Prediction of Higher Heating Value of Solid Biomass Fuels Using Artificial Intelligence Formalisms

摘要: The higher heating value (HHV) is an important property defining the energy content of biomass fuels. A number proximate and/or ultimate analysis based predominantly linear correlations have been proposed for predicting HHV scrutiny relationships between constituents and analyses corresponding HHVs suggests that all are not thus nonlinear models may be more appropriate. Accordingly, a novel artificial intelligence (AI) formalism, namely genetic programming (GP) has employed first time developing two prediction models, respectively using as model inputs. generalization performance these was compared rigorously with multilayer perceptron (MLP) neural network also currently available high-performing models. This comparison reveals GP MLP consistently better than their existing counterparts. Specifically, GP- MLP-based exhibit excellent overall accuracy high (>0.95) magnitudes coefficient correlation low (<4.5 %) mean absolute percentage error in respect experimental model-predicted HHVs. It found analysis-based outperformed In case exhibited best when AI-based introduced this paper due to potential replace