城市污水处理过程动态多目标智能优化控制研究

韩红桂; 张璐; 卢薇; 乔俊飞

doi:10.16383/j.aas.c190154

城市污水处理过程动态多目标智能优化控制研究

doi: 10.16383/j.aas.c190154

韩红桂^1,,
张璐^1,,
卢薇^2,,
乔俊飞^1,

1.
北京工业大学信息学部, 计算智能与智能系统北京市重点实验室北京 100124
2.
中国石化青岛安全工程研究院环境保护研究室青岛 266100

基金项目: 国家自然科学基金(61890931, 61622301, 61533002), 北京自然科学基金(4172005)资助

详细信息

作者简介:
韩红桂：北京工业大学信息学部教授. 主要研究方向为城市污水处理过程智能优化控制, 神经网络结构设计与优化. 本文通信作者. E-mail: rechardhan@bjut.edu.cn

张璐：北京工业大学信息学部博士研究生. 2014年获得菏泽学院控制科学与工程学士学位. 主要研究方向为城市污水处理过程多目标智能优化控制. E-mail: zhlulu1991@163.com

卢薇：中国石化青岛安全工程研究院, 环境保护研究室助理工程师. 主要研究方向为神经网络, 智能系统, 多目标优化. E-mail: luweiwei@emails.bjut.edu.cn

乔俊飞：北京工业大学信息学部教授. 主要研究方向为城市污水处理过程智能优化控制, 神经网络结构设计与优化. E-mail: junfeq@bjut.edu.cn

计量
- 文章访问数: 1651
- HTML全文浏览量: 500
- PDF下载量: 622
- 被引次数: 0
出版历程
- 收稿日期: 2019-03-13
- 录用日期: 2019-07-10
- 网络出版日期: 2021-01-18
- 刊出日期: 2021-04-02

Research on Dynamic Multiobjective Intelligent Optimal Control for Municipal Wastewater Treatment Process

1.
Faculty of Information Technology, Beijing University of Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing 100124
2.
Environmental Protection Laboratory, Sinopec Research Institute of Safety Engineering, Qingdao 266100

Funds: Supported by National Natural Science Foundation of China (61890931, 61622301, 61533002) and Natural Science Foundation of Beijing (4172005)

More Information

Author Bio:
HAN Hong-Gui　Professor at the Faculty of Information Technology, Beijing University of Technology. His research interest covers intelligent control of wastewater treatment process, structure design and optimization of neural networks. Corresponding author of this paper

ZHANG Lu　Ph.D. candidate at the Faculty of Information Technology, Beijing University of Technology. She received her bachelor degree from Heze University in 2014. Her research interest covers multi-objective intelligent control of wastewater treatment process

LU Wei　Assistant engineer at the Environmental Protection Laboratory, Sinopec Research Institute of Safety Engineering. Her current research interest covers neural networks, intelligent systems, and multiobjective optimization

QIAO Jun-Fei　Professor at the Faculty of Information Technology, Beijing University of Technology. His research interest covers intelligent control of wastewater treatment process, structure design and optimization of neural networks

摘要

摘要:
城市污水处理过程(Municipal wastewater treatment process, MWWTP)是一个典型的复杂流程工业过程, 其优化运行涉及到多个动态性能指标. 为了实现城市污水处理运行过程的优化控制, 本文提出了一种城市污水处理过程动态多目标智能优化控制方法(Dynamic multiobjective intelligent optimal control, DMIOC). 首先, 建立了一种基于自适应核函数的动态性能指标模型, 实现了城市污水处理关键性能指标的准确描述; 其次, 设计了一种基于自适应飞行参数调整机制的动态多目标粒子群优化算法(Dynamic multiobjective particle swarm optimization, DMOPSO), 可有效平衡粒子的多样性和收敛性, 完成了溶解氧和硝态氮优化设定值的实时获取; 最后, 利用多回路PID控制方法对溶解氧和硝态氮优化设定值进行控制, 实现了城市污水处理过程安全稳定运行. 将提出的DMIOC应用于城市污水处理基准仿真平台, 实验结果显示: DMIOC 能够提高溶解氧和硝态氮的控制效果, 实现城市污水处理过程出水水质达标, 并降低运行成本.
- 城市污水处理过程 /
- 动态多目标智能优化控制 /
- 动态多目标粒子群优化 /
- 优化设定值
Abstract:
Municipal wastewater treatment process (MWWTP) is a typical complex industrial process, where multiple dynamic performance indices are contained in the optimal operational process. To realize the optimal operational control of MWWTP, a dynamic multiobjective intelligent optimal control (DMIOC) strategy is proposed in this paper. First, dynamic performance index model based on adaptive kernel function was established. Then the dynamic characteristics of performance indices could be accurately captured. Second, a dynamic multiobjective particle swarm optimization (DMOPSO) algorithm, based on an adaptive flight parameter adjustment mechanism, was designed. It can efficiently balance the diversity and convergence of the particles. Then the real-time optimal set-points of the control variables dissolved oxygen and nitrate nitrogen could be obtained. Third, a multi-loop PID control strategy was utilized to realize the control of the optimal set-points of dissolved oxygen and nitrate nitrogen. The proposed DMIOC strategy was tested in the benchmark simulation model to evaluate its effectiveness. The results demonstrate that the proposed DMIOC strategy can realize the dynamic optimal control of the control variables dissolved oxygen and nitrate nitrogen, guarantee the effluent qualities in the limits and reduce the operation cost.

