Estimation of the GCV of Coal Using Real‐Time Plant Data

Online or real‐time strategies of estimating the gross calorific value (GCV) of coal are still not fully explored in academic literature, even though both conventional and sophisticated offline methods for estimating the GCV are well described. Soft computing and machine learning models concentrate on offline data, relying on lab‐derived inputs rather than continuous sensor data. None of the existing methods of estimating the GCV of coal go into detail about deployment within real‐time monitoring systems at coal‐fired power plants (CFPP). This study applied a novel approach of using real‐time plant data to estimate the GCV of coal by employing computational fluid dynamics (CFD) and mass and energy balance (MEB) modelling to simulate a full‐scale coal fired boiler since currently, the plant does not have enough data to establish a correlation between the GCV of coal and real‐time plant data. To estimate the GCV of coal under operating conditions, empirical correlations were established using the CFD and MEB model outputs for the main flue gas constituents, carbon dioxide (), carbon monoxide (CO), oxygen (), and sulfur dioxide (). The flue gas constituents used as regressors were selected for this study since they are currently measured at the plant, which is the “real‐time plant data” selected for this study. The study applied the multilinear regression (MLR) method to establish a correlation between the GCV of coal and flue gas constituents. MLR might be viewed as a traditional method of establishing correlations, but studies referenced in this study have presented that MLR provides the same results when compared to the recent artificial intelligence (AI) tools that have been explored by other researchers to estimate the GCV of coal. The correlations established in this study showed dependable prediction capacity with a coefficient of determination () of 0.84 and relative errors ≤ 6.2%. The results provided the groundwork for implementing real‐time GCV estimation techniques in coal‐fired power plants that are currently in operation, which could enhance combustion efficiency monitoring and control.