生物柴油
酯交换
生物柴油生产
同种类的
生物燃料
可再生能源
生化工程
环境友好型
催化作用
化学
制浆造纸工业
产量(工程)
环境科学
工艺工程
材料科学
有机化学
废物管理
工程类
热力学
物理
生物
复合材料
生态学
电气工程
作者
Somboon Sukpancharoen,Tossapon Katongtung,Nopporn Rattanachoung,Nakorn Tippayawong
标识
DOI:10.1016/j.biortech.2023.128961
摘要
The growing demand for fossil fuels has motivated the search for a renewable energy source, and biodiesel has emerged as a promising and environmentally friendly alternative. In this study, machine learning techniques were employed to predict the biodiesel yield from transesterification processes using three different catalysts: homogeneous, heterogeneous, and enzyme. Extreme gradient boosting algorithms showed the highest accuracy in predictions, with a coefficient of determination accuracy of nearly 0.98, as determined through a 10-fold cross-validation of the input data. The results indicated that linoleic acid, behenic acid, and reaction time were the most crucial factors affecting biodiesel yield predictions for homogeneous, heterogeneous, and enzyme catalysts, respectively. This research provides insights into the individual and combined effects of key factors on transesterification catalysts, contributing to a deeper understanding of the system.
科研通智能强力驱动
Strongly Powered by AbleSci AI