Fuzzy controller training using particle swarm optimization for nonlinear system control

Karakuzu C.

ISA TRANSACTIONS, cilt.47, ss.229-239, 2008 (SCI İndekslerine Giren Dergi) identifier identifier identifier

  • Cilt numarası: 47 Konu: 2
  • Basım Tarihi: 2008
  • Doi Numarası: 10.1016/j.isatra.2007.09.003
  • Sayfa Sayıları: ss.229-239


This paper proposes and describes an effective utilization of particle swarm optimization ( PSO) to train a Takagi-Sugeno ( TS)-type fuzzy controller. Performance evaluation of the proposed fuzzy training method using the obtained simulation results is provided with two samples of highly nonlinear systems: a continuous stirred tank reactor (CSTR) and a Van der Pol ( VDP) oscillator. The superiority of the proposed learning technique is that there is no need for a partial derivative with respect to the parameter for learning. This fuzzy learning technique is suitable for real-time implementation, especially if the system model is unknown and a supervised training cannot be run. In this study, all parameters of the controller are optimized with PSO in order to prove that a fuzzy controller trained by PSO exhibits a good control performance. (c) 2007, ISA. Published by Elsevier Ltd. All rights reserved.