Deep Learning Models for SO(2) Distribution in a 30 MW Boiler via Computational Fluid Dynamics Simulation Data

[Image: see text] The distribution of SO(2) in a boiler is an important factor affecting tube corrosion in a furnace. To investigate the correlation between SO(2) distribution and numerous variables (e.g., temperature, O(2) distribution, etc.), a hybrid deep learning model is developed via the computational fluid dynamics (CFD) simulation data. First, the combustion process under typical working conditions is simulated to output the training data set. Then, a LASSO algorithm is adopted to select input variables with a high correlation with SO(2) distribution. Finally, a deep belief network combined with a restricted belief machine and a fully connected layer is developed to describe the nonlinear relationship. The proposed model is the first work to use a deep learning algorithm to obtain the correlation between SO(2) distribution and other products of combustion. The results show that O(2) concentration has the highest influence on SO(2) distribution.