Low-voltage transformer area electricity stealing diagnosis method and system based on event triggering

Abstract

The invention discloses a low-voltage transformer area electricity larceny diagnosis method and system based on event triggering, and belongs to the technical field of intelligent measurement. The method comprises the steps of obtaining a list of cover opening events / end button cover opening events of an electric energy meter of a power consumer, filtering out invalid events in the list, and taking residual events in the list as valid events; screening out users whose regression coefficient b value is in a preset electricity stealing interval; acquiring synchronous transparent reading data, and determining a current vector relationship of the user with the regression coefficient b value in the preset electricity stealing interval; whether the users with the regression coefficient b values in the preset electricity stealing interval are matched with a preset common zero mode or not is verified, the matched users are removed, and the remaining users with the regression coefficient b values in the preset electricity stealing interval serve as suspected electricity stealing users. According to the method, the measured value transparent reading task can be automatically triggered, so that the normalized data acquisition value is greatly reduced, and the problem of data acquisition pressure caused by accidental and less-incidence events is avoided.

Description

Technical Field

[0001] This invention relates to the field of intelligent measurement technology, and more specifically, to a method and system for diagnosing electricity theft in low-voltage distribution areas based on event triggering. Background Technology

[0002] With the increasing load capacity of low-voltage distribution areas, anti-electricity theft diagnosis faces a prominent contradiction between data acquisition efficiency and diagnostic accuracy. Traditional methods rely on high-frequency, full-volume data collection, such as daily 96-point load curves or daily 24-point live and neutral wire current, leading to strained communication channel resources and soaring storage costs. Especially in rural areas with weak communication conditions, data integrity rates are often below 70%. Current mainstream electricity theft diagnosis technologies have two major limitations:

[0003] First, routine, fixed-frequency data collection is prone to missing key abnormal features, while full-volume, high-frequency data collection is too costly and technically feasible in low-voltage distribution areas.

[0004] Secondly, it does not take into account the abnormal current in the live and neutral wires caused by the common neutral connection, and the existing simple threshold comparison algorithm has a high false alarm rate. Summary of the Invention

[0005] To address the above problems, this invention proposes an event-triggered method for diagnosing electricity theft in low-voltage distribution areas, comprising:

[0006] Obtain a list of events related to opening the cover / opening the button on the electricity meter of the electricity user, filter out invalid events in the list, and treat the remaining events in the list as valid events;

[0007] After a valid event triggers a data copying command, data copying is performed to obtain the copied data and verify the integrity of the copied data in order to obtain the valid copied data.

[0008] Based on effective over-the-horizon data, a linear regression equation for the current of the live and neutral wires is established, and users whose regression coefficient b value is within a preset electricity theft range are selected based on the linear regression equation for the current of the live and neutral wires.

[0009] For users whose regression coefficient b value is within the preset electricity theft range, synchronous transparent reading of the neutral and live wire current is initiated at the typical moment of uneven neutral and live wire current, synchronous transparent reading data is obtained, and the current vector relationship of users whose regression coefficient b value is within the preset electricity theft range is determined.

[0010] Based on the current vector relationship, it is verified whether users whose regression coefficient b value is in the preset electricity theft range match the preset common zero mode. Users whose regression coefficient b value matches the preset electricity theft range are removed, and the remaining users whose regression coefficient b value is in the preset electricity theft range are regarded as suspected electricity theft users.

[0011] Optional, invalid events include any of the following:

[0012] The time it takes for the lid to open is less than the time it takes for the lid to open.

[0013] Date greater than 31, month greater than 12;

[0014] The opening of the cover occurred three months prior to the installation date of the electricity meter.

[0015] The lid is open for more than 12 hours;

[0016] The incident of opening the meter cover occurred within the meter's calibration period;

[0017] The number of times the electricity meter was opened per day was greater than 3.

[0018] The number of button-cover incidents at the beginning of the day is greater than 3;

[0019] The number of times the lid was opened in a single week was greater than 5;

[0020] The number of button cover incidents at the beginning of a single week is greater than 5;

[0021] The incident of the lid being opened occurred during the start and end times of the metrological inspection and verification process.

[0022] Optional, transparent data includes:

[0023] The time of the user's electricity meter opening event / opening button event is used as the time node to obtain the user's electricity freezing data and neutral and live wire data for 14 days before and after the power outage / power failure event.

