|本期目录/Table of Contents|

[1]黄 辉*,马思佳,王 庆,等.多参数影响下污水总氮浓度预测最优方法研究[J].南京大学学报(自然科学),2017,53(6):1194.[doi:10.13232/j.cnki.jnju.2017.06.022]
 Huang Hui*,Ma Sijia,Wang Qing,et al.Optimal method for predicting the total nitrogen concentration of wastewater under the influence of multiple parameters[J].Journal of Nanjing University(Natural Sciences),2017,53(6):1194.[doi:10.13232/j.cnki.jnju.2017.06.022]
点击复制

多参数影响下污水总氮浓度预测最优方法研究()
     

《南京大学学报(自然科学)》[ISSN:0469-5097/CN:32-1169/N]

卷:
53
期数:
2017年第6期
页码:
1194
栏目:
出版日期:
2017-12-01

文章信息/Info

Title:
Optimal method for predicting the total nitrogen concentration of wastewater under the influence of multiple parameters
作者:
 黄 辉123*马思佳12王 庆3任洪强123
1.南京大学环境学院污染控制与资源化研究国家重点实验室,南京,210023;
2.江苏中宜金大环保产业技术研究院有限公司,宜兴,214200;
3.南京大学宜兴环保研究院,宜兴,214200
Author(s):
Huang Hui123*Ma Sijia12Wang Qing3Ren Hongqiang 123
1.School of the Environment,Nanjing University,State Key Laboratory of Pollution Control and Resource Reuse,Nanjing,210023,China;
2.Jiangsu Zhongyijinda Institute of Environmental Industry Technology CO.,LTD.,Yixing,214200,China;
3.Nanjing University-Yixing Environmental Research Institute,Yixing,214200,China
关键词:
 多参数总氮预测神经网络支持向量回归机
Keywords:
multiple parametersprediction of total nitrogenneural networksupport vector regression machine(SVR)
分类号:
X824
DOI:
10.13232/j.cnki.jnju.2017.06.022
文献标志码:
A
摘要:
 污水总氮(TN)深度脱除是当前我国污水处理领域的重大科技需求.TN的去除受到多种环境及操作条件的影响,开发多参数条件下稳健的TN浓度预测方法是降低污水厂能耗、实现智能化控制的重要前提.针对以上问题,以某实际污水处理厂反硝化深床滤池为例,采用BP神经网络(BP)、量子遗传算法优化的BP神经网络(QGA_BP)、改进的QGA_BP和支持向量回归机(SVR),在进水流量和碳源投加量等13种变量条件下,对滤池出水TN进行了模拟预测.共选取147组数据,其中130组用于出水水质和工艺参数的拟合模拟,17组用于结果验证.将总氮实测值依次与BP,QGA_BP和改进的QGA_BP神经网络以及SVR预测结果进行对比,相关系数R2依次增大,分别为0.221,0.275,0.826和0.951,即预测值与实测值之间的拟合度逐渐升高.SVR克服了神经网络预测误差较大的问题,对多参数影响下TN浓度的预测具有较高的准确性和稳定性,用其替代常用的神经网络算法具有明显的优势.
Abstract:
The deep removal of total nitrogen(TN)is a major scientific and technological demand in the field of wastewater treatment in China nowadays.Multiple parameters-affected TN removal desires a robust prediction of TN concentration in order for the energy consumption reduction and intelligent control of the treating system.In respect of the issues above,taking the denitrification deep bed filter of a real wastewater treatment plant as an example,this paper applied four types of predicting methods containing the Back Propagation(BP)neural network,quantum genetic algorithm BP neural network(QGA_BP),improved QGA_BP neural network and support vector regression machine(SVR),to simulate effluent TN concentration under a total of 13 parameters of inlet flow,carbon source addition,and so on.A total of 147 groups of data were selected,among which 130 groups for the simulation of effluent water quality and process parameters,and 17 groups for results verification.Measured values of TN were compared with predicted results from BP,QGA_BP,improved QGA_BP and SVR,respectively.The fitting degree between the predicted value and the measured value increased gradually,with the correlation coefficients(R2)of 0.221,0.275,0.826 and 0.951 for each method,respectively.SVR algorithm overcomes the relatively big error by neural network and has a high accuracy and stability for TN concentration prediction under the influence of multiple parameters,exhibiting a good alternative to neural network algorithms.

