Machine learning prediction of pyrolytic gas yield and compositions with feature reduction methods: Effects of pyrolysis conditions and biomass characteristics.

Journal: Bioresource technology
Published Date: Nov 1, 2021

Abstract

This study aimed to utilize machine learning algorithems combined with feature reduction for predicting pyrolytic gas yield and compositions based on pyrolysis conditions and biomass characteristics. To this end, random forest (RF) and support vector machine (SVM) was introduced and compared. The results suggested that six features were adequate to accurately forecast (R > 0.85, RMSE < 5.7%) the yield while the compositions only required three. Moreover, the profound information behind the models was extracted. The relative contribution of pyrolysis conditions was higher than that of biomass characteristics for yield (55%), CO (73%), and H (81%), which was inverse for CO (12%) and CH (38%). Furthermore, partial dependence analysis quantified the effects of both reduced features and their interactions exerted on pyrolysis process. This study provided references for pyrolytic gas production and upgrading in a more convenient manner with fewer features and extended the knowledge into the biomass pyrolysis process.

Authors

  • Qinghui Tang
    State Key Laboratory of Coal Combustion, Huazhong University of Science and Technology, Wuhan 430074, China; China-EU Institute for Clean and Renewable Energy, Huazhong University of Science and Technology, Wuhan 430074, China.
  • Yingquan Chen
    State Key Laboratory of Coal Combustion, Huazhong University of Science and Technology, Wuhan 430074, China.
  • Haiping Yang
    School of Microelectronics, Southeast University, Wuxi 214135, China. 220153614@seu.edu.cn.
  • Ming Liu
    School of Land Engineering, Chang'an University, Xi'an 710064, China; Xi'an Key Laboratory of Territorial Spatial Information, School of Land Engineering, Chang'an University, Xi'an 710064, China. Electronic address: mingliu@chd.edu.cn.
  • Haoyu Xiao
    State Key Laboratory of Coal Combustion, Huazhong University of Science and Technology, Wuhan 430074, China.
  • Shurong Wang
    State Key Laboratory of Clean Energy Utilization, Zhejiang University, Hangzhou 310027, China. Electronic address: srwang@zju.edu.cn.
  • Hanping Chen
    State Key Laboratory of Coal Combustion, Huazhong University of Science and Technology, Wuhan 430074, China.
  • Salman Raza Naqvi
    School of Chemical & Materials Engineering, National University of Sciences & Technology, H-12, Islamabad 44000, Pakistan.

Keywords

External Resources

Popular Topics
Recent Journals