Stability analysis of nonlinear systems using high order derivatives of universal learning networks

K. Hirasawa, Y. Yu, Takayuki Furuzuki, J. Murata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, a stability analysis method based on the higher order derivatives of ULNs is proposed. In the proposed method, the following are proposed. Firstly, if the absolute values of the first order derivatives of any nodes with respect to any initial disturbances approach zero at time infinity, then the trajectory is locally asymptotically stable. Secondly, the locally asymptotically stable region, where asymptotical stability is secured approximately is obtained by comparing the first order derivatives and higher order derivatives.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages1273-1278
Number of pages6
Volume2
Publication statusPublished - 2001
Externally publishedYes
EventInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC
Duration: 2001 Jul 152001 Jul 19

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'01)
CityWashington, DC
Period01/7/1501/7/19

    Fingerprint

ASJC Scopus subject areas

  • Software

Cite this

Hirasawa, K., Yu, Y., Furuzuki, T., & Murata, J. (2001). Stability analysis of nonlinear systems using high order derivatives of universal learning networks. In Proceedings of the International Joint Conference on Neural Networks (Vol. 2, pp. 1273-1278)