Electricity　theft　detection　is　very　important　for　the　economic　benefits　of　power　companies　and　the　effectiveness　of　safe　operation　of　power　systems.　At　present,　the　traditional　power　theft　detection　method　can　only　identify　whether　the　user　has　power　theft,　but　cannot　perform　rapid　and　accurate　inspections　for　various　types　of　power　theft　users.　Aiming　at　the　characteristics　of　medium-voltage　users　with　large　power　consumption　and　regular　power　consumption,　this　paper　proposed　a　method　for　detecting　the　type　of　power　theft　in　medium-voltage　distribution　lines　based　on　robust　regression　and　convolutional　neural　network.　Firstly,　considering　the　existence　of　abnormal　data　due　to　factors　such　as　communication　delay　interruption,　a　robust　regression　algorithm　is　used　to　reduce　its　impact　and　improve　the　accuracy　of　regression　analysis.　Secondly,　the　correction　coefficient　and　error　term　of　each　user　obtained　by　regression　are　taken　as　the　characteristics　of　user　stealing　electricity,　and　input　into　the　convolutional　neural　network　model　for　training　to　complete　the　identification　of　stealing　electricity　type.　Finally,　the　method　is　verified　by　simulation　and　measured　data.　The　results　show　that　under　different　disturbance　conditions,　the　proposed　method　can　accurately　identify　different　types　of　power　stealing　behaviors,　which　can　better　assist　on-site　investigation,　narrow　the　investigation　scope　and　improve　the　verification　rate.　©　2024　The　Author(s)