The Hourglass of Industrial Data: from Real-Time Signal Processing to AI

#real-time #control #artificial #intelligence #(AI) #analytics #in #the #cloud #hourglass #architecture
Share

Modern industrial systems increasingly need to bridge two worlds with fundamentally different constraints: deterministic, real-time control at the shop floor and data-intensive, AI-driven analytics in the cloud. This talk argues that real-time performance is not a property that scales uniformly through the system; it exists only in a narrow "waist" between two much 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 deployments. At the top, big data, AI/ML pipelines, digital twins, and LLM-based agents operate on volumes of data that preclude hard real-time guarantees. Only in between - where standards such as OPC UA FX and the emerging IEC/IEEE 60802 Time-Sensitive Networking profile now converge to provide a common data model over deterministic Ethernet - can true real-time behavior be achieved. Drawing on the presenter's work in industrial communication and Service-Oriented Architecture, as well as recent work on vision-based diagnostic systems (including the MEDUSA project for ultrasound-based 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" architecture 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 control with modern AI-based decision support.


  Date and Time

  Location

  Hosts

  Registration


  • Add_To_Calendar_icon Add Event to Calendar

Loading virtual attendance info...

  • POZNAŃ UNIVERSITY OF TECHNOLOGY
  • ul. Jana Pawła II 24, 61-131 Poznań, Poland
  • Poznań, Wielkopolskie
  • Poland 61-131
  • Building: CENTER FOR MECHATRONICS, BIOMECHANICS, AND NANOENGINEERING
  • Room Number: room 201
  • Contact Event Host

  • The meeting on Sep. 16, 2026 at 9:30 AM CEST will be organized in a hybrid form

    https://emeeting.put.poznan.pl/eMeeting/paw-frx-owr-w28

    ul. Jana Pawła II 24, 61-131 Poznan, Poland, room 201

  • Co-sponsored by Poznan University of Technology
  • Starts 01 September 2026 10:00 PM UTC
  • Ends 16 September 2026 06:00 AM UTC
  • No Admission Charge

  Speakers

Professor Marcin Andrzej Fojcik

Topic:

The Hourglass of Industrial Data: from Real-Time Signal Processing to AI

Modern industrial systems increasingly need to bridge two worlds with fundamentally different constraints: deterministic, real-time control at the shop floor and data-intensive, AI-driven analytics in the cloud. This talk argues that real-time performance is not a property that scales uniformly through the system; it exists only in a narrow "waist" between two much 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 deployments. At the top, big data, AI/ML pipelines, digital twins, and LLM-based agents operate on volumes of data that preclude hard real-time guarantees. Only in between - where standards such as OPC UA FX and the emerging IEC/IEEE 60802 Time-Sensitive Networking profile now converge to provide a common data model over deterministic Ethernet - can true real-time behavior be achieved. Drawing on the presenter's work in industrial communication and Service-Oriented Architecture, as well as recent work on vision-based diagnostic systems (including the MEDUSA project for ultrasound-based 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" architecture 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 control with modern AI-based decision support.

Biography:

Professor Marcin Andrzej Fojcik is a professor in the Department of Computer Science, Electrical Engineering and Mathematical Sciences at Western Norway University of Applied Sciences (HVL), campus Førde, Norway. His research spans automation, electronics and informatics in industrial and wireless communication, Quality of Service, and Service-Oriented Architecture: from real-time protocols and Factory 4.0 to the Internet of Things and has more recently extended into vision-based systems and AI-assisted diagnostics. He is the author of over 80 peer-reviewed publications and has served as a reviewer and on the program committee for numerous international conferences. In 2021, he received the HVL Educational Quality Award for his work on engineering education. ORCID: 0000-0002-8109-2175.

Email:

Address:Western Norway University of Applied Sciences (HVL), Dept. of Computer Science, Electrical Engineering, a. Mathematical Sciences, Campus Førde, Inndalsveien 28, 5063 Bergen, Norway, Bergen, Vestfold, Norway, 5063