Energy Efficiency Monitoring in a Coal Boiler Based on Optical Variables and Artificial Intelligence

In this work, we present the fundamentals of the estimation of the energy efficiency in an industrial coal boiler based in novel optical combustion diagnostics variables and several machine learning regression methods. The total radiation Radt and flame temperature Tf were considered. The inclusion of those variables allows to increase the overall performance in the estimation of the energy efficiency. The comparison in the performance of the tested methods for regression, suggest that Extreme Learning Machines in combination with Partial Least Squares for regression, lead to the best performance with a Pearson correlation coefficient R ≈ 0.7 in the test data set.