Student Projects
AI-Enhanced Simulation of a Watch Movement for Predictive Failure Analysis
Developing a complete watch movement is a process that lasts several years. With over 100 individual components, many interactions between these parts can introduce imprecisions or lead to failures. While mathematical principles, engineers’ expertise, and hands-on experimentation ensure a high-quality design, the number of physical prototypes produced is limited and cannot capture the full range of tolerances across all components. The ability to simulate key elements of the watch movement would support engineers in making informed design decisions, especially in edge cases, and would accelerate innovation in watchmaking by enabling faster iteration on new concepts. In addition, by combining accurate parts metrology with simulation capabilities, a usable digital twin of a specific watch could be developed, enabling precise preventive failure analysis.
Keywords
Watch industry, Simulation, Computer Vision, Machine Learning
Labels
Semester Project , Internship , Master Thesis
Description
Goal
Contact Details
More information
Published since: 2025-12-19 , Earliest start: 2026-02-02 , Latest end: 2026-09-07
Organization Institute of Machine Tools and Manufacturing
Hosts Laborde Antoine
Topics Engineering and Technology
Process monitoring and optimization in grinding technology
Artificial intelligence (AI) is increasingly applied in manufacturing to enhance production efficiency and product quality. In grinding, typically the final step in machining, workpiece is subjected to intense thermo-mechanical loads, which can result in surface defects like grinding burn. Traditional detection methods, such as nital etching, remain widely used but are subjective, time-consuming, and environmentally unsustainable. In contrast, modern process monitoring techniques based on data-driven approaches offer more scalable and efficient alternatives. In collaboration with our industry partner, we are developing an innovative monitoring framework integrating advanced signal processing and machine learning to reduce setup time for new components, improve production efficiency, and ensure product quality.
Keywords
Artificial intelligence (AI), Machine learning (ML), manufacturing, grinding, signal processing
Labels
Semester Project , Bachelor Thesis , Master Thesis , ETH Zurich (ETHZ)
Contact Details
More information
Published since: 2025-09-17 , Earliest start: 2025-10-01
Organization Institute of Machine Tools and Manufacturing
Hosts Ilten Mert
Topics Engineering and Technology