Towards the estimation of quantity of fuel consumed in steam generation through predictive modelling of feedwater temperature

Abstract

Fuel consumption is a critical parameter that every steam boiler operator seeks to minimize, due to its direct relationship with the operational cost of the steam boiler. Feedwater temperature has been identified as a key parameter that influences the fuel consumption of a steam boiler. In view of this, this study aimed to develop predictive models of feedwater temperature in order to estimate the quantity of fuel consumed by the boiler. Feedwater temperature data of a steam boiler has been acquired, examined, and found to be of time-dependent characteristic. Four time-dependent models, namely, Autoregressive Moving Average, Neural Network, Long-Shot Term Memory, and Autoregressive Integrated Moving Average, have been used in modelling the feedwater temperature and validated. The Autoregressive Moving Average, ARMA(1,1) successfully predicts the feedwater temperature within a margin of error of ± 3.967 at 95% confidence level with validation criteria R, RMSE and MSE values recorded as 0.827, 1.022 and 1.044 respectively. A negative linear correlation is found between the feedwater temperature and the quantity of fuel consumed by the steam boiler. Hence, feedwater temperature can be used to control the quantity of fuel consumed by a steam boiler.