Abstract: This study investigates the dry reformation of methane (DRM) over Ni/Al2O3 catalysts in a dielectric barrier discharge (DBD) non-thermal plasma reactor. A novel hybrid machine learning (ML) model is developed to optimize the plasma-catalytic DRM reaction with limited experimental data. To address the non-linear and complex nature of the plasma-catalytic DRM process, the hybrid ML model integrates three well-established algorithms: regression trees, support vector regression, and artificial neural networks. A genetic algorithm (GA) is then used to optimize the hyperparameters of each algorithm within the hybrid ML model. The ML model achieved excellent agreement with the experimental data, demonstrating its efficacy in accurately predicting and optimizing the DRM process. The model was subsequently used to investigate the impact of various operating parameters on the plasma-catalytic DRM performance. We found that the optimal discharge power (20 W), CO2/CH4 molar ratio (1.5), and Ni loading (7.8 wt%) resulted in the maximum energy yield at a total flow rate of
51 mL/min. Furthermore, we investigated the relative significance of each operating parameter on the performance of the plasmacatalytic DRM process. The results show that the total flow rate had the greatest influence on the conversion, with a significance exceeding 35% for each output, while the Ni loading had the least impact on the overall reaction performance. This hybrid model demonstrates a remarkable ability to extract valuable insights from limited datasets, enabling the development and optimization of more efficient and selective plasma-catalytic chemical processes.

Abstract: CO2 conversion into value-added chemicals is gaining increasing interest in recent years, and a gliding arc plasma has great potential for this purpose, because of its high energy efficiency. In this study, a chemical reaction kinetics model is presented to study the CO2 splitting in a gliding arc discharge. The calculated
conversion and energy efficiency are in good agreement with experimental data in a range of different operating conditions. Therefore, this reaction kinetics model can be used to elucidate the dominant chemical reactions contributing to CO2 destruction and formation. Based on this reaction pathway analysis, the restricting factors for CO2 conversion are figured out, i.e., the reverse reactions and the small treated gas fraction. This allows us to propose some solutions in order to improve the CO2 conversion, such as decreasing the gas temperature, by using a high frequency discharge, or increasing the power
density, by using a micro-scale gliding arc reactor, or by removing the reverse reactions, which could be realized in practice by adding possible scavengers for O atoms, such as CH4. Finally, we compare our results with other types of plasmas in terms of conversion and energy efficiency, and the results illustrate that gliding arc discharges are indeed quite promising for CO2 conversion, certainly when keeping in mind the possible solutions for further performance improvement.