Conferences

Meet us

Meet us in person at the upcoming conferences listed below.

Are you interested in joining and meeting team members of ECOMAI? Just send an short email!

Embedded world
Exhibition + Conference
11 – 13 March 2025 | Nürnberg, Germany

 

Conference Talks and Tutorials

March 11, 2025

Session 1.1 IOT & CONNECTIVITY
A Visionary Modelling Approach for Predictive Maintenance in a Highly Regulated Environment
Peter Lieber, SparxSystems Europe

 

 

 

 

 

 

Class 7.1: 14:00h – 17:00h
Introduction to tinyML – Running Deep Learning Models on Low-Power Micro-Controllers
Prof. Daniel Mueller-Gritschneder, TU Vienna

 

March 13, 2025

Session 7.7 EDGE AI // AI Assisted Motor Control, 12:15h – 12:45h
From Simulation to Silicon on a RISC-V with AI Accelerator
Steven Klotz, Infineon

Exhibition Booth 4-410
presenting partners: Moteon, SparxSystems Europe, Infineon, neuroConn

 

 

 

Use Case: AI for Platform Screen Door Systems (PSD). PSDs are used in public transportation and separate the waiting area from the rail line, preventing passenger contact with moving vehicles. These systems require high availability (99.4%+), leading to costly preventive maintenance. PdM (Predictive Maintenance) is not yet applied to PSD. This use case discusses the innovation development of Albayrak (Aldoor/Turkiye), a designer and manufacturer of PSD.  

 

Intelligence for the IoT requires to stream huge amounts of data from edge sensors towards the cloud, where deep learning models interpret the data. EdgeAI moves deep learning models from the cloud onto the Edge platforms themselves offering huge gains in terms of connectivity requirements, energy, cost, privacy and end-to-end latency. tinyML or Extreme Edge AI moves the deep learning tasks even further right onto the microcontrollers connected to the sensors.


AI concepts offer sophisticated approaches for condition monitoring and control in embedded applications.

However, deploying these strategies on industrial-scale embedded microcontroller systems presents significant challenges.
Imperfect simulation models can undermine the successful transfer of developed concepts, limiting their applicability in real systems.
Additionally, the limited computational power of real-time microcontrollers necessitates adaptations to ensure efficient execution of learned policies.
In this work, a reinforcement learning-based control policy for energy-efficient motor control is presented, highlighting the sim-to-real challenges of deploying this artificial intelligence controller. The AI control concept is studied in the context of a motor control application, with the microcontroller evaluated accordingly.
Additional focus is placed on the computational constraints of a low-resource RISC-V microcontroller,
presenting toolchain and optimization strategies for real-time operation on cost-effective hardware

 

EFECS 2024
5-6 December 2024 | Ghent, Belgium

 

Meet us in Person to discuss the lates development of ECOMAI:

Fabiola Bermudez-Elsinger

  • Director Funding Project Manager bei Infineon Technologies
  • ECOMAI Commercial Project Leader

Salomé Wagner

  • Business Development / Research Projects Sparx Systems Europe
  • ECOMAI Dissemination + Exploitation

 

Software Architecture Alliance
22. + 23. Oktober 2024 | München, Germany

 

Talk

Modellbasierte Architektur für die Entwicklung von IoT Geräten bei usePAT

Modellbasierte Architektur für die Entwicklung von IoT Geräten bei usePAT

 

Presenters

Salomé Wagner, Sparx Systems CE
Georg Heinz, usePAT GmbH

usePAT ist Anbieter einer neuen Ultraschalltechnologie, die von einem multidisziplinären Team entwickelt wird. Die angebotenen IoT Systeme schließen Hard- und Softwarekomponenten ein, die Schnittstellen sind besonders komplex. Sie verbinden einerseits das Gerät mit der Steuerung eines industriellen Prozesses und andererseits die im Gerät erhobenen Daten mit den Menschen dahinter. Es werden auf Grund der Analysen sicherheitskritische Entscheidungen getroffen, die regulatorischen Anforderungen an diese Systeme sind dementsprechend anspruchsvoll.

Diese Komplexität gab den konkreten Ausschlag für die Evaluation einer neuen Methodik. usePAT hat sich dabei entschieden, die modellbasierte Systementwicklung als strategisches Entwicklungselement über das gesamte Unternehmen einzuführen, um diese Komplexität zu meistern.

Die Herangehensweise:

  • ermöglicht durch Daten-, Infrastruktur- und Applikationsarchitekturen eine ganzheitliche Entwicklung von IoT Systemen,
  • dokumentiert diese Systementwicklung über den gesamten Lebenszyklus,
  • stellt das Wissensmanagement auch bei Fehlentwicklungen sicher.

Diese Evaluation und Einführung der modellbasierten Systemarchitektur erfolgt im Rahmen des EU Förderprojektes PENTA  „ECOMAI“, Ecological Motor Control and Predictive Maintenance with Artificial Intelligence.

Enterprise Architect
Global Summit 2024

 

September, 18 + 19 2024
online

Talk
Pioneering AI-driven MBSE Methodologies within a Diverse Ecosystem

Presenter
Salomé Wagner, Sparx Systems CE

The development of an AI-driven Model-Based Systems Engineering (MBSE) methodology within a robust ecosystem that bridges industry and academia – this is the Penta Project ECOMAI (Ecological Motor Control and Predictive Maintenance with AI).

This research project is founded by the European Union under the umbrella of the European Chips Act. Its goal is to address critical challenges such as energy efficiency and skill shortages in the semiconductor market. With members of the ECOMAI consortium, we explore the MBSE methodology, the barriers to adopt and the benefits of implementing. Features like call graph visualization are essential for the understanding, the modelling language essential for broad adoption.

The ECOMAI design kit for AI-enhanced drive systems will orchestrate hard- and software and will include the ECOMOD Modelling Toolbox. In this talk, we will give you an insight of this ongoing development.

The paper introduces a novel design of a reinforcement learning agent. Compared to application-tuned classical control methods, the agent demonstrated advanced capability to save energy, showcasing its potential for future applications.

Authors 

Klotz Steven, Buksch Thorsten, Infineon Technologies AG, Goswami Dip, Eindhoven University of Technology, Mueller-Gritschneder Daniel, TU Munich

 

ICENSOS 2023

4th to 6th April 2023
Konya, Turkey

Paper Contribution, Abstract

Machine Learning based Diagnostic Approach to Condition Monitoring of Railway Platform Screen Door Systems

by Şükrü Görgülü 1, İsa Koç 2, Necim Kırımça 3, Ömer Mermer 4, Mehmet Karaköse 5, and Mehmet Tankut Özgen 6 (1,6 Dept. of Electrical and Electronics Engineering, Eskişehir Technical University, Türkiye; 2 Dept. of Electrical and Electronics Engineering, Eskişehir Osmangazi University, Türkiye; 5 Dept. of Computer Engineering, Elazığ Fırat University, Türkiye; 1,2,3,4 Albayrak Makine Elektronik San. Tic. A.Ş. Eskişehir, Türkiye)

Embedded World

Nürnberg Germany
14 – 16 March 2023

March, 14th, 2023, 2PM – 6 PM

Class 8.1

An Introduction to TinyML: Bringing Deep Learning to Ultra-low-power Micro-Controllers

by Prof. Dr. Daniel Müller-Gritschneder, TU Munich