Machine learning-driven optimization of plasma-catalytic dry reforming of methane

This study investigates the dry reformation of methane(DRM)over Ni/Al_(2)O_(3)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),CO_(2)/CH_(4)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 plasma-catalytic 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.

Special issue on selected papers from HVDP 2020

High-voltage and discharge plasma technology is playing an increasingly important role in the construction of national economy and social development,and has attracted extensive attention from both academia and industry.As a novel molecular activation method,discharge plasma can enable thermodynamically difficult reactions to occur under relatively mild conditions,and its effectiveness has successfully been demonstrated in gas cleaning and material surface treatment.

Plasma reforming of toluene as a model tar compound from biomass gasification:effect of CO_(2) and steam

In this study, plasma reforming of toluene as a tar model compound from biomass gasification has been carried out using an AC gliding arc discharge reactor. The influence of steam and CO_(2) addition on the reforming of toluene has been evaluated. The results show that the highest toluene conversion (59.9%) was achieved when adding 3 vol% CO_(2) at a toluene concentra-tion of 16.1 g/Nm3 and a specific energy input of 0.25 kWh/m3. Further increasing CO_(2) concentration to 12 vol% decreased the conversion of toluene. The presence of steam in the plasma CO_(2) reforming of toluene creates oxidative OH radicals which contribute to the enhanced conversion of toluene and energy efficiency of the plasma reforming process through stepwise oxidation of toluene and reaction intermediates. Hydrogen and C_(2)H_(2) were identified as the major gas products in the plasma reforming of toluene without CO_(2) or steam, with a yield of 9.7% and 14.5%, respectively, while syngas was the primary products with a maximum yield of 58.3% (27.5% for H_(2) and 30.8% for CO) in the plasma reforming with the addition of 12 vol% CO_(2). The plausible reaction pathways and mechanism in the plasma reforming of toluene have been proposed through the combination of the analysis of gas and condensed products and spectroscopic diagnostics.

Liquid discharge plasma for fast biomass liquefaction at mild conditions: The effects of homogeneous catalysts

Non-thermal plasma exhibits unique advan-tages in biomass conversion for the sustainable production of higher-value energy carriers.Different homogeneous catalysts are usually required for plasma-enabled biomass liquefaction to achieve time-and energy-efficient conver-sions.However,the effects of such catalysts on the plasma-assisted liquefaction process and of the plasma on those catalysts have not been thoroughly studied.In this study,an electrical discharge plasma is employed to promote the direct liquefaction of sawdust in a mixture of polyethylene glycol 200 and glycerol.Three commonly used chemicals,sulfuric acid,nitric acid and sodium p-toluene sulfate,were selected as catalysts.The effects of the type of catalyst and concentration on the liquefaction yield were examined;further,the roles of the catalysts in the plasma liquefaction process have been discussed.The results showed that the liquefaction yield attains a value of 90%within 5 min when 1%sulfuric acid was employed as the catalyst.Compared with the other catalysts,sulfuric acid presents the highest efficiency for the liquefaction of sawdust.It was observed that hydrogen ions from the catalyst were primarily responsible for the significant thermal effects on the liquefaction system and the generation of large quantities of active species;these effects directly con-tributed to a higher efficacy of the plasma-enabled liquefaction process.