When　the　manufacturers　produce　capacitor　voltage　transformers　(CVT),　the　function　of　harmonic　measurement　is　not　considered.　Therefore,　this　paper　explores　methods　to　solve　the　problems　of　harmonic　measurement　from　the　perspective　of　manufacturers.　Using　the　amplitude-frequency　characteristic　curve　of　CVT　under　no-load　condition　and　standard　environment　as　the　benchmark,　the　estimation　method　of　stray　capacitance　parameters　in　CVT　based　on　CSO　algorithm　is　proposed.　Besides,　in　order　to　improve　the　accuracy　of　harmonic　correction　of　CVT　in　different　operating　environments,　this　paper　deeply　studies　the　influence　of　oil　temperature　and　industrial　frequency　on　internal　parameters　and　harmonic　transfer　characteristics　of　CVT.　On　this　basis,　this　paper　proposes　a　correction　method　of　CVT　harmonic　transfer　characteristic　curves　under　different　operating　environments　based　on　BP　neural　network　algorithm.　Finally,　under　the　actual　operating　environment,　calculating　the　amplitude-frequency　characteristic　curve　of　CVT　by　utilizing　the　actual　harmonic　voltages　at　the　secondary　side　of　the　TYP3-0.02HF$$　\mathrm{TYP}\sqrt{3}\hbox{-}　0.02\mathrm{HF}　$$　CVT　and　RCVT,　and　comparing　it　with　the　amplitude-frequency　characteristic　curve　of　CVT　predicted　by　the　BP　neural　network.　The　results　show　that　the　proposed　methods　are　effective　and　feasible.