Refine
Year of publication
- 2023 (5) (remove)
Document Type
- Article (5) (remove)
Language
- English (5)
Is part of the Bibliography
- yes (5)
Keywords
- CO2 methanation (1)
- Catastrophic forgetting (1)
- Concept drift (1)
- Continual learning (1)
- Convex optimization (1)
- Energetic and exergetic efficiencies (1)
- Kinetics (1)
- Local thermal non-equilibrium (1)
- Long-term stability (1)
- Melting (1)
- Ni catalyst (1)
- Porous media (1)
- Power-to-Gas (1)
- Pulsating flow (1)
- Solidification process (1)
- Thermal lattice Boltzmann method (1)
Department/institution
- Fachbereich - Maschinenbau und Verfahrenstechnik (5) (remove)
Process models in industrial applications, e.g. predictive maintenance or automation, are subject to both divergence from the underlying system due to their time-variant nature and to high complexity resulting from a wide operational range being covered. Hence, regression models require high accuracy for the present system state and at the same time need to be valid across the whole system operating space. While accuracy for the current system state can be gained by updating the model on the current data, the overall validity must often be retrieved from historical or design data. We propose a method to find an appropriate compromise for these two demands. A pre-trained artificial neural network (ANN) is continually updated on the current sensor data stream using convex optimisation. Thus, a unique and optimal solution is generated in each update step, while robust regression accuracy on the domain that is not covered by the arriving data subset is maintained. This is achieved by introducing a data management system to provide some historical data, constraining the optimisation problem and manipulating the architecture of the ANN. Models updated with this method show reasonable stability but display plastic behaviour at the current operating point.
In the context of using renewable energies and recycling climate-changing gases, methanation of CO2 provides one possibility. However, volatile availability of renewable energies for hydrogen production and fluctuating CO2streams from different sources lead to enhanced demand in investigating the influence of dynamic process operation on the catalyst performance, including detailed kinetic characterization. Reliable kinetic measurements require isothermal temperature control and absence of macrokinetic diffusion limitations. Both were investigated in this work while the determination of steady-state kinetic parameters is part of ongoing studies. Furthermore, a detailed analysis with respect to the long-term-stability of the nickel-based catalyst was performed