智能算法在水体氨氮含量预测中的应用研究综述
|
摘要
随着国民经济的快速发展,工业、农业、水产养殖业以及生活污水排放带来的水体氨氮污染日益加重,如何有效治理氨氮污染,已成为人们关心的热点问题。与实验室取样检测相比,智能算法预测水体氨氮含量的方法由于具有实时性、检测时间短、误差小等优点,正逐步被应用到水体氨氮污染治理中。综述神经网络、粒子群、遗传算法等智能算法在水体氨氮含量预测中的研究进展,指出多种智能算法的组合应用将是预测水体氨氮含量、有效治理氨氮污染的应用发展方向,并提出进一步完善研究方法的建议。
With the rapid development of national economy, ammonia nitrogen pollution in water body caused by industrial, agricultural, aquaculture and domestic sewage discharge is increasing. How to effectively control ammonia nitrogen pollution has become a hot issue of concern. Compared with laboratory sampling and detection, the method of predicting ammonia nitrogen content in water body by intelligent algorithm is gradually applied to the treatment of ammonia nitrogen pollution in water body due to its advantages of online real-time, short time and small error. This paper summarizes the research progress of intelligent algorithms such as artificial neural network, particle swarm optimization and genetic algorithm in predicting ammonia nitrogen content in water body, points out that the combination of several intelligent algorithms will be the application and development direction of predicting ammonia nitrogen content in water body and effectively controlling ammonia nitrogen pollution, and puts forward some suggestions for further improving the research methods.
With the rapid development of national economy, ammonia nitrogen pollution in water body caused by industrial, agricultural, aquaculture and domestic sewage discharge is increasing. How to effectively control ammonia nitrogen pollution has become a hot issue of concern. Compared with laboratory sampling and detection, the method of predicting ammonia nitrogen content in water body by intelligent algorithm is gradually applied to the treatment of ammonia nitrogen pollution in water body due to its advantages of online real-time, short time and small error. This paper summarizes the research progress of intelligent algorithms such as artificial neural network, particle swarm optimization and genetic algorithm in predicting ammonia nitrogen content in water body, points out that the combination of several intelligent algorithms will be the application and development direction of predicting ammonia nitrogen content in water body and effectively controlling ammonia nitrogen pollution, and puts forward some suggestions for further improving the research methods.
引文
[1] 国家统计局.中国统计年鉴2014[M].北京:中国统计出版社,2014.
[2] 国家统计局.中国统计年鉴2015[M].北京:中国统计出版社,2015.
[3] 国家统计局.中国统计年鉴2016[M].北京:中国统计出版社,2016.
[4] 国家统计局.中国统计年鉴2017[M].北京:中国统计出版社,2017.
[5] 国家统计局.中国统计年鉴2018[M].北京:中国统计出版社,2018.
[6] 付婉霞,聂正武,高杰,等.饮用水氨氮的去除方法综述[J].能源环境保护,2006,20(3):15-17.
[7] 刘刚.生活饮用水中的氨氮污染问题探讨[J].中国高新技术企业,2011(27):146-148.
[8] 张卫强,朱英.养殖水体中氨氮的危害及其检测方法研究进展[J].环境卫生学杂志,2012,2(6):324-327.Zhang Weiqiang,Zhu Ying.Advances on the research of the hazard of Ammonia Nitrogen in aquaculture water and its determination method [J].Journal of Environmental Hygiene,2012,2(6):324-327.
[9] 高亚峰,孙洪杰.氨氮对鱼类的危害[J].河北渔业,2014(8):62-63,67.
[10] 张光林.循环冷却水系统中氨氮的危害与对策[J].石油和化工设备,2011,14(8):68-70.
[11] 林根仙,何蓉,郭俊文.氨氮对循环冷却水系统的危害与对策[J].工业水处理,2006,26(5):82-84.
[12] 杜晓旭,康俊巍,徐艳伟,等.污水氨氮检测方法问题分析及改进[J].轻工科技,2012(11):115-117,123.
[13] 刘林斌.水中氨氮测定方法比较[J].广州化工,2011,39(10):110-111.
