Machine learning methods for modelling the gasification and pyrolysis of biomass and waste
Machine learning methods for modelling the gasification and pyrolysis of biomass and waste
复制标题
DOI：
10.1016/j.rser.2021.111902
复制
发表时间：
2022-01-03
影响因子：
15.9
通讯作者：
You, Siming
中科院分区：
文献类型：
--
作者：
Ascher, Simon;Watson, Ian;You, Siming
在过去的二十年中，使用机器学习（ML）方法来模拟生物质和废物气化/热解的情况迅速增加。 2000 年代仅发表了 70 篇论文，而 2010 年代共发表了 549 篇论文。然而，这些方法和研究结果仍有待系统审查。在这项工作中，讨论了最常用于气化和热解过程建模的机器学习方法，并参考其应用、优点和局限性。虽然决定系数 (R-2) 可能难以直接比较，但由于一些研究的方法和目标差异很大，但大多数研究一致实现了较高的预测精度，R-2 > 0.90。人工神经网络因其学习高度非线性输入输出关系的潜力而得到最广泛的应用。然而，根据应用、数据可用性、模型速度等，有多种方法（例如回归方法、基于树的方法和支持向量机）是合适的。可以得出的结论是，机器学习在开发更高精度的模型方面具有巨大的潜力。与现有模型相比，机器学习模型的一些优点是它们能够合并相关的非数值参数，并且能够为各种输入参数生成多种解决方案。应更加重视模型的可解释性，以便更好地理解正在研究的过程。
Over the past two decades, the use of machine learning (ML) methods to model biomass and waste gasification/pyrolysis has increased rapidly. Only 70 papers were published in the 2000s compared to a total of 549 publications in the 2010s. However, the approaches and findings have yet to be systematically reviewed. In this work, the machine learning methods most commonly employed for modelling gasification and pyrolysis processes are discussed with reference to their applications, merits, and limitations. Whilst coefficients of determination (R-2) can be difficult to compare directly, due to some studies having greatly different approaches and aims, most studies consistently achieved a high prediction accuracy with R-2 > 0.90. Artificial neural networks have been most widely used due to their potential to learn highly non-linear input-output relationships. However, a variety of methods (e.g. regression methods, tree-based methods, and support vector machines) are appropriate depending on the application, data availability, model speed, etc. It is concluded that ML has great potential for the development of models with greater accuracy. Some advantages of machine learning models over existing models are their ability to incorporate relevant non-numerical parameters and the power to generate a multitude of solutions for a wide range of input parameters. More emphasis should be placed on model interpretability in order to better understand the processes being studied.