[0024] Optional, pass-through data, meeting the following requirements:

[0025] With four sampling points per day for seven consecutive days:

[0026] The current values ​​of the live and neutral wires collected at the same time should both be greater than 0.05A;

[0027] The time deviation of the live and neutral wire current acquisition at the same moment is within 30 seconds.

[0028] Optionally, verify the integrity of the transparent recording data to obtain valid transparent recording data, including:

[0029] Verify the transparent data to check for missing live and neutral wire current, timing deviations greater than 30 seconds, or abnormal differences.

[0030] If it exists, it will be removed, and the remaining copy data will be considered as valid pass-through data.

[0031] Eliminate cases where the absolute value of the difference between the live and neutral wire currents is the same across multiple rounds;

[0032] If the live and neutral wire current values ​​are missing at the same time, remove abnormal data where the live wire current is greater than the neutral wire current.

[0033] Optional, the linear regression equation for the live and neutral wire currents is as follows:

[0034] y = bx + a

[0035] Where y is the live wire current, x is the neutral wire current, b is the regression coefficient, and a is a constant.

[0036] Optionally, the method also includes:

[0037] Update the preset electricity theft zones based on users suspected of electricity theft.

[0038] Furthermore, this invention also proposes an event-triggered low-voltage transformer area electricity theft diagnosis system, comprising:

[0039] The event validity filtering unit is used to obtain a list of events related to opening the cover / opening the button cover of the electricity meter of the power user, filter out invalid events in the list, and treat the remaining events in the list as valid events.

[0040] The targeted data copying unit is used to perform data copying after a valid event triggers a data copying instruction, obtain the copied data, and verify the integrity of the copied data in order to obtain the valid copied data.

[0041] The electricity theft feature extraction unit is used to establish a linear regression equation for the current of the live and neutral wires based on valid over-the-counter data, and to screen out users whose regression coefficient b value is within a preset electricity theft range based on the linear regression equation for the current of the live and neutral wires.

[0042] The zero-crossing analysis unit is used to initiate synchronous transparent reading of the neutral and live wire current at the transformer substation level during typical moments of uneven neutral and live wire current for users whose regression coefficient b value is within the preset electricity theft range, obtain synchronous transparent reading data, and determine the current vector relationship of users whose regression coefficient b value is within the preset electricity theft range.

[0043] The diagnostic result generation unit is used to verify, based on the current vector relationship, whether users whose regression coefficient b value is in the preset electricity theft range match the preset common zero mode, remove users whose regression coefficient b value matches the preset electricity theft range, and regard the remaining users whose regression coefficient b value is in the preset electricity theft range as suspected electricity theft users.

[0044] Optional, invalid events include any of the following:

[0045] The time it takes for the lid to open is less than the time it takes for the lid to open.

[0046] Date greater than 31, month greater than 12;

[0047] The opening of the cover occurred three months prior to the installation date of the electricity meter.

[0048] The lid is open for more than 12 hours;

[0049] The incident of opening the meter cover occurred within the meter's calibration period;

[0050] The number of times the electricity meter was opened per day was greater than 3.

[0051] The number of button-cover incidents at the beginning of the day is greater than 3;

[0052] The number of times the lid was opened in a single week was greater than 5;

[0053] The number of button cover incidents at the beginning of a single week is greater than 5;

[0054] The incident of the lid being opened occurred during the start and end times of the metrological inspection and verification process.

[0055] Optional, transparent data includes:

[0056] The time of the user's electricity meter opening event / opening button event is used as the time node to obtain the user's electricity freezing data and neutral and live wire data for 14 days before and after the power outage / power failure event.

[0057] Optional, pass-through data, meeting the following requirements:

[0058] With four sampling points per day for seven consecutive days:

[0059] The current values ​​of the live and neutral wires collected at the same time should both be greater than 0.05A;

[0060] The time deviation of the live and neutral wire current acquisition at the same moment is within 30 seconds.

[0061] Optionally, verify the integrity of the transparent recording data to obtain valid transparent recording data, including:

[0062] Verify the transparent data to check for missing live and neutral wire current, timing deviations greater than 30 seconds, or abnormal differences.

[0063] If it exists, it will be removed, and the remaining copy data will be considered as valid pass-through data.

[0064] Eliminate cases where the absolute value of the difference between the live and neutral wire currents is the same across multiple rounds;

[0065] If the live and neutral wire current values ​​are missing at the same time, remove abnormal data where the live wire current is greater than the neutral wire current.

