首页|基于机器学习的生物质热解高值化利用研究进展

基于机器学习的生物质热解高值化利用研究进展

扫码查看
生物质热解是一种高效的生物质资源利用方式,然而热解过程影响因素众多,传统方法很难全面了解影响因素与热解结果之间的关联。为了解决这一问题,研究人员采用机器学习方法建立生物质热解模型,并针对模型的优化与应用开展深入研究。鉴于此,本综述在简单介绍机器学习方法的基础上,从热解动力学参数、热解产物产率和热解产物特性3个方面,对应用机器学习方法建立生物质热解过程模型的相关工作进行了总结,寻找热解条件与热解结果之间关联性的规律。同时讨论了机器学习在生物质热解领域的相关研究中存在的问题和未来的研究方向,以期进一步推动机器学习方法在生物质热解领域的发展和应用。
Research Progress of Biomass Pyrolysis for High-value Utilization Based on Machine Learning
Biomass pyrolysis was an efficient way of utilizing biomass resources.However,the pyrolysis process involved numerous influencing factors,making it difficult to fully understand the correlation between the factors and the pyrolysis results through traditional methods.To solve this problem,researchers had utilized machine learning(ML)methods to establish biomass pyrolysis models and conducted in-depth research on the optimization and application of ML models.Given this,on the basis of a brief introduction of ML methods,this review summarized the relevant work of applying ML methods to establish biomass pyrolysis process models from three aspects:pyrolysis kinetics parameters,pyrolysis product yields,and characteristics of pyrolysis products,and looked for the correlations between pyrolysis conditions and pyrolysis results.Additionally,the problems existed in ML research in the field of biomass pyrolysis and future research directions were discussed,with the goal of further promoting the development and application of ML methods in the field of biomass pyrolysis.

biomass pyrolysismachine learningcorrelationdynamicsproduct characteristics

薛培轩、贺添乐、夏加庚、杨雯淇、胡强、杨海平

展开 >

华中科技大学能源与动力工程学院

煤燃烧与低碳利用全国重点实验室,湖北武汉 430074

生物质热解 机器学习 关联性 动力学 产物特性

国家杰出青年科学基金资助项目华中科技大学交叉研究支持计划

521256012023JCYJ004

2024

林产化学与工业
中国林业科学研究院林产化学工业研究所 中国林学会林产化学化工分会

林产化学与工业

CSTPCD北大核心
影响因子:0.696
ISSN:0253-2417
年,卷(期):2024.44(5)