New nonlinear system control method using second order derivatives of Universal Learning Network

Kotaro Hirasawa, Masanao Ohbayashi, Masayuki Hashimoto, Jinglu Hu, Junichi Murata

研究成果: Conference article


Recently Universal Learning Networks (ULNs) have been proposed, which are a super set of any kinds of supervised learning networks. One of the important features of the ULNs is that the ULNs have a systematic algorithm for calculating higher order derivatives of the criterion function with respect to parameters. And a robust control method and chaos control method using the second order derivatives of the ULNs have been proposed. In this paper, a new control design method of the nonlinear systems is proposed, which is an extension of the above robust control method in terms of considering not only the stability but also the quick response of the systems.

ジャーナルProceedings of the IEEE International Conference on Systems, Man and Cybernetics
出版物ステータスPublished - 1998 12 1
イベントProceedings of the 1998 IEEE International Conference on Systems, Man, and Cybernetics. Part 3 (of 5) - San Diego, CA, USA
継続期間: 1998 10 111998 10 14


ASJC Scopus subject areas

  • Control and Systems Engineering
  • Hardware and Architecture