Register now After registration you will be able to apply for this opportunity online.
Generative Adversarial Networks for Autonomous Tool Wear Assessment
Tool wear has a significant impact on the productivity of machining processes. Currently, tools are replaced based on an estimate of their remaining life, often with significant safety margins that lead to inefficiency. Developments are underway to measure wear automatically by image segmentation of microscope images. Increasing the size of the training data set has a positive effect on the performance and robustness of deep learning systems. However, when it comes to tool wear, datasets are not openly available and are expensive and time consuming to create.
This thesis builds on an existing segmentation pipeline and dataset of labeled war images. The goal is to leverage advanced deep learning techniques, such as Generative Adversarial Networks (GANs) to create an improved, data-efficient pipeline. You will work towards a system that can classify and quantify different types of wear for objective tool condition monitoring.
Tasks:
- Literature Review: Conduct a review of current developments in computer vision-based tool wear assessment and advanced deep learning methods for image processing.
- Image Analysis Pipeline: Implement generation of synthetic data and build on the existing segmentation pipeline. Validate the results by comparing them to manual measurements.
- Documentation: Prepare a written report documenting the project results and methodology.
Tasks:
- Literature Review: Conduct a review of current developments in computer vision-based tool wear assessment and advanced deep learning methods for image processing.
- Image Analysis Pipeline: Implement generation of synthetic data and build on the existing segmentation pipeline. Validate the results by comparing them to manual measurements.
- Documentation: Prepare a written report documenting the project results and methodology.
Build a a system that can classify and quantify different types of wear for objective tool condition monitoring.
Build a a system that can classify and quantify different types of wear for objective tool condition monitoring.
Ruben Zwicker, +41 44 556 58 84, ruben.zwicker@inspire.ch
Sebastian Lang, +41 44 556 58 36, selang@ethz.ch
Dr. Markus Maier, +41 44 556 58 38, markus.maier@inspire.ch
241218_Ausschreibung_GANwear.pdf
