BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260402T024534Z
LOCATION:Level 3 Lobby
DTSTART;TZID=America/Los_Angeles:20250622T180000
DTEND;TZID=America/Los_Angeles:20250622T190000
UID:dac_DAC 2025_sess261_RESEARCH991@linklings.com
SUMMARY:GAIA: A Generative AI Approach for Enabling Aircraft Digital Twin 
 Creation
DESCRIPTION:Francesco Biondani, Luigi Capogrosso, and Nicola Dall'Ora (Uni
 versity of Verona); Enrico Fraccaroli (University of North Carolina, Chape
 l Hill); Domenico Migliore and Francesco Acerra (Leonardo S.p.A.); and Mar
 co Cristani and Franco Fummi (University of Verona)\n\nThe integrity and r
 eliability of Landing Gear System (LGS) is crucial for aircraft safety. \n
 However, the scarcity of real-world fault data hinders the creation of eff
 ective Predictive Maintenance (PdM) strategies, especially those relying o
 n modern Machine Learning (ML) techniques.\nAs a result, this paper presen
 ts GAIA: the first Generative Artificial Intelligence (GenAI) approach for
  enabling the creation of digital twins to support PdM in the aviation dom
 ain.\nSpecifically, by leveraging multi-physics modeling and data-driven t
 echniques, GAIA generates realistic in-distribution faulty samples to augm
 ent existing datasets.\nAs a use case, we consider the LGS and introduce D
 SLG D/R, a novel dataset specifically designed for LGS fault classificatio
 n, created in collaboration with omitted due to blind review.\nOur results
  demonstrate a significant 10.56% improvement in fault classification accu
 racy compared to other data augmentation methods.\nTo showcase the broader
  applicability of our method, we also evaluate it on the Electrical Faults
  dataset, a well-established benchmark for power system fault diagnosis.\n
 Again, GAIA consistently outperforms pure physics-driven and other data au
 gmentation methods, highlighting its versatility across critical safety do
 mains.\nThe code and dataset will be released upon acceptance.\n\nTracks: 
 DES5: Emerging Device and Interconnect Technologies\n\n
END:VEVENT
END:VCALENDAR