[0066] Optional, the linear regression equation for the live and neutral wire currents is as follows:

[0067] y = bx + a

[0068] Where y is the live wire current, x is the neutral wire current, b is the regression coefficient, and a is a constant.

[0069] Optionally, the diagnostic result generation unit is also used for:

[0070] Update the preset electricity theft zones based on users suspected of electricity theft.

[0071] In another aspect, the present invention also provides a computing device, comprising: one or more processors;

[0072] A processor is used to execute one or more programs;

[0073] When the one or more programs are executed by the one or more processors, the method described above is implemented.

[0074] In another aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the method described above.

[0075] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0076] This invention provides a low-voltage transformer area electricity theft diagnosis method based on event triggering, comprising: acquiring a list of meter opening events / terminal cover opening events of electricity users, filtering out invalid events in the list, and taking the remaining events in the list as valid events; triggering a data transparent reading instruction for valid events, performing data transparent reading, acquiring transparent reading data, and verifying the integrity of the transparent reading data to obtain valid transparent reading data; based on the valid transparent reading data, establishing a linear regression equation for the neutral and live wire currents, and filtering out users whose regression coefficient b value is within a preset electricity theft range based on the linear regression equation for the neutral and live wire currents; for users whose regression coefficient b value is within the preset electricity theft range, initiating transformer area-level synchronous transparent reading of the neutral and live wire currents at typical moments of neutral and live wire imbalance, acquiring synchronous transparent reading data, and determining the current vector relationship of users whose regression coefficient b value is within the preset electricity theft range; based on the current vector relationship, verifying whether users whose regression coefficient b value is within the preset electricity theft range match a preset common zero mode, removing users whose regression coefficient b value matches the preset electricity theft range, and taking the remaining users whose regression coefficient b value is within the preset electricity theft range as suspected electricity theft users. This invention can automatically trigger measurement value transcribing tasks, which greatly reduces the amount of routine data collection and avoids the data collection pressure problem caused by occasional or infrequent events. Attached Figure Description

[0077] Figure 1 This is a flowchart of the method of the present invention;

[0078] Figure 2 This is a flowchart of an embodiment of the method of the present invention;

[0079] Figure 3 This is a structural diagram of the system of the present invention. Detailed Implementation

[0080] Exemplary embodiments of the invention will now be described with reference to the accompanying drawings. However, the invention may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided to fully and completely disclose the invention and to fully convey its scope to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the drawings is not intended to limit the invention. In the drawings, the same units / elements are referred to by the same reference numerals.

[0081] Unless otherwise stated, the terms used herein (including technical terms) have their common meaning as understood by one of ordinary skill in the art. Furthermore, it is understood that terms defined in commonly used dictionaries should be understood to have a meaning consistent with the context of their relevant field, and not to be interpreted as having an idealized or overly formal meaning.

[0082] Example 1:

[0083] This invention proposes an event-triggered method for diagnosing electricity theft in low-voltage distribution areas, such as... Figure 1 As shown, it includes:

[0084] Step 1: Obtain a list of cover opening events / start button cover events of the electricity meter of the electricity user, filter out invalid events in the list, and take the remaining events in the list as valid events;

[0085] Step 2: After triggering the data copying command for a valid event, perform data copying, obtain the copied data, and verify the integrity of the copied data to obtain the valid copied data.

[0086] Step 3: Based on the effective over-metering data, establish a linear regression equation for the current of the live and neutral wires, and screen out users whose regression coefficient b value is within the preset electricity theft range based on the linear regression equation for the current of the live and neutral wires.

[0087] Step 4: For users whose regression coefficient b value is within the preset electricity theft range, initiate synchronous transparent reading of the neutral and live wire current at the transformer substation level at typical times of neutral-live wire imbalance, obtain synchronous transparent reading data, and determine the current vector relationship of users whose regression coefficient b value is within the preset electricity theft range.

[0088] Step 5: Based on the current vector relationship, verify whether users whose regression coefficient b value is in the preset electricity theft range match the preset common zero mode. Eliminate users whose regression coefficient b value is in the preset electricity theft range and identify the remaining users whose regression coefficient b value is in the preset electricity theft range as suspected electricity theft users.

[0089] Invalid events include any of the following:

[0090] The time it takes for the lid to open is less than the time it takes for the lid to open.

[0091] Date greater than 31, month greater than 12;

[0092] The opening of the cover occurred three months prior to the installation date of the electricity meter.

