中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 广州能源研究所
  3. 中国科学院广州能源研究所
Biomass hydrothermal gasification characteristics study: based on deep learning for data generation and screening strategies

文献类型：期刊论文

作者Qi, Jingwei1,2; Wang, Yijie3; Xu, Pengcheng2; Hu, Ming4; Huhe, Taoli1,5; Ling, Xiang1; Yuan, Haoran6; Li, Jiadong7; Chen, Yong1,6
刊名ENERGY
出版日期2024-12-15
卷号312页码:17
关键词Biomass Hydrothermal gasification Data generation Data screening Generative adversarial networks
ISSN号0360-5442
DOI10.1016/j.energy.2024.133492
通讯作者Yuan, Haoran(yuanhr@ms.giec.ac.cn) ; Li, Jiadong(jd.li@upc.edu.cn)
英文摘要Hydrothermal gasification is an import-ant way to utilize biomass resources, and accurate prediction of the biomass hydrothermal gasification process is of great significance for the formulation and optimization of process parameters and equipment. Data is a key factor in machine learning, but due to the high experimental costs associated with hydrothermal gasification processes, acquiring a large amount of experimental data for machine learning modeling is a major challenge. To address this issue, this study proposes a data generation and screening strategy based on generative adversarial networks (GAN). The data generation and screening strategy primarily rely on GAN networks trained with real data as data generators and random forest models trained with real data as data screeners. High-quality synthetic data is selected through screening criteria to augment the dataset. Four machine learning models are used to model the biomass hydrothermal gasification process based on synthetic data to validate this strategy. The results show that, compared to the original data, modeling with synthetic data leads to a significant increase in the evaluation metrics for predicting H2, CH4, and CO2, especially during the testing phase. This indicates the rationality of the proposed data generation and screening strategy.
WOS关键词SUPERCRITICAL WATER GASIFICATION ; HYDROGEN-PRODUCTION ; WASTE ; GAS ; MODEL ; OIL
WOS研究方向Thermodynamics ; Energy & Fuels
语种英语
WOS记录号WOS:001339419400001
出版者PERGAMON-ELSEVIER SCIENCE LTD
源URL[http://ir.giec.ac.cn/handle/344007/43245]  
专题中国科学院广州能源研究所
通讯作者Yuan, Haoran; Li, Jiadong
作者单位1.Nanjing Tech Univ, Sch Mech & Power Engn, Nanjing 211816, Peoples R China
2.Everbright Environm Res Inst Nanjing Co Ltd, Nanjing 210000, Peoples R China
3.China Univ Petr, Beijing 102249, Peoples R China
4.Everbright Greentech Technol Serv Jiangsu Ltd, Nanjing 210000, Peoples R China
5.Changzhou Univ, Changzhou 213164, Peoples R China
6.Chinese Acad Sci, Guangzhou Inst Energy Convers, Guangzhou 510640, Peoples R China
7.China Univ Petr East China, Qingdao 266580, Peoples R China
推荐引用方式
GB/T 7714		 Qi, Jingwei,Wang, Yijie,Xu, Pengcheng,et al. Biomass hydrothermal gasification characteristics study: based on deep learning for data generation and screening strategies[J]. ENERGY,2024,312:17.
APA Qi, Jingwei.,Wang, Yijie.,Xu, Pengcheng.,Hu, Ming.,Huhe, Taoli.,...&Chen, Yong.(2024).Biomass hydrothermal gasification characteristics study: based on deep learning for data generation and screening strategies.ENERGY,312,17.
MLA Qi, Jingwei,et al."Biomass hydrothermal gasification characteristics study: based on deep learning for data generation and screening strategies".ENERGY 312(2024):17.

入库方式： OAI收割

来源：广州能源研究所

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。