燃煤电厂SCR烟气脱硝催化剂寿命预测研究
|
摘要
为保证燃煤电厂烟气脱硝系统的安全、稳定运行,需要制定科学合理的选择性催化还原(SCR)催化剂寿命预测方案。SCR催化剂失效是多个物理和化学因素共同作用的结果,难以用传统的物理模型或数学公式对其失活程度进行预测。本研究针对电厂大数据特性,对原始数据进行预处理,建立了曲线拟合、灰色预测、BP神经网络、灰色神经网络4种预测模型。实例对比分析发现:数据预处理可以提高预测精度;当数据满足等时距特性时,灰色神经网络优化后的直接输出模型预测精度较高;当数据不满足等时距特性时,使用BP神经网络模型预测效果更好。
In order to ensure the safe and stable operation of denitrification system in coal-fired power plants, a scientific and reasonable life prediction plan must be formulated for the SCR catalysts. The deactivation of the SCR catalysts is determined by the combined effects of multiple physical and chemical factors. Therefore, it is difficult to predict the catalysts' service life by using conventional physical models and mathematical formulas.According to the characteristics of big data in power plants, this article preprocessed the raw data and established four prediction models, including curve fitting model, grey prediction model, BP neural network model and grey neural network model. Through case analysis, it is found that data preprocessing can improve the prediction accuracy. Generally, the optimized direct output model of the grey neural network shows high accuracy for the data that met the equidistant time requirement. Whereas, the BP neural network model can achieve better prediction results for the non-equidistant time data.
In order to ensure the safe and stable operation of denitrification system in coal-fired power plants, a scientific and reasonable life prediction plan must be formulated for the SCR catalysts. The deactivation of the SCR catalysts is determined by the combined effects of multiple physical and chemical factors. Therefore, it is difficult to predict the catalysts' service life by using conventional physical models and mathematical formulas.According to the characteristics of big data in power plants, this article preprocessed the raw data and established four prediction models, including curve fitting model, grey prediction model, BP neural network model and grey neural network model. Through case analysis, it is found that data preprocessing can improve the prediction accuracy. Generally, the optimized direct output model of the grey neural network shows high accuracy for the data that met the equidistant time requirement. Whereas, the BP neural network model can achieve better prediction results for the non-equidistant time data.
引文
[1]安敬学,王磊,秦淇,等.SCR脱硝系统催化剂磨损机理分析与治理[J].热力发电,2015,44(12):119-125.AN Jingxue,WANG Lei,QIN Qi,et al.Mechanism research on catalyst attrition in SCR denitration system and the treatment[J].Thermal Power Generation,2015,44(12):119-125.
[2]姚燕,王丽朋,孔凡海,等.SCR脱硝系统蜂窝式催化剂性能评估及寿命管理[J].热力发电,2016,45(11):114-119.YAO Yan,WANG Lipeng,KONG Fanhai,et al.Performance evaluation and life management of honeycomb catalyst for SCR denitrification system[J].Thermal Power Generation,2016,45(11):114-119.
[3]喻小伟,周瑜,刘帅,等.SCR脱硝催化剂失活原因分析及再生处理[J].热力发电,2014,43(2):109-113.YU Xiaowei,ZHOU Yu,LIU Shuai,et al.Reason analysis for deactivation of commercial SCR de-NOx catalyst and its regeneration[J].Thermal Power Generation,2014,43(2):109-113.
[4]徐秀林,吴卫红,柳东海,等.SCR蜂窝状脱硝催化剂磨损数值模拟研究[J].应用化工,2015,44(6):986-990.XU Xiulin,WU Weihong,LIU Donghai.et al.Numerical study of erosion on honeycomb SCR catalyst[J].Applied Chemical Industry,2015,44(6):986-990.
[5]LEI T Y,LI Q C,CHEN S F,et al.KCl-induced deactivation of V2O5-WO3/TiO2 catalyst during selective catalytic reduction of NO by NH3:comparison of poisoning methods[J].Chemical Engineering Journal,2016,296:1-10.
