基于粒子群优化双支持向量机的SCR烟气脱硝效率预测模型
|
摘要
为了更好地分析燃煤电厂脱硝效率与相关影响因素之间的非线性关系,引入双支持向量机(TWSVM)作为分类预测框架,利用粒子群算法(PSO)对TWSVM的惩罚因子和核参数进行寻优,进而构建了针对选择性催化还原(SCR)烟气脱硝效率预测的PSO-TWSVM模型。通过提取某电厂工况监控系统近期数据,结合三倍标准差检验法与归一化法对数据进行预处理,并选取训练集与测试集。仿真结果表明:SCR烟气脱硝效率预测PSO-TWSVM模型最大相对误差小于±0.6%,平均相对误差保持在±0.3%以下,证明该模型的准确性高;对比支持向量机(SVM)模型发现,PSO-TWSVM模型既提高了预测精度,也节省了计算时间。
In order to better analyze the nonlinear relationship between the denitration efficiency of coal-fired power plants and related factors, the twin support vector machine(TWSVM) was introduced as a classification framework. The particle swarm algorithm(PSO) was used to optimize the penalty factor and kernel function parameter of the TWSVM, and then the PSO-TWSVM model for predicting the SCR flue gas denitration efficiency was built up. Through extracting recent data of the power plant monitoring system and combining with three times standard deviation test and normalization method for data preprocessing, the training set and test set can be obtained. The simulation results show that, the maximum relative prediction error of the PSO-TWSVM model is no more than ±0.6%, and the average relative error is about ±0.3%, which proves the high efficiency of the model. In contrast with the SVM model, the PSO-TWSVM model not only improves the prediction accuracy, but also saves time.
In order to better analyze the nonlinear relationship between the denitration efficiency of coal-fired power plants and related factors, the twin support vector machine(TWSVM) was introduced as a classification framework. The particle swarm algorithm(PSO) was used to optimize the penalty factor and kernel function parameter of the TWSVM, and then the PSO-TWSVM model for predicting the SCR flue gas denitration efficiency was built up. Through extracting recent data of the power plant monitoring system and combining with three times standard deviation test and normalization method for data preprocessing, the training set and test set can be obtained. The simulation results show that, the maximum relative prediction error of the PSO-TWSVM model is no more than ±0.6%, and the average relative error is about ±0.3%, which proves the high efficiency of the model. In contrast with the SVM model, the PSO-TWSVM model not only improves the prediction accuracy, but also saves time.
引文
[1]张荀,柏源,刘涛,等.火电厂氮氧化物控制对策研究[J].电力科技与环保,2014,30(1):30-32.ZHANG Xun,BAI Yuan,LIU Tao,et al.Thinking on control strategy and problems of industrialization for nitrogen oxides control in thermal power industry[J].Electric Power Environmental Protection,2014,30(1):30-32.
[2]项昆.3种烟气脱硝工艺技术经济比较分析[J].热力发电,2011,40(6):1-3.XIANG Kun.Comparison and analysis in technoeconomic aspects for three kinds of flue gas denitrification technologies[J].Thermal Power Generation,2011,40(6):1-3.
[3]包鑫,戴连奎.基于局部最小二乘支持向量机的光谱定量分析[J].分析化学,2008,36(1):75-78.BAO Xin,DAI Liankui.Spectral quantitative analysis based on local least square support vector machine regression[J].Chinese Journal of Analytical Chemistry,2008,36(1):75-78.
[4]王美玲,王念平,李晓.BP神经网络算法的改进及应用[J].计算机工程与应用,2009,45(35):47-48.WANG Meiling,WANG Nianping,LI Xiao.Improvement and application of BPNN algorithm[J].Computer Engineering and Applications,2009,45(35):47-48.
[5]DAI Q,MA Z C,XIE Q Y.A two-phased and ensemble scheme integrated back propagation algorithm[J].Applied Soft Computing,2014,24:1124-1135.
[6]KODIYALAM S,GURUMOORTHY R.Neural networks with modified backpropagation learning applied to structural optimization[J].AIAA Journal,2015,34(2):408-412.
[7]杨碧源,赵金笑,魏宏鸽,等.基于BP神经网络的SCR蜂窝状催化剂脱硝性能预测[J].中国电力,2016,49(10):127-131.YANG Biyuan,ZHAO Jinxiao,WEI Hongge,et al.Performance forecasting for SCR honeycomb catalyst based on BP neural network[J].Electric Power,2016,49(10):127-131.
[8]汪海燕,黎建辉,杨风雷.支持向量机理论及算法研究综述[J].计算机应用研究,2014,31(5):1281-1286.WANG Haiyan,LI Jianhui,YANG Fenglei.Overview of support vector machine analysis and algorithm[J].Application Research of Computers,2014,31(5):1281-1286.
