upachate Innet.. Performance inconsistencies in biomass higher heating value models for ultimate analysis. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2567.
Performance inconsistencies in biomass higher heating value models for ultimate analysis
Abstract:
Biomass is a sustainable renewable energy that can replace fossil fuels, reduce greenhouse gas
emissions, and be integrated into the energy structure of Thailand. Ultimate analysis measures the Higher
Heating Value (HHV) of chemical elements to determine the energy quantity of a fuel. The accuracy and
consistency of the out-of-sample data for the prediction model are essential for data-poor regions like
Thailand. The present study conducted three experiments to verify the consistency of the HHV models
using out-of-sample data. The published datasets were the treatments, with the accuracy stabilities being
the responses. Multiple situations of out-of-sample implementation were simulated. The results confirmed
accuracy inconsistencies in both linear and nonlinear HHV models. The models presented statistical
indifferences in the average error of the in-sample performance, while the higher moments of error
distribution remained distinct. All higher moments of the residuals of the model were different in the
out-of-sample data. The simulated examples indicated that previous models could not maintain the
accuracy of their training sets. Additionally, they could not provide an accurate prediction of the
biomass data of Thailand. Therefore, a practical dataset is necessary to retrain the HHV models before
implementation to ensure accurate HHV prediction in Thailand."