CN113311379A - Low-voltage electricity stealing intelligent diagnosis method based on big data - Google Patents
Low-voltage electricity stealing intelligent diagnosis method based on big data Download PDFInfo
- Publication number
- CN113311379A CN113311379A CN202110582683.6A CN202110582683A CN113311379A CN 113311379 A CN113311379 A CN 113311379A CN 202110582683 A CN202110582683 A CN 202110582683A CN 113311379 A CN113311379 A CN 113311379A
- Authority
- CN
- China
- Prior art keywords
- electricity stealing
- data
- suspected
- electricity
- 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.)
- Pending
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 186
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000003745 diagnosis Methods 0.000 title claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims description 32
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000008439 repair process Effects 0.000 claims description 3
- 238000012795 verification Methods 0.000 abstract 1
- 230000006399 behavior Effects 0.000 description 9
- 230000008901 benefit Effects 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000036626 alertness Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000005612 types of electricity Effects 0.000 description 1
- 235000001892 vitamin D2 Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/04—Testing or calibrating of apparatus covered by the other groups of this subclass of instruments for measuring time integral of power or current
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
A low-voltage electricity stealing intelligent diagnosis method based on big data comprises the steps of firstly collecting correlation data based on an electric energy meter, establishing a plurality of low-voltage electricity stealing intelligent diagnosis models based on multiple dimensions, then selecting one unused model from the established models to judge suspected electricity stealing users, if the model is judged to be the suspected electricity stealing users, outputting the suspected electricity stealing users, and carrying out field check; if the suspected electricity stealing users are judged to be the non-suspected electricity stealing users, one model which is not used is continuously selected from the established models to judge the suspected electricity stealing users until the judgment results of all the models are the non-suspected electricity stealing users, the non-suspected electricity stealing users are output, and the method is ended. The model and the set threshold value in the invention can efficiently and accurately judge suspected electricity stealing users of installing the remote control electricity stealing device, replacing internal components of the electric energy meter, short-circuit electric energy meter binding posts and short-circuit internal metering loops of the electric energy meter, and provide technical support and theoretical basis for field verification.
Description
Technical Field
The invention relates to a low-voltage electricity stealing intelligent diagnosis method based on big data, and belongs to the technical field of electric energy metering detection.
Background
Electric power enterprises often have electricity stealing accidents in the process of power transmission, and the frequency of the electricity stealing accidents is higher and higher. Along with the improvement and progress of science and technology, the difficulty is brought to the work of preventing electricity stealing.
Firstly, relevant anti-electricity-stealing work law and regulation is not sound enough, though clearly stipulate in the law that electricity-stealing belongs to the act of violation, nevertheless punishment dynamics to the act of electricity-stealing is far away not enough, leads to the electricity-stealing person to try on awkwardly before the benefit lures, and is rampant even more, and the enterprise does not have the assurance of law in order to maintain self economic benefits, leads to anti-electricity-stealing work ten minutes difficultly. In the power consumer, no matter enterprises or individuals maintain own interests, the importance of legal power utilization is not really recognized, the recognition degree of power safety is not high, and the behavior of stealing power is generated under the drive of intangible interests. Thirdly, the electricity stealing manipulation is increasingly high-tech and concealed, the electricity stealing people have strong consciousness and high alertness, and the electricity stealing behavior is difficult to obtain evidence and check.
The resident user is used as the electricity utilization main body, has the characteristics of large quantity, wide range, fast diffusion, difficult investigation and the like, and how to effectively utilize the mass electricity utilization information acquisition data to accurately lock the abnormal user is the content of key research.
Disclosure of Invention
In order to solve the defects in the prior art, the invention aims to provide a low-voltage electricity stealing intelligent diagnosis method based on big data.
The invention adopts the following technical scheme:
a low-voltage electricity stealing intelligent diagnosis method based on big data comprises the following steps:
step 1: collecting associated data of the electric energy meter; the associated data comprises current data, uncapping event information, electric quantity data, business expansion process information and transformer area line loss data;
step 2: cleaning the data collected in the step 1, and removing invalid data;
and step 3: establishing various low-voltage electricity stealing intelligent diagnosis models based on the electric energy meter associated data processed in the step 2;
and 4, step 4: selecting an unused model from the models established in the step 3 to judge a suspected electricity stealing user, if the model is judged to be the suspected electricity stealing user, outputting the suspected electricity stealing user, and entering a step 5; if the user is judged to be not suspected to be the electricity stealing user, repeating the step; if all the models are used and the judgment result is that the electricity stealing users are not suspected, outputting the electricity stealing users and ending the method;
and 5: and performing field check work according to the judgment result of the step 4.