[14] 国家环境保护总局,水和废水监测分析方法编委会.水和废水监测分析方法(第四版)[M].北京:中国环境科学出版社,2002.
[15] 安慧慧.水中氨氮测定方法的比较分析[J].山西化工,2017,37(4):55-57.
[16] 乔俊飞,安茹,韩红桂.基于RBF神经网络的出水氨氮预测研究[J].控制工程,2016,23(9):1301-1305.
[17] 居锦武.基于LS-SVM的养殖水体氨氮含量分析模型的优化[J].大连海洋大学学报,2016,31(4):444-448.
[18] 易仲强.智能算法在湖库富营养化预测中的应用研究综述[J].水电能源科学,2010,28(8):33-36,26.Yi Zhongqiang.Review of research on eutrophication prediction in lakes and reservoirs with intelligent algorithm [J].Water Resources and Power,2010,28(8):33-36,26.
[19] 吴冬春,陆广平,顾春雷.池塘养殖水体溶氧度检控集群系统设计[J].中国农机化学报,2014,35(5):213-216.Wu Dongchun,Lu Guangping,Gu Chunlei.Design of monitoring cluster system for dissolved oxygen of pond aquaculture water [J].Journal of Chinese Agricultural Mechanization,2014,35(5):213-216.
[20] 付焕森,曹健,李元贵.基于Zigbee和GPRS的仿真机器鱼水质监测系统设计[J].中国农机化学报,2016,37(7):179-182,194.Fu Huansen,Cao Jian,Li Yuangui.Design on simulation robotic fish water monitoring system based on Zigbee and GPRS [J].Journal of Chinese Agricultural Mechanization,2016,37(7):179-182,194.
[21] 张丽,王彦,刘娜,等.基于水、肥、温、气系统一体化的水质改善工艺[J].中国农机化学报,2014,35(3):248-251.Zhang Li,Wang Yan,Liu Na,et al.Integration improvement process based on water,fertilizer,temperature,air quality system [J].Journal of Chinese Agricultural Mechanization,2014,35(3):248-251.
[22] 潘贺,关久念,李太浩.基于无线传感器网络的水产养殖水环境监测系统设计与试验[J].中国农机化学报,2014,35(5):246-250.Pan He,Guan Jiunian,Li Taihao.Design and test of aquaculture water environment monitoring system based on wireless sensor network [J].Journal of Chinese Agricultural Mechanization,2014,35(5):246-250.
[23] 陈冲,沈翠凤.集约化水产养殖水质多参数测控系统研究与设计[J].中国农机化学报,2013,34(6):268-272.Chen Chong,Shen Cuifeng.Research and design of intensive aquaculture water multi-parameter measurement and control system [J].Journal of Chinese Agricultural Mechanization,2013,34(6):268-272.
[24] Refsgaard J C,S?rensen H R,Mucha I,et al.An integrated model for the danubian lowland-methodology and applications [J].Water Resources Management,1998,12(6):433-465.
[25] 梁识栋.高维参数水质模型参数不确定性分析方法研究[D].北京:清华大学,2016.Liang Shidong.Research on parameter uncertainty analysis method for water quality model with high-dimensional parameter space [D].Beijing:Tsinghua University,2016.
[26] Filoso S,Vallino J,Hopkinson C,et al.Modeling Nitrogen transport in the IPSwich River Basin,Massa chusetts,using a Hydrological Simulation Program in Fortran (HSPF) [J].Journal of the American Water Resources Association,2004,40(5):1365-1384.
[27] Mona R,Alaa E S,Patrick W,et al.Modeling of Nitrogen in river water using a detailed and a simplified model [J].The Scientific World Journal,2001,1:200-206.
[28] 李如忠,汪家权,钱家忠.基于灰色动态模型群法的河流水质预测研究[J].水土保持通报,2002,22(4):10-12.Li Ruzhong,Wang Jiaquan,Qian Jiazhong.Prediction of river water quality based on gray dynamic model group [J].Bulletin of Soil and Water Conservation,2002,22(4):10-12.
[29] Rumelhart D E,Hinton G E,Williams R J.Learning representations by back-propagating errors [J].Nature,1986,323:533-536.