[6]姜烨.钛基SCR催化剂及其钾、铅中毒机理研究[D].杭州:浙江大学,2010:34.JIANG Ye.Study on titania-based SCR catalysts and their poisoning mechanism of potassium and lead[D].Hangzhou:Zhejiang University,2010:34.
[7]吴俊升,李晓刚,公铭扬,等.几种催化裂化催化剂的磨损机制与动力学[J].中国腐蚀与防护学报,2010,30(2):135-140.WU Junsheng,LI Xiaogang,GONG Mingyang,et al.Kinetics and mechanism of attrition of several FCCcaytalysts[J].Journal of Chinese Society for Corrosion and Protection,2010,30(2):135-140.
[8]孙克勤,钟秦,于爱华.SCR催化剂的砷中毒研究[J].中国环保产业,2008(1):40-42.SUN Keqin,ZHONG Qin,YU Aihua,Arsenic poisoning of SCR catalyst[J].China Environmental Protection Industry,2008(1):40-42.
[9]UPADHYAY D,NIEUWSTADT M V.Robust separation of signal domain from single channel mixed signal output of automotive urea based selective catalytic reduction systems[J].Journal of Dynamic Systems Measurement&Control,2014,136:115-134.
[10]杨志雄,袁岱菁.非线性混合效应模型和广义线性模型拟合随机效应logistic回归的应用比较[J].中国卫生统,2011,28(3):321-323.YANG Zhixiong,YUAN Daijing.Application of logistic regression in random effects of non-linear mixed effects models and generalized linear models[J].Chinese Journal of Health Statistics,2011,28(3):321-323.
[11]董长青,马帅,傅玉,等.火电厂SCR脱硝催化剂寿命预估研究[J].华北电力大学学报(自然科学版),2016,43(3):64-68.DONG Changqing,MA Shuai,FU Yu,et al.Study on life prediction of SCR denitrification Catalyst in Thermal Power Plants[J].Journal of North China Electric Power University(Natural Science Edition),2016,43(3):64-68.
[12]傅玉,陆强,庄柯,等.基于灰色预测模型和曲线拟合模型的SCR烟气脱硝催化剂寿命预测[J].热力发电,2017,46(7):60-65.FU Yu,LU Qiang,ZHUANG Ke,et al.Life prediction for SCR flue gas denitrification catalyst in coal-fired power plants[J].Thermal Power Generation,2017,46(7):60-65.
[13]ANDONOVA S,VOVK E,SJ?BLOM J,et al.Chemical deactivation by phosphorous under lean hydrothermal conditions over Cu/BEA NH3-SCR catalysts[J].Applied Catalysis B Environmental,2013,147(8):251-263.
[14]MUZIO L J,SMITH R A.In-line localized monitoring of catalyst activity in selective catalytic NOx reduction systems:US7635593[P].2009-12-22.
[15]宋玉宝,杨杰,金理鹏,等.SCR脱硝催化剂宏观性能评估和寿命预测方法研究[J].中国电力,2016(4):17-22.SONG Yubao,YANG Jie,JIN Lipeng,et al.Study on methodology of SCR catalyst macroscopical performance evaluation and lifetime prediction[J].Electric Power,2016(4):17-22.
[16]杨继旺,吴熳红.几种负荷预测方法及其应用[J].农村电气化,2004(7):9-10.YANG Jiwang,WU Manhong.Several load forecasting methods and their applications[J].Rural Electrification,2004(7):9-10.
[17]王晓佳.基于数据分析的预测理论与方法研究[D].合肥:合肥工业大学,2012:31.WANG Xiaojia.Research on forecasting theory and method based on data analysis[D].Hefei:Hefei University of Technology,2012:31.
[18]吴剑,张迎春.软基路堤最终沉降量的灰色预测[J].西部探矿工程,2003(7):30-32.WU Jian,ZHANG Yingchun.Gray forecast of final settlement of soft foundation[J].West-China Exploration Engineering,2003(7):30-32.
[19]ZHANG W P,ZHAO S Q.Forecasting research on the total volume of import and export trade of Ningbo Port by gray forecasting model[J].Journal of Software,2013,8(2):466.
