A new approach for classification of calorific coal properties in boiler systems

In this paper a new approach for obtaining the coal quality classification is proposed. The main goal is to classify the coal into three classes: “good”, “medium” and “bad” coal based on its calorific value. Instead of having chemical analysis the classification is obtained by using only two electrical signals available from SCADA system, which are the speed of the belt feeder and the current of the mill motor. Two parameters of the cross-correlation function between these signals with mean values of these two signals from SCADA are used to form training set patterns for designing a classifier. The procedure of classifying the coal characterizing pattern has been introduced.