In the step 1, the electric energy meter has a current measuring function, and the electricity consumption information acquisition system can acquire the operating parameters of the phase line current and the zero line current in real time.
In step 1, the current data refers to the real-time phase line current I acquired by the electric energy meterLWith real-time zero line current IN；
Uncapping event messageThe information comprises the uncapping times and the uncapping starting time TStart ofAnd end time T of uncappingEnd up；
For a user with an uncapping event, the electric quantity data refers to n before the uncapping event of the electric energy meter occurs1N after the sun2Daily electricity consumption data; if the uncapping recording event occurs on the Nth day, SNThe power on the Nth day, the first N1The data of the daily power consumption is
Rear n2The data of the daily power consumption is
For a user without an uncapping event, the electricity quantity data refers to electricity consumption data of each month from a self-contained meter date;
the business expansion process information refers to fault first-aid repair information so as to distinguish the abnormal event of uncovering caused by normal operation;
the station area line loss data comprises station area power supply quantity, station area power selling quantity and station area line loss rate;
in step 2, the invalid data includes data of failed acquisition, null data and scrambled data.
In step 3, 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 the phase current and the zero line current, a user corresponding to the electric energy meter with the difference value larger than the difference value threshold value and the error value of the phase current and the zero line exceeding the error threshold value is screened out as a suspected electricity stealing user, and the phase current and the zero line current difference value I satisfies the following relational expression:
I＝IN-IL
the phase and zero line current error k satisfies the following relation:
and if I is larger than the difference threshold and k is larger than the error threshold, the suspected electricity stealing user is judged.
The difference threshold is 0.5A and the error threshold is 30%.
And the event analysis model calculates the uncapping duration irrelevant to the business expansion process information in the uncapping abnormal event, screens suspected electricity stealing users according to whether the duration meets a set uncapping threshold value, and judges the specific electricity stealing type.
The decap threshold is [2,50 ]]Minute, i.e. opening time TEnd up-TStart ofIs [2,50 ]]The user in the minute is judged as a suspected electricity stealing user;
the method for judging the type of electricity stealing is as follows:
if T is less than or equal to 2minEnd up-TStart ofIf the time is less than or equal to 20min, judging that electricity is stolen for suspected short-circuit electric energy meter terminals and a metering loop inside the short-circuit electric energy meter;
if T is less than 20minEnd up-TStart ofIf the time is less than or equal to 30min, judging that the electricity is stolen by replacing the internal components of the electric energy meter;
if T is less than 30minEnd up-TStart ofAnd if the time is less than or equal to 50min, judging that the remote control electricity stealing device is installed.
The electric quantity analysis model respectively analyzes the users with and without the cover opening abnormal event;
if the uncapping abnormal event of the user is irrelevant to the business expansion process information, calculating n before the uncapping recording event of the user electric energy meter occurs1N after and2average daily charge per day, e.g. n1N after and2when the average daily electricity consumption of the day is larger than the electricity quantity difference threshold value, the user is considered as a suspected electricity stealing user;
and for the users without the abnormal uncapping events, calculating the electric quantity deviation of every two adjacent months from the self-meter-installing date, and screening out the users with the electric quantity difference exceeding the electric quantity threshold value of two adjacent months as suspected electricity stealing users.
The electric quantity difference threshold value and the used electric quantity threshold value are both 30 percent, n1And n2Are all 7.
The line loss analysis model judges the users meeting the following relations as suspected electricity stealing users:
wherein, if the suspected electricity stealing day of the user is D, the previous day electricity consumption of the user is SD-1The power supply amount of the station area in the previous day is TD-1The electricity sold before the platform area is RD-1The electricity consumption of the suspected electricity stealing day of the user is SDThe power supply quantity of the distribution room is TDThe electricity selling quantity of the distribution room is RD。
The line loss analysis threshold was 5%.
