高级搜索

基于改进支持向量回归机的污水处理厂出水总氮预测模型

,  , 

downloadPDF

上一篇

下一篇

刘杰, 李佟, 李军. 基于改进支持向量回归机的污水处理厂出水总氮预测模型[J]. 环境工程学报, 2018, 12(1): 119-126. doi: 10.12030/j.cjee.201706050
引用本文: 刘杰, 李佟, 李军. 基于改进支持向量回归机的污水处理厂出水总氮预测模型[J]. 环境工程学报, 2018, 12(1): 119-126. doi: 10.12030/j.cjee.201706050
shu
LIU Jie, LI Tong, LI Jun. Prediction of effluent total nitrogen concentration in a wastewater treatment plant using a particle swarm optimization-support vector regression model[J]. Chinese Journal of Environmental Engineering, 2018, 12(1): 119-126. doi: 10.12030/j.cjee.201706050
Citation: LIU Jie, LI Tong, LI Jun. Prediction of effluent total nitrogen concentration in a wastewater treatment plant using a particle swarm optimization-support vector regression model[J]. Chinese Journal of Environmental Engineering, 2018, 12(1): 119-126. doi: 10.12030/j.cjee.201706050
shu

基于改进支持向量回归机的污水处理厂出水总氮预测模型

  • 1.

    太原理工大学环境科学与工程学院,太原 030024

  • 2.

    北京工业大学建筑工程学院,北京 100124

  • 3.

    北京城市排水集团有限责任公司,北京 100044

  • 基金项目:

    国家水体污染控制与治理科技重大专项(2014ZX07201-001)

Prediction of effluent total nitrogen concentration in a wastewater treatment plant using a particle swarm optimization-support vector regression model

  • 1.

    College of Environmental Science and Engineering, Taiyuan University of Technology, Taiyuan 030024, China

  • 2.

    College of Architecture and Civil Engineering, Beijing University of Technology, Beijing 100124, China

  • 3.

    Beijing Drainage Group Co.Ltd., Beijing 100044, China

  • Fund Project:

