[1]张伟,乔俊飞.神经网络的污水处理过程多目标优化控制方法[J].智能系统学报,2016,11(5):594-599.[doi:10.11992/tis.201512022]
 ZHANG Wei,QIAO Junfei.Multi-objective optimization control for wastewatertreatment processing based on neural network[J].CAAI Transactions on Intelligent Systems,2016,11(5):594-599.[doi:10.11992/tis.201512022]
点击复制

神经网络的污水处理过程多目标优化控制方法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第11卷
期数:
2016年5期
页码:
594-599
栏目:
出版日期:
2016-11-01

文章信息/Info

Title:
Multi-objective optimization control for wastewatertreatment processing based on neural network
作者:
张伟123 乔俊飞13
1. 北京工业大学 电子信息与控制工程学院, 北京 100124;
2. 河南理工大学 电气工程与自动化学院, 河南 焦作 454000;
3. 计算智能与智能系统北京市重点实验室, 北京 100124
Author(s):
ZHANG Wei123 QIAO Junfei13
1. College of Electronic and Control Engineering, Beijing University of Technology, Beijing 100124, China;
2. School of Electrical Engineering & Automation, Henan Polytechnic University, Jiaozuo 454000, China;
3. Beijing Key Laboratory of Computational Intelligence and Intelligence System, Beijing 100124, China
关键词:
多目标优化神经网络能量消耗污水处理基准仿真模型BSM1
Keywords:
multi-objective optimizationneural networkenergy consumptionwastewater treatmentbenchmark simulation model
分类号:
TP18
DOI:
10.11992/tis.201512022
摘要:
针对污水处理过程能耗过高问题,提出一种基于神经网络的动态多目标优化控制方法。该方法对污水处理过程中的曝气能耗和泵送能耗同时优化,通过NSGA-II进化算法实现溶解氧浓度和硝态氮浓度设定值的动态寻优,由PID控制实现底层跟踪。采用神经网络在线建模方法构造污水处理过程多目标优化模型,解决了优化变量与性能指标间没有精确数学描述的问题。基于国际基准仿真平台BSM1的实验表明,与PID控制、单目标优化控制方法相比,多目标优化控制在保证出水水质达标的前提下可以获得更优的节能效果。
Abstract:
To solve the energy-extensive consumption problem of the wastewater treatment process (WWTP), a dynamic multi-objective optimization control strategy is proposed in this paper.The proposed method simultaneously optimizes the aerate energy and pumped energy consumption of WWTP, and the set-points of dissolved oxygen concentration and nitrate level can be optimized dynamically using the NSGA-Ⅱ evolutionary algorithm. The proportion-integral-derivative(PID) is chosen to realize the tracking control task for the low layer. To overcome the difficulty of establishing an optimal model for WWTP, an online neural network modeling method was proposed for constructing the multi-objective optimization model, which solves the problem that there is no accurate mathematical description with the optimization variables and performance indexes. The simulation results, based on the international benchmark simulation model No. 1, demonstrate that compared with the PID and the single-objective optimization methods, energy consumption can be significantly reduced by using the proposed method while still assuring water quality.

参考文献/References:

[1] ALEX J, BENEDETTI L, COPP J, et al. Benchmark simulation model No.1[R]. London:Lund University, 2008.
[2] OLSSON G. ICA and me-a subjective review[J]. Water research, 2012, 46(6):1585-1624.
[3] HAMITLON R, BRAUN B, DARE R, et al. Control issues and challenges in wastewater treatment plants[J]. IEEE control systems magazine, 2006, 26(4):63-69.
[4] HOLENDA B, DOMOKOS E, RéDEY Á, et al. Dissolved oxygen control of the activated sludge wastewater treatment process using model predictive control[J]. Computers & chemical engineering, 2008, 32(6):1270-1278.
[5] O’BRIEN M, MACK J, LENNOX B, et al. Model predictive control of an activated sludge process:A case study[J]. Control engineering practice, 2011, 19(1):54-61.
[6] DUZINKIEWICZ K, BRDYS M A, KUREK W, et al. Genetic hybrid predictive controller for optimized dissolved-oxygen tracking at lower control level[J]. IEEE transactions on control systems technology, 2009, 17(5):1183-1192.
[7] QIAO Junfei, BO Yingchun, CHAI Wei, et al. Adaptive optimal control for a wastewater treatment plant based on a data-driven method[J]. Water science and technology, 2013, 67(10):2314-2320.
[8] GUERRERO J, GUISASOLA A, COMAS J, et al. Multi-criteria selection of optimum WWTP control setpoints based on microbiology-related failures, effluent quality and operating costs[J]. Chemical engineering journal, 2012, 188:23-29.
[9] 韩广, 乔俊飞, 韩红桂, 等. 基于Hopfield神经网络的污水处理过程优化控制[J]. 控制与决策, 2014, 29(11):2085-2088. HAN Guang, QIAO Junfei, HAN Honggui, et al. Optimal control for wastewater treatment process based on Hopfield neural network[J]. Control and decision, 2014, 29(11):2085-2088.
[10] BéRAUD B, STEYER J P, LEMOINE C, et al. Towards a global multi objective optimization of wastewater treatment plant based on modeling and genetic algorithms[J]. Water science and technology, 2007, 56(9):109-116.
[11] VRECKO D, HVALA N, KOCIJAN J, et al. System analysis for optimal control of a wastewater treatment benchmark[J]. Water science and technology, 2001, 43(7):199-206.
[12] CADET C, BéTEAU J F, HERNANDEZ S C. Multicriteria control strategy for cost/quality compromise in wastewater treatment plants[J]. Control engineering practice, 2004, 12(3):335-347.
[13] HAKANEN J, SAHLSTEDT K, MIETTINEN K. Wastewater treatment plant design and operation under multiple conflicting objective functions[J]. Environmental modelling & software, 2013, 46:240-249.
[14] ZHANG Rui, XIE Wenming, YU Hanqing, et al. Optimizing municipal wastewater treatment plants using an improved multi-objective optimization method[J]. Bioresource technology, 2014, 157:161-165.
[15] DEB K, PRATAP A, AGARWAL S, et al. A fast and elitist multiobjective genetic algorithm:NSGA-Ⅱ[J]. IEEE transactions on evolutionary computation, 2002, 6(2):182-197.

