As　many　bridges　have　been　installed　with　monitoring　systems　presently,　automatic　damage　detection　becomes　a　core　technique　of　bridge　health　monitoring　systems,　which　attracts　the　attention　of　many　researchers.　Based　on　the　characteristics　of　artificial　neural　networks　and　genetic　algorithm,　a　new　approach,　genetic　optimization　and　neural　networks　hybrid　algorithm,　is　put　forward　to　identify　the　damage　location　and　degree　of　bridge　structure.　Compared　with　the　traditional　artificial　neural　networks　algorithm,　the　global　convergence　effect　of　this　hybrid　algorithm　is　enhanced　by　use　of　the　optimization　rule　of　the　genetic　algorithm　in　the　searching　process.　A　testing　data　are　analyzed　with　this　method　and　the　results　are　compared　with　those　due　to　other　methods.　The　results　show　that　this　method　is　rational　and　credible.