[30] Kennedy J.Particle swarm optimization [J].Proc.of 1995 IEEE Int.Conf.Neural Networks,(Perth,Australia),Nov.27-Dec.
[31] 乔俊飞,马士杰,许进超.基于递归RBF神经网络的出水氨氮预测研究[J].计算机与应用化学,2017,34(2):145-151.Qiao Junfei,Ma Shijie,Xu Jinchao.The water ammonia nitrogen prediction research based on a recursive RBF neural network [J].Computers and Applied Chemistry,2017,34(2):145-151.
[32] 树锦.人工神经网络模型在黄河水质预测中的应用[D].南京:河海大学,2006.Shu Jin.Using artificial neutral network model to predict water quality in Yellow River [D].Nanjing:HohaiUniversity,2006.
[33] 杨琴,谢淑云.BP神经网络在洞庭湖氨氮浓度预测中的应用[J].水资源与水工程学报,2006,17(1):65-70.
[34] 高艳萍,周敏,姜凤娇.基于BP网络养殖水体氨氮预测模型及实现[J].农机化研究,2008(7):48-50.
[35] 赵世新,张晨,李静怡,等.基于BP神经网络方法的引滦入津工程黎河段水质预测研究[J].安全与环境学报,2010,10(2):93-96.
[36] 操建华,林宏伟,张实诚.基于BP神经网络的丹江口库区水质指标预测[J].电子设计工程,2010,18(3):17-18,24.
[37] 邵雪.松花江哈尔滨段水质变化趋势分析与控制对策研究[D].哈尔滨:哈尔滨工业大学,2011.Shao Xue.Analysis the SongHua River in HarBin section's water quality trend and research on the control measures [D].Harbin:Harbin Institute of Technology,2011.
[38] 张昕,许伟明,邓春龙.BP神经网络在水质参数预测中的应用[J].微计算机信息,2012,28(4):37-38,48.
[39] 严玉洁.AMBR工艺畜禽养殖污水处理及BP神经网络水质预测研究[D].银川:宁夏大学,2017.Yan Yujie.Study on dairy waste water treatment by AMBR and effluent quality forecast by BP Neural Network [D].Yinchuan:Ningxia University,2017.
[40] 郭庆春,何振芳,李力.人工神经网络模型在黄河水质预测中的应用[J].人民黄河,2011,33(10):42-43.
[41] 卢超,杨翠丽,乔俊飞.基于尖峰自组织径向基网络的氨氮软测量方法[J].信息与控制,2017,46(6):752-758.
[42] Ruben G B,Yuebo X,Samuel A AA.Estimation of Ammonia-Nitrogen (NH3-N) using an Artificial Neural Networks under bacterial technology [J].Oriental Journal of Chemistry,2016,32(1):37-45.
[43] Jami M S,Mujeli M,Kabbashi N A.Simulation of ammoniacal nitrogen effluent using feed forward multilayer neural networks [J].African Journal of Biotechnology,2011,10(81):18755-18762.
[44] Chang F J,Tsai Y H,Chen P A,et al.Modeling water quality in an urban river using hydrological factors-Data driven approaches [J].Journal of Environmental Management,2015,151:87-96.
[45] 余伟,罗飞,杨红,等.基于多神经网络的污水氨氮预测模型[J].华南理工大学学报(自然科学版),2010,38(12):79-83.
[46] 汪翔,何吉祥,佘磊,等.Elman网络在养殖水体氨氮预测中的应用研究[J].安徽农业科学,2015,43(31):365-367.
[47] Ju J W,Wang L Y.Analysis of Ammonia Nitrogen Content in water based on Weighted Least Squares Support Vector Machine (WLSSVM)algorithm [J].Journal of Software Engineering & Applications,2016,9(2):45-51.
[48] 任作为.水产养殖氨氮在线检测方法及系统研究[D].镇江:江苏大学,2017.Ren Zuowei.Research on online detection method and system of Ammonia Nitrogen in aquaculture [D].Zhenjiang:Jiangsu University,2017.
[49] 居锦武.基于LS-SVM的养殖水体氨氮含量分析预测模型[J].江苏农业科学,2017,45(2):210-212.
