BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//modelica.simtek.cc//amfc2026//speaker//9CVJHH
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:CST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-amfc2026-HAMFRX@modelica.simtek.cc
DTSTART;TZID=CST:20260921T135000
DTEND;TZID=CST:20260921T165000
DESCRIPTION:There is an increasing need for hybrid models consisting of phy
 sical and machine-learning or surrogate model parts. XRG has developed the
  SMArtInt+ Library\, which enables the easy generation and integration of 
 neural networks from different sources and types. This tutorial provides a
  hands-on introduction to the use of this library\, which also includes a 
 Python toolbox. The main use case is the creation and integration of a tra
 nsient surrogate model for a thermodynamic application.\nThe tutorial focu
 ses on the generation and utilization of training data\, as well as the de
 finition and training of neural network architectures\, with the objective
  of developing high-performance surrogate models. Participants will be int
 roduced to different concepts and approaches for creating data-driven surr
 ogate models and will gain an understanding of the underlying methodologie
 s and best practices.\nA central part of the tutorial is the integration o
 f the trained neural networks and surrogate models into Modelica models us
 ing the SMArtInt+ Interface-Blocks\, allowing seamless substitution of phy
 sical components with learned surrogates. Additionally\, several concepts 
 of hybrid modeling that combine physical and data-driven approaches are in
 troduced\, with a strong focus on the practical integration of trained neu
 ral networks and surrogate models within the Modelica environment.\nFinall
 y\, model performance is evaluated through comparisons with the original p
 hysical model.
DTSTAMP:20261004T070712Z
LOCATION:Main hall (R1016)
SUMMARY:Workshop 5: SMArtInt+ - Hands-on AI: Generation and Integration of 
 Neural Networks and Surrogate Models into Modelica - Tim Hanke
URL:https://modelica.simtek.cc/amfc2026/talk/HAMFRX/
END:VEVENT
END:VCALENDAR