Learning Koopman operator under dissipativity constraints

Keita Hara, Masaki Inoue, Noboru Sebe

研究成果: Conference article査読

2 被引用数 (Scopus)

抄録

This paper addresses a learning problem for nonlinear dynamical systems with incorporating any specified dissipativity property. The nonlinear systems are described by the Koopman operator, which is a linear operator defined on the infinite-dimensional lifted state space. The problem of learning the Koopman operator under specified quadratic dissipativity constraints is formulated and addressed. The learning problem is in a class of the non-convex optimization problem due to nonlinear constraints and is numerically intractable. By applying the change of variable technique and the convex overbounding approximation, the problem is reduced to sequential convex optimization and is solved in a numerically efficient manner. Finally, a numerical simulation is given, where high modeling accuracy achieved by the proposed approach including the specified dissipativity is demonstrated.

本文言語English
ページ(範囲)1169-1174
ページ数6
ジャーナルIFAC-PapersOnLine
53
2
DOI
出版ステータスPublished - 2020
イベント21st IFAC World Congress 2020 - Berlin, Germany
継続期間: 2020 7月 122020 7月 17

ASJC Scopus subject areas

  • 制御およびシステム工学

フィンガープリント

「Learning Koopman operator under dissipativity constraints」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル