Abstract: In this outreach session we elaborate upon hybrid machine learning for smart maintenance. We show how to find synergies in data-driven and expert-based approaches. We detail how providing expert feedback can be used for model optimization of smart maintenance, what physics-based machine learning strategies can be deployed, and how expert knowledge can be incorporated into machine learning for root cause analysis and anomaly detection. Next to academic perspectives on smart maintenance, testimonials from a service and manufacturing company will be provided on how they perform smart maintenance using hybrid machine learning.

Target Audience: Maintenance service providers, manufacturing companies. Data scientists interested in the industrial maintenance domain

Agenda:

• 10 min - “Finding synergies in data-driven and expert-based approaches for smart maintenance” – Anatolii Sianov, EELab/UGent-Flanders Make
• 20 min – “Combining expert knowledge and machine learning for predictive maintenance of valves and pumps” Jan Verhasselt, Yazzoom
• 20 min - “Expert feedback for model optimization” – Sofie Van Hoecke, Femke Ongenae, IDLab/UGent-imec
• 10 min – Q&A
• 20 min - “Physics-based ML for smart maintenance” – Guillaume Crevecoeur, EELab/UGent-Flanders Make and Sofie Van Hoecke, IDLAb/UGent-imec
• 20 min - “Incorporating expert knowledge into ML for root cause analysis and anomaly detection” – Femke Ongenae, Sofie Van Hoecke, IDLab/UGent-imec
• 10 min – Closure by Sabine Demey, imec, director Flanders AI Research Program
• 10 min – Q&A

Moderator: Pieter Nguyen Phuc (EELab-UGent) pieter.nguyenphuc@ugent.be