This paper describes the application of genetic algorithms (GA) to identify a class of nonlinear SISO models composed of a memoryless nonlinearity in series with a linear transfer function. In contrast with recent literature on the considered problem, we encode in the chromosomes also the structure of the model (type of nonlinearity, number of zeros and poles), and use the GA to identify both the optimal structure and the associated parameters. New operators for mutation and crossover to deal with chromosomes with variable length are introduced. The effectiveness of the approach is tested on a set of case studies derived from literature
Genetic identification of dynamical systems with static nonlinearities / Dotoli, Mariagrazia; Maione, Guido; Naso, David; Turchiano, Biagio. - (2001), pp. 65-70. (Intervento presentato al convegno IEEE SMCia/01, Mountain Workshop on Soft Computing in Industrial Applications tenutosi a Virginia Tech, Blacksburg, Virginia, USA nel 25–27 giugno 2001) [10.1109/SMCIA.2001.936730].
Genetic identification of dynamical systems with static nonlinearities
DOTOLI, Mariagrazia;MAIONE, Guido;NASO, David;TURCHIANO, Biagio
2001-01-01
Abstract
This paper describes the application of genetic algorithms (GA) to identify a class of nonlinear SISO models composed of a memoryless nonlinearity in series with a linear transfer function. In contrast with recent literature on the considered problem, we encode in the chromosomes also the structure of the model (type of nonlinearity, number of zeros and poles), and use the GA to identify both the optimal structure and the associated parameters. New operators for mutation and crossover to deal with chromosomes with variable length are introduced. The effectiveness of the approach is tested on a set of case studies derived from literatureI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.