Linguistic　dynamic　systems　(LDS)　are　dynamic　processes　involving　computing　with　words　instead　of　numbers　for　modeling　and　analysis　of　complex　systems.　In　this　paper,　a　fuzzy　neural　network　(FNN)　structure　of　LDS　base　on　nonlinear　particle　swarm　optimization　was　proposed.　Finally,　experiment　results　on　logistics　formulation　demonstrated　the　feasibility　and　the　efficiency　of　the　proposed　FNN　model.