BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//modelica.simtek.cc//amfc2026//speaker//DEW3SC
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-WEKZ8K@modelica.simtek.cc
DTSTART;TZID=CST:20260921T111000
DTEND;TZID=CST:20260921T113500
DESCRIPTION:Reflections on the Development Stages and Engineering Deploymen
 t of Physics-AI Integration: Challenges\, Solutions\, and Case Studies of 
 AI Agents in System Modeling and Simulation
DTSTAMP:20261004T070606Z
LOCATION:Main hall (R1016)
SUMMARY:Joint Host Spotlight - Aiguo Xu
URL:https://modelica.simtek.cc/amfc2026/talk/WEKZ8K/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-amfc2026-NAPY3J@modelica.simtek.cc
DTSTART;TZID=CST:20260921T144000
DTEND;TZID=CST:20260921T150500
DESCRIPTION:Web-based modeling platforms and automated modelchecking work
 flows in CI/CD pipelines require remotely callable Modelica frontend serv
 ices. This paper presents SMC (Simtek Modelica Compiler)\, a service-orien
 ted Modelica frontend implemented in Go. SMC exposes model loading\, struc
 tured queries\, diagnostics\, and flattening through a service API backed
  by a pipeline for parsing\, instantiation\, semantic analysis\, connectio
 n processing\, and flat-model generation. Drawing on the SMC implementati
 on\, we also discuss the engineering implications of Go for single-binary 
 deployment\, concurrent processing\, representation of Modelica language c
 onstructs\, and memory allocation. We demonstrate the prototype through in
 tegration with a web modeling platform. A common set of 606 comparable cla
 sses from the Modelica Standard Library (MSL) 4.0.0 is used both to assess
  frontend-result consistency against the OpenModelica Compiler (OMC) and t
 o measure flattening time\, memory allocation\, and garbage-collection be
 havior. The evaluation covers frontend artifacts and in-process processing
  costs\; backend processing\, code generation\, simulation\, and FMU expor
 t are outside its scope.
DTSTAMP:20261004T070606Z
LOCATION:Modelica Technology & AI (R1001)
SUMMARY:SMC: A Cloud-Deployable Modelica Frontend Service in Go - Hailong W
 ang\, Qingda Xu\, Enyang Zhang\, Longsheng Sun\, Rui Gao\, Aiguo Xu
URL:https://modelica.simtek.cc/amfc2026/talk/NAPY3J/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-amfc2026-GKSRCG@modelica.simtek.cc
DTSTART;TZID=CST:20260922T141500
DTEND;TZID=CST:20260922T144000
DESCRIPTION:Deep peak-shaving in coal-fired boilers causes non-linear dynam
 ics\, rendering traditional PID control insufficient for NOx emission mana
 gement. This paper proposes a Modelica-based digital twin framework for a 
 600 MW boiler. The CFD-PINN model is coupled with a physicsbased steam-sid
 e dynamic model and an adaptive correction layer driven by DCS (Distribute
 d Control System) data to ensure high-precision synchronization under oper
 ating condition drift. An intelligent reinforcement learning agent using t
 he Recurrent Proximal Policy Optimization (Recurrent PPO) algorithm is dev
 eloped to inject residual bias signals into the main loop\, optimizing NOx
  emissions without altering the original architecture. Validated in seven 
 scenarios spanning 300–600 MW\, this strategy reduces the 95thpercentile
  NOx by 19%–23% and emission fluctuations by 32.7%–43.2% across four d
 ynamic scenarios relative to both manually tuned and gain-scheduled PID ba
 selines\, while maintaining combustion efficiency. This approach provides 
 a deployable\, low-risk pathway for achieving stricter NOx compliance unde
 r deep peak shaving operation.
DTSTAMP:20261004T070606Z
LOCATION:FMI & MBSE (R2001)
SUMMARY:A Modelica-FMI digital twin for reinforcement learning-based NOx em
 ission control of boilers under deep peak shaving - Qing Duan\, Shengshan 
 Bi\, Xuyao Tang\, Dongyang Zhou\, Aiguo Xu
URL:https://modelica.simtek.cc/amfc2026/talk/GKSRCG/
END:VEVENT
END:VCALENDAR