Although there is an optimal manufacturing process for every component, there is currently a lack of sufficient assistance for designers to select this process in a data-based and targeted manner. In addition, there is considerable potential for optimization when changing manufacturing processes, which has so far only been insufficiently exploited.

Objective

The aim of this thesis is to optimize the design process through the use of data-driven approaches. The aim is to provide designers with valuable support in selecting the optimal manufacturing process. The focus is on the application of machine learning and rule-based algorithms to analyze the potential of different manufacturing processes and to optimize the component design (semi-)automatically.

Possible tasks

• Literature research on data-driven design optimization and manufacturing processes
• Collection and preparation of data on various manufacturing processes and their application to different components
• Development and implementation of machine learning models and rule-based algorithms for design analysis and optimization
• Integration of design knowledge and guidelines into the developed models to improve prediction accuracy and decision-making

Profile

• Independent and structured way of working
• Basic knowledge in the areas of machine learning and data analysis
• Analytical skills and interest in the optimization of technical processes