Juloski, Aleksandar (Eindhoven Univ. of Tech.), Weiland, Siep (Eindhoven Univ. of Tech.)

A Bayesian Framework for the Identification of Hybrid Systems

Scheduled for presentation during the Regular Session "Hybrid Systems I" (WeA05), Wednesday, July 26, 2006, 12:05−12:30, Room F

17th International Symposium on Mathematical Theory of Networks and Systems, July 24-28, 2006, Kyoto, Japan

This information is tentative and subject to change. Compiled on April 18, 2024

Abstract

In this paper we present a framework for identification of hybrid systems, based on switched input/output (SIO) models. The property of linearity for SIO models is defined. We further define hybrid generalizations of classic linear input/output models, such as switched ARX, switched ARMAX, and switched output error models which are shown to be linear in the SIO sense, and Box-Jenkins model, which is not linear. A Bayesian algorithm for identification of linear SIO models is developed. Operation of the developed algorithm is demonstrated on an example.