ICAI Lab

EAISI AIMM Lab

The new EAISI lab “AI-enabled Manufacturing and Maintenance” (AIMM) is the first ICAI-Lab in Eindhoven. TU/e has set up this new lab together with a number of industrial partners, under the academic supervision of Ivo Adan and Geert-Jan van Houtum, to improve decision making in manufacturing and maintenance using artificial intelligence.

Improve decision making using AI

The AIMM Lab aims to promote research in cooperation with high-tech industry and is a collaboration with four industrial partners, Nexperia, KMWE, Marel and Lely. These companies have a solid history of commitment to developing new innovative approaches in their respective industries and are working in close partnership with the TU/e.  Besides existing research in manufacturing and maintenance, it is expected that the EAISI AIMM research lab will also become a fertile starting point for new initiatives, such as developing online trainings and placing Master and final year Bachelor students in projects with the companies. 

The lab will also provide companies with better access to expertise in potential applications of artificial intelligence such as improved planning, detecting anomalies in production and operation, predicting quality issues and machine behavior, and enabling fast root cause analysis.

ICAI is a Dutch network aimed at technology and talent development between knowledge institutes, industry, and government in the area of artificial intelligence. 

Our team

Business Process Manager KMWE

Arthur van Hout

AI Program manager High Tech Systems - EAISI

Shane O'Seasnáin

Senior Project Manager - Lely

Oscar Moers

Assistant Professor

Collin Drent

Dean

Geert-Jan van Houtum

Science & Technology Program Manager - Marel

Jeannette Lankhaar

Full Professor

Ivo Adan

Associate Professor

Mathias Funk

Smart Manufacturing Architect - Nexperia

Jan Driessen

Full Professor

Lin-Lin Chen

Research Director MultiM3D Fieldlab

Frits Feenstra

Director Quality IT & BCM at NXP Semiconductors

Onno Buijs

Assistant Professor

Zaharah Bukhsh

Associate Professor

Alp Akçay

Associate Professor

Tugce Martagan

Assistant Professor

Mike Holenderski

Associate Professor

Stella Kapodistria

Assistant Professor

Davide Leonetti

Associate Professor

Yingqian Zhang

Full Professor

Nathan van de Wouw

Full Professor
(Part-time)

Wim Nuijten

Partners in AIMM

AIMM Projects

Digital Twin project

Integrated Master Planning and Control (IMPACT)

Jeroen Didden, Ivo Adan, Vinh Dang (all IE&IS)

This project is part of a use case from the Digital Factory of the Future initiative of Brainport Industries. It aims to develop an autonomous scheduling system, based on a Digital Twin of the factory floor, to control real-time production and simultaneously enable predictive capabilities to aid higher level planning.

DIGITAL TWIN OF A FRONT-END SEMICONDUCTOR FACTORY TO IMPROVE WIP CONTROL

Ivo Adan, Patrick Deenen and Alp Akcay (all IE&IS)

Production control is a challenging task in a semiconductor wafer fabrication facility (fab) and can be characterized as a complex job shop. The amount of unfinished products which are in production - referred to as work-in-progress (WIP) - in different areas of the fab can fluctuate greatly over time, causing an unwanted variability on the production lead-times. Dispatching and scheduling decisions, i.e. deciding in what sequence lots from the queue are produced, influence how the WIP flows through the fab and is  therefore called WIP control.

The ambition of this project is to develop a proof-of-concept for a new WIP control system for the front-end wafer fabs of Nexperia which (1) stabilizes the lead-times and (2) maximizes the throughput.

To test this new control system in a virtual environment, a digital twin is developed. This digital twin is a discrete-event simulation model which mimics the behavior of the full fab and can be used to analyze future behavior.

Digital Twin project

Predictive Maintenance

ProSeLoNext project

Rob Basten (TU/e), Simme Douwe Flapper (TU/e), Geert-Jan van Houtum (TU/e), Henk Akkermans (Tilburg University), Rommert Dekker (Erasmus University), Matthieu van der Heijden (Universiteit Twente), Henk Zijm (Universiteit Twente).

Involved companies: Marel, ASML, Fokker Services, IBM, Océ, Thales, Vanderlande, Gordian Logistics Experts, Service Logistics Forum.

By collecting data with sensors in machines, the Internet of Things makes it possible to predict when maintenance is necessary. Smart use of data in combination with tools such as a service control tower allow us to introduce predictive maintenance and better service logistics, provided that the business model changes  accordingly.

Research project ProSeLoNext (Pro-active Service Logistics for capital goods – the Next steps) gave us a wealth of tools and practical experiments, thanks to the close cooperation between researchers and seven companies.

 

"Collaboration as one of the engines driving innovation"

Jeannette Lankhaar, Science & Technology Program Manager Marel 

The Netherlands is one of the world's most innovative countries. It is home to world-class universities and research institutes, with TU/e taking the fifth spot on the World University Research Ranking in multi-disciplinarity, impact and collaboration. The Dutch are also the world’s second-largest exporters of agriculture and food products, and the number three suppliers of machinery and technology for the global agriculture and food processing industry.

What if we mix these impressive ingredients with a strong partnership between universities, industry and government and add in plenty of cross-pollination between the Top Sector High Tech Systems & Materials and the Top Sector Agri&Food? The outcome will be a fruitful Dutch AgriFoodTech innovation ecosystem.

Researcher in the Spotlight: Kay Peeters

My name is Kay Peeters. Within the Dynamics & Control research group of the Department of Mechanical Engineering, my PhD concerns the production planning and control of poultry processing plants. These typically produce fixed-weight batches of products such as filets. Any weight over the minimum is effectively a ‘giveaway’ by the plant. Meanwhile, retailers require their daily batch orders to be finished before their due dates. Operational costs, food waste and other performance measures can therefore be improved by optimizing poultry processing plants. In turn, this will reduce production costs and improve the reliability of deliveries, making it possible for supermarkets to offer reduced prices.

My PhD concerns the production planning and control of poultry processing plants.

Contact