Improved Prediction of the Higher Heating Value of Biomass Using an Artificial Neural Network Model Based on the Selection of Input Parameters

Abstract

Recently, biomass has become an increasingly widely used energy resource. The problem with the use of biomass is its variable composition. The most important property that determines the energy content and thus the performance of fuels such as biomass is the heating value (HHV). This paper focuses on selecting the optimal number of input variables using linear regression (LR) and the multivariate adaptive regression splines approach (MARS) to create an artificial neural network model for predicting the heating value of selected biomass. The MARS model selected the input data better than the LR model. The best modeling results were obtained for a network with three input neurons and nine neurons in the hidden layer. This was confirmed by a high correlation coefficient of 0.98. The obtained results show that artificial neural network (ANN) models are effective in predicting the calorific value of woody and field biomass, and can be considered a worthy simulation model for use in selecting biomass feedstocks and their blends for renewable fuel applications.

Comparative Analysis of Machine Learning Methods for Predicting Energy Recovery from Waste

“…The statistical performance of the developed GEP, SVM, and FFNN models for R2 were 0.966, 0.973, and 0.978, respectively, and for RMSE were 1.57, 1.44, and 1.25, respectively [6]. In the authors' previous studies, a machine learning model for HHV prediction of different types of biomass was developed [16]. The input data used were the results of elemental biomass analysis, carbon, nitrogen, and hydrogen analysis.…”

“…The models that use waste chemical analyses as input data are presented above. These models are employed to develop and optimize specific waste processing technologies [16].…”