Machine Learning-Driven Optimization of Ni-based Catalysts for Catalytic Steam Reforming of Biomass Tar
ENERGY CONVERSION AND MANAGEMENT(2024)
摘要
•Machine learning was used to predict and optimize catalytic toluene reforming.•The reaction temperature has the highest relative importance (0.24).•The optimal reaction temperature for this reaction is 600–700 °C.•The optimal Ni loading and calcination temperature are 5–15 wt% and 500–650 °C.•The optimization was validated through experiments using γ-Al2O3 as a support.
更多查看译文
关键词
Machine learning,Biomass gasification,Tar reforming,Syngas,Toluene,Catalytic reforming
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要