The method has the advantages that the existing diagnosis method is single diagnosis, electricity stealing methods have obvious characteristics of equipment intellectualization, behavior hiding and the like, the existing methods comprise means of clearing events in the meter, simulating current of the electric energy meter and the like, and the traditional single diagnosis cannot identify electricity stealing behaviors of users. The method comprehensively studies and judges suspected electricity stealing users by monitoring the self electric energy data and the associated data of the electric energy meter and establishing a multi-model diagnosis method based on big data from four dimensions of current comparison, event analysis, electric quantity comparison and transformer area line loss matching, flexibly configures the study and judgment models in an independent or combined mode, realizes the low-voltage electricity stealing intelligent diagnosis method based on the big data, accurately and quickly locks the electricity stealing users, and provides technical support for field investigation work. The set threshold value is an optimal value obtained through a large number of case analyses, so that the model can efficiently and accurately judge suspected electricity stealing users of a plurality of electricity stealing types, such as installation of a remote control electricity stealing device, replacement of internal components of the electric energy meter, short connection of terminals of the electric energy meter and short connection of an internal metering loop of the electric energy meter.
Drawings
Fig. 1 is an overall flow chart of a low-voltage electricity stealing intelligent diagnosis method based on big data.
Detailed Description
The present application is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present application is not limited thereby.
A low-voltage electricity stealing intelligent diagnosis method based on big data comprises the following steps:
step 1: collecting associated data of the electric energy meter;
the associated data comprises current data, uncapping event information, electric quantity data, business expansion process information and transformer area line loss data.
The electric energy meter has a current measuring function, and the electricity consumption information acquisition system can acquire operating parameters of phase line current and zero line current in real time; thus, the current data refers to the real-time phase line current I of the electric energy meterLWith real-time zero line current IN
The uncapping event information comprises uncapping abnormal event times and uncapping starting time TStart ofAnd end time T of uncappingEnd up；
For users with uncapping events, the electric quantity data refers to n before the uncapping event of the electric energy meter occurs1N after the sun2Daily electricity consumption data; if the uncapping recording event occurs on the Nth day, SNThe power on the Nth day, the first N1The data of the daily power consumption is
Rear n2The data of the daily power consumption is
For users without uncapping events, the electricity quantity data refers to electricity consumption data of each month from the self-contained meter date;
in the present embodiment, n1And n2Are all 7.
The business expansion process information refers to fault first-aid repair information and is used for distinguishing abnormal uncapping events caused by normal operation;
the station area line loss data comprises station area power supply quantity, station area power selling quantity and station area line loss rate;
step 2: cleaning the data collected in the step 1, and removing invalid data;
the invalid data comprises data which fails to be collected, null data and messy code data.
And step 3: establishing various low-voltage electricity stealing intelligent diagnosis models based on the electric energy meter associated data processed in the step 2;
the model established in the embodiment can be used for diagnosing the electricity stealing type, and the diagnosis comprises the steps of installing a remote control electricity stealing device, replacing an internal component of the electric energy meter, short-circuiting a binding post of the electric energy meter and short-circuiting an internal metering loop of the electric energy meter;
the low-voltage electricity stealing intelligent diagnosis model is established from several latitudes of electricity quantity, current, event records and line loss and comprises a current analysis model, an event analysis model, an electricity analysis model and a line loss analysis model.
The current analysis model includes the following:
under the normal wiring condition, current flows into the metering unit of the electric energy meter through the phase line, and returns to the electric energy meter through the zero line after flowing through the load, so that a complete closed loop is formed, the current of the phase line and the zero line flowing through the electric energy meter is the same current, and the amplitude is basically equal. If the electricity stealing behavior occurs, the phase and zero line currents of the electric energy meter are different inevitably.
The electric energy meter has a current measuring function, the electricity consumption information acquisition system can acquire phase and zero line current operating parameters in real time, and suspected electricity stealing users can be preliminarily judged by comparing the difference of the detected phase and zero line currents.
Calculating step 1 to detect the difference between the phase line current and the zero line current, and screening an object meeting the judgment logic of the difference between the phase line current and the zero line current, thereby intelligently identifying the suspected electricity stealing electric energy meter, wherein the specific matching rule is as follows: and (4) calculating and analyzing the difference of the phase and zero line currents, and screening out the electric energy meter of which the difference value is greater than the difference threshold value and the error value of the phase and zero lines exceeds the error threshold value. After the electricity stealing behavior occurs, the phase and zero line currents of the electric energy meter are different inevitably, and the difference value changes in direct proportion to the load. Through the analysis of the checking and treatment cases and the statistics of the difference value of the current phase and the zero line which are commonly used by the user, the difference threshold value is preferably 0.5A and the error threshold value is preferably 30%.
