Prediction of torrefied biomass properties from raw biomass

Abstract The torrefaction process enhances the quality of raw biomass and has gained widespread attention as an effective technique in energy production. Therefore, the estimation of torrefied biomass characteristics at certain operating conditions is critical to obtain desired solid products. In this study, the carbon, hydrogen, oxygen content and higher heating value (HHV) of torrefied biomass were estimated based on the results of proximate analysis (the fixed-carbon, volatile matter and ash values) of raw biomass and experimental conditions (torrefaction temperature and time). A total of 448 input and output sets belonging to lignocellulosic biomass were collected from 61 different works in the literature. Subsequently, the feedforward backpropagation algorithm based artificial neural network (ANN) model and adaptive neuro-fuzzy inference system (ANFIS) were developed as a machine learning approach for modeling the torrefaction process. The estimation capability of the developed models was examined with evaluation indicators such as mean squared error, mean absolute percentage error, and coefficient of determination. The method developed in this study provided acceptable accuracies for both elemental composition and heating value estimates. Moreover, the ANN model provided slightly better performance than ANFIS. The results show that the developed ANN model is a useful tool to obtain the desired torrefied biomass.