相似文献/References:

[1]丁永生.计算智能的新框架:生物网络结构[J].智能系统学报,2007,2(02):26.
 DING Yong-sheng.A new scheme for computational intelligence: bio-network architecture[J].CAAI Transactions on Intelligent Systems,2007,2(5):26.
[2]徐 雄.人工情感的进化控制系统实现[J].智能系统学报,2008,3(02):135.
 XU Xiong.Implementation of an evolutionary control system based on artificial emotion[J].CAAI Transactions on Intelligent Systems,2008,3(5):135.
[3]周孔丹,李 宁,鲁华祥.单电子电路的鲁棒性研究[J].智能系统学报,2008,3(03):195.
 ZHOU Kong-dan,LI Ning,LU Hua-xiang.Researching the robustness of single electron devices[J].CAAI Transactions on Intelligent Systems,2008,3(5):195.
[4]王 艳,曾建潮.多目标微粒群优化算法综述[J].智能系统学报,2010,5(05):377.[doi:10.3969/j.issn.1673-4785.2010.05.001]
 WANG Yan,ZENG Jian-chao.A survey of a multiobjective particle swarm optimization algorithm[J].CAAI Transactions on Intelligent Systems,2010,5(5):377.[doi:10.3969/j.issn.1673-4785.2010.05.001]
[5]张米娜,韩红桂,乔俊飞.前馈神经网络结构动态增长-修剪方法[J].智能系统学报,2011,6(02):101.
 ZHANG Mina,HAN Honggui,QIAO Junfei.Research on dynamic feedforward neural network structure based on growing and pruning methods[J].CAAI Transactions on Intelligent Systems,2011,6(5):101.
[6]张文辉,高九州,马静,等.漂浮基空间机器人的径向基神经网络鲁棒自适应控制[J].智能系统学报,2011,6(02):114.
 ZHANG Wenhui,GAO Jiuzhou,MA Jing,et al.The RBF neural network robust adaptive control of a freefloating space robot[J].CAAI Transactions on Intelligent Systems,2011,6(5):114.
[7]薄迎春,乔俊飞,杨刚.一种多模块协同参与的神经网络[J].智能系统学报,2011,6(03):225.
 BO Yingchun,QIAO Junfei,YANG Gang.A multimodule cooperative neural network[J].CAAI Transactions on Intelligent Systems,2011,6(5):225.
[8]蒲兴成,张军,张毅.基于神经网络的改进行为协调控制及其在智能轮椅路径规划中的应用[J].智能系统学报,2011,6(05):456.
 PU Xingcheng,ZHANG Jun,ZHANG Yi.Modified behavior coordination for intelligent wheelchair path planning based on a neural network[J].CAAI Transactions on Intelligent Systems,2011,6(5):456.
[9]段海庆,朱齐丹.基于反步自适应神经网络的船舶航迹控制[J].智能系统学报,2012,7(03):259.
 DUAN Haiqing,ZHU Qidan.Trajectory tracking control of ships based onan adaptive backstepping neural network[J].CAAI Transactions on Intelligent Systems,2012,7(5):259.
[10]乔俊飞,逄泽芳,韩红桂.基于改进粒子群算法的污水处理过程神经网络优化控制[J].智能系统学报,2012,7(05):429.
 QIAO Junfei,PANG Zefang,HAN Honggui.Neural network optimal control for wastewater treatment processbased on APSO[J].CAAI Transactions on Intelligent Systems,2012,7(5):429.

备注/Memo

备注/Memo:
收稿日期:2015-12-12。
基金项目:国家杰出青年科学基金项目(61225016);国家自然科学基金项目(61533002,61203099);北京市自然科学基金项目(4122006).
作者简介:张伟,女,1978年生,副教授,主要研究方向为污水处理系统的智能控制与优化控制;乔俊飞,男,1968年生,教授,博士生导师,主要研究方向为智能信息处理、智能控制理论与应用。国家杰出青年基金获得者,教育部长江学者特聘教授,教育部新世纪优秀人才。获教育部科技进步奖一等奖和北京市科学技术奖三等奖各1项。发表学术论文近100篇,其中被SCI检索18篇,EI检索60篇,获得授权发明专利20项。
通讯作者:张伟.E-mail:zwei1563@126.com
更新日期/Last Update: 1900-01-01