The　prediction　of　PM2.5　is　difficult　because　the　variation　of　PM2.5　concentration　is　a　nonlinear　dynamic　process.　Therefore,　a　recurrent　fuzzy　neural　network　prediction　method　is　proposed　to　predict　the　PM2.5　concentration　in　this　paper.　Firstly,　the　partial　least　squares　(PLS)　algorithm　is　used　to　select　key　input　variables　as　a　preprocessing　step.　Then,　a　recurrent　fuzzy　neural　network　model　is　established　and　the　gradient　descent　algorithm　with　an　adaptive　learning　rate　is　used　to　train　the　neural　network.　Simulation　results　show　that　the　recurrent　neural　network　has　better　prediction　performance　and　higher　interpretability　than　fuzzy　neural　network　(FNN)　and　radial-basis　function　(RBF)　feed　forward　neural　network.　©　2017　Technical　Committee　on　Control　Theory,　CAA.