基于数据处理与BP神经网络的SCR脱硝效率预测模型  

SCR Denitration Efficiency Prediction Model Based on Data Processing and BP Neural Network

作　　者：朱洁雯 金保昇[1] 张勇[1] 张友卫 周春蕾[2] 李逗 孙栓柱[2] 孙和泰[2] Zhu Jiewen

机构地区：[1]东南大学能源与环境学院,江苏南京210096 [2]江苏方天电力技术有限公司,江苏南京211102

出　　处：《工业控制计算机》2020年第2期49-50,共2页Industrial Control Computer

摘　　要：基于数据处理与分析的方法,充分利用电厂DCS系统中存储的大量实际运行数据,以SCR系统相关参数为输入,SCR出口NOx浓度为输出,采用BP神经网络构建SCR脱硝系统预测模型。该模型充分考虑脱硝效率与其他变量的关系。实验结果表明模型预测结果可靠,为下一步脱硝系统优化运行、实现节能减排提供模型基础。Based on the method of data processing and analysis,a large amount of actual data stored in the DCS of power plant are fully utilized.With relevant parameters of SCR system as input and NOx concentration at SCR outlet as output,BP neural network is used to construct the prediction model of SCR denitrification system.The model fully considers the relationship between denitrification efficiency and other variables.The experimental results show that the prediction results of the model are reliable,providing a model basis for the optimization of denitrification system in the next step and the realization of energy saving and emission reduction.

关 键 词：SCR脱硝 数据处理 BP神经网络 参数预测 

分 类 号：X773[环境科学与工程—环境工程] TM621[电气工程—电力系统及自动化] TP183[自动化与计算机技术—控制理论与控制工程]