Prediction of Higher Heating Value HHV of Date Palm Biomass Fuel using Artificial Intelligence Method

Abstract

Date palm biomass can be considered as an alternative to conventional energy combined with other renewable energy sources in the oasis. Its energy recovery requires a precise knowledge of its energy rate potential represented by its calorific value. Relationships of ultimate and proximate analysis of date palm biomass with higher heating value (HHV) have been investigated through artificial neural networks (ANNs) methods, especially, Multilayer Perceptron (MLP) model. Seven set of inputs including: (a) proximate analysis i.e. volatile matter (VM), ash (A) and moisture (M) and (b) ultimate analysis i.e carbon (C), hydrogen (H), oxygen (O) were identified and used for the prediction of (HHV) by ANNs. The adopted model allowed HHV prediction of phoenicicole biomass with a determination coefficient (R2) of up to 84% and a mean absolute percentage error (MAPE) of 2,61. (MLP) gives a good HHV prediction results for date palm biomass by taking into account hybrid variables (proximate and ultimate) especially carbon and oxygen. These input parameters were omnipresent in all the identified combinations and provided the optimum finding rates in association with volatile matter.