BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20261101T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260330T214930Z UID:447AF434-38B3-4706-95E6-6D7A649652AB DTSTART;TZID=America/New_York:20260327T130000 DTEND;TZID=America/New_York:20260327T140000 DESCRIPTION:Abstract:\n\nBrake pad wear directly impacts vehicle safety\, y et most existing sensors only issue warnings when pads are nearly depleted \, offering no estimate of remaining useful life. This thesis investigates a simulation-based machine-learning approach for predictive brake wear mo deling. A physics-based digital twin of an automotive braking system is us ed to generate synthetic data under varying operating and fault conditions . A public real-world EV dataset (EVIoT predictive maintenance) serves as an external reference to assess realism. The digital twin integrates a sys tem-level vehicle and brake model with a Finite Element Analysis-derived w ear formulation\, where wear rate depends on brake pressure\, rotor speed\ , and accumulated braking events. Time-series signals from each braking ev ent are processed as fixed-length sequences and analyzed using a recurrent neural network to estimate brake wear and classify brake health and fault states.\n\nOn another front\, sensing technologies in unmanned vehicles a re rapidly evolving. In a parallel research effort\, we conduct a comprehe nsive survey of recent advances in sensor technologies for unmanned and au tonomous systems\, examining applications and enabling techniques such as multi-sensor fusion\, calibration\, and synchronization to identify curren t capabilities\, limitations\, and emerging research directions supporting reliable autonomous operation.\n\nSpeaker(s): Dr. Mohammad El-Yabroudi\, Yerassyl Zhaikenov\, Megan Rumija\n\nRoom: E101\, Bldg: Engineering Buildi ng\, Southfield\, Michigan\, United States LOCATION:Room: E101\, Bldg: Engineering Building\, Southfield\, Michigan\, United States ORGANIZER:mguduri@ltu.edu SEQUENCE:19 SUMMARY:Simulation-Based Brake Wear Prediction and a Survey of Sensing Tech nologies for Autonomous Systems URL;VALUE=URI:https://events.vtools.ieee.org/m/550443 X-ALT-DESC:Description: <br /><p class="p1"><strong>Abstract:</strong></p>\ n<p class="p1">Brake pad wear directly impacts vehicle safety\, yet most e xisting sensors only issue warnings when pads are nearly depleted\, offeri ng no estimate of remaining useful life. This thesis investigates a simula tion-based machine-learning approach for predictive brake wear modeling. A physics-based digital twin of an automotive braking system is used to gen erate synthetic data under varying operating and fault conditions. A publi c real-world EV dataset (EVIoT predictive maintenance) serves as an extern al reference to assess realism. The digital twin integrates a system-level vehicle and brake model with a Finite Element Analysis-derived wear formu lation\, where wear rate depends on brake pressure\, rotor speed\, and acc umulated braking events. Time-series signals from each braking event are p rocessed as fixed-length sequences and analyzed using a recurrent neural n etwork to estimate brake wear and classify brake health and fault states.& nbsp\;</p>\n<p class="p1">On another front\, sensing technologies in unman ned vehicles are rapidly evolving. In a parallel research&nbsp\;effort\, w e conduct a comprehensive survey of recent advances in sensor technologies for unmanned and&nbsp\;autonomous systems\, examining applications and en abling techniques such as multi-sensor fusion\,&nbsp\;calibration\, and sy nchronization to identify current capabilities\, limitations\, and emergin g research&nbsp\;directions supporting reliable autonomous operation.</p> END:VEVENT END:VCALENDAR