[0093] The lid is open for more than 12 hours;

[0094] The incident of opening the meter cover occurred within the meter's calibration period;

[0095] The number of times the electricity meter was opened per day was greater than 3.

[0096] The number of button-cover incidents at the beginning of the day is greater than 3;

[0097] The number of times the lid was opened in a single week was greater than 5;

[0098] The number of button cover incidents at the beginning of a single week is greater than 5;

[0099] The incident of the lid being opened occurred during the start and end times of the metrological inspection and verification process.

[0100] The data copied over includes:

[0101] The time of the user's electricity meter opening event / opening button event is used as the time node to obtain the user's electricity freezing data and neutral and live wire data for 14 days before and after the power outage / power failure event.

[0102] The transparent data transmission must meet the following requirements:

[0103] With four sampling points per day for seven consecutive days:

[0104] The current values ​​of the live and neutral wires collected at the same time should both be greater than 0.05A;

[0105] The time deviation of the live and neutral wire current acquisition at the same moment is within 30 seconds.

[0106] This includes verifying the integrity of the transparent recording data to obtain valid transparent recording data, including:

[0107] Verify the transparent data to check for missing live and neutral wire current, timing deviations greater than 30 seconds, or abnormal differences.

[0108] If it exists, it will be removed, and the remaining copy data will be considered as valid pass-through data.

[0109] Eliminate cases where the absolute value of the difference between the live and neutral wire currents is the same across multiple rounds;

[0110] If the live and neutral wire current values ​​are missing at the same time, remove abnormal data where the live wire current is greater than the neutral wire current.

[0111] The linear regression equation for the live and neutral wire current is as follows:

[0112] y = bx + a

[0113] Where y is the live wire current, x is the neutral wire current, b is the regression coefficient, and a is a constant.

[0114] The methods also include:

[0115] Update the preset electricity theft zones based on users suspected of electricity theft.

[0116] The invention will be described below with reference to specific examples:

[0117] The process is as follows Figure 2 As shown, it includes:

[0118] Step 1: First, obtain the list of events related to opening the cover / opening the cover of the electricity meter for the electricity user.

[0119] Step 2: Determine the validity of the electricity meter cover opening event / start button cover opening event. Filter out cover opening events / start button cover opening events that meet any of the following conditions:

[0120] (1) The time it takes for the lid to open is less than the time it takes for the lid to open;

[0121] (2) The date is greater than 31 and the month is greater than 12;

[0122] (3) The opening time occurred before "electricity meter installation time + 3 months";

[0123] (4) The lid is open for more than 12 hours;

[0124] (5) The opening of the meter cover occurred within the meter's calibration period;

[0125] (6) The number of times the electricity meter is opened per day is greater than 3;

[0126] (7) The number of button cover events at the beginning of a single day is greater than 3;

[0127] (8) The number of times the lid was opened in a single week is greater than 5;

[0128] (9) The number of button cover incidents at the beginning of a single week is greater than 5;

[0129] (10) The opening of the lid occurred during the start and end times of the metrological inspection and verification;

[0130] Step 3: Automatically trigger the electricity meter data reading task. Use the time of the user's electricity meter opening event / cover opening event as the time node for data analysis, and obtain the user's electricity consumption freeze data and live / neutral wire data for 14 days before and after the power outage / disconnection event. The data must meet the following conditions: 4 data points per day for 7 days before and after the event.

[0131] The current values ​​of the live and neutral wires collected at the same time should both be greater than 0.05A;

[0132] The time deviation of the live and neutral wire current acquisition at the same moment is within 30 seconds;

[0133] Eliminate cases where the absolute value of the difference between the live and neutral wire currents is the same across multiple rounds;

[0134] If the current values ​​for the live and neutral wires are missing at the same time, remove any abnormal data where the live wire current is greater than the neutral wire current.

[0135] Step 4: Screen users with abnormal live and neutral wire current. The least squares method is used to derive the fitted equation for the live and neutral wire current, i.e., the linear equation y = bx + a (where y is the live wire current, x is the neutral wire current, and a is the correction coefficient). This eliminates interference from asynchronous live and neutral wire current collection. The regression coefficient b is obtained through sample training. Users whose b values ​​fall within [θ1, θ2] (generally [1, 3, 20] corresponds to a theft rate of 30%-95%, and the threshold can be adjusted) are selected.

[0136] Step 5: Verify whether the imbalance between the live and neutral wires for low-voltage users is caused by a common neutral wire. The verification process is as follows:

[0137] First, select a typical moment when the current in the live and neutral wires is uneven.

