BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//modelica.simtek.cc//amfc2026//speaker//F9SREQ
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-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:20261004T070711Z
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