参考文献/References:

 [1] Zhu S M,Deng Y L,Ruan Y J,et al.Biological denitrification using poly(butylene succinate)as carbon source and biofilm carrier for recirculating aquaculture system effluent treatment.Bioresource Technology,2015,192:603-610.
[2] Bundy C A,Wu D,Jong M C,et al.Enhanced denitrification in downflow hanging sponge reactors for decentralised domestic wastewater treatment.Bioresource Technology,2017,226:1-8.
[3] Sun H H,Wu Q,Yu P,et al.Denitrification using excess activated sludge as carbon source:Performance and the microbial community dynamics.Bioresource Technology,2017,238:624-632. 
[4] Zhang Y M,Wang L M,Han W,et al.Nitrate removal,spatiotemporal communities of denitrifiers and the importance of their genetic potential for denitrification in novel denitrifying bioreactors.Bioresource Technology,2017,241:552-562.
[5] Guerrero J,Guisasola A,Baeza J A.The nature of the carbon source rules the competition between PAO and denitrifiers in systems for simultaneous biological nitrogen and phosphorus removal.Water Research,2011,45(16):4793-4802.
[6] Zhang Y Y,Pan B C.Modeling batch and column phosphate removal by hydrated ferric oxide-based nanocomposite using response surface methodology and artificial neural network.Chemical Engineering Journal,2014,249:111-120. 
[7] Parmar K S,Bhardwaj R.Wavelet and statistical analysis of river water quality parameters.Applied Mathematics and Computation,2013,219(20):10172-10182.
[8] 魏佳明,崔丽娟,李 伟等.两种模型对潜流湿地出水中总氮含量的预测能力对比.湿地科学,2017,15(2):281-286.(Wei J M,Cui L J,Li W,et al.Comparison of predictive ability on contents of total nitrogen in the effluent of subsurface flow constructed wetlands by two kinds of models.Wetland Science,2017,15(2):281-286.)
[9] Yonar T,Kilic M Y.Chemical oxygen demand and color removal from textile wastewater by UV/H2O2 using artificial neural networks.Water Environment Research,2014,86(11):2159-2165. 
[10] Bagheri M,Mirbagheri S A,Ehteshami M,et al.Modeling of a sequencing batch reactor treating municipal wastewater using multi-layer perceptron and radial basis function artificial neural networks.Process Safety and Environmental Protection,2015,93:111-123.
[11] 龙 华,赵继东,王晓东等.改进的QGA-BP模型在弥苴河总氮量预测中的应用.环境工程学报,2016,10(11):6099-6105.(Long H,Zhao J D,Wang X D,et al.Application research on total nitrogen content forecast of River Miju with improved QGA-BP model.Chinese Journal of Environmental Engineering,2016,10(11):6099-6105.)
[12] 许少鹏,韩红桂,乔俊飞.基于模糊递归神经网络的污泥容积指数预测模型.化工学报,2013,64(12):4550-4556.(Xu S P,Han H G,Qiao J F.Prediction of activated sludge bulking based on recurrent fuzzy neural network.CIESC Journal,2013,64(12):4550-4556.)
[13] 赵 慢,韩红桂,乔俊飞.基于神经网络预测控制的污水处理过程多目标优化.第34届中国控制会议论文集.杭州,中国:北京航空航天大学出版社,2015:28-30.(Zhao M,Han H G,Qiao J F.Optimal control of multi-objective for wastewater treatment process based on neural network predictive control.In:Proceeding of the 34th Chinese Control Conference.Hangzhou,China:Beihang University Press,2015:28-30.)
[14] 曹慧玲,张 卓,曲春刚.SVR在航空发动机基线挖掘中的应用研究.机械科学与技术,2017,36(1):152-160.(Cao H L,Zhang Z,Qu C G.The application research of support vector regression in aero-engine’s baseline mining.Mechanical Science and Technology,2017,36(1):152-160.)
[15] 李永娜.基于支持向量机的回归预测综述.信息通信,2014(11):32-33.(Li Y N.Review of regression forecasting based on support vector machines.Information & Communications,2014(11):32-33.)