[0138] Next, a data transfer task is triggered to transfer the live and neutral current data values ​​of all users in the low-voltage distribution area at that moment.

[0139] Determine if the current meets the following common-zero condition:

[0140] Determine if the user with the zero-fire anomaly is related to users A, B, C... within the same transformer area, satisfying condition I. A0 ≈I A +I B +I C ,I B0 ≈0,I C0 If the value is approximately 0, it indicates a common zero situation where multiple meters' neutral wires are short-circuited.

[0141] Determine if the user with the zero-fire anomaly meets the I-value requirement with other users within the same area. A0 ≈I A +I B +I C， I B0 ≈I B+I C， I C0 ≈I C If so, it means that the user has a common neutral connection: the neutral wire output of meter A is connected to the neutral wire input of meter B, and the neutral wire output of meter B is connected to the neutral wire input of meter C.

[0142] Determine if the user with the zero-fire anomaly meets the I-value requirement with other users within the same area. A0 ≈I B0 ≈I C0 ≈I A +I B +I C If so, it means that the user connects the neutral wire out of meter A to the neutral wire in of meter B, and the neutral wire out of meter B to the neutral wire in of meter C, and users A, B, and C share the neutral wire out of user C.

[0143] Determine if the user with the zero-fire anomaly meets the I-value requirement with other users within the same area. A0 ≈I B I B0 ≈I A If so, it means that the problem is caused by the neutral wire of meter A being connected to user B, and the neutral wire of meter B being connected to user A, resulting in cross-connection of neutral wires.

[0144] To determine whether the ratio of the neutral current of users with abnormal neutral-liveness conditions to that of users within the transformer area is constant, let's assume users A, B, and C have a neutral current ratio of I... A0 ≈k1(I A +I B +I C ), I B0 ≈k2(I A +I B +I C ), I C0 ≈k3(I A +I B +I C K1, K2, and K3 are fixed values. If they are, it means that the neutral wires of the energy meters A, B, and C are connected in parallel to form a common neutral.

[0145] Step 6: Output a list of suspected electricity theft users and push it to the maintenance terminal. Adjust the threshold range based on the historical false alarm rate.

[0146]

[0147] Example 2:

[0148] Furthermore, this invention also proposes an event-triggered low-voltage distribution area electricity theft diagnosis system, such as... Figure 3 As shown, it includes:

[0149] The event validity filtering unit is used to obtain a list of events related to opening the cover / opening the button cover of the electricity meter of the power user, filter out invalid events in the list, and treat the remaining events in the list as valid events.

[0150] The targeted data copying unit is used to perform data copying after a valid event triggers a data copying instruction, obtain the copied data, and verify the integrity of the copied data in order to obtain the valid copied data.

[0151] The electricity theft feature extraction unit is used to establish a linear regression equation for the current of the live and neutral wires based on valid over-the-counter data, and to screen out users whose regression coefficient b value is within a preset electricity theft range based on the linear regression equation for the current of the live and neutral wires.

[0152] The zero-crossing analysis unit is used to initiate synchronous transparent reading of the neutral and live wire current at the transformer substation level during typical moments of uneven neutral and live wire current for users whose regression coefficient b value is within the preset electricity theft range, obtain synchronous transparent reading data, and determine the current vector relationship of users whose regression coefficient b value is within the preset electricity theft range.

[0153] The diagnostic result generation unit is used to verify, based on the current vector relationship, whether users whose regression coefficient b value is in the preset electricity theft range match the preset common zero mode, remove users whose regression coefficient b value matches the preset electricity theft range, and regard the remaining users whose regression coefficient b value is in the preset electricity theft range as suspected electricity theft users.

[0154] Invalid events include any of the following:

[0155] The time it takes for the lid to open is less than the time it takes for the lid to open.

[0156] Date greater than 31, month greater than 12;

[0157] The opening of the cover occurred three months prior to the installation date of the electricity meter.

[0158] The lid is open for more than 12 hours;

[0159] The incident of opening the meter cover occurred within the meter's calibration period;

[0160] The number of times the electricity meter was opened per day was greater than 3.

[0161] The number of button-cover incidents at the beginning of the day is greater than 3;

[0162] The number of times the lid was opened in a single week was greater than 5;

[0163] The number of button cover incidents at the beginning of a single week is greater than 5;

[0164] The incident of the lid being opened occurred during the start and end times of the metrological inspection and verification process.