[9]凌武能,杭乃善,李如琦.基于云支持向量机模型的短期风电功率预测[J].电力自动化设备,2013,33(7):34-38.LING Wuneng,HANG Naishan,LI Ruqi.Short-term wind power forecasting based on cloud SVM model[J].Electric Power Automation Equipment,2013,33(7):34-38.
[10]ROJO-áLVAREZ J L,MartíNez-RAMóN M,MU?OZMARíJ,et al.A unified SVM framework for signal estimation[J].Digital Signal Processing,2013,26(1):1-20.
[11]崔仕文,铁治欣,丁成富,等.基于偏最小二乘支持向量机的烟气湿法脱硫效率预测模型[J].热力发电,2017,46(4):81-87.CUI Shiwen,TIE Zhixin,DING Chengfu,et al.Prediction model for flue gas wet desulfurization efficiency based on partial least squares support vector machine[J].Thermal Power Generation,2017,46(4):81-87.
[12]江彤,左青松,谢常清.柴油机SCR反应器性能FLSSVM预测模型[J].中南大学学报(自然科学版),2012,43(10):3906-3911.JIANG Tong,ZUO Qingsong,XIE Changqing.FLS-SVM performance forecasting model of SCR reactor in diesel engine[J].Journal of Central South University,2012,43(10):3906-3911.
[13]刘吉臻,秦天牧,杨婷婷,等.基于偏互信息的变量选择方法及其在火电厂SCR系统建模中的应用[J].中国电机工程学报,2016,36(9):2438-2443.LIU Jizhen,QIN Tianmu,YANG Tingting,et al.Variable selection method based on partial mutual information and its application in power plant SCR system modeling[J].Proceedings of the CSEE,2016,36(9):2438-2443.
[14]赵志宏,韩超,赵文杰.主元分析及多变量过程监测联合预测NOx质量浓度[J].热力发电,2016,45(7):98-103.ZHAO Zhihong,HAN Chao,ZHAO Wenjie.NOx content prediction based on principal component analysis and multivariable process monitoring[J].Thermal Power Generation,2016,45(7):98-103.
[15]郭伟,王西闯,肖振久.基于K均值和双支持向量机的P2P流量识别方法[J].计算机应用,2013,33(10):2734-2738.GUO Wei,WANG Xichuang,XIAO Zhenjiu.P2P traffic identification method based on K-means and twin support vector machine[J].Journal of Computer Applications,2013,33(10):2734-2738.
[16]丁胜锋,孙劲光.基于混合模糊隶属度的模糊双支持向量机研究[J].计算机应用研究,2013,30(2):432-435.DING Shengfeng,SUN Jinguang.Research on fuzzy twin support vector machine based on hybrid fuzzy membership[J].Application Research of Computers,2013,30(2):432-435.
[17]WU W H,WU H,Luo J,et al.Research progress on the regeneration of SCR catalysts for flue gas denitrification[J].Applied Chemical Industry,2013,42(7):1304-1307.
[18]秦天牧,刘吉臻,方连航,等.基于改进偏互信息的火电厂SCR脱硝系统建模[J].动力工程学报,2016,36(9):726-731.QIN Tianmu,LIU Jizhen,FANG Lianhang,et al.Modeling of power plant SCR denitrification system based on improved partial mutual information method[J].Journal of Chinese Society of Power Engineering,2016,36(9):726-731.
[19]杨加强,梅毅,王驰,等.湿法烟气脱硝技术现状及发展[J].化工进展,2017,36(2):695-704.YANG Jiaqiang,MEI Yi,WANG Chi,et al.Current status and trends wet flue gas denitration technology[J].Chemical Industry and Engineering Progress,2017,36(2):695-704.
[2]项昆.3种烟气脱硝工艺技术经济比较分析[J].热力发电,2011,40(6):1-3.XIANG Kun.Comparison and analysis in technoeconomic aspects for three kinds of flue gas denitrification technologies[J].Thermal Power Generation,2011,40(6):1-3.
[3]包鑫,戴连奎.基于局部最小二乘支持向量机的光谱定量分析[J].分析化学,2008,36(1):75-78.BAO Xin,DAI Liankui.Spectral quantitative analysis based on local least square support vector machine regression[J].Chinese Journal of Analytical Chemistry,2008,36(1):75-78.
[4]王美玲,王念平,李晓.BP神经网络算法的改进及应用[J].计算机工程与应用,2009,45(35):47-48.WANG Meiling,WANG Nianping,LI Xiao.Improvement and application of BPNN algorithm[J].Computer Engineering and Applications,2009,45(35):47-48.
