Development of multiple machine-learning computational techniques for optimization of heterogenous catalytic biodiesel production from waste vegetable oil

被引:27
作者
Abdelbasset, Walid Kamal [1 ,2 ]
Elkholi, Safaa M. [3 ]
Opulencia, Maria Jade Catalan [4 ]
Diana, Tazeddinova [5 ,6 ]
Su, Chia-Hung [7 ]
Alashwal, May [8 ]
Zwawi, Mohammed [9 ]
Algarni, Mohammed [9 ]
Abdelrahman, Anas [10 ]
Hoang Chinh Nguyen [11 ]
机构
[1] Prince Sattam Bin Abdulaziz Univ, Coll Appl Med Sci, Dept Hlth & Rehabil Sci, POB 173, Al Kharj 11942, Saudi Arabia
[2] Cairo Univ, Kasr Al Aini Hosp, Dept Phys Therapy, Giza 12613, Egypt
[3] Princess Nourah Bint Abdulrahman Univ, Coll Hlth & Rehabil Sci, Dept Rehabil Sci, POB 84428, Riyadh 11671, Saudi Arabia
[4] Ajman Univ, Coll Business Adm, Ajman, U Arab Emirates
[5] South Ural State Univ, Dept Technol & Catering Org, Chelyabinsk, Russia
[6] Zhangir Khan Agr Tech Univ, Uralsk, Kazakhstan
[7] Ming Chi Univ Technol, Dept Chem Engn, New Taipei, Taiwan
[8] Jeddah Int Coll, Dept Comp Sci, Jeddah, Saudi Arabia
[9] King Abdulaziz Univ, Fac Engn, Mech Engn Dept, POB 344, Rabigh 21911, Saudi Arabia
[10] Future Univ Egypt, Fac Engn & Technol, Dept Mech Engn, New Cairo 11845, Egypt
[11] Deakin Univ, Sch Life & Environm Sci, Geelong, Vic 3216, Australia
关键词
Biodiesel; Esterification; Renewable energy; Process optimization; Machine learning; NEURAL-NETWORKS; PREDICTION; MODELS; TEMPERATURE;
D O I
10.1016/j.arabjc.2022.103843
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Multiple machine learning models were developed in this study to optimize biodiesel production from waste cooking oil in a heterogenous catalytic reaction mode. Several input parameters were considered for the model including reaction temperature, reaction time, catalyst loading, methanol/oil molar ratio, whereas the percent of biodiesel production yield was the only output. Three ensemble models were utilized in this study: Boosted Linear Regression, Boosted Multi-layer Perceptron, and Forest of Randomized Tree for optimization of the yield. We then found their optimized configurations for each model, namely hyper-parameters. This critical task is done by running more than 1000 combinations of hyper-parameters. Finally, The R-2-Scores for Boosted Linear Regression, Boosted Multi-layer Perceptron, and Forest of Randomized Tree, respectively, were 0.926, 0.998, and 0.992. MAPE criterion revealed that the error rates for boosted linear regression, boosted multi-layer perceptron, and Forest of Randomized Tree was 5.68 x 10(-2), 5.20 x 10(-2), and 9.83 x 10(-2), respectively. Furthermore, utilizing the input vector (X1 = 165, X2 = 5.72, X3 = 5.55, X4 = 13.0), the proposed technique produces an ideal output value of 96.7 % as the optimum yield in catalytic production of biodiesel from waste cooking oil. (C) 2022 The Author(s). Published by Elsevier B.V. on behalf of King Saud University.
引用
收藏
页数:10
相关论文
共 91 条
  • [91] Zhou Z.H., 2012, ENSEMBLE METHODS FDN, DOI DOI 10.1201/B12207