Detail Stochastic Simulation of Variable-Structure Hybrid Models for Worst-Case Analyses   Oleh:  Urquía, Alfonso ; Dormido, Sebastián Jenis: Article from Article Dalam koleksi: Final Program and Book of Abstracts: The 4th Asian Control Conference, September 25-27, 2002 (Sep. 2002), page 1975-1980. Topik: Hybrid Models; Stochastic Simulation; Dynamic Model Fulltext: AC021545.PDF (134.18KB) Isi artikel A new approach to the computer simulation of hybrid dynamic models with random parameters and random initial condition is presented. It is especially appropriate for worst-case analysis, i.e., when the stochastic simulation purpose is bounding the range (i.e., the certain event space) of the output random variables. The stochastic-simulation traditional methodology is not adequate for this kind of analysis. According to the proposed new methodology, only one simulation of the hybrid model is carried out. The result of any mathematical calculus in which random variables are involved is another random variable. The probability of this new variable is calculated mathematically operating the probability of the random operands and the value of the deterministic operands. A computational framework conceived to facilitate the application of this methodology is proposed and its implementation current status discussed. Opini Anda Klik untuk menuliskan opini Anda tentang koleksi ini! Kembali

Copyright © 2006, 2007 Unika Atma Jaya, all rights reserved