BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//jEvents 2.0 for Joomla//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:4g7i3vd65kmc05mld7aoa2t00c@google.com
CATEGORIES:RTportal.ru
CREATED:20170606T092329
SUMMARY:Семинар СМиГО: Anomaly-to-failure Matching for Predictive Maintenance of Complex Systems
LOCATION:ИППИ РАН в 615 аудитории (6 этаж)
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:Докладчик: Евгений Бурнаев (совместная работа с Ерофеевым П.Д., Назаровым И
 .Н., Смоляковым Д.С.)\nТема: Anomaly-to-failure Matching for Predictive Mai
 ntenance of Complex Systems\n\nАннотация:\nPredictive analytics and modelin
 g become more and more important for maintenance of complex technical syste
 ms. Introduction of condition-based maintenance strategies in different ind
 ustries significantly reduces overall maintenance costs and improves reliab
 ility. Modern complex technical systems, e.g. aircraft engines, are fully e
 quipped with batches of sensors and detectors allowing for real time monito
 ring and diagnostics. Typically equipment falls into pre-failure state star
 ting with some minor flaws, e.g. cracks or leaks, that evolve in time and l
 ead up to critical failure events such as complete engine destruction. Natu
 ral need of the maintenance engineers is to be able to identify this flaws 
 as early as possible and thus try to prevent or even avoid critical events.
  Or at least be able to prepare for the event on time. In some cases based 
 on real time sensor observations it is possible to indirectly identify anom
 alies in system behavior related to the minor problems. That is where devel
 opment of accurate and reliable mathematical models and tools comes up to t
 he stage. In some industries, e.g. aviation, it is crucial to have models w
 ith maximum predictive power and strictly limited false alarm rate. In this
  presentation we specify generic validation framework for failure predictio
 n models and propose a novel exhaustive methodology for anomaly-to-failure 
 matching. We prove effectiveness and reliability of the proposed methodolog
 y in the specified validation framework on the real test case from aerospac
 e industry.\n This event was imported from: https://rtportal.ru/index.php/k
 alendar-sobytij/eventdetail/125/-/seminar-smigo-anomaly-to-failure-matching
 -for-predictive-maintenance-of-complex-systems?tmpl=component
DTSTAMP:20260812T215902Z
DTSTART;TZID=Europe/Moscow:20161115T183000
DTEND;TZID=Europe/Moscow:20161115T200000
SEQUENCE:0
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR