A　damage　detection　method　using　BP　neural　network　based　on　a　novel　damage　index　and　the　correlation　characteristic　of　acceleration　response　was　proposed,　and　was　evaluated　through　FE　simulations　and　test　verifications.　On　the　basis　of　achievements　in　existence,　the　feasibility　of　taking　correlation　characteristic　as　a　damage　index　was　validated　theoretically.　The　damage　detection　for　a　simply-supported　beam　using　the　proposed　method　was　simulated.　The　results　showed　that　the　trained　BP　neural　network　can　correctly　detect　the　location　and　level　of　damages　in　both　single　damage　case　and　multi-damage　case.　A　model　test　of　a　reinforced　concrete　simply-supported　beam　was　performed　to　verify　the　validity　and　efficiency　of　the　damage　detection　method.