[50] 崔雪梅,汪殿蓓,熊思.基于随机遗传算法的LM-BP模型的氨氮预测[J].水利水电技术,2013,44(11):26-28,39.
[51] 高峰,冯民权,滕素芬.基于PSO优化BP神经网络的水质预测研究[J].安全与环境学报,2015,15(4):338-341.
[52] 宋益春.智能算法在水产养殖水质预测中的应用研究[D].无锡:江南大学,2015.Song Yichun.Application research of intelligent algorithm in the prediction of water quality in aquaculture [D].Wuxi:Jiangnan University,2015.
[53] 高平,宋益春,彭新建,等.基于QPSO-GRNN的水质氨氮预测建模[J].电脑知识与技术,2013,9(23):5373-5376.
[54] 徐大明.基于机器学习的跨平台水产精准养殖管理系统设计[D].太原:太原理工大学,2016.Xu Daming.Design of cross platform aquaculture management system based on machine learning [D].Taiyuan:Taiyuan University of Technology,2016.
[55] 徐大明,杜永贵,孙传恒,等.基于改进粒子群优化极限学习机的养殖氨态氮含量预测模型[J].江苏农业科学,2017,45(4):183-186.
[2] 国家统计局.中国统计年鉴2015[M].北京:中国统计出版社,2015.
[3] 国家统计局.中国统计年鉴2016[M].北京:中国统计出版社,2016.
[4] 国家统计局.中国统计年鉴2017[M].北京:中国统计出版社,2017.
[5] 国家统计局.中国统计年鉴2018[M].北京:中国统计出版社,2018.
[6] 付婉霞,聂正武,高杰,等.饮用水氨氮的去除方法综述[J].能源环境保护,2006,20(3):15-17.
[7] 刘刚.生活饮用水中的氨氮污染问题探讨[J].中国高新技术企业,2011(27):146-148.
[8] 张卫强,朱英.养殖水体中氨氮的危害及其检测方法研究进展[J].环境卫生学杂志,2012,2(6):324-327.Zhang Weiqiang,Zhu Ying.Advances on the research of the hazard of Ammonia Nitrogen in aquaculture water and its determination method [J].Journal of Environmental Hygiene,2012,2(6):324-327.
[9] 高亚峰,孙洪杰.氨氮对鱼类的危害[J].河北渔业,2014(8):62-63,67.
[10] 张光林.循环冷却水系统中氨氮的危害与对策[J].石油和化工设备,2011,14(8):68-70.
[11] 林根仙,何蓉,郭俊文.氨氮对循环冷却水系统的危害与对策[J].工业水处理,2006,26(5):82-84.
[12] 杜晓旭,康俊巍,徐艳伟,等.污水氨氮检测方法问题分析及改进[J].轻工科技,2012(11):115-117,123.
[13] 刘林斌.水中氨氮测定方法比较[J].广州化工,2011,39(10):110-111.
[14] 国家环境保护总局,水和废水监测分析方法编委会.水和废水监测分析方法(第四版)[M].北京:中国环境科学出版社,2002.
[15] 安慧慧.水中氨氮测定方法的比较分析[J].山西化工,2017,37(4):55-57.
[16] 乔俊飞,安茹,韩红桂.基于RBF神经网络的出水氨氮预测研究[J].控制工程,2016,23(9):1301-1305.
[17] 居锦武.基于LS-SVM的养殖水体氨氮含量分析模型的优化[J].大连海洋大学学报,2016,31(4):444-448.
[18] 易仲强.智能算法在湖库富营养化预测中的应用研究综述[J].水电能源科学,2010,28(8):33-36,26.Yi Zhongqiang.Review of research on eutrophication prediction in lakes and reservoirs with intelligent algorithm [J].Water Resources and Power,2010,28(8):33-36,26.
[19] 吴冬春,陆广平,顾春雷.池塘养殖水体溶氧度检控集群系统设计[J].中国农机化学报,2014,35(5):213-216.Wu Dongchun,Lu Guangping,Gu Chunlei.Design of monitoring cluster system for dissolved oxygen of pond aquaculture water [J].Journal of Chinese Agricultural Mechanization,2014,35(5):213-216.
