摘要
为提高选择性催化还原(SCR)脱硝系统的控制品质与经济性,需要建立精确的SCR脱硝反应器入口NO_x生成量动态模型。本文基于模糊树模型建立了SCR反应器入口NO_x生成量动态模型,提出采用复相关系数的时滞联合估计方法,对影响NO_x生成量的模型输入变量进行时滞估计。将该方法应用于某600 MW燃煤机组的运行数据,并对输入变量采用相关系数法和复相关系数法进行时滞估计对比。结果表明:模糊树模型的建模精度较高、泛化能力强;在模型输入变量进行时滞估计时,相较于相关系数法,采用复相关系数法对模型精度和泛化能力提升程度更高。
In order to improve the control quality and economy of selective catalytic reduction(SCR) denitration system, it is necessary to establish an accurate dynamic model of NO_x production at inlet of the SCR denitrification reactor. On the basis of fuzzy tree model, this paper builds up a dynamic model for NO_x production at the SCR reactor inlet, and proposes using a joint time-delay estimation method based on multiple correlation coefficients to estimate the time-delay of the input variables which affect the NO_x production. The method was applied to the operation data of a 600 MW coal-fired unit, and the time-delay of input variables were estimated by correlation coefficient method and multiple correlation coefficient method. The experimental results show that,the fuzzy-tree model has high accuracy and generalization ability, the time-delay estimation of input variables based on multiple correlation coefficient method improves more accurate and generalization ability for the model than the correlation coefficient method.
引文
[1]火电厂大气污染物排放标准:GB 13223-2011[S].北京:中国环境科学出版社,2011.Emission standard of air pollutants for thermal power plants:GB 13223-2011[S].Beijing:China Environ-mental Science Press,2011.
[2]张东辉,庄烨,朱润儒,等.燃煤烟气污染物超低排放技术及经济分析[J].电力建设,2015,36(5):125-130.ZHANG Donghui,ZHUANG Ye,ZHU Runru,et al.Ultra-low air pollutant control technologies for coal-fired flue gas and its economic analysis[J].Electric Power Construction,2015,36(5):125-130.
[3]伏甲琪,郭为民,刘延泉,等.SCR烟气脱硝系统Smith预估条件积分型滑模控制[J].热力发电,2017,46(4):93-98.FU Jiaqi,GUO Weimin,LIU Yanquan,et al.Conditional integral sliding mode control for SCR denitrification system based on Smith predictor[J].Thermal Power Generation,2017,46(4):93-98.
[4]FORTUNA L,GRAZIANI S,XIBILIA M G.Soft sensors for product quality monitoring in debutanizer distillation columns[J].Control Engineering Practice,2005,13(4):499-508.
[5]GOVINDAN R B,RAETHJEN J,KOPPER F,et al.Estimation of time delay by coherence analysis[J].Physica A Statistical Mechanics&Its Applications,2004,350(2):277-295.
[6]LOU H,SU H,XIE L,et al.Inferential model for industrial polypropylene melt index prediction with embedded priori knowledge and delay estimation[J].Industrial&Engineering Chemistry Research,2012,51(25):8510-8525.
[7]李妍君,熊伟丽,徐保国.一种带过程变量时滞估计的在线软测量建模方法[J].信息与控制,2016,45(6):641-646.LI Yanjun,XIONG Weili,XU Baoguo.An online soft-sensor modeling method including process variable time-delay estimation[J].Information and Control,2016,45(6):641-646.
[8]阮宏镁,田学民,王平.基于联合互信息的动态软测量方法[J].化工学报,2014,65(11):4497-4502.RUAN Hongmei,TIAN Xuemin,WANG Ping.Dynamic soft sensor method based on joint mutual information[J].Journal of Chemical Industry and Engineering(China),2014,65(11):4497-4502.
[9]王钧炎,黄德先.基于混合差分进化算法的软测量时延参数估计[J].化工学报,2008,59(8):2058-2064.WANG Junyan,HUANG Dexian.Time delay estimation of soft-sensor model based on hybrid differential evolution[J].Journal of Chemical Industry and Engineering(China),2008,59(8):2058-2064.
[10]管燕,吴和成,黄舜.基于改进DEA的江苏省科技资源配置效率研究[J].科研管理,2011,32(2):145-150.GUAN Yan,WU Hecheng,HUANG Shun.The efficiency of science and technology resource allocation in Jiangsu Province based on an improved DEA model[J].Science Research Management,2011,32(2):145-150.
[11]范德成,李昊,刘贇.基于改进DEA--以复相关系数为基准的滞后期的我国产业结构演化效率评价[J].运筹与管理,2016,25(3):195-203.FAN Decheng,LI Hao,LIU Yun.A modified DEAmodel:with the lag periods based on multiple correlation coefficients to evaluate the efficiency of industriai structure evolution in china[J].Operations Research and Management Science,2016,25(3):195-203.
[12]许童羽,马艺铭,曹英丽,等.基于主成分分析和遗传优化BP神经网络的光伏输出功率短期预测[J].电力系统保护与控制,2016,44(22):90-95.XU Tongyu,MA Yiming,CAO Yingli,et al.Short term forecasting of photovoltaic output power based on principal component analysis and genetic optimization of BP neural network[J].Power System Protection and Control,2016,44(22):90-95.
[13]王宁,谢敏,邓佳梁,等.基于支持向量机回归组合模型的中长期降温负荷预测[J].电力系统保护与控制,2016,44(3):92-97.WANG Ning,XIE Min,DENG Jialiang,et al.Mid-long term temperature-lowering load forecasting based on combination of support vector machine and multiple regression[J].Power System Protection and Control,2016,44(3):92-97.
[14]MAO J,ZHANG J,YUE Y,et al.Adaptive-tree-structurebased fuzzy inference system[J].IEEE Transactions on Fuzzy Systems,2005,13(1):1-12.
[15]ZHANG W,MAO J.Robust intelligent modeling for giant magnetostrictive actuators with rate-dependent hysteresis[J].International Journal of Intelligent Computing&Cybernetics,2012,5(4):500-514.
[16]ZHANG W,ZHANG Y,SUN Y,et al.Condition monitoring of limestone and soft sensing model of SO2emissions in a circulating fluidized bed boiler[J].Energy&Fuels,2016,30(4):3519-3528.
[17]ZHANG W,ZHANG Y,BAI X,et al.A robust fuzzy tree method with outlier detection for combustion models and optimization[J].Chemometrics&Intelligent Laboratory Systems,2016,158:130-137.
[18]吕游,刘吉臻,杨婷婷,等.[J].仪器仪表学报,2013,34(11):2418-2424.LV You,LIU Jizhen,YANG Tingting,et al.NOx emission characteristic modeling based on feature extraction using PLS and LS-SVM[J].Chinese Journal of Scientific Instrument,2013,34(11):2418-2424.