Clean Technology and Applied Materials Research Group, Department of Chemical and Metallurgical Engineering, Vaal University of Technology, Vanderbijlpark, South Africa.
J Environ Sci Health A Tox Hazard Subst Environ Eng. 2023;58(3):191-203. doi: 10.1080/10934529.2023.2174334. Epub 2023 Feb 9.
The performance of a flue gas desulfurization (FGD) system is characterized by SO removal efficiency () and reagent conversion (). Achieving a near-perfect reaction environment has been of concern in dry FGD (DFGD) due to the low reactivity compared to the wet and semi-dry units. This study will appraise output responses using modeling by response surface methodology (RSM) and artificial neural networks (ANN) approaches. The impacts of input parameters like hydration time, hydration temperature, diatomite to hydrated lime (Ca(OH)), sulfation temperature and inlet gas concentration will be studied using a randomized central composite design (CCD). ANN fitting tool mapped the CCD metadata using the Levenberg-Marquardt (LM) algorithm activated by the hyperbolic tangent () function. The hidden cells ranged from 7 to 10 to ascertain the effect node architecture on modeling accuracy. Validation of each procedure was assessed using root mean square error (RMSE), mean square error (MSE) and R-Squared studies. The outcomes presented a more accurate 5-10-2 ANN model in the mapping of the DFGD from R data of = 0.993 and = 0.9986 with a mapping deviation from the RMSE values of = 0.48465; = 0.44971 and MSE results of = 0.23488; = 0.20229.
烟气脱硫（FGD）系统的性能主要由 SO 去除效率（）和试剂转化率（）来表征。与湿法和半干法相比，干法 FGD（DFGD）的反应性较低，因此一直以来人们都很关注如何在其中实现近乎完美的反应环境。本研究将采用响应面法（RSM）和人工神经网络（ANN）方法进行建模，评估输出响应。使用随机中心复合设计（CCD）研究水合时间、水合温度、硅藻土与熟石灰（Ca(OH)）、硫酸盐化温度和入口气体浓度等输入参数的影响。ANN 拟合工具使用 Levenberg-Marquardt（LM）算法对 CCD 元数据进行映射，该算法由双曲正切（）函数激活。隐藏层的范围为 7 到 10 个，以确定模型准确性的影响节点结构。使用均方根误差（RMSE）、均方误差（MSE）和 R-Squared 研究评估了每个程序的验证。结果表明，在 R 数据的映射中，具有 5-10-2 个隐藏层的 ANN 模型更为准确，=0.993 和 =0.9986，映射偏差为 RMSE 值=0.48465；=0.44971 和 MSE 结果=0.23488；=0.20229。
