An innovative application of machine learning in prediction of the syngas properties of biomass chemical looping gasification based on extra trees regression algorithm

Zhen Wang, Lin Mu, Hongchao Miao, Yan Shang, Hongchao Yin and Ming Dong

Energy, 2023, vol. 275, issue C

Abstract: Biomass chemical looping gasification (BCLG) is a promising carbon capture technology to produce hydrogen−rich syngas. In this study, the advanced machine learning method based on extra trees regression (ETR) algorithm was proposed to predict the syngas properties in the BCLG process. The prediction performance of the ETR algorithm was compared with traditional artificial neural network (ANN) and random forest (RF) algorithms. The outcomes demonstrated that the ETR algorithm had stronger prediction performance than RF and ANN algorithms in all target features with R2 > 0.88, which indicated the potential value of the ETR algorithm in small sample machine learning. Moreover, the results of elaborate feature importance analysis showed that the S/B ratio expressed a strong positive correlation with H2/CO ratio, and the most useful way to improve the gas yield and carbon conversion efficiency were reducing the λ value and increasing the temperature. The ETR algorithm was innovatively applied in the biomass field, which was beneficial to reduce the experiment consumption. It provided a comprehensive understanding of design and optimization of the commercial BCLG devices.

Keywords: Biomass chemical looping gasification; Extra trees regression algorithm; Machine learning; Syngas property; Feature analysis (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544223008320
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:275:y:2023:i:c:s0360544223008320

DOI: 10.1016/j.energy.2023.127438

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().