
step 2, cleaning the data acquired in the step 1, and removing invalid data;
Step 3, based on the electric energy meter associated data processed in the step 2, establishing various low-voltage electricity stealing intelligent diagnosis models;
The low-voltage electricity stealing intelligent diagnosis model is a current analysis model, an event analysis model, an electric quantity analysis model and a line loss analysis model;
The current analysis model calculates and analyzes the difference of phase and zero line currents, and the users corresponding to the electric energy meters with the difference value larger than a difference value threshold and the phase and zero line error value exceeding the error threshold are suspected electricity larceny users, so that the phase and zero line current difference I meets the following relation:
I=IN-IL
The phase and neutral current errors k satisfy the following relationship:
if the I > difference value threshold value and the k > error threshold value are judged to be suspected electricity larceny users;
The event analysis model calculates the duration of uncovering irrelevant to the business expansion flow information in the uncovering abnormal event, screens suspected electricity larceny users according to whether the duration meets a set uncovering threshold value, and judges specific electricity larceny types;
The uncovering threshold value is [2,50] minutes, namely, a user with the uncovering time T Ending -T Start to of [2,50] minutes is judged to be a suspected electricity larceny user;
the method for judging the electricity stealing type comprises the following steps:
If T Ending -T Start to is less than or equal to 2 minutes and less than or equal to 20 minutes, judging that the suspected short circuit ammeter wiring terminal or the short circuit ammeter internal metering loop steals electricity;
If T Ending -T Start to is less than or equal to 30min, judging that the internal components of the replacement electric energy meter steal electricity;
If 30min < T Ending -T Start to is less than or equal to 50min, judging that the remote control electricity larceny device is installed;
the electric quantity analysis model is used for respectively analyzing users with and without abnormal events of uncovering;
If the abnormal event of the uncovering of the user is irrelevant to the business expansion flow information, calculating average daily electric quantity of n 1 days before and n 2 days after the uncovering recording event of the user electric energy meter, and if the average daily electric quantity of n 1 days before and n 2 days after is larger than an electric quantity difference threshold value, considering the user as a suspected electricity stealing user;
for users without abnormal events of uncovering, calculating the electric quantity deviation of every two adjacent months from the date of loading, and screening out that the users with the electric quantity difference exceeding the electric quantity threshold value of two adjacent months are suspected electricity larceny users;
the line loss analysis model judges the users meeting the following relation as suspected electricity larceny users:
1+ line loss analysis threshold Line loss analysis threshold
Setting the suspected electricity stealing day of the user as D, wherein the electricity consumption of the user in the previous day is S D-1, the electricity consumption of the platform in the previous day is T D-1, the electricity selling amount of the platform in the previous day is R D-1, the electricity consumption of the user in the suspected electricity stealing day is S D, the electricity consumption of the suspected electricity stealing current platform is T D, and the electricity selling amount of the suspected electricity stealing current platform is R D;
Step 4, selecting one model which is not used from the models established in the step 3 to judge the suspected electricity larceny user, outputting the suspected electricity larceny user if the model is judged to be the suspected electricity larceny user, and entering the step 5;
and 5, performing field checking work according to the judging result in the step 4.
2. The big data based low voltage electricity theft intelligent diagnosis method according to claim 1, characterized in that:
in the step 1, the electric energy meter has a current measurement function, and the power consumption information acquisition system can acquire phase line current and zero line current operation parameters in real time.
3. The big data based low voltage electricity theft intelligent diagnosis method according to claim 1 or 2, characterized in that:
For users with the uncapping event, the electric quantity data refers to the electric quantity data of the electric energy meter in the days N 1 and N 2 before the uncapping event, if the uncapping event occurs in the N day, S N is the electric quantity of the N day, and the electric quantity data of the first N 1 days is The power consumption data of the last n 2 days is
For users without the cover event, the electric quantity data refer to the electric quantity data of each month from the date of the meter loading;
The business expansion flow information refers to fault rush repair information so as to distinguish uncapping abnormal events caused by normal operation;
the station area line loss data comprise station area power supply quantity, station area sales quantity and station area line loss rate.
4. The low-voltage electricity theft intelligent diagnosis method based on big data according to claim 3, wherein the method comprises the following steps:
In the step 2, the invalid data includes data of acquisition failure, null data and messy code data.
5. The big data based low voltage electricity theft intelligent diagnosis method according to claim 4, characterized in that:
The difference threshold is 0.5A and the error threshold is 30%.
6. The big data based low voltage electricity theft intelligent diagnosis method according to claim 1, characterized in that:
The electric quantity difference threshold and the electric quantity threshold are both 30%, and n 1 and n 2 are both 7.
7. The big data based low voltage electricity theft intelligent diagnosis method according to claim 1, characterized in that:
The line loss analysis threshold is 5%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110582683.6A CN113311379B (en) | 2021-05-26 | 2021-05-26 | Low-voltage electricity larceny intelligent diagnosis method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110582683.6A CN113311379B (en) | 2021-05-26 | 2021-05-26 | Low-voltage electricity larceny intelligent diagnosis method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113311379A CN113311379A (en) | 2021-08-27 |
| CN113311379B true CN113311379B (en) | 2024-11-29 |
Family
ID=77375198
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110582683.6A Active CN113311379B (en) | 2021-05-26 | 2021-05-26 | Low-voltage electricity larceny intelligent diagnosis method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113311379B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116307092A (en) * | 2023-02-01 | 2023-06-23 | 福建网能科技开发有限责任公司 | Anti-stealing electricity analysis method in station area based on electricity consumption information collection |
Citations (2)
| 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 |
| CN107039970A (en) * | 2017-03-13 | 2017-08-11 | 广东电网有限责任公司信息中心 | Gong Biantai areas line loss per unit abnormal cause detection method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4239677B2 (en) * | 2003-05-16 | 2009-03-18 | 株式会社日立製作所 | Electricity sales system to prevent theft of electricity |
| CN110047013B (en) * | 2018-01-15 | 2023-06-13 | 国网江苏省电力公司常州供电公司 | Discontinuous Electricity Stealing Method for Anti-Special User |
| CN112269048A (en) * | 2020-10-19 | 2021-01-26 | 杭州中著智能科技开发有限公司 | Remote control intelligent water and electricity integrated meter |
| AU2020102880A4 (en) * | 2020-10-20 | 2020-12-17 | Chordiya, S. B. PROF | Power Theft Detection: POWER THEFT DETECTION AND NOTIFICATION USING WIRELESS NETWORK |
-
2021
- 2021-05-26 CN CN202110582683.6A patent/CN113311379B/en active Active
Patent Citations (2)
| 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 |
| CN107039970A (en) * | 2017-03-13 | 2017-08-11 | 广东电网有限责任公司信息中心 | Gong Biantai areas line loss per unit abnormal cause detection method and system |
Non-Patent Citations (2)
| Title |
|---|
| 拆旧智能电能表检测系统的设计;申丽曼等;湖南电力;第37卷(第6期);第55-57、60页 * |
| 聚类k-means算法在新疆反窃电工作中的应用;刘卫新等;南昌大学学报（理科版）;20171031;第41卷(第5期);第450-454页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113311379A (en) | 2021-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106405475A (en) | Electric energy meter abnormity diagnosis method | |
| CN106291253A (en) | A kind of anti-electricity-theft early warning analysis method | |
| CN106443556A (en) | Method for intelligently diagnosing electric energy meter | |
| CN110728836A (en) | Concentrator meter reading abnormity analysis method and system | |
| CN110703009B (en) | Abnormal Analysis and Treatment Method of Line Loss Rate in Taiwan Area | |
| CN112461289A (en) | Ring main unit fault monitoring method, system, terminal and storage medium | |
| CN115219903B (en) | Battery self-discharge rate abnormality judgment method and device based on vehicle networking data analysis | |
| CN107543989B (en) | Method for judging abnormal line loss based on voltage loss and phase failure of electric energy meter | |
| CN118962573B (en) | A method for detecting a user's power load using an intelligent electric energy meter | |
| CN113311379B (en) | Low-voltage electricity larceny intelligent diagnosis method based on big data | |
| Yip et al. | Detection of energy theft and metering defects in advanced metering infrastructure using analytics | |
| CN115809805A (en) | Power grid multi-source data processing method based on edge calculation | |
| CN113888360A (en) | Method, device, equipment and storage medium for identifying electricity stealing users | |
| CN107703383A (en) | A kind of method for building up of information acquisition system fault diagnosis knowledge base | |
| CN111781554A (en) | Metering device fault determination method and system based on four-quadrant electric energy data | |
| CN116089856A (en) | Power stealing electricity quantity analysis method and device based on electricity consumption data and electronic equipment | |
| CN108171960B (en) | A self-diagnosis method and system for abnormality of metering device of integrated energy management platform | |
| CN115510781A (en) | Anti-electricity-stealing early warning model verification method based on anti-electricity-stealing simulation experiment platform | |
| CN119511187A (en) | A fault detection method and system for electric energy metering device | |
| CN110988420A (en) | Anti-electricity-theft system and anti-electricity-theft control method | |
| CN119519142A (en) | Power supply and distribution supervision system based on data processing | |
| CN117609926B (en) | Pollution discharge mechanism production state determining method and device based on power data | |
| CN106646106A (en) | Power grid fault detection method based on change point detection technology | |
| CN113985124B (en) | A method for preventing electricity theft based on LTU, electric energy meter and fusion terminal | |
| CN110968838A (en) | Power utilization abnormity analysis method based on intelligent electric energy meter uncovering event |
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 |