基于遗传算法优化反向传播神经网络的锅炉NO_(x)排放研究及应用  

Research and Application of Boiler NO_(x)Emission Based on BP Neural Network Optimized by Genetic Algorithm

作　　者：唐永基 李前宇 陈虎亮 TANG Yongji;LI Qianyu;CHEN HuUang(Ningxia Jingneng Ningdong Electric Power Co.,Ltd.,Yinchuan,Ningxia 750409,China;Beijing Jingneng Power Co.,Ltd.,Beijing 100124,China;Bering Yuanshen Energy Saving Technology Co.,Ltd.,Beijing 100036,China)

机构地区：[1]宁夏京能宁东发电有限责任公司,宁夏银川750409 [2]北京京能电力股份有限公司,北京100124 [3]北京源深节能技术有限责任公司,北京100036

出　　处：《山西电力》2021年第2期56-59,共4页Shanxi Electric Power

摘　　要：为了降低NO_(x)排放浓度,提高机组运行效率,建立了锅炉燃烧系统遗传算法一反向传播模型,并利用该模型通过反向传播神经网络对锅炉燃烧系统中NO_(x)排放浓度进行建模,利用遗传算法对限定范围内的对象输入进行参数全局寻优。以内蒙古某330 MW超临界机组为研究对象,利用该模型对运行参数进行实时优化,结果表明该模型能够有效降低NO_(x)排放浓度,具有一定的推广价值。In order to reduce NO_(x)emission concentration and improve unit operation efficiency,a Genetic algorithm-back propagation(GA-BP)model of boiler combustion system is established.The model is employed to model the emission concentration in the boiler combustion system based on the BP neural network,and the genetic algorithm is used to optimize the parameters of the object input within the limited range globally.With a 330 MW supercritical unit in Inner Mongolia as the research object,this model is used to optimize the operation parameters in real time,and the results show that the model can effectively reduce the NO_(x)emission concentration,which has certain popularization value.

关 键 词：燃烧优化 NO_(x)排放 反向传播神经网络 遗传算法 

分 类 号：TM621.2[电气工程—电力系统及自动化] X773[环境科学与工程—环境工程]