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

Your tasks

You will be part of an innovative research project where data-driven methods meet cutting-edge technology. Ready to turn your ideas into impact? Apply now and help shape future solutions.

• 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.

Your profile

• 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, Tensor Flow/Py Torch, 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