Predictive modelling of the higher heating value in biomass torrefaction for the energy treatment process using machine-learning techniques
PJ García Nieto, E García-Gonzalo… - Neural Computing and …, 2019 - Springer
PJ García Nieto, E García-Gonzalo, JP Paredes-Sánchez, A Bernardo Sánchez…
Neural Computing and Applications, 2019•SpringerTorrefaction of biomass can be described as a mild form of pyrolysis at temperatures
typically ranging between 200 and 300° C in the absence of oxygen. Common biomass
reactions during torrefaction include devolatilization, depolymerization, and carbonization of
hemicellulose, lignin, and cellulose. Torrefaction of biomass improves properties like
moisture content as well as calorific value. The aim of this study was to obtain a predictive
model able to perform an early detection of the higher heating value (HHV) in a biomass …
typically ranging between 200 and 300° C in the absence of oxygen. Common biomass
reactions during torrefaction include devolatilization, depolymerization, and carbonization of
hemicellulose, lignin, and cellulose. Torrefaction of biomass improves properties like
moisture content as well as calorific value. The aim of this study was to obtain a predictive
model able to perform an early detection of the higher heating value (HHV) in a biomass …
Abstract
Torrefaction of biomass can be described as a mild form of pyrolysis at temperatures typically ranging between 200 and 300 °C in the absence of oxygen. Common biomass reactions during torrefaction include devolatilization, depolymerization, and carbonization of hemicellulose, lignin, and cellulose. Torrefaction of biomass improves properties like moisture content as well as calorific value. The aim of this study was to obtain a predictive model able to perform an early detection of the higher heating value (HHV) in a biomass torrefaction process. This study presents a novel hybrid algorithm, based on support vector machines (SVMs) in combination with the particle swarm optimization (PSO) technique, for predicting the HHV of biomass from operation input parameters determined experimentally during the torrefaction process. Additionally, a multilayer perceptron network (MLP) and random forest (RF) were fitted to the experimental data for comparison purposes. To this end, the most important physical–chemical parameters of this industrial process are monitored and analysed. The results of the present study are two-fold. In the first place, the significance of each physical–chemical variables on the HHV is presented through the model. Secondly, several models for forecasting the calorific value of torrefied biomass are obtained. Indeed, when this hybrid PSO–SVM-based model with cubic kernel function was applied to the experimental dataset and regression with optimal hyperparameters was carried out, a coefficient of determination equal to 0.94 was obtained for the higher heating value estimation of torrefied biomass. Furthermore, the results obtained with the MLP approach and RF-based model are worse than the best obtained with the PSO–SVM-based model. The agreement between experimental data and the model confirmed the good performance of the latter. Finally, we expose the conclusions of this study.
Springer