The phase and zero line current difference value I is expressed by the following formula:
I＝IN-IL
the phase and zero line current error k is expressed by the following formula:
and if I is larger than the difference threshold and k is larger than the error threshold, the suspected electricity stealing user is judged.
The event analysis model includes the following:
under the normal power consumption condition of user, the electric energy meter operation is reliable and stable, except normal maintenance and few false alarm condition, the electric energy meter can not report the unusual incident of uncapping voluntarily. And analyzing whether a rush-repair or fault processing work order exists during the uncovering period of the electric energy meter with the reported uncovering abnormal event, if no related industry expansion process information exists, calculating whether the uncovering duration meets a set uncovering threshold or not, eliminating the situation of false alarm, and screening suspected electricity stealing users.
The electric energy meter has an event active reporting function, the marketing system and the electricity utilization information acquisition system can acquire the business expansion process information and the uncovering event information in real time, suspected electricity stealing users can be screened and suspected electricity stealing methods can be given out by matching the uncovering recording time length of the electric energy meter with the time length required by the known electricity stealing strategy.
To opening the behavior that the electric energy meter stolen electricity in its inside implementation, can trigger the event record of uncapping of electric energy meter, to the electric installation remote control electricity stealing device of mainstream on the market at present, change the inside components and parts of electric energy meter, short circuit electric energy meter terminal, the electricity stealing modes such as the inside measurement circuit of short circuit electric energy meter are counted, find that the uncapping duration of above-mentioned electricity stealing mode all is in 2 ~ 50 minutes within ranges, consequently judge the user that uncapping duration all is in 2 ~ 50 minutes within ranges to be suspected electricity stealing user, concrete matching rule is as follows:
if T is less than or equal to 2minEnd up-TStart ofIf the time is less than or equal to 20min, judging that electricity is stolen for suspected short-circuit electric energy meter terminals and a metering loop inside the short-circuit electric energy meter;
if T is less than 20minEnd up-TStart ofIf the time is less than or equal to 30min, judging that the electricity is stolen by replacing the internal components of the electric energy meter;
if T is less than 30minEnd up-TStart ofAnd if the time is less than or equal to 50min, judging that the remote control electricity stealing device is installed.
The electric quantity analysis model comprises the following contents:
the electricity consumption of normal users can fluctuate within a certain range along with factors such as working days, rest days, holidays and the like, the electricity consumption of normal low-voltage residential users is relatively stable and small, and the situation that the electricity continuity fluctuates greatly can not occur. If the user steals electricity, the electric quantity before and after the electricity stealing will have a big difference. 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 quantities in the two time periods have obvious difference or not and are in accordance with the set electric quantity difference threshold value is analyzed, and therefore suspected electricity stealing users are judged. And for the behavior that electricity stealing is not carried out by opening the cover, calculating the electricity quantity data of adjacent months since the self-contained meter date, and analyzing whether the electricity quantity of two time periods has obvious difference and exceeds the electricity consumption threshold of two adjacent months, thereby judging the suspected electricity stealing users. Through statistics of the checked cases, in the embodiment, the electricity quantity difference threshold value and the electricity consumption threshold value are both 30%. The specific calculation method is as follows:
for users with uncapping abnormal events and irrelevant to the industry expansion process information, calculating n before the uncapping abnormal events of the user electric energy meter occur1N after and2average daily electricity consumption per day;
first n thereof1Average daily electricity:
rear n2Average daily electricity:
in bookIn the examples, n1And n2Are all 7.
When in use
And
and when the difference ratio of the power consumption is larger than the power consumption difference threshold value, the user is considered as a suspected electricity stealing user.
And for the users without the abnormal uncapping events, calculating the electric quantity deviation of every two adjacent months from the self-meter-installing date, and screening out the users with the electric quantity difference exceeding the electric quantity threshold value of two adjacent months as suspected electricity stealing users.
And if K is larger than the electricity consumption threshold of two adjacent months, the user is considered as a suspected electricity stealing user.
