Temperature control by a recurrent fuzzy network designed by Clustering-aided Simplex Particle Swarm Optimization, called CSPSO, is proposed in this paper. With CSPSO, the number of rules in a recurrent fuzzy controller is determined automatically by fuzzy clustering. Once a new rule is generated, the corresponding parameters are further tuned by the hybrid of simplex method and particle swarm optimization. Design of a recurrent fuzzy controller for a practical experiment on water bath temperature control is performed. Comparisons with other learning approaches in this control problem have verified the performance of CSPSO.