SVR在城市污水BOD预测中的应用
|
摘要
针对城市污水中重要污染参数BOD的水质参数不易直接测得的特点。本文采用机器学习的方式,通过建立基于SVR的非线性回归模型,利用城市污水中的COD、SS、pH和氨氮的测量值,预测出城市污水中的生化含氧量。并通过对北京某城市污水处理厂的进水污水测量数据进行预测实验。实验结果证明,本文所使用预测模型,对于城市污水中BOD参数的预测具有有效性,且该预测模型有较高的精度。
Because the water quality parameters of BOD, an important pollution parameter in urban sewage, are not easily measured directly. In this paper,I have built a non-linear regression model based on SVR, to predict the biochemical oxygen content in wastewater, by COD, SS, pH and ammonia nitrogen, based on machine learning. And through the simulation prediction experiment of the influent sewage measurement data of a treatment plant in a city in Beijing. The results show that the prediction model used in this paper is effective for predicting BOD parameters in municipal wastewater, and the prediction model has high precision.
Because the water quality parameters of BOD, an important pollution parameter in urban sewage, are not easily measured directly. In this paper,I have built a non-linear regression model based on SVR, to predict the biochemical oxygen content in wastewater, by COD, SS, pH and ammonia nitrogen, based on machine learning. And through the simulation prediction experiment of the influent sewage measurement data of a treatment plant in a city in Beijing. The results show that the prediction model used in this paper is effective for predicting BOD parameters in municipal wastewater, and the prediction model has high precision.
引文
[1]郭泓利,李鑫玮,任钦毅,等.全国典型城市污水处理厂进水水质特征分析[J].给水排水,2018(6):12-15.GUO Hong-li,LI Xin-wei,REN Qin-yi,et al.Analysis of Influent Water Quality Characteristics of Typical Urban Sewage Treatment Plants in China[J].Geomatics World,2018(6):12-15.
[2]张宗可.通州地区污水处理厂污水COD与BOD的相关性研究[J].资源节约与环保,2015(12):48-52.ZHANG Zong-ke.Correlation between COD and BOD in Wastewater Treatment Plant of Tongzhou District[J].Resources Economization&Environment Protection,2015(12):48-52.
[3]李国刚,王德龙.生化需氧量(BOD)测定方法综述[J].中国环境监测,2004,20(2):54-57.LI Guo-gang,WANG De-long.Summary of methods for determination of biochemical oxygen demand(BOD)[J].Environmental Monitoring in China,2004,20(2):54-57.
[4]乔俊飞,李瑞祥,柴伟,等.基于PSO-ESN神经网络的污水BOD预测[J].控制工程,2016,23(4):463-467.QIAO Jun-fei,LI Rui-xiang,CHAI We,et al.Prediction of BOD based on PSO-ESN neural network[J].Control Engineering of China,2016,23(4):463-467.
[5]刘帮,秦斌,彭小玉.污水出水水质的SVR建模[J].新型工业化,2015,5(1):45-48.LIU Bang,QIN Bin,PENG Xiao-yu.Modeling of Wastewater Effluent water Quality on Support Vector Regression Machine[J].The Journal of New Industrialization,2015,5(1):45-48.
[6]张俊,殷坤龙,王佳佳,等.基于时间序列与PSOSVR耦合模型的白水河滑坡位移预测研究[J].岩石力学与工程学报,2015,34(2):382-391.ZHANG Jun,YIN Kun-long,WANG Jia-jia,et al.Displacement prediction of Baishuihe landslide based on time series and PSO-SVR model[J].ChineseJournal of Rock Mechanics and Engineering,2015,34(2):382-391.
[7]段青玲,张磊,魏芳芳,等.基于时间序列GA-SVR的水产品价格预测模型及验证[J].农业工程学报,2017,33(1):308-314.DUAN Qing-Ling,ZHANG Lei,WEI Fang-fang,et al.Forecasting model and validation for aquatic product price based on time series GASVR[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(1):308-314.
[8]郭劲松,霍国友,龙腾锐.BOD-DO耦合人工神经网络水质模拟的研究[J].环境科学学报,2001,21(2):140-143.GUO Jin-song,HUO Guo-you,LONG-Teng-rui.BOD-DOStudy on water quality simulation of coupled artificial neural network[J].Acta Scientiae Circumstantiae,2001,21(2):140-143.
[9]张青,王学雷,张婷,等.基于BP神经网络的洪湖水质指标预测研究[J].湿地科学[J].2016,14(2):212-218.ZHANG Qing,WANG Xue-lei,ZHANG Ting,et al.Prediction of water quality index of Honghu lake based on back propagation neural network model[J].Wetland Science,2016,14(2):212-218.
