Application of Adaptive Resonance Theory for the classification of coal seams with respect to their spontaneous heating susceptibility

Abstract

Mine fire due to spontaneous heating is an inherent and major problem in coal mining industry. These fires endanger valuable lives of men in a mine, and cause considerable economic losses to the organisation and serious environmental degradation. This paper presents the application of adaptive resonance theory of artificial neural networks (ANN) for classification of coal seams with respect to their proneness to spontaneous heating. To apply this method, a number of coal samples were collected from different Indian coalfields covering both fiery and non-fiery coal seams of varying ranks spreading over 8 different mining companies. The intrinsic properties and spontaneous heating susceptibility indices of these samples were determined by different experimental techniques. Exhaustive correlation studies between susceptibility indices and the intrinsic properties have been carried out for identifying the appropriate spontaneous heating susceptibility indices and intrinsic properties to be used for classification of coal seams. The identified parameters are used as inputs and adaptive resonance theory of ANN has been applied to classify the coal seams into four different categories.