[20]黄文燕,罗飞,许玉格,等.基于模拟退火PSO-BP算法的钢铁生产能耗预测研究[J].科学技术与工程,2012,12(30):7906-7910.HUANG Wenyan,LUO Fei,XU Yuge,et al.Research of steel production consumption forecast based on simulated annealing PSO-BP algorithm[J].Science Technology and Engineering,2012,12(30):7906-7910.
[21]刘冰,郭海霞.MATLAB神经网络超级学习手册[M].人民邮电出版社,2014:160-161.LIU Bing,GUO Haixia.MATLAB neural network super study manual[M].Post&Telecom Press,2014:160-161.
[22]墨蒙,赵龙章,龚嫒雯,等.基于遗传算法优化的BP神经网络研究应用[J].现代电子技术,2018,41(9):41-44.MO Meng,ZHAO Longzhang,GONG Yuanwen,et al.Research on application of BP neural network based on genetic algorithm optimization[J].Modern Electronics Technique,2018,41(9):41-44.
[23]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.Prediction of denitration performance of SCRhoneycomb catalyst based on BP neural network[J].Electric Power,2016,49(10):127-131.
[24]袁景凌,钟珞,李小燕.灰色神经网络的研究及发展[J].武汉理工大学学报,2009,31(3):91-93.YUAN Jingling,ZHONG Luo,LI Xiaoyan.Grey neural network research and development[J].Journal of Wuhan University of Technology,2009,31(3):91-93.
[2]姚燕,王丽朋,孔凡海,等.SCR脱硝系统蜂窝式催化剂性能评估及寿命管理[J].热力发电,2016,45(11):114-119.YAO Yan,WANG Lipeng,KONG Fanhai,et al.Performance evaluation and life management of honeycomb catalyst for SCR denitrification system[J].Thermal Power Generation,2016,45(11):114-119.
[3]喻小伟,周瑜,刘帅,等.SCR脱硝催化剂失活原因分析及再生处理[J].热力发电,2014,43(2):109-113.YU Xiaowei,ZHOU Yu,LIU Shuai,et al.Reason analysis for deactivation of commercial SCR de-NOx catalyst and its regeneration[J].Thermal Power Generation,2014,43(2):109-113.
[4]徐秀林,吴卫红,柳东海,等.SCR蜂窝状脱硝催化剂磨损数值模拟研究[J].应用化工,2015,44(6):986-990.XU Xiulin,WU Weihong,LIU Donghai.et al.Numerical study of erosion on honeycomb SCR catalyst[J].Applied Chemical Industry,2015,44(6):986-990.
[5]LEI T Y,LI Q C,CHEN S F,et al.KCl-induced deactivation of V2O5-WO3/TiO2 catalyst during selective catalytic reduction of NO by NH3:comparison of poisoning methods[J].Chemical Engineering Journal,2016,296:1-10.
[6]姜烨.钛基SCR催化剂及其钾、铅中毒机理研究[D].杭州:浙江大学,2010:34.JIANG Ye.Study on titania-based SCR catalysts and their poisoning mechanism of potassium and lead[D].Hangzhou:Zhejiang University,2010:34.
[7]吴俊升,李晓刚,公铭扬,等.几种催化裂化催化剂的磨损机制与动力学[J].中国腐蚀与防护学报,2010,30(2):135-140.WU Junsheng,LI Xiaogang,GONG Mingyang,et al.Kinetics and mechanism of attrition of several FCCcaytalysts[J].Journal of Chinese Society for Corrosion and Protection,2010,30(2):135-140.
[8]孙克勤,钟秦,于爱华.SCR催化剂的砷中毒研究[J].中国环保产业,2008(1):40-42.SUN Keqin,ZHONG Qin,YU Aihua,Arsenic poisoning of SCR catalyst[J].China Environmental Protection Industry,2008(1):40-42.
[9]UPADHYAY D,NIEUWSTADT M V.Robust separation of signal domain from single channel mixed signal output of automotive urea based selective catalytic reduction systems[J].Journal of Dynamic Systems Measurement&Control,2014,136:115-134.
[10]杨志雄,袁岱菁.非线性混合效应模型和广义线性模型拟合随机效应logistic回归的应用比较[J].中国卫生统,2011,28(3):321-323.YANG Zhixiong,YUAN Daijing.Application of logistic regression in random effects of non-linear mixed effects models and generalized linear models[J].Chinese Journal of Health Statistics,2011,28(3):321-323.
[11]董长青,马帅,傅玉,等.火电厂SCR脱硝催化剂寿命预估研究[J].华北电力大学学报(自然科学版),2016,43(3):64-68.DONG Changqing,MA Shuai,FU Yu,et al.Study on life prediction of SCR denitrification Catalyst in Thermal Power Plants[J].Journal of North China Electric Power University(Natural Science Edition),2016,43(3):64-68.
[12]傅玉,陆强,庄柯,等.基于灰色预测模型和曲线拟合模型的SCR烟气脱硝催化剂寿命预测[J].热力发电,2017,46(7):60-65.FU Yu,LU Qiang,ZHUANG Ke,et al.Life prediction for SCR flue gas denitrification catalyst in coal-fired power plants[J].Thermal Power Generation,2017,46(7):60-65.
[13]ANDONOVA S,VOVK E,SJ?BLOM J,et al.Chemical deactivation by phosphorous under lean hydrothermal conditions over Cu/BEA NH3-SCR catalysts[J].Applied Catalysis B Environmental,2013,147(8):251-263.
[14]MUZIO L J,SMITH R A.In-line localized monitoring of catalyst activity in selective catalytic NOx reduction systems:US7635593[P].2009-12-22.
[15]宋玉宝,杨杰,金理鹏,等.SCR脱硝催化剂宏观性能评估和寿命预测方法研究[J].中国电力,2016(4):17-22.SONG Yubao,YANG Jie,JIN Lipeng,et al.Study on methodology of SCR catalyst macroscopical performance evaluation and lifetime prediction[J].Electric Power,2016(4):17-22.
[16]杨继旺,吴熳红.几种负荷预测方法及其应用[J].农村电气化,2004(7):9-10.YANG Jiwang,WU Manhong.Several load forecasting methods and their applications[J].Rural Electrification,2004(7):9-10.
[17]王晓佳.基于数据分析的预测理论与方法研究[D].合肥:合肥工业大学,2012:31.WANG Xiaojia.Research on forecasting theory and method based on data analysis[D].Hefei:Hefei University of Technology,2012:31.
[18]吴剑,张迎春.软基路堤最终沉降量的灰色预测[J].西部探矿工程,2003(7):30-32.WU Jian,ZHANG Yingchun.Gray forecast of final settlement of soft foundation[J].West-China Exploration Engineering,2003(7):30-32.
[19]ZHANG W P,ZHAO S Q.Forecasting research on the total volume of import and export trade of Ningbo Port by gray forecasting model[J].Journal of Software,2013,8(2):466.
[20]黄文燕,罗飞,许玉格,等.基于模拟退火PSO-BP算法的钢铁生产能耗预测研究[J].科学技术与工程,2012,12(30):7906-7910.HUANG Wenyan,LUO Fei,XU Yuge,et al.Research of steel production consumption forecast based on simulated annealing PSO-BP algorithm[J].Science Technology and Engineering,2012,12(30):7906-7910.
[21]刘冰,郭海霞.MATLAB神经网络超级学习手册[M].人民邮电出版社,2014:160-161.LIU Bing,GUO Haixia.MATLAB neural network super study manual[M].Post&Telecom Press,2014:160-161.
[22]墨蒙,赵龙章,龚嫒雯,等.基于遗传算法优化的BP神经网络研究应用[J].现代电子技术,2018,41(9):41-44.MO Meng,ZHAO Longzhang,GONG Yuanwen,et al.Research on application of BP neural network based on genetic algorithm optimization[J].Modern Electronics Technique,2018,41(9):41-44.
[23]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.Prediction of denitration performance of SCRhoneycomb catalyst based on BP neural network[J].Electric Power,2016,49(10):127-131.
[24]袁景凌,钟珞,李小燕.灰色神经网络的研究及发展[J].武汉理工大学学报,2009,31(3):91-93.YUAN Jingling,ZHONG Luo,LI Xiaoyan.Grey neural network research and development[J].Journal of Wuhan University of Technology,2009,31(3):91-93.