Information　fusion　is　introduced　to　enhance　the　accuracy　of　damage　detection　with　multi　sensors.　In　the　damage　information　fusion　for　character　level,　the　concept　for　integral　support　vector　machine　damage　detection　matrix,　damage　self-information　and　damage　information　entropy　are　presented.　The　structure　is　divided　into　multiple　substructures,　the　data　acquisition　and　support　vector　machine　are　established　for　each　substructure　in　order　to　form　integral　SVM　damage　detection　matrix.　In　the　damage　information　fusion　for　decision　level,　the　methods　based　on　fuzzy　set　theory,　material　element　theory　and　fuzzy　neural　network　are　studied.　The　results,　proven　by　a　numerical　example　of　space　structure,　show　that　the　methods　are　valid　and　effective.