An Artificial intelligence-based modification to calorific value estimation of biomass from their proximate analysis

초록

This paper presents an artificial intelligence-based modification to the net heating value (NHV) estimation of biomass from their proximate analysis earlier proposed in the literature. Artificial neural network (ANN) and the gene expression programming (GEP) were used for the modification. For the ANN, a feed-forward back-propagation multi-layer perceptron (MLP) was used. The moisture content (M), fixed carbon content (FC), ash content (A), volatile matter (VM), and organic matter (OM) are the input parameters. The NHV is the targeted output parameter. The ANN-based model was developed using the weights and biases obtained from the ANN simulation, while the GEP model directly presents its result in the form of a mathematical model and expression trees. The performance of the proposed models were also tested using the coefficient of determination (R2), error analysis and variance accounted for (VAF) as the performance indices. The R2 and VAF of the proposed models were the highest with them having the lowest errors as compared with the models subjected to the modification