BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//16thmodelicafmiconference//talk//CLGH3S
BEGIN:VTIMEZONE
TZID:Europe/Zurich
BEGIN:DAYLIGHT
DTSTART:20240909T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241027T030000
RDATE:20251026T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250330T030000
RDATE:20260329T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Towards Integration of PeN-ODEs in a Modelica-based workflow - Lar
 s Mikelsons\, Andreas Hofmann
DTSTART;TZID=Europe/Zurich:20250909T102000
DTEND;TZID=Europe/Zurich:20250909T104500
DTSTAMP:20261110T114151Z
UID:pretalx-16thmodelicafmiconference-CLGH3S@pretalx.com
DESCRIPTION:Hybrid modeling – the combination of first-principle models 
 and machine learning – offers the potential to increase model accuracy w
 hile reducing modeling effort. Although approaches for creating hybrid mod
 els from system simulation models exist\, the unique characteristics of Mo
 delica-based\, object-oriented models – such as modularity and reusabili
 ty – can\, as of today\, not be utilized. In this contribution\, we expl
 ore approaches for bridging this gap to enable the use of hybrid models wi
 th Modelica. Key challenges of architecture definition\, training environm
 ent and reintegration of the trained machine learning parts into a Modelic
 a model are addressed. To illustrate our approach\, we present a case stud
 y involving a SCARA robot. This example demonstrates a partially integrate
 d workflow for hybrid modeling\, intended to serve as a foundation and mot
 ivation for further research.
LOCATION:Audi-Midi
URL:https://pretalx.com/16thmodelicafmiconference/talk/CLGH3S/
END:VEVENT
END:VCALENDAR
