Assessing synergies between thermal energy and torrefaction severity index of wood spruce sawdust via machine learning algorithms

Assessing the synergies between thermal energy and the torrefaction severity index by elucidating the effects of biomass torrefaction conditions on product characteristics is still a relevant research question. This study explores the optimization of torrefaction of spruce wood sawdust by analyzing the chemical and physical features of the resultant material. The study employs thermogravimetric analysis and Thermal Desorption-Gas Chromatography/Mass Spectrometry (TD-GC/MS) to examine the changes in the components during torrefaction. The torrefaction process has a profound effect on the composition, causing conversion of up to 30 % of the initial mass to volatile organic compounds and incondensable gases when subjected to a temperature of 300 °C. The correlation matrix highlights the relationships between variables, including time, temperature, heating value, mass yield, energy yield, and ratios of C, H, and O. The matrix visually represents the interplay between these factors during the torrefaction process. Principal component analysis (PCA) and hierarchical cluster analysis (HCA) revealed that torrefaction severity index, cellulose, lignin, torrefaction time, and temperature correlate positively, while H/C, O/C, and hemicellulose content correlate negatively. The ANN model exhibited superior predictive accuracy (R² = 0.99982, RMSE = 0.00359), surpassing C&RT (R² = 0.99483, RMSE = 0.01943), KNN (R² = 0.99467, RMSE = 0.01974), and SVM (R² = 0.99022, RMSE = 0.02674), thus validating the efficacy of machine learning for precise torrefaction severity index (TSI) prediction. This finding enhances the efficiency of biomass processing and provides reliable tools for future research in the field, thereby informing and guiding future studies and industrial applications.