Master Thesis in Data-Driven Force Prediction for Rotary Grinding in the Semiconductor Industry

• You will conduct a comprehensive review of existing force modeling methods for rotational grinding and explore state-of-the-art machine learning approaches for sequence-to-sequence regression on time-series data, such as Symbolic Regression, Convolutional Neural Networks, and Mamba.
• As part of the data analysis process, you will analyze and prepare the provided time-series data, including feature engineering to extract relevant physical parameters.
• Based on your research, you will implement and train various machine learning frameworks for force prediction.
• To assess the developed approaches, you will create and apply a robust comparison matrix using key performance indicators such as prediction accuracy (RMSE, MAE), computational cost, and interpretability.
• Throughout the project, you will regularly document, present, and discuss your findings and progress with the project team.

• Education: master studies in the field of Mechanical Engineering, Data Science, Computer Science, Physics, or comparable
• Experience and Knowledge:

• strong programming skills in Python
• familiarity with common data science libraries such as Scikit-learn, TensorFlow/PyTorch, and Pandas

• Personality and Working Practice: you are highly self-motivated and enjoy tackling challenging research topics independently
• Work Routine: your on-site presence is required
• Languages: fluent in English and very good in German

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people's lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference.