A Deep Learning Method for Acid Concentration and Temperature Prediction in Acid Production with Flue Gas

The dry absorption process is one of the critical steps in sulfuric acid production with flue gas. The concentration and temperature of sulfuric acid within the absorption tower directly impact the efficiency of acid production. Therefore, accurately predicting the concentration and temperature of sulfuric acid plays a significant role in acid production with flue gas. This paper proposes a method based on an improved Transformer model for real-time prediction of sulfuric acid concentration and temperature in the dry absorption process. To validate the effectiveness of the model, ablation experiments were designed using data from an actual dry absorption process. The experimental results demonstrated that the model proposed in this paper has higher predictive accuracy and is capable of accurately predicting the concentration and temperature of sulfuric acid.