Effects of Proximate Analysis on Coal Ash Fusion Temperatures: An Application of Artificial Neural Network.

Abstract

The temperature at which coal ash melts has a significant impact on the operation of a coal-fired boiler. The coal ash fusion temperature (AFT) is determined by its chemical composition, although the relationship between the two varies. Therefore, it is important to have mathematical models that can reliably predict the coal AFTs when designing coal-based processes based on their coal ash chemistry and proximate analysis. A computational intelligence model based on the interrelationships between coal properties and AFTs was used to predict the AFTs of the coal investigated. A model that integrates the ash, volatile matter, fixed carbon contents, and ash chemistry as input and the AFT [softening temperature, deformation temperature, hemispherical temperature, and flow temperature] as an output provided the best indicators to predict AFTs. The findings from the models indicate (a) a method for determining the AFTs from the coal properties; (b) a reliable technique to calculate the AFTs by varying the proximate analysis; and (c) a better understanding of the impact, significance, and interactions of coal properties regarding the thermal properties of coal ash. This study creates a predictive model that is easy to use, computer-efficient, and highly accurate in predicting coal AFTs based on their ash chemistry and proximate analysis data.