Continuously　maintaining　software　requirements　traceability　links　is　essential　for　managing　and　evolving　software　systems.　Due　to　development　pressure,　traceability　links　are　usually　missing　during　the　early　development　phase　in　practice,　and　thus　many　information　retrieval-based　approaches　have　been　proposed　to　automatically　recover　the　traceability　links.　However,　such　approaches　typically　calculate　textual　similarities　among　software　artifacts　without　considering　specific　features　of　different　software　artifacts,　leading　to　less　accurate　results.　In　this　paper,　we　propose　a　hybrid　approach　to　recover　requirements　traceability　links,　which　combines　machine　learning　and　logical　reasoning　to　explore　features　of　use　cases　and　code.　On　one　hand,　our　approach　engineers　features　of　use　cases　and　code　by　taking　into　account　their　semantics,　based　on　which　a　classifier　is　trained　by　using　supervised　learning　algorithms.　On　the　other　hand,　we　investigate　and　leverage　the　structural　information　of　code　to　incrementally　discover　traceability　links　by　defining　a　list　of　reasoning　rules.　We　have　carried　out　a　series　of　experiments　to　compare　our　approach　with　state-of-the-art　methods,　the　results　of　which　show　that　our　approach　significantly　outperforms　others.