[0165] The data copied over includes:

[0166] The time of the user's electricity meter opening event / opening button event is used as the time node to obtain the user's electricity freezing data and neutral and live wire data for 14 days before and after the power outage / power failure event.

[0167] The transparent data transmission must meet the following requirements:

[0168] With four sampling points per day for seven consecutive days:

[0169] The current values ​​of the live and neutral wires collected at the same time should both be greater than 0.05A;

[0170] The time deviation of the live and neutral wire current acquisition at the same moment is within 30 seconds.

[0171] This includes verifying the integrity of the transparent recording data to obtain valid transparent recording data, including:

[0172] Verify the transparent data to check for missing live and neutral wire current, timing deviations greater than 30 seconds, or abnormal differences.

[0173] If it exists, it will be removed, and the remaining copy data will be considered as valid pass-through data.

[0174] Eliminate cases where the absolute value of the difference between the live and neutral wire currents is the same across multiple rounds;

[0175] If the live and neutral wire current values ​​are missing at the same time, remove abnormal data where the live wire current is greater than the neutral wire current.

[0176] The linear regression equation for the live and neutral wire current is as follows:

[0177] y = bx + a

[0178] Where y is the live wire current, x is the neutral wire current, b is the regression coefficient, and a is a constant.

[0179] The diagnostic result generation unit is also used for:

[0180] Update the preset electricity theft zones based on users suspected of electricity theft.

[0181] The invention will be described below with reference to specific examples:

[0182] The system includes:

[0183] The event validity filtering unit is configured to: collect a list of events related to opening the cover / opening the button cover from the energy meter; and filter invalid events based on preset rules, including events with contradictory timing, illegal dates, initial installation events, excessively long events, verification period events, or events exceeding the frequency limit.

[0184] The targeted data transparent reading unit is configured to: trigger a data transparent reading instruction for a valid event, and request the power freezing data and neutral and live wire current data within the time window [T0-7 days, T0+7 days] based on the event occurrence time T0; perform integrity verification on the transparent reading data, and remove data points with missing neutral and live wire current, timing deviation > 30 seconds or abnormal difference;

[0185] The electricity theft feature extraction unit is configured as follows: based on valid over-the-horizon data, construct a linear regression equation for the live wire current y=bx+a (y is the live wire current, x is the neutral wire current); and filter users whose regression coefficient b value is in the preset electricity theft interval [θ1,θ2].

[0186] The common zero analysis unit is configured to: initiate synchronous transparent reading of the neutral and live line currents at the substation level during typical moments of neutral-live line imbalance; and verify whether it matches the preset common zero mode based on the multi-user current vector relationship.

[0187] The diagnostic result generation unit is configured to output a list of suspected electricity theft after removing users with zero electricity consumption.

[0188] The event validity filtering unit includes:

[0189] The frequency calculation subunit counts the number of events per day / week and compares them with a threshold.

[0190] The time verification subunit verifies the legality of the event timing and whether it is within the metering inspection period.

[0191] Among them: the data acquisition instruction sending unit sends a data reading instruction with a time window to the energy meter;

[0192] The data preprocessor performs at least one of the following operations:

[0193] Data points where both live and neutral wire current values ​​are ≤0.05A are excluded;

[0194] Correct asynchronous data with a time deviation greater than 30 seconds;

[0195] Filter out abnormal records where the live wire current is greater than the neutral wire current.

[0196] The electricity theft feature extraction module as described in claim 1 is characterized in that:

[0197] The least squares method is used to fit the equation for the live wire and neutral wire current: y = bx + a (y: live wire current, x: neutral wire current).

[0198] Users with regression coefficients b ∈ [θ1, θ2] are selected. (θ is a threshold, typically between 1.3 and 20.)

[0199] The common-zero analysis unit includes:

[0200] The neutral wire short-circuit identification unit detects whether the condition IA0≈∑I is met. h And for other users, I0≈0;

[0201] Cascaded zero-identification units detect whether the following conditions are met: IA0≈IA+IB+IC, IB0≈IB+IC, IC0≈IC;

[0202] Parallel common-zero identification units are used to detect whether the multi-user I0 and ∑I are satisfied. h They are in a fixed proportional relationship.

[0203] Among them, the cascaded common-zero identification unit verifies the topology through the current relationship formula:

[0204] |(IA0-(IA+IB+IC))|<δ1,

[0205] |(IB0-(IB+IC))|<δ2,

[0206] |IC0-IC|<δ3 (δ is the error threshold).

