Shraddha Gupta(AG Embedded Intelligence, Prof. Lukowicz)
hosted by PhD Program in CS @ TU KL
"Explainable and informed machine learning based predictive maintenance in hot staking resistance welding process"
To know about up-coming maintenance at manufacturing in advance is always beneficial. Especially when this could save a lot of cost and time due to hindrance at production line. To understand from combination of data and domain knowledge about probable anomalies, relation between parameters and integrating that information using machine learning models, is an important area for advancement in predictive maintenance. The use case is focused to hot staking resistance welding process, which is thermo-compacting process to join material using pressure and heat. This is typically done in resistance welding machine with pair of electrodes but without any filler material to achieve electrical as well as mechanical joints. Currently the electrodes are being changed on a fixed duration, and also the cleaning is done periodically. The aim of this thesis is to provide insights upon prediction of lifetime of electrode using combination of domain knowledge and data-driven techniques.
|Time:||Monday, 08.02.2021, 15:45|