Industrial-scale Chemical Vapor Deposition Processes are tackled with a hybrid Workflow that combines Equation-based modelling with Computational Fluid Dynamics (CFD) software and machine learning algorithms. Data from the reactor sensors are correlated to ex-situ product characterization measurements and simulation results, giving unique predictive capabilities, currently out-of-reach. The goal is to increase productivity by 15% and accelerate new product development by at least 20%.
A simplified process model, bypasses the problem of immense computational resources required by typically by CFD models. To compensate for its reduced predictive quality, it is combined with machine learning algorithms for data compression and regression modelling. The integrated computational tool will be able to correlate data from models with various sensors and measurements, in-situ and ex-situ and deliver accurate predictions in realistic time-frames for industrial practice.
This project is in collaboration with CERATIZIT Luxembourg S.à r.l.
Team:
Dr. Eleni D. Koronaki (P.I)
References:
Hochauer, D.; Mitterer, C.; Penoy, M.; Puchner, S.; Michotte, C.; Martinz, H. P.; Hutter, H.; Kathrein, M. Carbon Doped α-Al2O3 Coatings Grown by Chemical Vapor Deposition. Surface and Coatings Technology 2012, 206 (23), 4771–4777. https://doi.org/10.1016/j.surfcoat.2012.03.059.
Papavasileiou, P.; Koronaki, E. D.; Pozzetti, G.; Kathrein, M.; Czettl, C.; Boudouvis, A. G.; Mountziaris, T. J.; Bordas, S. P. A. An Efficient Chemistry-Enhanced CFD Model for the Investigation of the Rate-Limiting Mechanisms in Industrial Chemical Vapor Deposition Reactors. Chemical Engineering Research and Design 2022, 186, 314–325. https://doi.org/10.1016/j.cherd.2022.08.005
Papavasileiou, P.; Koronaki, E. D.; Pozzetti, G.; Kathrein, M.; Czettl, C.; Boudouvis, A. G.; Bordas, S. P. A. Equation-Based and Data-Driven Modeling Strategies for Industrial Coating Processes. Computers in Industry 2023, 149, 103938. https://doi.org/10.1016/j.compind.2023.103938.
The project OptiSimCVD proposes a data-driven framework for prediction, sensitivity analysis and uncertainty quantification in industrial-scale processes used to produce hard coatings and wear protection. The core of the production process is Chemical Vapor Deposition (CVD) reactors with different set up but common goal: uniform coatings with strict quality requirements.
With the proposed computational framework, different clusters of reactors will be identified, with different set-up but similar qualitative characteristics of the coating. Then, in each one of the clusters, predictive models will be developed, able to correlate the inputs of the process to the output.
Eventually, efficient and accurate process models will be implemented in the context of uncertainty quantification and sensitivity analysis with the ambition to contribute to process efficiency by reducing scrap rate (30%) and improve quality by enhancing homogeneity (15%).
This project is in collaboration with CERATIZIT Luxembourg S.à r.l.
Team:
Dr. Eleni D. Koronaki
References:
Hochauer, D.; Mitterer, C.; Penoy, M.; Puchner, S.; Michotte, C.; Martinz, H. P.; Hutter, H.; Kathrein, M. Carbon Doped α-Al2O3 Coatings Grown by Chemical Vapor Deposition. Surface and Coatings Technology 2012, 206 (23), 4771–4777. https://doi.org/10.1016/j.surfcoat.2012.03.059.
Nagel, J. B.; Rieckermann, J.; Sudret, B. Principal Component Analysis and Sparse Polynomial Chaos Expansions for Global Sensitivity Analysis and Model Calibration: Application to Urban Drainage Simulation. Reliability Engineering & System Safety 2020, 195, 106737. https://doi.org/10.1016/j.ress.2019.106737.
Papavasileiou, P.; Koronaki, E. D.; Pozzetti, G.; Kathrein, M.; Czettl, C.; Boudouvis, A. G.; Bordas, S. P. A. Equation-Based and Data-Driven Modeling Strategies for Industrial Coating Processes. Computers in Industry 2023, 149, 103938. https://doi.org/10.1016/j.compind.2023.103938.