High　voltage　direct　current　(HVDC)　interference　is　the　stray　current　discharged　from　HVDC　transmission　line　to　the　ground　during　operation,　which　will　cause　great　damage　to　the　pipeline.　Pipeline　corrosion　protection　personnel　use　pipeline　potential　as　monitoring　data　to　monitor　interference　from　HVDC　in　real　time　and　determine　the　health　of　the　pipeline.　At　present,　the　corrosion　protection　industry　relies　on　human　experience　to　judge　HVDC　interference,　but　no　machine　learning　methods　have　been　used　to　detect　HVDC　interference.　In　this　study,　one-dimensional　convolutional　neural　network　(1-D　CNN)　was　used　to　analyze　the　time-series　data　of　pipeline　potential,　and　a　classifier　of　HVDC　interference　was　constructed　to　realize　the　automatic　detection　of　HVDC　interference.　The　experimental　results　show　that　the　classification　accuracy　of　1-D　CNN　in　the　pipeline　spontaneous　potential　time　series　data　reaches　91.6%,　which　is　better　than　the　general　feature　extraction　method,　and　can　effectively　detect　HVCD　interference.　©　2022,　The　Author(s),　under　exclusive　license　to　Springer　Nature　Singapore　Pte　Ltd.