During her PhD studies, Fatemeh Kakavandi conducted research on the utilization of emerging technologies, including Digital Twins and Machine Learning (ML), in Industrial Medical Device Assembly Processes. Her focus was on exploring how these concepts could offer insights into process quality and identify abnormal situations. Fatemeh Kakavandi investigated the challenges associated with the deployment of ML models in industrial settings, such as the issues of interpretability and the availability of sufficient labeled data. She developed solutions to address these challenges, and her research findings provide valuable insights into the development of ML-based fault detection models for industrial use cases with specific challenges.

The PhD study was completed at: Electrical and Computer Engineering Department, Faculty of Technical Sciences, Aarhus University.

This résumé is prepared by the PhD student

Time: Friday, 05 April 2024 at 13:00
Place: building 5124, room 038, Aarhus University, Finlandsgade 20, 8200 Aarhus N
Title of PhD thesis: Enabling Machine Learning-Based Fault Detection in an Industrial Medical Device Assembly Process
Contact information: Fatemeh Kakavandi, e-mail: fateme.kakavandi@ece.au.dk

Members of the assessment committee:
Professor Murat Kulahci, Department of Applied Mathematics and Computer Science, DTU, Denmark.

Professor Vilmar Æsøy, Department of Ocean Operations and Civil Engineering, NTNU, Norway.

Associate Professor Stefan Hallerstede (chair), ECE, Aarhus University, Denmark.

Main supervisor:
Professor Peter Gorm Larsen, ECE, Aarhus University, Denmark

Language: The PhD dissertation will be defended in English

The defence is public.
The PhD thesis is available for reading at the Graduate School of Technical Sciences/GSTS,

Jens Baggesens Vej 53, building 5221, 8200 Aarhus N.