Robust modelling development for optimisation of hydrogen production from biomass gasification process using bootstrap aggregated neural network

Kargbo, Hannah O.; Zhang, Jie; Phan, Anh N.

doi:10.1016/j.ijhydene.2022.12.110

Cited by 9 publications

(1 citation statement)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 describes the independent variables of the data set, and Table 2 shows examples of datasets. The data were collected from the sources specified in the literature [2,8,[24][25][26][27][28][29][30][31][32][33][34][35]. Data in which catalysts were not used in production processes where hydrogen was released was also included in the study.…”

Section: Sample Experimental Dataset Collectionmentioning

confidence: 99%

Comparison of Random Forest and Support Vector Regression Models in Predicting Hydrogen Production Process from Biomass

Bilgiç,

Gök

2024

Çukurova Üniversitesi Mühendislik Fakültesi Dergisi

View full text Add to dashboard Cite

The need for energy in the world is increasing day by day and various energy production methods are used to meet this need. Production of hydrogen from biomass is one of these methods. Hydrogen production from biomass is a promising process to produce hydrogen and energy which has advantages such as the ability to use sustainable energy sources like biomass and solid waste, being carbon neutral, and increasing energy independence thanks to the variation of resources and the availability of local resources. The catalysts used in this process which can be conducted in three separate ways, affect hydrogen and energy production positively or negatively. One of the most important steps in effectively acquiring the ideal amount of product is predicting the outcomes of this procedure. This article compares a support vector regression (SVR) and random forest (RF) model to predict how various inputs used to produce hydrogen from biomass will affect hydrogen output. Additionally, the effect of catalyst addition on hydrogen yield in biomass processes was examined. In this context, 57 experimental studies from the literature were selected as a data set. From this data, 90% was selected for training and 10% for testing. The outputs were evaluated according to parameters such as R2, RMSE and MSE. The results show that RF and SVR models can significantly predict catalyst activity and hydrogen production.

show abstract