Performance Analysis of Intelligent Computational Algorithms for Biomass Higher Heating Value Prediction

Abstract

Higher heating value (HHV) is an essential parameter to consider when evaluating and choosing biomass substrates for combustion and  power generation. Traditionally, HHV is determined in the laboratory using an adiabatic oxygen bomb calorimeter. Meanwhile, this  approach is laborious and cost-intensive. Hence, it is essential to explore other viable options. In this study, two distinct artificial  intelligence-based techniques, namely, a support vector machine (SVM) and an artificial neural network (ANN) were employed to develop  proximate analysis-based biomass HHV prediction models. The input variables comprising ash, volatile matter, and fixed carbon were  paired to form four separate inputs to the prediction models. The overall findings showed that both the ANN and the SVM tools can guarantee accurate prediction in all the input combinations. The optimal prediction performances were observed when fixed carbon and  volatile matter were paired as the input combination. This combination showed that the ANN outperformed the SVM, having presented  the least root mean squared error of 0.0008 and the highest correlation coefficient of 0.9274. This study, therefore, concluded that the  ANN is more preferred compared to SVM for biomass HHV prediction based on the proximate analysis.