[5]DAI Q,MA Z C,XIE Q Y.A two-phased and ensemble scheme integrated back propagation algorithm[J].Applied Soft Computing,2014,24:1124-1135.
[6]KODIYALAM S,GURUMOORTHY R.Neural networks with modified backpropagation learning applied to structural optimization[J].AIAA Journal,2015,34(2):408-412.
[7]杨碧源,赵金笑,魏宏鸽,等.基于BP神经网络的SCR蜂窝状催化剂脱硝性能预测[J].中国电力,2016,49(10):127-131.YANG Biyuan,ZHAO Jinxiao,WEI Hongge,et al.Performance forecasting for SCR honeycomb catalyst based on BP neural network[J].Electric Power,2016,49(10):127-131.
[8]汪海燕,黎建辉,杨风雷.支持向量机理论及算法研究综述[J].计算机应用研究,2014,31(5):1281-1286.WANG Haiyan,LI Jianhui,YANG Fenglei.Overview of support vector machine analysis and algorithm[J].Application Research of Computers,2014,31(5):1281-1286.
[9]凌武能,杭乃善,李如琦.基于云支持向量机模型的短期风电功率预测[J].电力自动化设备,2013,33(7):34-38.LING Wuneng,HANG Naishan,LI Ruqi.Short-term wind power forecasting based on cloud SVM model[J].Electric Power Automation Equipment,2013,33(7):34-38.
[10]ROJO-áLVAREZ J L,MartíNez-RAMóN M,MU?OZMARíJ,et al.A unified SVM framework for signal estimation[J].Digital Signal Processing,2013,26(1):1-20.
[11]崔仕文,铁治欣,丁成富,等.基于偏最小二乘支持向量机的烟气湿法脱硫效率预测模型[J].热力发电,2017,46(4):81-87.CUI Shiwen,TIE Zhixin,DING Chengfu,et al.Prediction model for flue gas wet desulfurization efficiency based on partial least squares support vector machine[J].Thermal Power Generation,2017,46(4):81-87.
[12]江彤,左青松,谢常清.柴油机SCR反应器性能FLSSVM预测模型[J].中南大学学报(自然科学版),2012,43(10):3906-3911.JIANG Tong,ZUO Qingsong,XIE Changqing.FLS-SVM performance forecasting model of SCR reactor in diesel engine[J].Journal of Central South University,2012,43(10):3906-3911.
[13]刘吉臻,秦天牧,杨婷婷,等.基于偏互信息的变量选择方法及其在火电厂SCR系统建模中的应用[J].中国电机工程学报,2016,36(9):2438-2443.LIU Jizhen,QIN Tianmu,YANG Tingting,et al.Variable selection method based on partial mutual information and its application in power plant SCR system modeling[J].Proceedings of the CSEE,2016,36(9):2438-2443.
[14]赵志宏,韩超,赵文杰.主元分析及多变量过程监测联合预测NOx质量浓度[J].热力发电,2016,45(7):98-103.ZHAO Zhihong,HAN Chao,ZHAO Wenjie.NOx content prediction based on principal component analysis and multivariable process monitoring[J].Thermal Power Generation,2016,45(7):98-103.
[15]郭伟,王西闯,肖振久.基于K均值和双支持向量机的P2P流量识别方法[J].计算机应用,2013,33(10):2734-2738.GUO Wei,WANG Xichuang,XIAO Zhenjiu.P2P traffic identification method based on K-means and twin support vector machine[J].Journal of Computer Applications,2013,33(10):2734-2738.
[16]丁胜锋,孙劲光.基于混合模糊隶属度的模糊双支持向量机研究[J].计算机应用研究,2013,30(2):432-435.DING Shengfeng,SUN Jinguang.Research on fuzzy twin support vector machine based on hybrid fuzzy membership[J].Application Research of Computers,2013,30(2):432-435.
[17]WU W H,WU H,Luo J,et al.Research progress on the regeneration of SCR catalysts for flue gas denitrification[J].Applied Chemical Industry,2013,42(7):1304-1307.
[18]秦天牧,刘吉臻,方连航,等.基于改进偏互信息的火电厂SCR脱硝系统建模[J].动力工程学报,2016,36(9):726-731.QIN Tianmu,LIU Jizhen,FANG Lianhang,et al.Modeling of power plant SCR denitrification system based on improved partial mutual information method[J].Journal of Chinese Society of Power Engineering,2016,36(9):726-731.
[19]杨加强,梅毅,王驰,等.湿法烟气脱硝技术现状及发展[J].化工进展,2017,36(2):695-704.YANG Jiaqiang,MEI Yi,WANG Chi,et al.Current status and trends wet flue gas denitration technology[J].Chemical Industry and Engineering Progress,2017,36(2):695-704.