Estimation of coal swelling index based on chemical properties of coal using artificial neural networks

Free swelling index (FSI) is an important parameter for cokeability and combustion of coals. In this research, the effects of chemical properties of coals on the coal free swelling index were studied by artificial neural network methods. The artificial neural networks (ANNs) method was used for 200 datasets to estimate the free swelling index value. In this investigation, ten input parameters such as moisture, volatile matter (dry), fixed carbon (dry), ash (dry), total sulfur (organic and pyretic)(dry), (British thermal unit (Btu)/lb) (dry), carbon (dry), hydrogen (dry), nitrogen (dry) as well as oxygen (dry) were used. For selecting the best model for this study the outputs of models were compared. A three-layer ANN was found to be optimum with architecture of ten and four neurons in first and second hidden layer, respectively, and one neuron in output layer. Results of artificial neural network shows that training, testing and validating data’s square correlation coefficients (R2) achieved 0.99, 0.92 and 0.96, respectively. The sensitivity analysis showed that the highest and lowest effects of coal chemical properties on the coal free swelling index were nitrogen (dry) and fixed carbon (dry), respectively. Keywords: Coal Chemical Properties, Free Swelling Index, Artificial Neural Networks (ANNs), Cokeability and Back Propagation Neural Network (BPNN).