Anti-electric-larceny prediction method based on machine learning and apparatus thereof

Abstract

The invention relates to an anti-electric-larceny prediction method based on machine learning and an apparatus thereof. The method comprises the following steps of acquiring learning sample data and prediction sample data, wherein the learning sample data comprises an electric larceny characteristic factor, a user number, a voltage grade, an industry type and a subordinated line; the prediction sample data comprises an electric larceny characteristic factor, a user number, a voltage grade, an industry type and a subordinated line; carrying out pretreatment on the learning sample data and the prediction sample data; determining an anti-electric-larceny neural network model to the learning sample data after pretreatment; taking the prediction sample data as an input quantity of the anti-electric-larceny neural network model, operating the anti-electric-larceny neural network model and outputting an electric-larceny suspected coefficient of each user; according to the electric-larceny suspected coefficient, predicting an electric-larceny suspected family.

Description

technical field [0001] The present invention relates to the technical field of anti-stealing electricity, in particular to an anti-stealing electricity prediction method and device based on machine learning. Background technique [0002] The electric energy meter is divided into several important components such as a voltage coil, a current coil, a disc, a magnet, and a counter. If you want to steal electricity, you only need to change any of the input voltage, current, phase, and speed of the energy meter. This is the basic principle of electricity stealing. The current stealing methods mainly include the following: [0003] 1) Electricity stealing by undervoltage method [0004] The so-called under-voltage method stealing electricity means that the electricity thieves deliberately cause the metering voltage circuit to open or have poor contact, or change the normal wiring of the metering voltage circuit, or connect resistors in series with the voltage coil circuit, etc. ...

AI Technical Summary

Problems solved by technology

[0005] 2) Electricity stealing by undercurrent method

[0007] 3) Electricity stealing by phase shifting method

[0009] 4) Electricity stealing by differential expansion method

[0011] 5) Stealing electricity without meters

Disadvantages: cannot accurately prove electricity theft and electricity theft time

The disadvantage is: it brings inconvenience to meter reading and regular inspection

The disadvantage is: since there are many users on each distribution line, it is relatively heavy to find out the specific electricity theft points

And if the electricity thief tries to destroy the meter device, he will leave evidence of the time of electricity theft

The disadvantage is: if it is disturbed, it will reduce the reliability of power supply

The disadvantage is: if the transformation ratio of the current transformer is changed, it will not be able to identify

First of all, measures such as the seal of the metering cabinet (box) are not absolutely safe, and cannot be completely tamper-proof or ensure the reliability of power supply; in addition, through manual inspections, suspicious power-stealing users are first found, and then corresponding anti-stealing hardware is installed This original artificial anti-stealing mode will inevitably cause a large number of stealers to be called fish that slipped through the net, and it is likely that only a few will be found; moreover, expensive anti-stealing hardware costs will be paid

Images