Abstract
This thesis is settled in the field of data-based modeling (identification) and specifically focuses on the weakening of the effects of the curse of dimensionality with local model networks (LMNs). The methods for fighting the curse of dimensionality originate from the fields of input selection and design of experiments (DoE).
Zusammenfassung
Das Themengebiet der Arbeit ist die datenbasierte Modellbildung (Identifikation). Das Hauptaugenmerk liegt auf Verfahren der Eingangsselektion und der Versuchsplanung, die dazu dienen, Effekte des Fluchs der Dimensionlität abzuschwächen, indem sie spezielle Eigenschaften lokaler Modellnetze ausnutzen.
About the author
Dr.-Ing. Julian Belz worked from 2012 to 2018 at the Chair of Automatic Control – Mechatronics (Prof. O. Nelles) at the University of Siegen, Germany. His main research topics concerned design of experiments and input selection for nonlinear system identification tasks. Today he works at SMS group GmbH in the research and development division. Main areas of work include feedback control tasks and active vibration damping in flat rolling mills.
© 2019 Walter de Gruyter GmbH, Berlin/Boston
