The　ageing　status　of　the　oil-paper　insulation　is　closely　related　to　the　operation　of　the　transformers.　Recently,　near　infrared　spectroscopy　(NIRS)　is　used　to　identify　the　ageing　condition　of　oil-paper　insulation　for　it　is　a　more　rapid　and　nondestructive　detection　than　the　traditional　viscometry　method.　However,　the　identification　accuracy　of　existing　quantitative　analysis　method　of　NIRS　are　still　insufficient.　This　paper　proposed　an　improved　Linear　discriminant　analysis　(LDA)　method　to　classify　the　spectra　and　to　identify　the　ageing　condition　of　the　insulating　paper.　Based　on　DP　measurement,　the　insulating　paper　specimens　prepared　in　laboratory　are　divided　into　varying　ageing　groups.　The　principle　of　LDA　method　is　introduced.　The　classic　LDA　method　has　been　applied　to　identify　the　ageing　status　of　specimens　respectively　from　4　ageing　groups　and　3　ageing　groups.　The　results　show　that　LDA　has　a　better　performance　in　classifying　four　groups　than　three　groups.　To　achieve　an　accurate　ageing　condition　identification　with　balanced　accuracy　of　the　model　and　enough　categories　of　ageing　status,　the　improved　LDA　method　is　proposed.　The　identification　results　show　that　the　improved　method　has　satisfactory　performance　and　indicates　great　application　potentials　in　the　ageing　assessment　of　the　oil-paper　impregnated　insulation.　©　2021　IEEE.