[10]肖晓,徐启华.基于SVM与BP的分类与回归比较研究[J].新型工业化,2014,4(5):48-53.XIAO Xiao,XU Qi-hua.A Comparative Reseach on the Classification and Regreesion Based on SVM and BP[J].The Journal of New Industrialization,2014,4(5):48-53.
[11]陈德忠,赵亮,何书静,等.BP神经网络和SVR用于GPS高程拟合研究分析[J].测绘地理信息,2012,37(5):47-49.CHEN De-zhong,ZHAO Ling,HE Shu-jing,et al.BP neural network and SVR for GPS elevation fitting research[J].Journal of Geomatics,2012,37(5):47-49.
[12]孙艳,张逢,胡洪营,等.上海市污水处理厂进水水质特征的统计学分析[J].环境工程学报,2014(12):5167-5173.SUN Yan,ZHANG Fang,HU Hong-ying,et al.Statistical Analysis of Influent Water Quality Characteristics of Shanghai Wastewater Treatment Plant[J].Chinese Journal of Environmental Engineering,2014(12):5167-5173.
[13]俞金寿.软测量技术及其应用[J].自动化仪表,2008,29(1):1-7.YU Jing-shou.A soft sensor technology and its application[J].Process Automation Instrumentation,2008,29(1):1-7.
[14]徐文祥,李金良,杨焱,等.计算机控制技术在工业自动化控制系统中的应用[J].新型工业化,2018,8(7):122-125.XU Wen-liang,LI Jin-liang,YANG Yan,et al.Application of Computer Control Technology in Industrial Automation ControlSystem[J].The Journal of New Industrialization,2018,8(7):122-125.
[15]李捷,王宏利,隋军.昆明某城市污水处理厂进水特征分析[J].给水排水,2015(s1):66-69.Li-Jie,Wang Hong-li,Sui-Jun.Analysis of Influent Characteristics of a Municipal Wastewater Treatment Plant in Kunming[J].Water Supply And Drainage,2015(s1):66-69.
[16]张军,李舒,徐晓力,等.河流水中的NH3-N与BOD5、COD、高锰酸盐指数相关关系研究[J].黑龙江环境通报,2001(1):67-68.ZHANG Jun,LI Shu,XU Xiao-li,et al.Study on the Correlation between NH3-N and BOD5,COD and Permanganate Index in River Water[J].Heilongjiang Environmental Journal,2001(1):67-68.
[17]陈丽琼,茹婉红,胡勇,等.生化需氧量测定方法的研究进展及现状[J].绿色科技,2013(2):138-141.CHEN Li-qiong,RU Wan-hong,HU yong,et al.Research progress and current status of biochemical oxygen demand determination methods[J].Journal of Green Science and Technology,2013(2):138-141.
[18]薛振北,李泽滔.基于计算机视觉的商场人流量检测系统的设计[J].新型工业化,2018,8(8):74-78.XUE Zhen-bei,LI Ze-tao.Design of Human Flow Detection System in Shopping Mall Based on Computer Vision[J].The Journal of New Industrialization,2018,8(8):74-78.
[19]丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综述[J].电子科技大学学报,2011,40(1):2-10.DING Shi-fei,QI Bing-juan,TAN Hong-yan.An overview on theory and algorithm of support vector machines[J].Journal of University of Electronic Science and Technology of China,2011,40(1):2-10.
[20]HSU C W,LIN C J.A Simple Decomposition Method for Support Vector Machines[J].Machine Learning,2002,46(1-3):291-314.
[2]张宗可.通州地区污水处理厂污水COD与BOD的相关性研究[J].资源节约与环保,2015(12):48-52.ZHANG Zong-ke.Correlation between COD and BOD in Wastewater Treatment Plant of Tongzhou District[J].Resources Economization&Environment Protection,2015(12):48-52.
[3]李国刚,王德龙.生化需氧量(BOD)测定方法综述[J].中国环境监测,2004,20(2):54-57.LI Guo-gang,WANG De-long.Summary of methods for determination of biochemical oxygen demand(BOD)[J].Environmental Monitoring in China,2004,20(2):54-57.
[4]乔俊飞,李瑞祥,柴伟,等.基于PSO-ESN神经网络的污水BOD预测[J].控制工程,2016,23(4):463-467.QIAO Jun-fei,LI Rui-xiang,CHAI We,et al.Prediction of BOD based on PSO-ESN neural network[J].Control Engineering of China,2016,23(4):463-467.
[5]刘帮,秦斌,彭小玉.污水出水水质的SVR建模[J].新型工业化,2015,5(1):45-48.LIU Bang,QIN Bin,PENG Xiao-yu.Modeling of Wastewater Effluent water Quality on Support Vector Regression Machine[J].The Journal of New Industrialization,2015,5(1):45-48.