HTML全文

图 1 城市污水处理过程动态多目标智能优化控制架构

Fig. 1 The scheme of DMIOC for municipal wastewater treatment process

下载: 全尺寸图片幻灯片

图 2 不同优化算法的逼近效果

Fig. 2 The approximation effect of different optimization algorithms

下载: 全尺寸图片幻灯片

图 3 平均PE值

Fig. 3 Average values of PE

下载: 全尺寸图片幻灯片

图 4 平均AE值

Fig. 4 Average values of AE

下载: 全尺寸图片幻灯片

图 5 平均EQ值

Fig. 5 Average values of EQ

下载: 全尺寸图片幻灯片

图 6 S_O的控制效果

Fig. 6 Control results of S_O

下载: 全尺寸图片幻灯片

图 7 S_NO的控制效果

Fig. 7 Control results of S_NO

下载: 全尺寸图片幻灯片

图 8 $S_{\rm{O}}$和$S_{{\rm{NO}}}$的误差值

Fig. 8 Control errors of $S_{\rm{O}}$ and $S_{{\rm{NO}}}$

下载: 全尺寸图片幻灯片

表 1 不同优化算法的性能比较

Table 1 The approximation effect of different optimization algorithms

函数	指标	DMOPSO	Pccs−AMOPSO	Cluster−MOPSO	NSGANSGA
ZDT3	GD	3.982E−03	3.323E−03	1.047E−02	5.834E−03
	std	3.623E−03	9.951E−05	7.052E−02	2.020E−04
	SP	7.025E−02	7.159E−02	7.784E−02	9.222E−02
	std	7.171E−03	4.054E−03	4.362E−02	8.415E−03
ZDT4	GD	4.147E−03	7.971E−03	3.989E+00	1.655E−02
	std	2.980E−04	1.470E−03	2.616E+00	3.174E−02
	SP	2.645E−02	2.881E−02	7.692E−02	3.838E−02
	std	4.998E−04	5.132E−04	1.931E−02	3.837E−03
DTLZ2	GD	6.595E−02	6.143E−02	1.265E−01	1.059E−01
	std	7.241E−04	1.898E−03	1.683E−02	8.383E−03
	SP	2.399E−01	3.411E−01	5.762E−01	4.162E−01
	std	9.732E−03	1.242E−02	4.472E−02	3.655E−02
DTLZ7	GD	1.215E−02	4.277E−02	4.022E−02	1.799E−02
	std	8.600E−04	9.506E−04	2.068E−03	1.294E−03
	SP	3.758E−01	3.988E−01	3.902E−01	4.191E−01
	std	7.593E−03	8.417E−03	1.293E−02	7.961E−03

下载: 导出CSV

表 2 不同优化算法的计算时间比较 (s)

Table 2 Calculation time comparison of different optimization methods (s)

函数	DMOPSO	PccsAMOPSO	ClusterMOPSO	NSGA
ZDT3	134	138	141	139
ZDT4	140	144	142	148
DTLZ2	249	280	230	287
DTLZ7	260	287	250	301

下载: 导出CSV

表 3 不同优化控制方法优化性能比较

Table 3 Comparison of optimization performance of different optimal control methods

方法	PE (kW·h)	AE (kW·h)	EQ (kg poll)
DMIOC	249	3630	6616
clusterMOPSO-OC	254	3691	7291
pccsAMOPSO-OC	255	3687	7220
NSGA+PI-OC	243	3694	7214

下载: 导出CSV

表 4 不同优化控制方法控制性能比较

Table 4 Comparison of control performance of different optimal control methods

方法	IAE (mg/L)	S_NH (mg/L)	SS (mg/L)
DMIOC	0.097	3.08	12.15
clusterMOPSO-OC	0.122	3.23	12.45
pccsAMOPSO-OC	0.012	3.31	13.25
NSGA+PI-OC	0.100	3.12	12.52

