In　the　area　of　fuzzy　control　for　civil　structures,　how　to　generate　fuzzy　rules　for　structural　vibration　control　is　a　key　issue.　In　this　paper,　a　dynamic　fuzzy　neural　network　(DFNN)　algorithm　is　adopted　to　extract　fuzzy　rules　based　on　the　sample　data　obtained　from　the　performance　of　the　system　under　optimal　control　algorithm.　First,　the　structure　and　algorithm　of　DFNN　is　introduced　.Then,　a　fuzzy　controller　is　designed　using　DFNN　algorithm　for　a　five-story　frame　controlled　by　an　active　mass　damper.　The　simulation　results　show　that　the　fuzzy　controller　is　very　effective　in　reducing　the　response　of　model　structure　under　seismic　excitation.　Moreover,　the　robustness　of　the　fuzzy　controller　is　validated　through　the　change　of　seismic　input　and　structural　parameters.　The　proposed　method　is　referential　to　the　design　of　fuzzy　controller　and　can　provide　a　necessary　foundation　for　the　practical　structural　control.　©2010　IEEE.