A5092244716- Fault Detection and Control Systems
- Manufacturing Process and Optimization
- Industrial Vision Systems and Defect Detection
- Advanced Surface Polishing Techniques
- Gear and Bearing Dynamics Analysis
- Sensor Technology and Measurement Systems
- Real-time simulation and control systems
- Water Quality Monitoring and Analysis
- Machine Fault Diagnosis Techniques
- Advanced machining processes and optimization
- Gamma-ray bursts and supernovae
Chemnitz University of Technology
2024
Fraunhofer Institute for Electronic Nano Systems
2023-2024
In this study, we present the Method of Spectral Redundancy Reduction (MSRR) for analyzing OES (optical emission spectroscopy) data dry etching processes based on principles spectral clustering. To achieve this, are transformed into abstract graph matrices whose associated eigenvectors directly indicate anomalies in set. We developed an approach that allows reduction temporally resolved optical spectra from plasma structuring such a way individual lines can be algorithmically detected, which...
We present a novel approach for modeling semiconductor processing that uses machine learning to combine expert knowledge, physics models, and actual process data into so-called knowledge-enhanced models. Our method is illustrated on models chemical-mechanical planarization, key technology processing. It an important step towards robust, accurate, transferable, real-time digital twins of processes chains.
In this work, we perform Physics guided data synthesis. Proposed method uses seed from the observed source state / domain for generation of unobserved target domain. Our adapts variation features with respect to across states. This approach knowledge and its associated impacts on statistical signal properties data. We use generative learning comprising a variational auto-encoder (VAE) based neural network model. model has influenced optimization function achieve adaptation domains. aims...