[20] 付焕森,曹健,李元贵.基于Zigbee和GPRS的仿真机器鱼水质监测系统设计[J].中国农机化学报,2016,37(7):179-182,194.Fu Huansen,Cao Jian,Li Yuangui.Design on simulation robotic fish water monitoring system based on Zigbee and GPRS [J].Journal of Chinese Agricultural Mechanization,2016,37(7):179-182,194.
[21] 张丽,王彦,刘娜,等.基于水、肥、温、气系统一体化的水质改善工艺[J].中国农机化学报,2014,35(3):248-251.Zhang Li,Wang Yan,Liu Na,et al.Integration improvement process based on water,fertilizer,temperature,air quality system [J].Journal of Chinese Agricultural Mechanization,2014,35(3):248-251.
[22] 潘贺,关久念,李太浩.基于无线传感器网络的水产养殖水环境监测系统设计与试验[J].中国农机化学报,2014,35(5):246-250.Pan He,Guan Jiunian,Li Taihao.Design and test of aquaculture water environment monitoring system based on wireless sensor network [J].Journal of Chinese Agricultural Mechanization,2014,35(5):246-250.
[23] 陈冲,沈翠凤.集约化水产养殖水质多参数测控系统研究与设计[J].中国农机化学报,2013,34(6):268-272.Chen Chong,Shen Cuifeng.Research and design of intensive aquaculture water multi-parameter measurement and control system [J].Journal of Chinese Agricultural Mechanization,2013,34(6):268-272.
[24] Refsgaard J C,S?rensen H R,Mucha I,et al.An integrated model for the danubian lowland-methodology and applications [J].Water Resources Management,1998,12(6):433-465.
[25] 梁识栋.高维参数水质模型参数不确定性分析方法研究[D].北京:清华大学,2016.Liang Shidong.Research on parameter uncertainty analysis method for water quality model with high-dimensional parameter space [D].Beijing:Tsinghua University,2016.
[26] Filoso S,Vallino J,Hopkinson C,et al.Modeling Nitrogen transport in the IPSwich River Basin,Massa chusetts,using a Hydrological Simulation Program in Fortran (HSPF) [J].Journal of the American Water Resources Association,2004,40(5):1365-1384.
[27] Mona R,Alaa E S,Patrick W,et al.Modeling of Nitrogen in river water using a detailed and a simplified model [J].The Scientific World Journal,2001,1:200-206.
[28] 李如忠,汪家权,钱家忠.基于灰色动态模型群法的河流水质预测研究[J].水土保持通报,2002,22(4):10-12.Li Ruzhong,Wang Jiaquan,Qian Jiazhong.Prediction of river water quality based on gray dynamic model group [J].Bulletin of Soil and Water Conservation,2002,22(4):10-12.
[29] Rumelhart D E,Hinton G E,Williams R J.Learning representations by back-propagating errors [J].Nature,1986,323:533-536.
[30] Kennedy J.Particle swarm optimization [J].Proc.of 1995 IEEE Int.Conf.Neural Networks,(Perth,Australia),Nov.27-Dec.
[31] 乔俊飞,马士杰,许进超.基于递归RBF神经网络的出水氨氮预测研究[J].计算机与应用化学,2017,34(2):145-151.Qiao Junfei,Ma Shijie,Xu Jinchao.The water ammonia nitrogen prediction research based on a recursive RBF neural network [J].Computers and Applied Chemistry,2017,34(2):145-151.
[32] 树锦.人工神经网络模型在黄河水质预测中的应用[D].南京:河海大学,2006.Shu Jin.Using artificial neutral network model to predict water quality in Yellow River [D].Nanjing:HohaiUniversity,2006.
[33] 杨琴,谢淑云.BP神经网络在洞庭湖氨氮浓度预测中的应用[J].水资源与水工程学报,2006,17(1):65-70.
[34] 高艳萍,周敏,姜凤娇.基于BP网络养殖水体氨氮预测模型及实现[J].农机化研究,2008(7):48-50.
[35] 赵世新,张晨,李静怡,等.基于BP神经网络方法的引滦入津工程黎河段水质预测研究[J].安全与环境学报,2010,10(2):93-96.