下载: 导出CSV

参考文献(33)

[1]	韩红桂, 伍小龙, 张璐, 乔俊飞. 城市污水处理过程异常工况识别和抑制研究. 自动化学报, 2018, 44(11): 1971−1984 Han Hong-Gui, Wu Xiao-Long, Zhang Lu, Qiao Jun-Fei. Identiflcation and suppression of abnormal conditions in municipal wastewater treatment process. Acta Automatica Sinica, 2018, 44(11): 1971−1984
[2]	Han H G, Wu X L, Qiao J F. A self-organizing sliding-mode controller for wastewater treatment processes. IEEE Transactions on Control Systems Technology, 2019, 27(4): 1480−1491 doi: 10.1109/TCST.87
[3]	栗三一, 乔俊飞, 李文静. 污水处理决策优化控制. 自动化学报, 2018, 44(12): 2198−2209 Li San-Yi, Qiao Jun-Fei, Li Wen-Jing. Advanced decision and optimization control for wastewater treatment plants. Acta Automatica Sinica, 2018, 44(12): 2198−2209
[4]	Han H G, Qiao J F. Nonlinear model-predictive control for industrial processes: An application to wastewater treatment process. IEEE Transactions on Industrial Electronics, 2013, 61(4): 1970−1982
[5]	Castelletviciano L, Torregrossa D, Hernandezsancho F. The relevance of the design characteristics to the optimal operation of wastewater treatment plants: Energy cost assessment. Journal of Environmental Management, 2018, 222: 275−283
[6]	乔俊飞, 韩改堂, 周红标. 基于知识的污水生化处理过程智能优化方法. 自动化学报, 2017, 43(6): 1038−1046 Qiao Jun-Fei, Han Gai-Tang, Zhou Hong-Biao. Knowledge-based intelligent optimal control for wastewater biochemical treatment process. Acta Automatica Sinica, 2017, 43(6): 1038−1046
[7]	丁进良, 杨翠娥, 陈远东, 柴天佑. 复杂工业过程智能优化决策系统的现状与展望. 自动化学报, 2018, 44(11): 1931−1943 Ding Jin-Liang, Yang Cui-E, Chen Yuan-Dong, Chai Tian-You. Research progress and prospects of intelligent optimization decision making in complex industrial process. Acta Automatica Sinica, 2018, 44(11): 1931−1943
[8]	辛斌, 陈杰, 彭志红. 智能优化控制: 概述与展望. 自动化学报, 2013, 39(11): 1831−1848 Xin Bin, Chen Jie, Peng Zhi-Hong. Intelligent optimized control: overview and prospect. Acta Automatica Sinica, 2013, 39(11): 1831−1848
[9]	Jeong E, Kim H W, Nam J Y, Shin H S. Enhancement of bioenergy production and effluent quality by integrating optimized acidification with submerged anaerobic membrane bioreactor. Bioresource Technology, 2010, 101(1): S7−S12 doi: 10.1016/j.biortech.2009.04.064
[10]	Xie W M, Zhang R, Li W W, Ni B J, Fang F, Sheng G P, Yu H Q, Song J, Le D Z, Bi X J, Liu C Q, Yang M. Simulation and optimization of a full-scale carrousel oxidation ditch plant for municipal wastewater treatment. Biochemical Engineering Journal, 2011, 56(1−2): 9−16 doi: 10.1016/j.bej.2011.04.010
[11]	Alsina F X, Arnell M, Amerlinck Y, Corominas L, Gernaey K V, Guo L, Lindblom E, Nopens I, Porro J, Shaw A, Snip L, Vanrolleghem P A, Jeppsson U. Balancing effluent quality, economic cost and greenhouse gas emissions during the evaluation of (plant-wide) control/operational strategies in WWTPs. Science of the Total Environment, 2014, 466−467(1): 616−624
[12]	Yang Y, Yang J K, Zuo J L, Li Y, He S, Yang X, Zhang K. Study on two operating conditions of a full-scale oxidation ditch for optimization of energy consumption and effluent quality by using CFD model. Water Research, 2011, 45(11): 3439−3452 doi: 10.1016/j.watres.2011.04.007
[13]	Santin I, Pedret C, Vilanova R. Applying variable dissolved oxygen set point in a two level hierarchical control structure to a wastewater treatment process. Journal of Process Control, 2015, 28: 40−55 doi: 10.1016/j.jprocont.2015.02.005
[14]	Hakanen J, Sahlstedt K, Miettinen K. Wastewater treatment plant design and operation under multiple conflicting objective functions. Environmental Modelling and Software, 2013, 46(7): 240−249
[15]	Asadi A, Verma A, Yang K. Wastewater treatment aeration process optimization: A data mining approach. Journal of Environmental Management, 2016, 203(2): 630−639