Wherein K is the adjacent electric quantity deviation every two months, MNFor electricity consumption in the first of two adjacent months, MN+1The electricity consumption of the second month in two adjacent months.
The line loss analysis model comprises the following contents:
when a user under the platform area steals electricity, the electricity consumption of the user, the electricity stealing proportion and other factors can influence the line loss to different degrees, and meanwhile, the loss electricity quantity of the platform area and the electricity consumption of the electricity stealing user can be in a certain proportional relation before and after the line loss rate changes. Matching the loss electric quantity before and after the line loss of the transformer area changes with the daily electric quantity of the user, and screening out the suspected abnormal users with the difference between the daily electric quantity difference before and after the user and the loss electric quantity of the transformer area within a line loss analysis threshold value. In the present embodiment, the line loss analysis threshold is 5%.
If D is the suspected electricity stealing day of the user, S is the previous day electricity consumption of the userD-1The power supply amount of the station area in the previous day is TD-1The electricity sold before the platform area is RD-1The electricity consumption of the suspected electricity stealing day of the user is SDThe power supply quantity of the distribution room is TDThe electricity selling quantity of the distribution room is RD。
The users meeting the following conditions are suspected electricity stealing users:
and 4, step 4: selecting an unused model from the models established in the step 3 to judge a suspected electricity stealing user, if the model is judged to be the suspected electricity stealing user, outputting the suspected electricity stealing user, and entering a step 5; if the user is judged to be not suspected to be the electricity stealing user, repeating the step; if all the models are used and the judgment result is that the user is not suspected to steal electricity, outputting the user which is not suspected to steal electricity, and ending the method.
And 5: and 4, performing corresponding field check work according to the judgment result of the step 4.
In the embodiment, the user type is a single-phase electric energy meter user capable of reading the phase current and the zero line current through transmission.
According to the low-voltage electricity stealing intelligent diagnosis method based on the big data, disclosed by the invention, the suspected electricity stealing behavior of a low-voltage user can be independently and compositely diagnosed by establishing the current, event record, electric quantity and transformer area line loss model, so that the problems of difficult analysis, large workload, difficult investigation and treatment and the like of the traditional low-voltage electricity stealing are solved, and the intelligent conversion of the low-voltage electricity stealing prevention work is realized.
The present applicant has described and illustrated embodiments of the present invention in detail with reference to the accompanying drawings, but it should be understood by those skilled in the art that the above embodiments are merely 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 for limiting the scope of the present invention, and on the contrary, any improvement or modification made based on the spirit of the present invention should fall within the scope of the present invention.
Claims (13)
1. The intelligent diagnosis method for low-voltage electricity stealing based on big data is characterized by comprising the following steps:
step 1: collecting associated data of the electric energy meter; the associated data comprises current data, uncapping event information, electric quantity data, business expansion process information and transformer area line loss data;
step 2: cleaning the data collected in the step 1, and removing invalid data;
and step 3: establishing various low-voltage electricity stealing intelligent diagnosis models based on the electric energy meter associated data processed in the step 2;
and 4, step 4: selecting an unused model from the models established in the step 3 to judge a suspected electricity stealing user, if the model is judged to be the suspected electricity stealing user, outputting the suspected electricity stealing user, and entering a step 5; if the user is judged to be not suspected to be the electricity stealing user, repeating the step; if all the models are used and the judgment result is that the electricity stealing users are not suspected, outputting the electricity stealing users and ending the method;
and 5: and performing field check work according to the judgment result of the step 4.
2. The intelligent diagnosis method for low-voltage electricity stealing based on big data as claimed in claim 1, wherein:
in the step 1, the electric energy meter has a current measuring function, and the electricity consumption information acquisition system can acquire the operating parameters of the phase line current and the zero line current in real time.
3. The intelligent diagnosis method for low-voltage electricity stealing based on big data according to claim 1 or 2, characterized in that:
in the step 1, the current data refers to a real-time phase line current I acquired by the electric energy meterLWith real-time zero line current IN；
The uncapping event information comprises uncapping times and uncapping starting time TStart ofAnd end time T of uncappingEnd up；
For a user with an uncapping event, the electric quantity data refers to n before the uncapping event of the electric energy meter occurs1N after the sun2Daily electricity consumption data; if the uncapping recording event occurs on the Nth day, SNThe power on the Nth day, the first N1The data of the daily power consumption is
Rear n2The data of the daily power consumption is
For a user without an uncapping event, the electricity quantity data refers to electricity consumption data of each month from a self-contained meter date;
the business expansion process information refers to fault first-aid repair information so as to distinguish an uncovering abnormal event caused by normal operation;
the transformer area line loss data comprise transformer area power supply quantity, transformer area electricity selling quantity and transformer area line loss rate.
4. The intelligent diagnosis method for low-voltage electricity stealing based on big data as claimed in claim 3, wherein:
in the step 2, the invalid data includes data of failed acquisition, null data and scrambled data.
5. The big data based intelligent diagnosis method for low-voltage electricity stealing according to claim 4, wherein:
in the step 3, 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.
6. The intelligent diagnosis method for low-voltage electricity stealing based on big data as claimed in claim 5, wherein:
the current analysis model calculates and analyzes the difference of the phase and zero line currents, and screens out that a user corresponding to the electric energy meter with the difference value larger than the difference threshold value and the error value of the phase and zero lines exceeding the error threshold value is a suspected electricity stealing user, and the phase and zero line current difference value I satisfies the following relational expression:
I＝IN-IL
the phase and zero line current error k satisfies the following relation:
and if I is larger than the difference threshold and k is larger than the error threshold, the suspected electricity stealing user is judged.
7. The intelligent diagnosis method for low-voltage electricity stealing based on big data as claimed in claim 6, wherein:
the difference threshold is 0.5A and the error threshold is 30%.
8. The intelligent diagnosis method for low-voltage electricity stealing based on big data as claimed in claim 5, wherein:
the event analysis model calculates the uncapping duration irrelevant to the business expansion process information in the uncapping abnormal event, screens suspected electricity stealing users according to whether the duration meets a set uncapping threshold value, and judges the specific electricity stealing type.
9. The intelligent diagnosis method for low-voltage electricity stealing based on big data as claimed in claim 8, wherein:
the uncapping threshold value is [2,50 ]]Minute, i.e. opening time TEnd up-TStart ofIs [2,50 ]]The user in the minute is judged as a suspected electricity stealing user;
the method for judging the electricity stealing type comprises the following steps:
if T is less than or equal to 2minEnd up-TStart ofIf the time is less than or equal to 20min, judging that electricity is stolen for suspected short-circuit electric energy meter terminals and a metering loop inside the short-circuit electric energy meter;
if T is less than 20minEnd up-TStart ofIf the time is less than or equal to 30min, judging that the electricity is stolen by replacing the internal components of the electric energy meter;
if T is less than 30minEnd up-TStart ofAnd if the time is less than or equal to 50min, judging that the remote control electricity stealing device is installed.
10. The intelligent diagnosis method for low-voltage electricity stealing based on big data as claimed in claim 5, wherein:
the electric quantity analysis model respectively analyzes users with and without cover opening abnormal events;
if the uncapping abnormal event of the user is irrelevant to the business expansion process information, calculating n before the uncapping recording event of the user electric energy meter occurs1N after and2average daily charge per day, e.g. n1N after and2when the average daily electricity consumption of the day is larger than the electricity quantity difference threshold value, the user is considered as a suspected electricity stealing user;
and for the users without the abnormal uncapping events, calculating the electric quantity deviation of every two adjacent months from the self-meter-installing date, and screening out the users with the electric quantity difference exceeding the electric quantity threshold value of two adjacent months as suspected electricity stealing users.
11. The intelligent diagnosis method for low-voltage electricity stealing based on big data as claimed in claim 10, wherein:
the electric quantity difference threshold and the power consumption threshold are both 30 percent, n1And n2Are all 7.
