TRAINING ANFIS USING ARTIFICIAL BEE COLONY ALGORITHM FOR NONLINEAR DYNAMIC SYSTEMS IDENTIFICATION


KARABOĞA D. , Kaya E.

22nd IEEE Signal Processing and Communications Applications Conference (SIU), Trabzon, Turkey, 23 - 25 April 2014, pp.493-496 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • City: Trabzon
  • Country: Turkey
  • Page Numbers: pp.493-496

Abstract

In this study, nonlinear dynamic systems are identified by using artificial bee colony (ABC) algorithm and adaptive neuro fuzzy inference system (ANFIS). ABC algorithm is used in training and updating of ANFIS. The most appropriate model is formed by optimizing the antecedent and conclusion parameters that are found in the structure of ANFIS. The dynamic systems that consist of one input and one output (SISO) are used for the identification of nonlinear dynamic systems. The obtained results are compared with fuzzy neural network, neural network and ANFIS-based methods such as RSONFIN, DFNN, RSEFNN-LF, WRFNN and RFNN. The simulation results show that the proposed method is successful in the identification of considered nonlinear dynamic systems.