Register now After registration you will be able to apply for this opportunity online.
Process Modelling of Flakkotting Process using Experiments and ML Techniques
Cutting-edge tools play a pivotal role in manufacturing processes, enduring wear and damage while consistently producing series of components. Maintaining an optimal cutting-edge geometry is crucial to uphold the quality of finished products over time. Additionally, sustaining the micro-geometry of the cutting edge is key to enhancing the lifespan of the tool and ensuring top-notch cutting performance. Profin addresses this challenge with Flakkotting, a novel surface finishing process designed explicitly to create and preserve the required micro-geometry.
The aim of this thesis is to develop the understanding of Flakkotting process and develop prediction model for process parameters for a given micro-geometry. The dynamics of flakkotting tools on Tungsten Carbide drills and cutting-edge inserts will be studied with varying parameters using high-speed imaging and microscopic analysis. Using the parameter data and evaluated workpieces, machine learning (ML) models will be developed for prediction of micro-geometry features and optimization of process based on the required micro-geometry.
Keywords: Machine Learning, Process optimization, Data Science, Manufacturing, Mechanical, Python
Tasks: (*Tasks will be defined depending on bachelor or master’s thesis)
• Literature review on Flakkotting process
• Data Acquisition using process parameters and evaluated micro-geometry features.
• Development of ML prediction models and optimization of process parameters for a desired micro-geometry.
• Computer Vision ML modeling for analysis of bristle interaction with workpiece
• Final report and presentation in English
Tasks: (*Tasks will be defined depending on bachelor or master’s thesis) • Literature review on Flakkotting process • Data Acquisition using process parameters and evaluated micro-geometry features. • Development of ML prediction models and optimization of process parameters for a desired micro-geometry. • Computer Vision ML modeling for analysis of bristle interaction with workpiece • Final report and presentation in English