[6]张俊,殷坤龙,王佳佳,等.基于时间序列与PSOSVR耦合模型的白水河滑坡位移预测研究[J].岩石力学与工程学报,2015,34(2):382-391.ZHANG Jun,YIN Kun-long,WANG Jia-jia,et al.Displacement prediction of Baishuihe landslide based on time series and PSO-SVR model[J].ChineseJournal of Rock Mechanics and Engineering,2015,34(2):382-391.
[7]段青玲,张磊,魏芳芳,等.基于时间序列GA-SVR的水产品价格预测模型及验证[J].农业工程学报,2017,33(1):308-314.DUAN Qing-Ling,ZHANG Lei,WEI Fang-fang,et al.Forecasting model and validation for aquatic product price based on time series GASVR[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(1):308-314.
[8]郭劲松,霍国友,龙腾锐.BOD-DO耦合人工神经网络水质模拟的研究[J].环境科学学报,2001,21(2):140-143.GUO Jin-song,HUO Guo-you,LONG-Teng-rui.BOD-DOStudy on water quality simulation of coupled artificial neural network[J].Acta Scientiae Circumstantiae,2001,21(2):140-143.
[9]张青,王学雷,张婷,等.基于BP神经网络的洪湖水质指标预测研究[J].湿地科学[J].2016,14(2):212-218.ZHANG Qing,WANG Xue-lei,ZHANG Ting,et al.Prediction of water quality index of Honghu lake based on back propagation neural network model[J].Wetland Science,2016,14(2):212-218.
[10]肖晓,徐启华.基于SVM与BP的分类与回归比较研究[J].新型工业化,2014,4(5):48-53.XIAO Xiao,XU Qi-hua.A Comparative Reseach on the Classification and Regreesion Based on SVM and BP[J].The Journal of New Industrialization,2014,4(5):48-53.
[11]陈德忠,赵亮,何书静,等.BP神经网络和SVR用于GPS高程拟合研究分析[J].测绘地理信息,2012,37(5):47-49.CHEN De-zhong,ZHAO Ling,HE Shu-jing,et al.BP neural network and SVR for GPS elevation fitting research[J].Journal of Geomatics,2012,37(5):47-49.
[12]孙艳,张逢,胡洪营,等.上海市污水处理厂进水水质特征的统计学分析[J].环境工程学报,2014(12):5167-5173.SUN Yan,ZHANG Fang,HU Hong-ying,et al.Statistical Analysis of Influent Water Quality Characteristics of Shanghai Wastewater Treatment Plant[J].Chinese Journal of Environmental Engineering,2014(12):5167-5173.
[13]俞金寿.软测量技术及其应用[J].自动化仪表,2008,29(1):1-7.YU Jing-shou.A soft sensor technology and its application[J].Process Automation Instrumentation,2008,29(1):1-7.
[14]徐文祥,李金良,杨焱,等.计算机控制技术在工业自动化控制系统中的应用[J].新型工业化,2018,8(7):122-125.XU Wen-liang,LI Jin-liang,YANG Yan,et al.Application of Computer Control Technology in Industrial Automation ControlSystem[J].The Journal of New Industrialization,2018,8(7):122-125.
[15]李捷,王宏利,隋军.昆明某城市污水处理厂进水特征分析[J].给水排水,2015(s1):66-69.Li-Jie,Wang Hong-li,Sui-Jun.Analysis of Influent Characteristics of a Municipal Wastewater Treatment Plant in Kunming[J].Water Supply And Drainage,2015(s1):66-69.
[16]张军,李舒,徐晓力,等.河流水中的NH3-N与BOD5、COD、高锰酸盐指数相关关系研究[J].黑龙江环境通报,2001(1):67-68.ZHANG Jun,LI Shu,XU Xiao-li,et al.Study on the Correlation between NH3-N and BOD5,COD and Permanganate Index in River Water[J].Heilongjiang Environmental Journal,2001(1):67-68.
[17]陈丽琼,茹婉红,胡勇,等.生化需氧量测定方法的研究进展及现状[J].绿色科技,2013(2):138-141.CHEN Li-qiong,RU Wan-hong,HU yong,et al.Research progress and current status of biochemical oxygen demand determination methods[J].Journal of Green Science and Technology,2013(2):138-141.
[18]薛振北,李泽滔.基于计算机视觉的商场人流量检测系统的设计[J].新型工业化,2018,8(8):74-78.XUE Zhen-bei,LI Ze-tao.Design of Human Flow Detection System in Shopping Mall Based on Computer Vision[J].The Journal of New Industrialization,2018,8(8):74-78.
[19]丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综述[J].电子科技大学学报,2011,40(1):2-10.DING Shi-fei,QI Bing-juan,TAN Hong-yan.An overview on theory and algorithm of support vector machines[J].Journal of University of Electronic Science and Technology of China,2011,40(1):2-10.
[20]HSU C W,LIN C J.A Simple Decomposition Method for Support Vector Machines[J].Machine Learning,2002,46(1-3):291-314.