BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical & Computer Engineering - ECPv6.17.5//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://ece.northeastern.edu
X-WR-CALDESC:Events for Department of Electrical & Computer Engineering
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Phoenix
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:20250101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Phoenix:20260224T133000
DTEND;TZID=America/Phoenix:20260224T163000
DTSTAMP:20260720T185325Z
CREATED:20260109T220817Z
LAST-MODIFIED:20260720T185325Z
UID:8222-1771939800-1771950600@ece.northeastern.edu
SUMMARY:Digital Twins for Printed Electronics: How Can AI Learn FHE Printing
DESCRIPTION:Benyamin Davaji\, Assistant Professor in the College of Engineering\, alongside Haiyang Yun\, Senior PhD Student\, will instruct a professional course titled “Digital Twins for Printed Electronics: How Can AI Learn FHE Printing” on February 24\, 2026\, from 1:30–4:30 p.m. MT. at FLEX 2026\, the premier international conference for Flexible and Hybrid Electronics (FHE)\, taking place in Phoenix\, Arizona. \nDigital Twin is a virtual representation of the structure\, context\, and behavior of physical systems or a process\, with a live link to a physical system serving as a key enabler for predictive and data-driven optimization. In Printed and Flexible Hybrid Electronics (FHE)\, manufacturing involves multiple interdependent variables—different printing technologies\, inks\, substrates\, and process conditions—each introducing its own complexity. In practice\, additional challenges such as equipment drift\, batch-to-batch variations\, and environmental fluctuations further impact process consistency and yield. Changing a process or transferring it between tools is often difficult\, as each setup is highly customized and sensitive to local conditions. To address these challenges\, Digital Twin frameworks connect data from design\, fabrication\, and metrology into continuously learning digital models. They enable early detection of process drifts\, virtual experimentation for process development\, and data-driven optimization that reduces time\, cost\, and waste. \nThis course introduces Digital Twin frameworks for FHE\, focusing on Deep Neural Network (DNN)-based predictive models. Participants will learn how to integrate design\, fabrication\, and metrology data into continuously learning virtual twins that detect process drifts\, enable virtual experimentation\, and optimize manufacturing. The program covers the full workflow—from image processing and virtual metrology to AI model training\, validation\, and hyperparameter tuning—using real datasets. A hands-on “Build Your Own Digital Twin” module in Google Colab will provide practical experience in training and refining models for printed electronics applications\, equipping attendees with both theoretical insight and applied skills for process optimization and performance prediction. \nFor more information\, visit the FLEX 2026 course page.
URL:https://ece.northeastern.edu/event/digital-twins-for-printed-electronics-how-can-ai-learn-fhe-printing/
LOCATION:MA
END:VEVENT
END:VCALENDAR