Development of multiple machine-learning computational techniques for optimization of heterogenous catalytic biodiesel production from waste vegetable oil |
| |
| Affiliation: | 1. Department of Health and Rehabilitation Sciences, College of Applied Medical Sciences, Prince Sattam bin Abdulaziz University, P.O. Box. 173, Al-Kharj 11942, Saudi Arabia;2. Department of Physical Therapy, Kasr Al-Aini Hospital, Cairo University, Giza 12613, Egypt;3. Department of Rehabilitation Sciences, College of Health and Rehabilitation Sciences, Princess Nourah bint Abdulrahman University, P.O. Box. 84428, Riyadh 11671, Saudi Arabia;4. College of Business Administration, Ajman University, Ajman, United Arab Emirates;5. Department of Technology and Catering Organization, South Ural State University, Chelyabinsk, Russian Federation;6. Zhangir Khan Agrarian Technical University, Uralsk, Kazakhstan;7. Department of Chemical Engineering, Ming Chi University of Technology, New Taipei City, Taiwan;8. Department of Computer Science, Jeddah International College, Jeddah, Saudi Arabia;9. Mechanical Engineering Department, Faculty of Engineering, King Abdulaziz University, P.O. Box 344, Rabigh 21911, Saudi Arabia;10. Department of Mechanical Engineering, Faculty of Engineering & Technology, Future University in Egypt, 11845 New Cairo, Egypt;11. School of Life and Environmental Sciences, Deakin University, Geelong, Victoria 3216, Australia |
| |
| Abstract: | 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 R2-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 × 10-2, 5.20 × 10-2, and 9.83 × 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. |
| |
| Keywords: | Biodiesel Esterification Renewable energy Process optimization Machine learning |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
