Manufacturing engineering is being transformed significantly by integrating machine learning (ML) techniques. As complexity and efficiency requirements increase, multiple industry sectors have recognized the need for data-driven approaches. To address these new demands and opportunities, this thesis focuses on integrating ML methods in production technology, considering specific key manufacturing components, i.e., tool, machine tool and process, on the example of milling, grinding and injection molding. To this end, several novel ML techniques and strategies were developed and applied to overcome the challenges posed by these components. The research documented in this thesis allows for various further studies and improvements, including the transferability of the developed models to different scenarios and the improvement of data augmentation strategies. Consequently, this represents a further step towards integrating ML into manufacturing in terms of transitioning from predictive to prescriptive and adaptive analytics, establishing the foundation for more efficient and sustainable manufacturing processes.weiterlesen