BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Warsaw BEGIN:DAYLIGHT DTSTART:20260329T030000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST END:DAYLIGHT BEGIN:STANDARD DTSTART:20261025T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260916T121417Z UID:DC301CCF-A991-4EBE-87A5-DED041658AC8 DTSTART;TZID=Europe/Warsaw:20260916T093000 DTEND;TZID=Europe/Warsaw:20260916T101500 DESCRIPTION:Modern industrial systems increasingly need to bridge two world s with fundamentally different constraints: deterministic\, real-time cont rol at the shop floor and data-intensive\, AI-driven analytics in the clou d. This talk argues that real-time performance is not a property that scal es uniformly through the system\; it exists only in a narrow "waist" betwe en two much larger\, inherently non-real-time layers. At the bottom\, sens ors\, PLCs\, and SCADA systems are constrained by energy budgets\, making continuous\, deterministic transmission impractical\, especially in IoT an d IIoT deployments. At the top\, big data\, AI/ML pipelines\, digital twin s\, and LLM-based agents operate on volumes of data that preclude hard rea l-time guarantees. Only in between - where standards such as OPC UA FX and the emerging IEC/IEEE 60802 Time-Sensitive Networking profile now converg e to provide a common data model over deterministic Ethernet - can true re al-time behavior be achieved. Drawing on the presenter's work in industria l communication and Service-Oriented Architecture\, as well as recent work on vision-based diagnostic systems (including the MEDUSA project for ultr asound-based synovitis detection)\, the talk traces how data flows from th e physical layer\, through this real-time core\, up to signal and image pr ocessing\, edge AI\, and cloud-based analytics. The talk situates this "ho urglass" architecture within current standardization efforts (ISA-95:2025\ , RAMI 4.0/Asset Administration Shell\, ISO 23247\, OPC UA FX/TSN) and dis cusses the practical implications for designing systems that combine deter ministic control with modern AI-based decision support.\n\nCo-sponsored by : Poznan University of Technology\n\nSpeaker(s): Professor Marcin Andrzej Fojcik\, \n\nRoom: room 201\, Bldg: CENTER FOR MECHATRONICS\, BIOMECHANICS \, AND NANOENGINEERING\, POZNAŃ UNIVERSITY OF TECHNOLOGY\, ul. Jana Pawł a II 24\, 61-131 Poznań\, Poland\, Poznań\, Wielkopolskie\, Poland\, 61- 131\, Virtual: https://events.vtools.ieee.org/m/575270 LOCATION:Room: room 201\, Bldg: CENTER FOR MECHATRONICS\, BIOMECHANICS\, AN D NANOENGINEERING\, POZNAŃ UNIVERSITY OF TECHNOLOGY\, ul. Jana Pawła II 24\, 61-131 Poznań\, Poland\, Poznań\, Wielkopolskie\, Poland\, 61-131\, Virtual: https://events.vtools.ieee.org/m/575270 ORGANIZER:adam.dabrowski@put.poznan.pl SEQUENCE:49 SUMMARY:The Hourglass of Industrial Data: from Real-Time Signal Processing to AI URL;VALUE=URI:https://events.vtools.ieee.org/m/575270 X-ALT-DESC:Description: <br /><p><span lang="EN-US" style="font-size: 11.0p t\; line-height: 102%\; font-family: 'Calibri'\,sans-serif\; mso-fareast-f ont-family: Calibri\; mso-bidi-font-family: 'Times New Roman'\; mso-ansi-l anguage: EN-US\; mso-fareast-language: EN-US\; mso-bidi-language: AR-SA\;" >Modern industrial systems increasingly need to bridge two worlds with fun damentally different constraints: deterministic\, real-time control at the shop floor and data-intensive\, AI-driven analytics in the cloud. This ta lk argues that real-time performance is not a property that scales uniform ly through the system\; it exists only in a narrow "waist" between two muc h larger\, inherently non-real-time layers. At the bottom\, sensors\, PLCs \, and SCADA systems are constrained by energy budgets\, making continuous \, deterministic transmission impractical\, especially in IoT and IIoT dep loyments. At the top\, big data\, AI/ML pipelines\, digital twins\, and LL M-based agents operate on volumes of data that preclude hard real-time gua rantees. Only in between - where standards such as OPC UA FX and the emerg ing IEC/IEEE 60802 Time-Sensitive Networking profile now converge to provi de a common data model over deterministic Ethernet - can true real-time be havior be achieved. Drawing on the presenter's work in industrial communic ation and Service-Oriented Architecture\, as well as recent work on vision -based diagnostic systems (including the MEDUSA project for ultrasound-bas ed synovitis detection)\, the talk traces how data flows from the physical layer\, through this real-time core\, up to signal and image processing\, edge AI\, and cloud-based analytics. The talk situates this "hourglass" a rchitecture within current standardization efforts (ISA-95:2025\, RAMI 4.0 /Asset Administration Shell\, ISO 23247\, OPC UA FX/TSN) and discusses the practical implications for designing systems that combine deterministic c ontrol with modern AI-based decision support. </span></p> END:VEVENT END:VCALENDAR