BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//16thmodelicafmiconference//talk//HE7NBB
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-16thmodelicafmiconference-HE7NBB@pretalx.com
DTSTART;TZID=CET:20250910T112500
DTEND;TZID=CET:20250910T115000
DESCRIPTION:Testing real hardware and simulation models in combination in a
  software- or hardware-in-the-loop set-up is challenging. One of the key f
 actors is the high demand for accuracy in the simulation model. If classic
 al modeling based on physical principles is not sufficient to reach the de
 sired level of accuracy\, hybrid modeling\, the combination of physical si
 mulation models and machine learning can be applied. In this publication\,
  we train a hybrid model for a controlled electric motor within the electr
 o-hydraulic braking system of a car under the conditions and restrictions 
 of a real engineering application in the field. We apply state-of-the-art 
 modeling patterns for this\, and further extend them with application spec
 ific methodological optimizations. Finally\, we investigate and show the q
 uantitative and qualitative advantages of the proposed approach for this s
 pecific application\, resulting in a gain in accuracy by multiple factors.
DTSTAMP:20260312T125634Z
LOCATION:Audi-Midi
SUMMARY:Br(e)aking the Boundaries of Physical Simulation Models: Neural Fun
 ctional Mock-up Units for Modeling the Automotive Braking System - Tobias 
 Thummerer\, Lars Mikelsons\, Fabian Jarmolowitz\, Daniel Sommer
URL:https://pretalx.com/16thmodelicafmiconference/talk/HE7NBB/
END:VEVENT
END:VCALENDAR