[16]	Durrenmatt D J. Data mining and data-driven modeling approaches to support wastewater treatment plant operation. Environmental Modelling and Software, 2011, 30(5): 47−56
[17]	丛秋梅, 柴天佑, 余文. 污水处理过程的递阶神经网络建模. 控制理论与应用, 2009, 26(1): 8−14 Cong Qiu-Mei, Chai Tian-You, Yu Wen. Modeling wastewater treatment plant via hierarchical neural networks. Control Theory and Applications, 2009, 26(1): 8−14
[18]	Qiao J F, Zhang W. Dynamic multi-objective optimization control for wastewater treatment process. Neural Computing and Applications, 2018, 29(11): 1261−1271
[19]	Hreiz R, Latifi M A, Roche N. Optimal design and operation of activated sludge processes: state-of-the-art. Chemical Engineering Journal, 2015, 281: 900−920 doi: 10.1016/j.cej.2015.06.125
[20]	Hreiz R, Roche N, Benyahia B, Latifi M A. Multi-objective optimal control of small-size wastewater treatment plants. Chemical Engineering Research and Design, 2015, 102: 345−353
[21]	Ozturk M C, Serrat F M, Teymour F. Optimization of aeration profiles in the activated sludge process. Chemical Engineering Science, 2016, 139: 1−14 doi: 10.1016/j.ces.2015.09.007
[22]	Vega P, Revollar S, Francisco M, Martin J M. Integration of set point optimization techniques into nonlinear MPC for improving the operation of WWTPs. Computers and Chemical Engineering, 2014, 68(8): 78−95
[23]	Schluter M, Egea J A, Antelo L T, Alonso A A, Banga J R. An extended ant colony optimization algorithm for integrated process and control system design. Industrial and Engineering Chemistry Research, 2009, 48(14): 6723−6738
[24]	Cai X, Yang Z, Fan Z, Zhang Q F. Decomposition- based-sorting and angle-based-selection for evolutionary multiobjective and many-objective optimization. IEEE Transactions on Cybernetics, 2017, 47(9): 2824−2837 doi: 10.1109/TCYB.2016.2586191
[25]	Yetilmezsoy K. Integration of kinetic modeling and desirability function approach for multi-objective optimization of UASB reactor treating poultry manure wastewater. Bioresource Technology, 2012, 118: 89−101 doi: 10.1016/j.biortech.2012.05.088
[26]	Guerrero J, Guisasola A, Comas J, Roda I R, Baeza J A. Multi-criteria selection of optimum WWTP control setpoints based on microbiology-related failures, effluent quality and operating costs. Chemical Engineering Journal, 2012, 188(8): 23−29
[27]	Beraud B, Steyer J P, Lemoine C, Latrille E, Manic G, Printemps-Vacquier C. Towards a global multi objective optimization of wastewater treatment plant based on modeling and genetic algorithms. Water Science and Technology, 2007, 56(9): 109−116
[28]	Yen G G, Leong W F. Dynamic multiple swarms in multiobjective particle swarm optimization. IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 2009, 39(4): 890−911 doi: 10.1109/TSMCA.2009.2013915
[29]	Sweetapple C, Fu G, Butler D. Multi-objective optimisation of wastewater treatment plant control to reduce greenhouse gas emissions. Water Research, 2014, 55(55C): 52−62
[30]	Qiao J F, Hou Y, Zhang L, Han H G. Adaptive fuzzy neural network control of wastewater treatment process with multiobjective operation. Neurocomputing, 2018, 67: 467−478
[31]	Hu W, Yen G G. Adaptive multiobjective particle swarm optimization based on parallel cell coordinate system. IEEE Transactions on Evolutionary Computation, 2015, 19(1): 1−18 doi: 10.1109/TEVC.2013.2296151
[32]	Chen W L, Yao C H, Lu X W. Optimal design activated sludge process by means of multi-objective optimization: case study in benchmark simulation model 1 (BSM1). Water Science and Technology, 2014, 69(10): 2052−2058
[33]	Chakraborty P, Das S, Roy G G, Abraham A. On convergence of the multi-objective particle swarm optimizers. Information Sciences, 2011, 181(8): 1411−1425 doi: 10.1016/j.ins.2010.11.036