BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Memento EPFL// BEGIN:VEVENT SUMMARY:Reliability modeling and forecasting with two-stage stochastic deg radation models: bridge reinforced concrete rebar example DTSTART:20241108T121500 DTEND:20241108T131500 DTSTAMP:20260501T024458Z UID:929023d39a4418e44e7bc5265e2cbcb9ab4bf3f4ce37e583407102b4 CATEGORIES:Conferences - Seminars DESCRIPTION:Prof. David W. Coit\, Rutgers University\, USA\nAbstract\nStoc hastic degradation models offer distinct advantages compared to traditiona l reliability analyses. Many degradation processes occur in two distinct s tages or phases. This is not unusual or unexpected because (a) often the d esign includes protective coverings or coatings that beneficially delay th e onset of a degradation process\, (b) some physical or chemical processes naturally do not occur until there has been a time-delay of some type\, o r (c) after progressing gradually for some time\, a degradation process ma y become more aggressive and fundamentally change.\n\nThere have already b een several useful two-stage degradation models in the literature includin g the gamma-gamma and Weiner-Weiner models and others. In this talk\, we i ntroduce a new two-stage degradation model called the Weibull-gamma model. The first stage is modeled by a time-to-event distribution\, instead of a stochastic process\, to more closely resemble the physical behavior of so me delayed failure mechanisms\, while the second stage is a stochastic pro cess similar to other models. In the new model\, both stages are modeled a s a function of stress covariates\, which can then be used to conduct acce lerated testing. The model is demonstrated using an example of a steel reb ar used in reinforced concrete to build more reliable bridges. Testing dat a was collected for three years under accelerated conditions to evaluate t he feasibility and reliability of new steel materials exposed to more stre ssful conditions. While the new model to useful to predict reliability\, i t is not particularly useful to forecast future degradation. In the final part of the talk\, various machine learning forecasting methods are discus sed and demonstrated.\n\nShort bio\nDavid Coit is a Professor in the Depar tment of Industrial & Systems Engineering at Rutgers University\, Piscataw ay\, NJ\, USA. He has also had visiting professor positions at CentraleSup elec Université Paris-Saclay\, Paris\, France\, Tsinghua University\, Bei jing\, China\, and others. His current teaching and research involves syst em reliability modeling and optimization\, and energy systems optimization . He has over 140 published journal papers and over 100 peer-reviewed conf erence papers (h-index 65). He is currently an Associate Editor for IEEE T ransactions on Reliability and Journal of Risk and Reliability and for 15 years was a Department Editor for IISE Transactions. He has been a special issue editor for IISE Transactions\, Reliability Engineering & System Saf ety (RESS) and Computers & Industrial Engineering. His research has been f unded by USA National Science Foundation (NSF)\, U.S. Army\, U.S. Navy\, i ndustry\, and power utilities. His NSF grants included a CAREER grant to d evelop new reliability optimization algorithms considering uncertainty. He was also the recipient of the P. K. McElroy award\, Alain O. Plait award and William A. J. Golomski award for best papers and tutorials at the Reli ability and Maintainability Symposium (RAMS). Prof. Coit received a BS deg ree in mechanical engineering from Cornell University\, an MBA from Rensse laer Polytechnic Institute (RPI)\, and MS and PhD in industrial engineerin g from the University of Pittsburgh. He is a fellow of Institute of Indust rial & Systems Engineers (IISE).\n\nSandwiches are offered at the end of t he seminar.\n  LOCATION:GC B1 10 https://plan.epfl.ch/?room==GC%20B1%2010 https://epfl.zo om.us/j/69105801975 STATUS:CONFIRMED END:VEVENT END:VCALENDAR