BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Effective Predictive Maintenance at the Intersection of Machine Le
 arning and Operations Research
DTSTART:20260305T140000Z
DTEND:20260305T150000Z
DTSTAMP:20260414T091700Z
UID:indico-event-90@conferences.enbis.org
DESCRIPTION:Speakers: Nikolaus Haselgruber (CIS Consulting in Industrial S
 tatistics GmbH)\n\n\nEffective Predictive Maintenance at the Intersection 
 of Machine Learning and Operations Research\nSpeaker: Dr. David W. Coit (R
 utgers University\, Piscataway\, NJ\, USA)\nChair: Nikolaus Haselgruber\n
 Date: 5th March 2026\, at 15:00-16:00 CET\nAbstract:\nThe most effective 
 and useful application of predictive maintenance requires both operations 
 research models and machine learning or AI working together. Historically\
 , development of maintenance planning models has involved the rigorous app
 lication of reliability and maintenance probabilistic models and theory co
 mbined with formal analytical tools associated with operations research an
 d mathematical programming. These models\, while effective\, tend to produ
 ce static and non-changing strategies that do not reflect changing usage a
 nd environment conditions. Furthermore\, they are based on population char
 acteristics and do not adequatelyreflect individual differences of units w
 ithin the population or system. Alternatively\, predictive maintenance mod
 els which embraced machine learning can dynamically predict a remaining us
 eful life or RUL. These models do specifically reflect individual units wi
 thin the system andcan also adapt to changing conditions. However\, their 
 true effectiveness also requires a meaningful decision-rule on when to tak
 e action and what action\, i.e.\, either replace or repair or dynamically 
 reduce work-load to compensate for anticipated degradation. To be truly ef
 fective\, a combination of these philosophies is needed. The usefulness of
  predictive maintenance decision rules require the three-way integration o
 r intersection of machine learning\, reliability/maintenance theory and op
 erations research. In this talk\, we will summarize different approaches t
 o preventive or predictive maintenance models\, discuss their relative adv
 antages and disadvantages\, highlight a few notable examples to demonstrat
 e this three-way integration\, and finally present future research challen
 ges.\nBio:\n\nDavid Coit is a Professor in the Department of Industrial & 
 Systems Engineering at Rutgers University\, Piscataway\, NJ\, USA. He has 
 also had visiting professor positions at Universite Paris-Saclay\, Paris\,
  France and Tsinghua University\, Beijing\, China. His current teaching an
 d research involves system reliability modeling and optimization\, and ene
 rgy systems optimization. He has over 140 published journal papers and ove
 r 100 peer-reviewed conference papers (h-index 70)\, including the most hi
 ghly cited paper ever in Reliability Engineering & System Safety (RESS) an
 d the 4th most cited paper in IEEE Transactions on Reliability. He is curr
 ently an Associate Editor for RESS and Journal of Risk and Reliability and
  was previously an Associate or Department Editor for IEEE Transactions on
  Reliability and IISE Transactions. His research has been funded by USA Na
 tional Science Foundation (NSF)\, including a NSF CAREER grant to develop 
 new reliability optimization algorithms considering uncertainty. He has be
 en the recipient of the P. K. McElroy award\, Alain O. Plait award and Wil
 liam A. J. Golomski award for best papers and tutorials at the Reliability
  and Maintainability Symposium (RAMS). Prof. Coit received a BS degree in 
 mechanical engineering from Cornell University\, an MBA from Rensselaer Po
 lytechnic Institute (RPI)\, and MS and PhD in industrial engineering from 
 the University of Pittsburgh. He is a fellow of the Institute of Industria
 l & Systems Engineers (IISE).\n\nhttps://conferences.enbis.org/event/90/
URL:https://conferences.enbis.org/event/90/
END:VEVENT
END:VCALENDAR