Deep Learning Models for SO2 Distribution in a 30 MW Boiler via Computational Fluid Dynamics Simulation Data

Zhenhao Tang; Hongrui Dong; Chong Zhang; Shengxian Cao; Tinghui Ouyang

doi:10.1021/acsomega.2c03468

Deep Learning Models for SO₂ Distribution in a 30 MW Boiler via Computational Fluid Dynamics Simulation Data

ACS Omega. 2022 Nov 11;7(46):41943-41955. doi: 10.1021/acsomega.2c03468. eCollection 2022 Nov 22.

Authors

Zhenhao Tang¹, Hongrui Dong¹, Chong Zhang¹, Shengxian Cao¹, Tinghui Ouyang²

Affiliations

¹ School of Automation Engineering, Northeast Electric Power University, Jilin132012, China.
² Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology (AIST), Tokyo135-0064, Japan.

Abstract

The distribution of SO₂ in a boiler is an important factor affecting tube corrosion in a furnace. To investigate the correlation between SO₂ distribution and numerous variables (e.g., temperature, O₂ 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 SO₂ 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 SO₂ distribution and other products of combustion. The results show that O₂ concentration has the highest influence on SO₂ distribution.