Modern manufacturing systems generate large amounts of data but turning that data into reliable decisions remains challenging. In his doctoral dissertation, MSc Reza Asadi investigated how carefully designed experiments, sensor data and artificial intelligence can be combined to monitor manufacturing processes and predict their quality across metal additive manufacturing, milling and micro injection molding. His research shows that reliable AI-based monitoring depends not only on the model itself, but also on how data are collected, prepared and connected to meaningful process indicators, enabling deployable monitoring, instability flagging and quality prediction. The work provides a practical foundation for smarter and increasingly autonomous manufacturing systems, where data can support process optimization and better-informed quality decisions.
The doctoral dissertation titled Data-Driven Monitoring in Advanced Manufacturing: From Indicator Discovery to Prediction and Decision Support by MSc Reza Asadi will be publicly examined in the Faculty of Engineering and Natural Sciences at Tampere University on 18 September 2026. HIs research is in the field of Automation Technology and Mechanical Engineering.
The Opponents will be Assistant Professor Marvin Carl May from Nanyang Technological University, Singapore, and Associate Professor Ashish Ganvir from the University of Turku, Finland. The Custos will be Associate Professor Iñigo Flores Ituarte from the Faculty of Engineering and Natural Sciences, Tampere University.