Estimation of coal gross calorific value based on various analyses by random forest method. (1st August 2016)

• Record Type: Journal Article
• Authors: Matin, S.S.; Chelgani, S. Chehreh
• Is Part Of: Fuel. Volume 177(2016)
• Page Start: 274
• Page End: 278
• Publication Date: 2016-08-01
• Subjects: Gross calorific value -- Random forest -- Proximate analysis -- Ultimate analysis -- Regression; Fuel -- Periodicals; Coal -- Periodicals; Coal; Fuel; Periodicals; 662.6
• DOI: 10.1016/j.fuel.2016.03.031
• Languages: English
• ISSNs: 0016-2361

Abstract

Highlights: Properties of US coal were studied for the prediction of gross calorific value (GCV). Random forest (RF) models indicated that RF can accurately predict GCV. RF models are much suitable to assess complicated relationships in coal processing. Results recommended random forest as a model can be applied for other coal resources. Abstract: The last decade has witnessed of increasing the application of random forest (RF) models that are known as an exhibit good practical performance, especially in high-dimensional settings. However, on the theoretical side, their predictive ability markedly remains unexplained, especially in coal preparation. RF as a predictive model can tend to work well with large dimensional databases and rank predictors through its inbuilt variable importance measures. In this study, relationships among ultimate and proximate analyses of 6339 US coal samples from 26 states with gross calorific value (GCV) have been investigated by multivariable regression (MVR) and random forest (RF) models. RF method has been used for the variable importance. Models have shown that the ultimate analysis parameters are the most suitable estimators for GCV and that RF can predict GCV quite satisfactory. Running of the best arranged RF structures for the input sets and assessment of errors have suggested that RF models are suitable for complicated relationships.