Individual particle optimized functional link neural network for real time identification of nonlinear dynamic systems
Authors:
- 1 June 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21562318,p. 35-40
Abstract
This study considers a functional link neural network (FLNN) structure for identifying nonlinear dynamic systems. We tackle the problem of system identification in noisy environments by introducing an adaptive tuning structure based on individual particle optimization (IPO) for the nonlinear systems identification via functional link neural network. The IPO algorithm is applied in order to train the FLNN and achieve the optimum weights of the network for efficiently identifying the nonlinear systems. The proposed optimized FLNN is tested through several experiments, including real-time identification of some nonlinear dynamic systems. Finally, we develop a comparison between the results with the previous counterpart optimized FLNN based LMS, BP, and some evolutionary (GA, PSO, CLPSO) training algorithms. Simulation results verify that the proposed optimization technique, IPO, outperforms these algorithms in the sense of speedup and performance. The remarkable issue addressed here is introducing the IPO algorithm as a real-time optimal tuning technique, which is applicable in other real-time adaptive structures.Keywords
This publication has 16 references indexed in Scilit:
- Transition from particle swarm optimization to individual particle optimization2009
- Functional Link Artificial Neural Network for Classification Task in Data MiningJournal of Computer Science, 2007
- A new optimizer using particle swarm theory2002
- Identification and control of unknown chaotic systems via dynamic neural networksIEEE Transactions on Circuits and Systems I: Regular Papers, 1999
- Identification of nonlinear dynamic systems using functional link artificial neural networksIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1999
- Cognitive representation of motion: Evidence for friction and gravity analogues.Journal of Experimental Psychology: Learning, Memory, and Cognition, 1995
- Hybrid neural networks for nonlinear system identification1994
- Database mining: a performance perspectiveIEEE Transactions on Knowledge and Data Engineering, 1993
- Identification and control of dynamical systems using neural networksIEEE Transactions on Neural Networks, 1990
- Implied velocity and acceleration induce transformations of visual memory.Journal of Experimental Psychology: General, 1986