Prediction of coal hydrogen content for combustion control in power utility using neural network approach

The solid nature of coal presents greater difficulties in measuring and controlling the combustion process compared to gas and oil fired power plants. Knowing the composition and energy content of coal can be very useful for combustion control in coal-fired power utilities. In this work, an attempt is made to establish relationships between the hydrogen composition of coal and available data from the proximate analysis. In the present work, artificial neural network based model is developed for the prediction of hydrogen content. For practical implications, a combustion control system utilising the neural network based model is also proposed to show the potential for coal-fired utilities.