Summer School on Data-Driven Predictive Maintenance for Industry 4.0

The Summer School is for students, researchers and practitioners who want to learn how to implement predictive maintenance to solve real industrial problems using machine learning approaches. Halmstad University is co-organising the Summer School which will be an online event on October 3–5, 2021.

Scope and aim

Predictive Maintenance (PM) becomes increasingly a central cornerstone in today’s industrial applications and systems in particular within the context of Industry 4.0. Its applications are ranging from on-line manufacturing rails and production lines through (cyber) security problems to energy fabrication and exploitation facilities. This is because it addresses and develops not only strategies for the early detection and prediction of machine failures, degraded performance, undesired situations and occurrences or downtrends in product quality, but also for taking appropriate actions upon the recognition and prediction of such occasions. Such actions are indispensable for reducing waste, production costs, customer complaints and thus, in the long run, also for increasing the income of companies, for guaranteeing higher quality of production items, software and user frontends and finally for reducing the pollution of the environment. In the extreme case of severe system failures, any risks of operators working with the system can be avoided by predictive maintenance.

A successful and efficient implementation of PM within the context of Industry 4.0 faces several challenges such as the system complexity in terms of dynamics and size, the data integrity, speed, and size, the non-stationarity of its environments, the availability of data about rare or dangerous degradation behaviours or modes etc. One of the alternatives to face these challenges is the use of data-driven approaches in particular machine learning approaches.

The Summer School on Data-Driven Predictive Maintenance for Industry 4.0, PM4.0 2021, will focus on recent developments of data-driven approaches, in particular machine learning, to address these challenges and their application in real-world predictive maintenance installations. It will demonstrate the implementation related to all PM’s activities and the performances of these approaches using real world applications.

For whom?

The Summer School will provide the basis guide for both theoretical and practical issues for Ph.D. students, postdocs, practitioners, engineers and researchers in the fields of predictive maintenance and machine learning. PM4.0 2021 is addressed to students, researchers and practitioners who want to learn how to implement predictive maintenance to solve real industrial problems using machine learning approaches. It also allows updating the advanced attendees about recent developments and future trends.

There are no formal prerequisites for attendance in terms of academic degrees or specific knowledge in a domain since the courses will target all levels and guide attendees through all the steps of the PM implementation.

When and where?

Registration

Early Registration: deadline August 31, 2021.
Early registration fee: €50

Late Registration deadline: October 1, 2021
Late registration fee: €80

Joint (early student) registration fee for the summer school and the DSAA conference: €90

Registration External link, opens in new window.

DSAA travel grants External link, opens in new window.

We also offer a very limited number of free attendance opportunities for students (just the summer school, not including the DSAA conference). If you would like to apply, provide a 1-2 page description of your research/studies, and a motivation why attending the Summer School on Data-Driven Predictive Maintenance for Industry 4.0 is important for you on GoogleForms. External link, opens in new window.

Program (preliminary)

Day 1 (October 3, 2021)

  • 9:00-10:40 Introduction to Predictive Maintenance in Industry 4.0, Moamar Sayed Mouchaweh
  • 10:40-11:00 Break
  • 11:00-12:40 Introduction to AI/ML/DL for predictive maintenance, Joao Gama
  • 12:40-14:00 Lunch
  • 14:00-15:40 Overview of data-driven and deep learning approaches for predictive maintenance (Part 1), Rita P. Ribeiro & Slawomir Nowaczyk
  • 15:40-16:00 Break
  • 16:00-18:00 Use case 1: Streaming data from Porto Metro - anomaly detection & online learning (Joao Gama & Bruno Veloso)

Day 2 (October 4, 2021)

  • 9:00-10:40 Overview of data-driven approaches and deep learning for predictive maintenance (Part 2), Sepideh Pashami & Slawomir Nowaczyk
  • 10:40-11:00 Break
  • 11:00-12:40 Prognostics and health management informed by domain knowledge and physics, Olga Fink
  • 12:40-14:00 Lunch
  • 14:00-15:40 Overview of asset management and optimization required to define or schedule the maintenance actions, TBD
  • 15:40-16:00 Break
  • 16:00-18:00 Use case 2: TBD, Grzegorz J. Nalepa

Day 3 (October 5, 2021)

  • 9:00-10:40 Cybersecurity and Federated Machine Learning, TBD
  • 10:40-11:00 Break
  • 11:00-12:40 Use case 3: Transfer learning & fleet-based approaches on heavy-duty vehicles, Sepideh Pashami & Slawomir Nowaczyk
  • 12:40-14:00 Lunch
  • 14:00-17:00 Competition (Bruno Veloso)

Sponsor

Project CHIST-ERA-19-XAI-012
Explainable Predictive Maintenance, XPM

updated

contact

share