[0207] The diagnostic result generation unit is connected as follows:

[0208] The alarm push interface sends a list of suspected users and current data to the operation and maintenance terminal.

[0209] The dynamic optimization unit dynamically adjusts the electricity theft interval [θ1, θ2] based on the historical false alarm rate. The adjustment formula is as follows:

[0210]

[0211] (FP: False positives, FN: False negatives, N / M: Statistical sample size, α / β: Learning rate factor)

[0212] This invention automatically triggers measurement value transcribing tasks based on screening effective alarm events and screening users with uneven fire conditions, thereby significantly reducing the amount of routine data collection and avoiding the data collection pressure problem caused by occasional or infrequent events.

[0213] This invention fully considers various situations of common neutral wiring in the field, and can effectively identify whether the unevenness between neutral and live wires is caused by common neutral wiring, thereby reducing the interference of diagnostic model misjudgment.

[0214] Example 3:

[0215] Based on the same inventive concept, this invention also provides a computer device, which includes a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to implement corresponding method flows or corresponding functions, thereby implementing the steps of the methods in the above embodiments.

[0216] Example 4:

[0217] Based on the same inventive concept, this invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of the method in the above embodiments.

[0218] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0219] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0220] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0221] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0222] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0223] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for diagnosing electricity theft in low-voltage distribution areas based on event triggering, characterized in that, include: Obtain a list of events related to opening the cover / opening the button on the electricity meter of the electricity user, filter out invalid events in the list, and treat the remaining events in the list as valid events; After a valid event triggers a data copying command, data copying is performed to obtain the copied data and verify the integrity of the copied data in order to obtain the valid copied data. Based on effective over-the-horizon data, a linear regression equation for the current of the live and neutral wires is established, and users whose regression coefficient b value is within a preset electricity theft range are selected based on the linear regression equation for the current of the live and neutral wires. For users whose regression coefficient b value is within the preset electricity theft range, synchronous transparent reading of the neutral and live wire current is initiated at the typical moment of uneven neutral and live wire current, synchronous transparent reading data is obtained, and the current vector relationship of users whose regression coefficient b value is within the preset electricity theft range is determined. Based on the current vector relationship, it is verified whether users whose regression coefficient b value is in the preset electricity theft range match the preset common zero mode. Users whose regression coefficient b value matches the preset electricity theft range are removed, and the remaining users whose regression coefficient b value is in the preset electricity theft range are regarded as suspected electricity theft users.

2. The method for diagnosing electricity theft in low-voltage distribution areas according to claim 1, characterized in that, The invalid event includes any of the following: The time it takes for the lid to open is less than the time it takes for the lid to open. Date greater than 31, month greater than 12; The opening of the cover occurred three months prior to the installation date of the electricity meter. The lid is open for more than 12 hours; The incident of opening the meter cover occurred within the meter's calibration period; The number of times the electricity meter was opened per day was greater than 3. The number of button-cover incidents at the beginning of the day is greater than 3; The number of times the lid was opened in a single week was greater than 5; The number of button cover incidents at the beginning of a single week is greater than 5; The incident of the lid being opened occurred during the start and end times of the metrological inspection and verification process.

3. The method for diagnosing electricity theft in low-voltage distribution areas according to claim 1, characterized in that, The data obtained through the transcribing includes: The time of the user's electricity meter opening event / opening button event is used as the time node to obtain the user's electricity freezing data and neutral and live wire data for 14 days before and after the power outage / power failure event.

4. The method for diagnosing electricity theft in low-voltage distribution areas according to claim 3, characterized in that, The transparent data must meet the following requirements: With four sampling points per day for seven consecutive days: The current values ​​of the live and neutral wires collected at the same time should both be greater than 0.05A; The time deviation of the live and neutral wire current acquisition at the same moment is within 30 seconds.

5. The method for diagnosing electricity theft in low-voltage distribution areas according to claim 3, characterized in that, The process of verifying the integrity of the transparent copy data to obtain valid transparent copy data includes: Verify the transparent data to check for missing live and neutral wire current, timing deviations greater than 30 seconds, or abnormal differences. If it exists, it will be removed, and the remaining copy data will be considered as valid pass-through data. Eliminate cases where the absolute value of the difference between the live and neutral wire currents is the same across multiple rounds; If the live and neutral wire current values ​​are missing at the same time, remove abnormal data where the live wire current is greater than the neutral wire current.

