论文信息 - A Method for Model Parameter Identification Using Parallel Genetic Algorithms

A Method for Model Parameter Identification Using Parallel Genetic Algorithms

In this paper we present a new approach for the model parameters identification problem of real time systems based on parallel genetic algorithms. The method has been applied to an specific problem such as the control movement of a high speed ship where parallelization allows us to achieve the time constraints. The algorithm has been developed using MPI and the experimental results has been obtained on an SGI Origin 2000.

[1] Lawrence. Davis,et al. Handbook Of Genetic Algorithms , 1990 .

[2] P.P.J. van den Bosch,et al. Modeling, identification, and simulation of dynamical systems , 1994 .

[3] Marco Dorigo,et al. Implicit Parallelism in Genetic Algorithms , 1993, Artif. Intell..

[4] Edward V. Lewis,et al. Principles of naval architecture , 1988 .

[5] Joaquín Aranda,et al. Identification of the Vertical Plane Motion Model of a High Speed Craft by Model Testing in Irregular Waves , 1998 .

[6] Zbigniew Michalewicz,et al. Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.

[7] Erick Cantú-Paz,et al. A Survey of Parallel Genetic Algorithms , 2000 .

[8] Thor I. Fossen,et al. Guidance and control of ocean vehicles , 1994 .

[9] Jens Lienig,et al. A parallel genetic algorithm for performance-driven VLSI routing , 1997, IEEE Trans. Evol. Comput..