Research on New Nonlinear Method Applied on Coal Calorific Value Prediction

Abstract

Based on research of the relationship between the industrial analysis of coal composition and the calorific value, a multiple linear regression - support vector machine model for predicting calorific value of coal is put forward. The training sample set is made up of the original industrial analysis data and calorific value. Then the preliminary predicted model is established based on multiple linear regression algorithm. At the same time, error compensation is achieved by the support vector machine amend sub-model. The final predicted value is the sum of the preliminary predicted model output and the error compensation. Experimental results demonstrate that the predicted accuracy of the integrated model is more accurate than the traditional predicted models.