基于GA-BP神经网络的用户窃电行为检测  

Detection of User Electric Stealing Behavior Based on GA-BP Neural Network

作　　者：钟海东 ZHONG Hai-dong(Guangzhou Huangpu Power Supply Bureau,Guangzhou 510000,China)

机构地区：[1]广州黄埔供电局,广东广州510000

出　　处：《电气开关》2024年第4期83-87,共5页Electric Switchgear

摘　　要：为了提升用户窃电行为检测结果的准确性,提出了一种基于GA-BP神经网络的用户窃电行为检测方法。采用GA算法对BP神经网络的权值和阈值进行优化,建立了GA-BP神经网络模型,采用某区域电力用户用电数据进行仿真分析,结果表明,GA-BP神经网络检测模型在用户窃电行为检测过程中的正确率高达95%,诊断效果更好,验证了所提方法的实用性和有效性。In order to improve the accuracy of user stealing behavior detection results,a user stealing behavior detection method based on GA-BP neural network is proposed.The GA algorithm was used to optimize the weights and thresholds of the BP neural network,and a GA-BP neural network model was established.Simulation analysis was conducted using electricity consumption data from a certain area of power users.The results showed that the accuracy of the GA-BP neural network detection model in the detection process of user electricity theft behavior was as high as 95%,and the diagnostic effect was better.This verified the practicality and effectiveness of the proposed method in this article.

关 键 词：窃电行为 检测 BP神经网络 遗传算法 

分 类 号：TM76[电气工程—电力系统及自动化]