Based　on　the　analysis　of　the　foundation　information　of　underground　pipelines　system,　a　suit　of　indexes＇　system　was　set　up　to　evaluate　the　earthquake　damage　degree　of　metropolitan　underground　pipelines　system,　and　then　taking　RS　for　former　disposal　system　to　optimize　the　indexes　structure.　The　LS-SVM　model　was　used　to　evaluate　the　earthquake　damage　degree　of　underground　pipelines　based　on　the　complementary　superiority　of　RS　and　SVM　each　other.　Finally,　taking　the　underground　pipelines　in　Quanzhou　as　an　example,　after　doing　lots　of　prediction　experiments　and　comparing　with　other　common　prediction　methods　such　as　the　theory　method　and　BP　neural　network　algorithm,　the　method　proposed　in　the　paper　proved　to　be　effective　and　feasible.