[36] 操建华,林宏伟,张实诚.基于BP神经网络的丹江口库区水质指标预测[J].电子设计工程,2010,18(3):17-18,24.
[37] 邵雪.松花江哈尔滨段水质变化趋势分析与控制对策研究[D].哈尔滨:哈尔滨工业大学,2011.Shao Xue.Analysis the SongHua River in HarBin section's water quality trend and research on the control measures [D].Harbin:Harbin Institute of Technology,2011.
[38] 张昕,许伟明,邓春龙.BP神经网络在水质参数预测中的应用[J].微计算机信息,2012,28(4):37-38,48.
[39] 严玉洁.AMBR工艺畜禽养殖污水处理及BP神经网络水质预测研究[D].银川:宁夏大学,2017.Yan Yujie.Study on dairy waste water treatment by AMBR and effluent quality forecast by BP Neural Network [D].Yinchuan:Ningxia University,2017.
[40] 郭庆春,何振芳,李力.人工神经网络模型在黄河水质预测中的应用[J].人民黄河,2011,33(10):42-43.
[41] 卢超,杨翠丽,乔俊飞.基于尖峰自组织径向基网络的氨氮软测量方法[J].信息与控制,2017,46(6):752-758.
[42] Ruben G B,Yuebo X,Samuel A AA.Estimation of Ammonia-Nitrogen (NH3-N) using an Artificial Neural Networks under bacterial technology [J].Oriental Journal of Chemistry,2016,32(1):37-45.
[43] Jami M S,Mujeli M,Kabbashi N A.Simulation of ammoniacal nitrogen effluent using feed forward multilayer neural networks [J].African Journal of Biotechnology,2011,10(81):18755-18762.
[44] Chang F J,Tsai Y H,Chen P A,et al.Modeling water quality in an urban river using hydrological factors-Data driven approaches [J].Journal of Environmental Management,2015,151:87-96.
[45] 余伟,罗飞,杨红,等.基于多神经网络的污水氨氮预测模型[J].华南理工大学学报(自然科学版),2010,38(12):79-83.
[46] 汪翔,何吉祥,佘磊,等.Elman网络在养殖水体氨氮预测中的应用研究[J].安徽农业科学,2015,43(31):365-367.
[47] Ju J W,Wang L Y.Analysis of Ammonia Nitrogen Content in water based on Weighted Least Squares Support Vector Machine (WLSSVM)algorithm [J].Journal of Software Engineering & Applications,2016,9(2):45-51.
[48] 任作为.水产养殖氨氮在线检测方法及系统研究[D].镇江:江苏大学,2017.Ren Zuowei.Research on online detection method and system of Ammonia Nitrogen in aquaculture [D].Zhenjiang:Jiangsu University,2017.
[49] 居锦武.基于LS-SVM的养殖水体氨氮含量分析预测模型[J].江苏农业科学,2017,45(2):210-212.
[50] 崔雪梅,汪殿蓓,熊思.基于随机遗传算法的LM-BP模型的氨氮预测[J].水利水电技术,2013,44(11):26-28,39.
[51] 高峰,冯民权,滕素芬.基于PSO优化BP神经网络的水质预测研究[J].安全与环境学报,2015,15(4):338-341.
[52] 宋益春.智能算法在水产养殖水质预测中的应用研究[D].无锡:江南大学,2015.Song Yichun.Application research of intelligent algorithm in the prediction of water quality in aquaculture [D].Wuxi:Jiangnan University,2015.
[53] 高平,宋益春,彭新建,等.基于QPSO-GRNN的水质氨氮预测建模[J].电脑知识与技术,2013,9(23):5373-5376.
[54] 徐大明.基于机器学习的跨平台水产精准养殖管理系统设计[D].太原:太原理工大学,2016.Xu Daming.Design of cross platform aquaculture management system based on machine learning [D].Taiyuan:Taiyuan University of Technology,2016.
[55] 徐大明,杜永贵,孙传恒,等.基于改进粒子群优化极限学习机的养殖氨态氮含量预测模型[J].江苏农业科学,2017,45(4):183-186.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |