Estimation of higher heating values (HHVs) of biomass fuels based on ultimate analysis using machine learning techniques and improved equation

To have a sustainable economy and environment, several countries have widely inclined to the utilization of non-fossil fuels like biomass fuels to produce heat and electricity. The advantage of employing biomass for combustion is emerging as a potential renewable energy, which is regarded as a cheap fuel. Chemical constituents or elements are essential properties in biomass applications, which would be costly and labor-intensive to experimentally estimate them. One of the criteria to evaluate the energy of biomass from an economic perspective is the higher heating value (HHV). In the present work, we have applied multilayer perceptron artificial neural network (MLP-ANN), least-squares support vector machine (LSSVM), ant colony-adaptive neuro-fuzzy inference system (ACO-ANFIS), particle swarm optimization- ANFIS (PSO-ANFIS), genetic algorithm-radial basis function (GA-RBF) and new multivariate nonlinear regression (MNR) as accurate correlation methods to estimate HHVs of biomass fuels based on the ultimate analysis. 535 experimental data were gathered from literature and categorized into eight classes of by-products of fruits, agri-wastes, wood chips/tree species, grasses/leaves/fibrous materials, other waste materials, briquettes/charcoals/pellets, cereal and Industrial wastes. In the term of statistical analysis, average absolute relative deviation (AARD) authenticates that MNR and GA-RBF algorithm with %AARD of 3.5 and 3.4 could be used to estimate HHV. In addition, developed models results were compared to the results of 69 recently previously published empirical correlations and it confirms the reliability of our results. Relevency factor shows the impact of biomass elements on HHV and outlier analysis indicates the unreliable experimental data. The results of this study can be used by researchers to design and optimize biomass combustion systems. • Novel models for estimating HHV of biomass based on elemental analysis are proposed. • State of art machine learning models and an empirical model are proposed. • 535 data of HHV in different biomass classes were gathered. • Our models have higher accuracy than all of the literature models.