基于神经网络的污水处理预测控制

吉林大学学报(工学版) ›› 2011, Vol. 41 ›› Issue (增刊1): 280-284.

基于神经网络的污水处理预测控制

逄泽芳, 韩红桂, 乔俊飞

北京工业大学电子信息与控制工程学院, 北京 100124

收稿日期:2010-02-13 出版日期:2011-09-01 发布日期:2011-09-01
作者简介:逄泽芳(1986 ),女,硕士研究生.研究方向:控制科学与工程.E-mail:miya29@126.com.
基金资助:
国家自然科学基金项目(61034008)

Predictive control for wastewater treatment process based on neural network

PANG Ze-fang, HAN Hong-gui, QIAO Jun-fei

College of Electronic and Control Engineering, Beijing University of Technology, Beijing 100124, China

Received:2010-02-13 Online:2011-09-01 Published:2011-09-01

摘要/Abstract

摘要：

针对国际水协(IWA)开发的基准仿真模型(Benchmark simulation model No.1,BSM1)中第5分区溶解氧质量分数和第2分区硝态氮质量分数的控制问题,提出了一种基于神经网络的多变量预测控制系统。控制系统中主要包括两部分:神经网络辨识器,用于提取对象的输出数据;神经网络控制器,用于输出控制变量。仿真结果表明:基于神经网络的预测控制系统具有较好的适应性和鲁棒性。

关键词: 神经网络预测控制, 污水处理, 溶解氧质量浓度, 硝态氮质量浓度

Abstract:

A new multi-objective predictive control system based on the neural network was proposed for activated sludge wastewater treatment process.Both the dissolved oxygen level in the fifth compartment and the nitrate level in the second anoxic tank were controlled in the benchmark simulation model No.1(BSM1).The control system mainly consists of two parts:one part is the identifier used to predict the outputs of the object;another part is the controller applied to control the variables of the system.The simulation results demonstrate the proposed control system owning better adaptability and greater robustness.

Key words: neural network predictive control, wastewater treatment, dissolved Oxygen, nitrate

中图分类号:

TP183

逄泽芳, 韩红桂, 乔俊飞. 基于神经网络的污水处理预测控制[J]. 吉林大学学报(工学版), 2011, 41(增刊1): 280-284.

PANG Ze-fang, HAN Hong-gui, QIAO Jun-fei. Predictive control for wastewater treatment process based on neural network[J]. 吉林大学学报(工学版), 2011, 41(增刊1): 280-284.

参考文献

[1] 刘大伟,沈文浩。活性污泥法污水处理基准仿真模型的开发及进展
[J].中国给水排水,2007,23(20):20-25. Liu Da-we,Shen Wen-hao.Development of benchmark simulation model for activated sludgew astewater treatment
[J].China Water and WasteW ater,2007,23(20):20-25.

[2] Traore A,Grieu S,Puig S,et al.Fuzzy control of dissolved oxygen in a sequencing batch reactor pilotp lant
[J].Chemical Engineering Journal,2005,111 (1):13-19.

[3] Leu S Y,Rosso D,Larson L E,et al.Real-time aeration efficiency monitoring in the activated sludgep rocess and methods to reduce energy consumptiona nd operating costs
[J].Water Environment Research,2009,81(12):2471-2481.

[4] Ekman M.Bilinear black-box identification and MPCo f the activated sludge process
[J].Journal ofP rocess Control,2008,18(7/8):643-653.

[5] Shen W H,Chen X Q,Corriou J P.Application ofm odel predictive control to the BSM1benchmark ofw astewater treatment process
[J].Computers andC hemical Engineering,2008,32(12):2849-2856.

[6] Holenda B,Domokos E.Dissolved oxygen control oft he activated sludge wastewater treatment process using model predictive control
[J].Computers andC hemical Engineering,2008,32(6):1270-1278.

[7] Piotrowski R,Brdys M A.Hierarchical dissolved oxygen control for activated sludge processes
[J].Control Engineering Practice,2008,16(1):114-131.

[8] 张平,苑明哲,王宏。基于国际评价基准的溶解氧控制方法研究
[J].信息与控制,2007,36(2):199-203.Z hang Ping,Yuan Ming-zhe,Wang Hong.Study ond issolved oxygen control method based on international evaluation benchmark
[J].Information andC ontrol,2007,36(2):199-203.

[9] Su H T,McAvoy T J.Identification of chemicalp rocesses using recurrent networks
[J].Proceedingo f American Control Confenrence,1990:2314-2319.

[10] Tan Y H,Cauwenberghe V A.Neural-network-basedd -step-ahead predictors for Nonlinear systems witht ime delay
[J].Applications of Artificial Intelligence, 1999,12(1):21-35.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed