Prediction of gross calorific value of coal based on proximate analysis using multiple linear regression and artificial neural networks
[ X ]
Tarih
2018
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Gross calorific value (GCV) of coal was predicted by using as-received basis proximate analysis data. Twomain objectives of the study were to develop prediction models for GCV using proximate analysis variables and toreveal the distinct predictors of GCV. Multiple linear regression (MLR) and artifcial neural network (ANN) (multilayerperceptron MLP, general regression neural network GRNN, and radial basis function neural network RBFNN) methodswere applied to the developed 11 models created by different combinations of the predictor variables. By conducting 10-fold cross-validation, the prediction accuracy of the models has been tested by using R2, RMSE , MAE , and MAP E .In this study, for the first time in the literature, for a single dataset, maximum number of coal samples were utilizedand GRNN and RBFNN methods were used in GCV prediction based on proximate analysis. The results showed thatmoisture and ash are the most discriminative predictors of GCV and the developed RBFNN-based models produce highperformance for GCV prediction. Additionally, performances of the regression methods, from the best to the worst, wereRBFNN, GRNN, MLP, and MLR
Açıklama
Anahtar Kelimeler
Kaynak
Turkish Journal of Electrical Engineering and Computer Sciences
WoS Q Değeri
Scopus Q Değeri
Cilt
26
Sayı
5
