In　order　to　make　full　use　of　redundant,　complementary　and　uncertain　information　and　thus　assess　the　structural　health　states　from　a　structural　health　monitoring　system,　a　new　damage　identification　method　by　integrating　with　rough　set　and　revised　counter-propagation　network　(RCPN)　model　is　proposed　in　this　paper.　In　this　method,　rough　set　is　used　to　deal　with　data　so　as　to　reduce　the　uncertainties　and　the　spatial　dimensions　of　data　firstly;　then　the　current　CPN　model　is　revised　so　as　to　improve　the　capabilities　of　processing　uncertainties　and　classification,　and　the　RCPN　model　is　used　to　identify　damage.　To　validate　the　method　proposed,　six　patterns　from　a　steel　frame　are　identified　finally,　and　the　effect　of　measurement　noise,　of　network　models　and　of　data　without　processing　by　rough　set　on　damage　identification　results　are　also　investigated.　The　results　show　that　the　proposed　method　not　only　reduces　the　spatial　dimension　of　data,　but　also　has　preferable　damage　identification　capability　and　robustness.　©Civil-Comp　Press,　2011.