6. The method for diagnosing electricity theft in low-voltage distribution areas according to claim 1, characterized in that, The linear regression equation for the live and neutral wire currents is as follows: y = bx + a Where y is the live wire current, x is the neutral wire current, b is the regression coefficient, and a is a constant.

7. The method for diagnosing electricity theft in low-voltage distribution areas according to claim 1, characterized in that, The method further includes: Update the preset electricity theft zones based on users suspected of electricity theft.

8. A low-voltage distribution area electricity theft diagnosis system based on event triggering, characterized in that, include: The event validity filtering unit is used to obtain a list of events related to opening the cover / opening the button cover of the electricity meter of the power user, filter out invalid events in the list, and treat the remaining events in the list as valid events. The targeted data copying unit is used to perform data copying after a valid event triggers a data copying instruction, obtain the copied data, and verify the integrity of the copied data in order to obtain the valid copied data. The electricity theft feature extraction unit is used to establish a linear regression equation for the current of the live and neutral wires based on valid over-the-counter data, and to screen out users whose regression coefficient b value is within a preset electricity theft range based on the linear regression equation for the current of the live and neutral wires. The zero-crossing analysis unit is used to initiate synchronous transparent reading of the neutral and live wire current at the transformer substation level during typical moments of uneven neutral and live wire current for users whose regression coefficient b value is within the preset electricity theft range, obtain synchronous transparent reading data, and determine the current vector relationship of users whose regression coefficient b value is within the preset electricity theft range. The diagnostic result generation unit is used to verify, based on the current vector relationship, whether users whose regression coefficient b value is in the preset electricity theft range match the preset common zero mode, remove users whose regression coefficient b value matches the preset electricity theft range, and regard the remaining users whose regression coefficient b value is in the preset electricity theft range as suspected electricity theft users.

9. The low-voltage distribution area electricity theft diagnosis system according to claim 8, characterized in that, The invalid event includes any of the following: The time it takes for the lid to open is less than the time it takes for the lid to open. Date greater than 31, month greater than 12; The opening of the cover occurred three months prior to the installation date of the electricity meter. The lid is open for more than 12 hours; The incident of opening the meter cover occurred within the meter's calibration period; The number of times the electricity meter was opened per day was greater than 3. The number of button-cover incidents at the beginning of the day is greater than 3; The number of times the lid was opened in a single week was greater than 5; The number of button cover incidents at the beginning of a single week is greater than 5; The incident of the lid being opened occurred during the start and end times of the metrological inspection and verification process.

10. The low-voltage distribution area electricity theft diagnosis system according to claim 8, characterized in that, The data obtained through the transcribing includes: The time of the user's electricity meter opening event / opening button event is used as the time node to obtain the user's electricity freezing data and neutral and live wire data for 14 days before and after the power outage / power failure event.

11. The low-voltage distribution area electricity theft diagnosis system according to claim 10, characterized in that, The transparent data must meet the following requirements: With four sampling points per day for seven consecutive days: The current values ​​of the live and neutral wires collected at the same time should both be greater than 0.05A; The time deviation of the live and neutral wire current acquisition at the same moment is within 30 seconds.

12. The low-voltage distribution area electricity theft diagnosis system according to claim 10, characterized in that, The process of verifying the integrity of the transparent copy data to obtain valid transparent copy data includes: Verify the transparent data to check for missing live and neutral wire current, timing deviations greater than 30 seconds, or abnormal differences. If it exists, it will be removed, and the remaining copy data will be considered as valid pass-through data. Eliminate cases where the absolute value of the difference between the live and neutral wire currents is the same across multiple rounds; If the live and neutral wire current values ​​are missing at the same time, remove abnormal data where the live wire current is greater than the neutral wire current.

13. The low-voltage distribution area electricity theft diagnostic system according to claim 10, characterized in that, The linear regression equation for the live and neutral wire currents is as follows: y = bx + a Where y is the live wire current, x is the neutral wire current, b is the regression coefficient, and a is a constant.

14. The low-voltage distribution area electricity theft diagnosis system according to claim 8, characterized in that, The diagnostic result generation unit is also used for: Update the preset electricity theft zones based on users suspected of electricity theft.

15. A computer device, characterized in that, include: One or more processors; A processor is used to execute one or more programs; When the one or more programs are executed by the one or more processors, the method described in any one of claims 1-7 is implemented.

16. A computer-readable storage medium, characterized in that, It contains a computer program, which, when executed, implements the method as described in any one of claims 1-7.

Images