Prediction of Coal Calorific Value Based on a Hybrid Linear Regression and Support Vector Machine Model

Abstract

The gross calorific value (GCV) is an important property defining the efficiency of coal. There exist a number of correlations for estimating the GCV of a coal sample based upon its proximate and ultimate analyses. These correlations are mainly linear in character although there are indications that the relationship between the GCV and a few constituents of the proximate and ultimate analyses could be nonlinear, which has made artificial intelligence models as a useful tool for a more accurate GCV prediction. This paper focuses on an innovative method of GCV prediction using combination of Multivariate Linear Regression (MLR) as predictor and Support Vector Machine (SVM) as an error correction tool based on proximate and ultimate analyses. The GCV have been predicted using the MLR, ANN and the hybrid MLR–SVM models. In the analysis root mean squared error have been employed to compare performances of the models. Results demonstrated that both models have good prediction ability; however the hybrid MLR–SVM has better accuracy.