Process optimization of biomass gasification with a Monte Carlo approach and random forest algorithm
文献类型:期刊论文
作者 | Fang, Yi3; Ma, Li4; Yao, Zhiyi1; Li, Wangliang2; You, Siming3 |
刊名 | Energy Conversion and Management |
出版日期 | 2022-07-15 |
卷号 | 264 |
ISSN号 | 1968904 |
关键词 | Biomass - Decision trees - Forecasting - Gasification - Intelligent systems - Kinetic parameters - Kinetic theory - Machine learning - Normal distribution - Optimization - Particle size - Synthesis gas - Thermal conductivity |
DOI | 10.1016/j.enconman.2022.115734 |
英文摘要 | Gasification technologies have been extensively studied for their potential to convert biomass feedstocks into syngas (a mixture of CH4, H2, and CO mainly) that can be further turned into heat or electricity upon combustion. It is crucial to understand optimal gasification process parameters for practical design and operation for maximizing the potential. This study combined the Monte Carlo simulation approach, gasification kinetic modeling, and the random forest algorithm to predict the optimal gasification process parameters (i.e. water content, particle size, porosity, thermal conductivity, emissivity, shape, and reaction temperature) towards a maximum syngas yield. The Monte Carlo approach randomly generated a data pool of the process parameters following either a normal or uniform distribution, which was then fed into a validated kinetic model to create 2,000 datasets (process parameters and syngas yields). For the random forest model, the mean decrease accuracy and mean decrease Gini were used to assess the importance of the process parameters on syngas yields. The accuracy of the optimization method was evaluated using the coefficient of determination (R2), the root means square error (RMSE), and the mean absolute error (MAE). Generally, the predictions for the normal distribution case were closer to the experimental data obtained from existing literature than that for the uniform distribution case. The model was used to predict the optimal syngas yield and process parameters of wood gasification and it was shown that the predictions were generally in good agreement ( 漏 2022 The Authors |
学科主题 | Monte Carlo Methods |
项目编号 | Siming You would like to acknowledge the financial support from the UK Engineering and Physical Sciences Research Council (EPSRC) Programme Grant (EP/V030515/1), Supergen Bioenergy Hub Rapid Response Funding (RR 2022_10), and Royal Society Research Grant (RGS\R1\211358). Wangliang Li would like to thank the financial support from the National Natural Science Foundation of China (No. 21878313 ). The authors would like to thank Ms. Yang Fang for supporting the design of Figs. 2 and 3 . All data supporting this study are provided in full in the 'Methodology' and 'Results and Discussion' sections of this paper. |
出版者 | Elsevier Ltd |
源URL | [http://ir.ipe.ac.cn/handle/122111/61254] |
作者单位 | 1.CBE Eco-Solutions Pte. Ltd., Singapore; 117602, Singapore 2.CAS Key Laboratory of Green Process and Engineering, Institute of Process Engineering, Chinese Academy of Sciences, Beijing; 100190, China 3.James Watt School of Engineering, University of Glasgow, Glasgow; G12 8QQ, United Kingdom 4.National Key Laboratory of Rotorcraft Aeromechanic, Nanjing University of Aeronautics and Astronautics, Nanjing; 210016, China |
推荐引用方式 GB/T 7714 | Fang, Yi,Ma, Li,Yao, Zhiyi,et al. Process optimization of biomass gasification with a Monte Carlo approach and random forest algorithm[J]. Energy Conversion and Management,2022,264. |
APA | Fang, Yi,Ma, Li,Yao, Zhiyi,Li, Wangliang,&You, Siming.(2022).Process optimization of biomass gasification with a Monte Carlo approach and random forest algorithm.Energy Conversion and Management,264. |
MLA | Fang, Yi,et al."Process optimization of biomass gasification with a Monte Carlo approach and random forest algorithm".Energy Conversion and Management 264(2022). |
入库方式: OAI收割
来源:过程工程研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。