[16] Kisi O,Parmar K S.Application of least square support vector machine and multivariate adaptive regression spline models in long term prediction of river water pollution.Journal of Hydrology,2016,534:104-112.
[17] Hiromasa K,Kimito F.Application of online support vector regression for soft sensors.Aiche Journal,2014,60(2):600-612.
[18] Serrà J,Arcos J L.An empirical evaluation of similarity measures for time series classification.Knowledge-Based Systems,2014,67:305-314.
[19] Shao Y H,Deng N Y,Yang Z M,et al.Probabilistic outputs for twin support vector machines.Knowledge-Based Systems,2012,33:145-151.
[20] 郝运河,张浩峰.基于双支持向量回归机的增量学习算法.计算机科学,2016,43(2):230-234,249.(Hao Y H,Zhang H F.Incremental learning algorithm based on twin support vector regression.Computer Science,2016,43(2):230-234,249.)
[21] 刘帮,秦斌,彭小玉.污水出水水质的SVR建模.新型工业化,2015,5(1):45-48.(Liu B,Qin B,Peng X Y.Modeling of wastewater effluent water quality on support vector regression machine.The Journal of New Industrialization,2015,5(1):45-48.)
[22] 王崇骏,于汶滌,陈兆乾等.一种基于遗传算法的BP神经网络算法及其应用.南京大学学报(自然科学),2003,39(5):459-466.(Wang C J,Yu W D,Chen Z Q,et al.A BP Neural network algorithm based on genetic algorithms and its application.Journal of Nanjing University(Natural Sciences),2003,39(5):459-466.)
[23] 朱云芳,朱利,李家国等.基于GF-1 WFV影像和BP神经网络的太湖叶绿素a反演.环境科学学报,2017,37(1):130-137.(Zhu Y F,Zhu L,Li J G,et al.The study of inversion of chlorophyll a in Taihu based on GF-1 WFV image and BP neural network.Acta Scientiae Circumstantiae,2017,37(1):130-137.)
[24] 白小宝.量子遗传算法研究.电脑开发与应用,2013,26(1):9-11,15.(Bai X B.Research on quantum genetic algorithm.Computer Development & Applications,2013,26(1):9-15.)
[25] 李明河,许俊杰.基于神经网络的污水处理软测量模型研究应用.工业控制计算机,2012,25(6):37-38,40.(Li M H,Xu J J.Sewage treatment soft measurement model based on neural network.Industrial Control Computer,2012,25(6):37-38,40.)
[26] 王泽平.基于GA-BP与多隐层BP网络模型的水质预测及比较分析.水资源与水工程学报,2013,24(3):154-160.(Wang Z P.Prediction and comparative analysis of water quality based on GA-BP and multi-hidden-layer BP network model.Journal of Water Resources and Water Engineering,2013,24(3):154-160.)
[27] Lin W Y,Jing L,Zhu Z W,et al.Removal of heavy metals from mining wastewater by micellar-enhanced ultrafiltration(MEUF):Experimental investigation and monte carlo-based artificial neural network modeling.Water,Air & Soil Pollution,2017,228:206.
[28] SekuliAc' Z,AntanasijeviAc' D,StevanoviAc' S,et al.Application of artificial neural networks for estimating Cd,Zn,Pb removal efficiency from wastewater using complexation microfiltration process.International Journal of Environmental Science and Technology,2017,14(7):1383-1396. 
[29] 李 佟,李 军.基于BP神经网络与马尔可夫链的污水处理厂脱氮效果模拟预测.环境科学学报,2016,36(2):576-581.(Li T,Li J.The prediction of denitrification efficiency of a wastewater treatment plant by using BP neural network and markov chain method.Acta Scientiae Circumstantiae,2016,36(2):576-581.) 
[30] Aydin K,Kisi O.Applicability of a fuzzy genetic system for crack diagnosis in Timoshenko beams.Journal of Computing in Civil Engineering,2015,29(5):04014073.
[31] Kundu P,Debsarkar A,Mukherjee S,et al.Artificial neural network modeling in biological removal of organic carbon and nitrogen for the treatment of slaughterhouse wastewater in a batch reactor.Environmental Technology,2014,35(10):1296-1306.

相似文献/References:

备注/Memo

备注/Memo:
 基金项目:国家水专项课题(2017ZX07204001),江苏省重点研发计划项目(BE2017632),江苏省科技成果转化专项资金项目(BA2016012),中央高校基本科研业务费项目(021114380046)
收稿日期:2017-09-04
*通讯联系人,E-mail:envhuang@nju.edu.cn
更新日期/Last Update: 2017-11-28