Estimation of syngas yield in hydrothermal gasification process by application of artificial intelligence models

Yousaf Ayub, Yusha Hu, Jingzheng Ren

Research output: Journal article publicationJournal articleAcademic researchpeer-review

10 Citations (Scopus)

Abstract

Quality syngas production with higher moles of hydrogen and methane are the primary objective of gasification process which is dependent upon the process parameters and composition of biomass. However, it is always a costly and time-consuming task to get the optimum biomass composition and process parameters for quality syngas production. In this research, artificial intelligence (AI) algorithms have been applied for high quality syngas prediction with better moles fractions of hydrogen and methane using hydrothermal gasification (HTG). Comparative analysis of Convolutional Neural Network (CNN), Artificial Neural Network (ANN), Gradient Boost Regressor (GBR), Extreme Boost Regressor (XGB), and Random Forest Regressor (RFR) based algorithms have been done to select an optimal one. Ultimate analysis of biomass and process input parameters inlcuding temperature, pressure, percentage solid content of biomass, and resident time have been used as an input parameter for prediction models. Final comparative results of these AI models conclude that XGB has a better prediction result as compared to other with coefficient of determinant (R 2) and mean square errors ranges from 0.85 to 0.95 and 0.008–0.01, respectively. Furthermore, process temperature and the resident time are the most contributing factors in mole fractions of hydrogen and methane. Higher hydrogen and oxygen contents in the biomass, significantly contributes to the production of quality syngas.

Original languageEnglish
Article number118953
Number of pages12
JournalRenewable Energy
Volume215
DOIs
Publication statusPublished - Oct 2023

Keywords

  • Artificial intelligence
  • Biomass energy
  • Extreme Gradient
  • Gasification
  • Machine learning

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment

Fingerprint

Dive into the research topics of 'Estimation of syngas yield in hydrothermal gasification process by application of artificial intelligence models'. Together they form a unique fingerprint.

Cite this