Study on Stealing Recognition Model Based on Multi Feature Fusion
DENG Mingbin
XU Zhimiao
DENG Zhifei
ZHANG Zhuo
CHI Yanjie
Abstract：For the present situation,the stealing power methods of specialized users are various.At the same time,the feasi?bility of traditional anti-stealing power measures is low. A scheme of abnormal electricity intelligent analysis model based on multi-feature fusion is provided for this phenomenon. This scheme extracts the features of abnormal power performance and then judge the feature with threshold which is trained by machine learning methods.By fusing the judged result of each feature with the multi-feature fusion,the result can be transformed to abnormal exponent for screening of abnormal based on abnormal threshold.By this method,abnormal electricity users will be screened out basically.
Keywords：electrical behaviorfeature extractionfeature fusionstealing recognition
Publication Date：2017-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 2398-2401,2414 )