Simultaneous prediction of coal rank parameters based on ultimate analysis using regression and artificial neural network

Results from ultimate analysis, proximate and petrographic analyses of a wide range of Kentucky coal samples were used to predict coal rank parameters (vitrinite maximum reflectance (Rmax) and gross calorific value (GCV)) using multivariable regression and artificial neural network (ANN) methods. Volatile matter, carbon, total sulfur, hydrogen and oxygen were used to predict both Rmax and GCV by regression and ANN. Multivariable regression equations to predict Rmax and GCV showed R2 = 0.77 and 0.69, respectively. Results from the ANN method with a 2–5–4–2 arrangement that simultaneously predicts GCV and Rmax showed R2 values of 0.84 and 0.90, respectively, for an independent test data set. The artificial neural network method can be appropriately used to predict Rmax and GCV when regression results do not have high accuracy.