文献类型：期刊文献

英文题名：Investigation and optimization of biodiesel production based on multiple machine learning technologies

作者：Jin, Xin[1] Li, Shihao[2] Ye, Haoran[1] Wang, Jin[3] Wu, Yingji[1] Zhang, Daihui[4] Ma, Hongzhi[5] Sun, Fubao[6] Pugazhendhi, Arivalagan[7,8] Xia, Changlei[1]

第一作者：Jin, Xin

通信作者：Xia, CL[1];Pugazhendhi, A[2];Pugazhendhi, A[3]

机构：[1]Nanjing Forestry Univ, Coll Mat Sci & Engn, Jiangsu Coinnovat Ctr Efficient Proc & Utilizat Fo, Int Innovat Ctr Forest Chem & Mat, Nanjing 210037, Jiangsu, Peoples R China;[2]Sichuan Univ, West China Hosp, Canc Ctr, Dept Biotherapy, Chengdu 610041, Sichuan, Peoples R China;[3]Northwestern Univ, Dept Mat Sci & Engn, Evanston, IL 60208 USA;[4]Chinese Acad Forestry, Inst Chem Ind Forest Prod, Nanjing 210042, Jiangsu, Peoples R China;[5]Univ Sci & Technol, Dept Environm Sci & Engn, Beijing Key Lab Resource oriented Treatment Ind Po, Beijing 100083, Peoples R China;[6]Jiangnan Univ, Sch Biotechnol, Key Lab Ind Biotechnol, Minist Educ, Wuxi 214122, Jiangsu, Peoples R China;[7]Lebanese Amer Univ, Sch Engn, Byblos, Lebanon;[8]Chandigarh Univ, Univ Ctr Res & Dev, Dept Civil Engn, Mohali 140103, India

年份：2023

卷号：348

外文期刊名：FUEL

收录：;EI(收录号：20231914074402);Scopus(收录号：2-s2.0-85158912522);WOS:【SCI-EXPANDED(收录号:WOS:001001045000001)】；

基金：This work is supported by National Key R&D Program of China (2022YFD2200705) , Jiangsu Agricultural Science and Technology Innovation Fund (CX (22) 2045) , and Natural Science Foundation of Jiangsu Province (BK20200775) .

语种：英文

外文关键词：Biodiesel yield; Machine learning; Random Forest regression; Transesterification reaction

摘要：Biodiesel prepared by transesterification reaction was a potential fuel to address the global energy issues due to obtaining from biomass resources (waste oils, micro-algae, and plant oils) and environmentally friendly. However, biodiesel production achieved by means of the transesterification process was affected by various factors such as feedstock type, reaction time, reaction temperature, and catalyst. Recently, machine learning (ML) presents a versatile approach to predicting biodiesel yield which avoids a number of experiments. Herein, we collected 13 cases with 381 individuals experimentally data and used four ML algorithms containing k-nearest neighbor algorithm (kNN), Support Vector Machine (SVM), Random Forest regression (RF), and AdaBoost regression to predict the biodiesel yield using transesterification reaction. The Random Forest regression can be more suitable to accurately predict biodiesel yield than other three ML models due to presenting a lower RMSE values for both Training (2.778) and Validation (5.178), and a higher correlation coefficient.