12. The intelligent diagnosis method for low-voltage electricity stealing based on big data as claimed in claim 5, wherein:
the line loss analysis model judges the users meeting the following relations as suspected electricity stealing users:
wherein, if the suspected electricity stealing day of the user is D, the previous day electricity consumption of the user is SD-1The power supply amount of the station area in the previous day is TD-1The electricity sold before the platform area is RD-1The electricity consumption of the suspected electricity stealing day of the user is SDThe power supply quantity of the distribution room is TDThe electricity selling quantity of the distribution room is RD。
13. The intelligent diagnosis method for low-voltage electricity stealing based on big data as claimed in claim 12, wherein:
the line loss analysis threshold is 5%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110582683.6A CN113311379A (en) | 2021-05-26 | 2021-05-26 | Low-voltage electricity stealing intelligent diagnosis method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110582683.6A CN113311379A (en) | 2021-05-26 | 2021-05-26 | Low-voltage electricity stealing intelligent diagnosis method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113311379A true CN113311379A (en) | 2021-08-27 |
Family
ID=77375198
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110582683.6A Pending CN113311379A (en) | 2021-05-26 | 2021-05-26 | Low-voltage electricity stealing intelligent diagnosis method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113311379A (en) |
Citations (3)
| 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 |
| CN110047013A (en) * | 2018-01-15 | 2019-07-23 | 国网江苏省电力公司常州供电公司 | It is anti-specially to become user's discontinuous form stealing electricity method |
| 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 |
-
2021
- 2021-05-26 CN CN202110582683.6A patent/CN113311379A/en active Pending
Patent Citations (3)
| 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 |
| CN110047013A (en) * | 2018-01-15 | 2019-07-23 | 国网江苏省电力公司常州供电公司 | It is anti-specially to become user's discontinuous form stealing electricity method |
| 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 |
Non-Patent Citations (5)
| Title |
|---|
| 孙洪波等: "三相三元件有功电能表防窃电技术", 重庆大学学报(自然科学版), vol. 25, no. 12, pages 87 - 90 * |
| 申丽曼等: "拆旧智能电能表检测系统的设计", 湖南电力, vol. 37, no. 6, pages 55 - 57 * |
| 肖明建等: "多维联动防窃电方法探讨", 佛山科学技术学院学报(自然科学版), vol. 31, no. 06, pages 4 - 8 * |
| 钟晓剑: "一种基于大数据分析的窃电嫌疑用户精准定位方法", 农村电气化, no. 07, pages 70 - 71 * |
| 陈仕军等: "基于曲线相似度和关联分析的窃电智能识别与预警", 浙江电力, vol. 36, no. 12, pages 33 - 36 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112098714B (en) | Electricity stealing detection method and system based on ResNet-LSTM | |
| CN103792420B (en) | Based on the anti-electricity-theft of load curve and supervision of power consumption method | |
| CN113221931B (en) | Electricity stealing prevention intelligent identification method based on electricity utilization information acquisition big data analysis | |
| CN111008193B (en) | Data cleaning and quality evaluation method and system | |
| CN110749784B (en) | Line electricity stealing detection method based on electric power data wavelet analysis | |
| CN110703009B (en) | Abnormal analysis and processing method for line loss rate of transformer area | |
| CN114094705A (en) | Low-voltage distribution room electricity stealing monitoring system based on line loss and user electricity consumption | |
| CN111506635A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive naive Bayes algorithm | |
| CN108233323A (en) | A kind of current leakage detection system | |
| CN115840922B (en) | Deep learning algorithm-based charging abnormal behavior analysis method | |
| CN115510781A (en) | Anti-electricity-stealing early warning model verification method based on anti-electricity-stealing simulation experiment platform | |
| CN109615273A (en) | A kind of electric car electrically-charging equipment method for evaluating state and system | |
| Yip et al. | Detection of energy theft and metering defects in advanced metering infrastructure using analytics | |
| CN113516336A (en) | Method and system for determining electricity stealing suspected user | |
| CN106685086B (en) | Remote power utilization management system | |
| CN115049410A (en) | Electricity stealing behavior identification method and device, electronic equipment and computer readable storage medium | |
| Douglas et al. | New approaches to the AGC nonconforming load problem | |
| Zhang et al. | Research on comprehensive diagnosis model of anti-stealing electricity based on big data technology | |
| CN113311379A (en) | Low-voltage electricity stealing intelligent diagnosis method based on big data | |
| CN110968838A (en) | Power utilization abnormity analysis method based on intelligent electric energy meter uncovering event | |
| CN109443395B (en) | Method and system for judging whether energy consumption intensity multipoint measurement difference value exceeds limit value | |
| CN114295880A (en) | Accurate location of electric power stealing and unusual power consumption behavior detection analysis model | |
| CN114839462A (en) | Intelligent anti-electricity-stealing monitoring method and system | |
| CN115514099A (en) | Electric power utilization safety inspection system and method | |
| CN115310982A (en) | Electricity larceny prevention early warning data analysis method |
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 |