  • 摘要: 在小样本数据的情况下,采用粒子群优化算法(PSO)对传统支持向量回归机(SVR)进行改进,将其应用于北京某大型污水处理厂出水总氮浓度预测上。 预测结果精度对比分析表明,PSO-SVR模型预测结果平均相对误差为1.836%,决定系数为67.76%,均方根误差为0.693 9,各评价指标均优于多元线性回归模型、BP神经网络模型。因此在小样本情况下,利用PSO-SVR模型对污水处理厂出水总氮浓度进行预测是可行有效的,为应用数据驱动模型对污水处理过程进行建模模拟提供了一种新方法尝试。
    Abstract: A particle swarm optimization (PSO)-support vector regression (SVR) was built based on small sample and applied it to predict effluent total nitrogen concentration in a wastewater treatment plant. The analysis of prediction accuracies indicated that the mean relative error (MRE) is 1.836%, the coefficient of determination (R2) is 67.76% as well as the root mean square error (RMSE) is 0.693 9. In addition, the accuracy of the PSO-SVR model was analyzed by comparison with the multivariable linear regression (MLR) model and the BP neural network (BP-ANN). The results indicated that the PSO-SVR model is better than MLR and BP-ANN in prediction of effluent total nitrogen concentration in a wastewater treatment plant. Therefore, it is feasible and effective to predict effluent total nitrogen concentration in a wastewater treatment plant by using PSO-SVR model, which provides the method to modeling the process of wastewater treatment.
  • 加载中
  • [1] NAZARI L, YUAN Z S, SANTORO D, et al.Low-temperature thermal pre-treatment of municipal wastewater sludge:Process optimization and effects on solubilization and anaerobic degradation[J].Water Research,2017,3:111-123
    [2] HVALA N, VREˇKO D, LEVSTEK M, et al.The use of dynamic mathematical models for improving the designs of upgraded wastewater treatment plants[J].Journal of Sustainable Development of Energy, Water and Environment Systems,2017,5(1):15-31
    [3] 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[J].环境科学学报,2016,6(2):576-581
    [4] 张晓军, 应启峰, 王洪臣, 等.质量平衡模型及其在污水处理厂节能降耗中的应用[J].环境工程学报,2016,0(3):1030-1034
    [5] BUSCH J, ELIXMANN D, KHL P, et al.State estimation for large-scale wastewater treatment plants[J].Water Research,2013,7(13):4774-4787
    [6] SANTA C J A, MUSSATI S F, SCENNA N J, et al.Reaction invariant-based reduction of the activated sludge model ASM1 for batch applications[J].Journal of Environmental Chemical Engineering,2016,4(3):3654-3664
    [7] ALIKHANI J, TAKACS I, AL-OMARI A, et al.Evaluation of the information content of long-term wastewater characteristics data in relation to activated sludge model parameters[J].Water Science and Technology,2017,5(6):1370-1389
    [8] HAMED M M, KHALAFALLAH M G, HASSANIEN E A.Prediction of wastewater treatment plant performance using artificial neural networks[J].Environmental Modelling & Software,2004,9(10):919-928
    [9] HONG Y S T, ROSEN M R, BHAMIDIMARRI R.Analysis of a municipal wastewater treatment plant using a neural network-based pattern analysis[J].Water Research,2003,7(7):1608-1618
    [10] MJALLI F S, AL-ASHEH S, ALFADALA H E.Use of artificial neural network black-box modeling for the prediction of wastewater treatment plants performance[J].Journal of Environmental Management,2007,3(3):329-338
    [11] ALVANI V, NABIZADEH R, ANSARIZADEH M, et al.Predicting TOC removal efficiency in hybrid biological aerated filter using artificial neural network[J].Desalination and Water Treatment,2016,7(43):20283-20291
    [12] ZHAO Y, GUO L, LIANG J B, et al.Seasonal artificial neural network model for water quality prediction via a clustering analysis method in a wastewater treatment plant of China[J].Desalination and Water Treatment,2016,7(8):3452-3465
    [13] 韩改堂, 乔俊飞, 韩红桂.基于递归模糊神经网络的污水处理控制方法[J].化工学报,2016,7(3):954-959
    [14] 何芳, 徐友宁, 袁汉春.矿山环境地质问题综合评价客观权值确定方法探讨[J].中国地质,2008,5(2):337-343
    [15] MIN J H, LEE Y C.Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters[J].Expert Systems with Applications,2005,8(4):603-614
    [16] 赖红松.基于支持向量回归机的耕地保有量组合预测[J].地理与地理信息科学,2011,7(2):56-60
    [17] 李佳, 张一敏, 刘振宇, 等.基于改进支持向量机的石煤提钒行业清洁生产评价研究[J].环境科学学报,2016,6(3):1113-1120
    [18] 秦喜文, 刘媛媛, 王新民, 等.基于整体经验模态分解和支持向量回归的北京市 PM2.5预测[J].吉林大学学报 (地球科学版),2016,6(2):563-568
    [19] 张成成, 陈求稳, 徐强, 等.基于支持向量机的太湖梅梁湾叶绿素 a 浓度预测模型[J].环境科学学报,2013,3(10):2856-2861
    [20] 张玉, 莫寒, 张烈平.基于模糊支持向量机的光伏发电量预测[J].热力发电,2017,6(1):116-120
    [21] 王霞, 王占岐, 金贵, 等.基于核函数支持向量回归机的耕地面积预测[J].农业工程学报,2014,0(4):204-211
    [22] VAPNIK V.The Nature of Statistical Learning Theory[M].New York:Springer Science & Business Media,2013
    [23] 韦佳, 何世钧, 周汝雁, 等.基于支持向量回归机的南黄海浒苔分布面积预测模型[J].环境工程学报,2015,9(6):3046-3050
    [24] KENNEDY J.Particle swarm optimization[M]//SAMMUT C, WEBB G I.Encyclopedia of Machine Learning.New York:Springer,2011:760-766
    [25] ARMAGHANI D J, SHOIB R S, FAIZI K, et al.Developing a hybrid PSO-ANN model for estimating the ultimate bearing capacity of rock-socketed piles[J].Neural Computing and Applications,2017,8(2):391-405
    [26] 安爱民, 祁丽春, 丑永新, 等.基于粒子群优化的溶解氧质量浓度支持向量回归机[J].北京工业大学学报,2016,2(9):1318-1323
    [27] BENVIDI A, ABBASI S, GHARAGHANI S, et al.Spectrophotometric determination of synthetic colorants using PSO-GA-ANN[J].Food Chemistry,2017,0:377-384
    [28] 姜体胜, 杨琦, 尚海涛, 等.温度和 pH 值对活性污泥法脱氮除磷的影响[J].环境工程学报,2007,1(9):10-14
    [29] 吴代顺, 桂丽娟, 侯红勋, 等.COD, MLSS, pH 值及污泥驯化对脱氮除磷的影响[J].中国给水排水,2012,8(13):117-120
    [30] GAJEWSKA M, J＇WIAKOWSKI K, GHRABI A, et al.Impact of influent wastewater quality on nitrogen removal rates in multistage treatment wetlands[J].Environmental Science and Pollution Research,2015,2(17):12840-12848
    [31] 付昆明, 王会芳, 苏雪莹, 等.初始 pH 值对序批式 CANON 工艺脱氮效果和 N2O释放的影响[J].环境科学,2016,7(11):4261-4267
  • 加载中
WeChat 点击查看大图
计量
  • 文章访问数:  3179
  • HTML全文浏览数:  2903
  • PDF下载数:  435
  • 施引文献:  0
出版历程
  • 刊出日期:  2018-01-14

基于改进支持向量回归机的污水处理厂出水总氮预测模型

  • 1. 太原理工大学环境科学与工程学院,太原 030024
  • 2. 北京工业大学建筑工程学院,北京 100124
  • 3. 北京城市排水集团有限责任公司,北京 100044
基金项目:

国家水体污染控制与治理科技重大专项(2014ZX07201-001)

摘要: 在小样本数据的情况下,采用粒子群优化算法(PSO)对传统支持向量回归机(SVR)进行改进,将其应用于北京某大型污水处理厂出水总氮浓度预测上。 预测结果精度对比分析表明,PSO-SVR模型预测结果平均相对误差为1.836%,决定系数为67.76%,均方根误差为0.693 9,各评价指标均优于多元线性回归模型、BP神经网络模型。因此在小样本情况下,利用PSO-SVR模型对污水处理厂出水总氮浓度进行预测是可行有效的,为应用数据驱动模型对污水处理过程进行建模模拟提供了一种新方法尝试。

English Abstract

参考文献 (31)

目录

/

返回文章
返回

Copyright © 2019 中国科学院生态环境研究中心