This paper presents the identification of non-linear dynamical systems by recurrent fuzzy system models. Two types of recurrent fuzzy systems (RFS) models are discussed, the Takagi-Sugeno-Kang (TSK) type and the linguistic or Mamdani type. Both models are equivalent and the latter model may be represented by a fuzzy finite-state automaton. An identification procedure is proposed based on a standard general purpose genetic algorithm. First, the TSK rule parameters are estimated and, in a second step, the TSK model is converted into an equivalent linguistic model. The parameter identification is evaluated in some benchmark problems for non-linear system identification described in literature. The results show that RFS models achieve good numerical performance while keeping the interpretability of the actual system dynamics.