知识和数据驱动的污水处理反硝化脱氮过程协同优化控制

韩红桂; 王玉爽; 刘峥; 孙浩源; 乔俊飞

doi:10.16383/j.aas.c230695

知识和数据驱动的污水处理反硝化脱氮过程协同优化控制

doi: 10.16383/j.aas.c230695

韩红桂^{1, 2, 3,},
王玉爽^{1, 2, 3,},
刘峥^{1, 2, 3,},
孙浩源^{1, 2, 3,},
乔俊飞^{1, 2,}

1.
北京工业大学信息学部北京 100124
2.
计算智能与智能系统北京市重点实验室北京 100124
3.
数字社区教育部工程研究中心北京 100124

基金项目: 国家自然科学基金(62125301, 62021003, 62103010, 62303024), 国家重点研发项目(2022YFB3305800-5), 中国博士后科学基金(2022M720319), 北京市自然科学基金(KZ202110005009), 青年北京学者项目(037), 北京市博士后工作经费资助项目(2023-zz-91)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

王玉爽：北京工业大学信息学部博士研究生. 主要研究方向为城市污水处理过程智能优化控制, 协同优化控制. E-mail: wangyushuang@emails.bjut.edu.cn

刘峥：北京工业大学信息学部讲师. 主要研究方向为神经网络, 智能系统, 过程系统的建模和控制. E-mail: liuzheng@bjut.edu.cn

孙浩源：北京工业大学信息学部讲师. 主要研究方向为城市污水处理网络化控制, 随机采样控制. E-mail: sunhaoyuan@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: adqiao@bjut.edu.cn

计量
- 文章访问数: 41
- HTML全文浏览量: 26
- 被引次数: 0
出版历程
- 收稿日期: 2023-11-09
- 录用日期: 2024-01-10
- 网络出版日期: 2024-03-25

Knowledge-data-driven Cooperative Optimal Control for Wastewater Treatment Denitrification Process

HAN Hong-Gui^{1, 2, 3
,},
WANG Yu-Shuang^{1, 2, 3
,},
LIU Zheng^{1, 2, 3
,},
SUN Hao-Yuan^{1, 2, 3
,},
QIAO Jun-Fei^{1, 2
,}

1.
Faculty of Information Technology, Beijing University of Technology, Beijing 100124
2.
Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing 100124
3.
Engineering Research Center of Digital Community, Ministry of Education, Beijing 100124

Funds: Supported by National Natural Science Foundation of China (62125301, 62021003, 62103010, 62303024), National Key Research and Development Program (2022YFB3305800-5), China Postdoctoral Science Foundation (2022M720319), Beijing Natural Science Foundation (KZ202110005009), The Youth Beijing Scholars Program (037), and Beijing Postdoctoral Research Foundation (2023-zz-91)

More Information

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

WANG Yu-Shuang　Ph.D. candidate at the Faculty of Information Technology, Beijing University of Technology. Her research interest covers intelligent optimal control of municipal wastewater treatment process, cooperative optimal control

LIU Zheng　Lecturer at the Faculty of Information Technology, Beijing University of Technology. His research interest covers neural networks, intelligent systems, modeling and control in process systems

SUN Hao-Yuan　Lecturer at the Faculty of Information Technology, Beijing University of Technology. His research interest covers networked control of municipal wastewater treatment process, stochastic sampled-data control

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

摘要

摘要: 为了有效提升城市污水处理过程的脱氮效果, 提出了一种知识和数据驱动的反硝化脱氮过程协同优化控制(Knowledge-data-driven cooperative optimal control, KDDCOC). 本文工作主要有以下两点: 首先, 建立了一种基于自适应知识核函数的协同优化控制目标模型, 动态描述出水水质以及泵送能耗、关键变量的协同关系; 其次, 提出了一种知识引导的协同优化算法(Knowledge guide-based cooperative optimization algorithm, KGCO), 快速准确求解硝态氮优化设定值, 提高KDDCOC的响应速度. KDDCOC利用了比例积分微分控制器对硝态氮优化设定值进行跟踪. 将提出的KDDCOC应用于城市污水处理过程基准仿真模型1, 实验结果表明该方法能够提高出水水质, 降低运行能耗, 有效改善脱氮效果.
- 反硝化脱氮过程 /
- 知识和数据驱动 /
- 协同优化控制 /
- 自适应知识核函数 /
- 知识引导的协同优化算法
Abstract: In order to effectively improve the performance of the wastewater treatment denitrification process, a knowledge-data-driven cooperative optimal control (KDDCOC) is proposed. The main work of this paper includes the following two points: First, a cooperative optimal control objective model, based on adaptive knowledge kernel function, is designed to dynamically describe the cooperative relationship between effluent quality, pumping energy consumption, and key variables; Second, a knowledge guide-based cooperative optimization algorithm (KGCO) is proposed to quickly and accurately obtain the optimum set points of nitrate nitrogen and improve the response speed of KDDCOC. A proportional integral derivative controller is used to track the optimum set points of nitrate nitrogen. The proposed KDDCOC is applied to the benchmark simulation model 1 for wastewater treatment process. The experimental results indicate that KDDCOC can improve the effluent quality, reduce the energy consumption, and effectively improve the removal of nitrogen.

HTML全文

图 1 KDDCOC结构

Fig. 1 Schematic diagram of knowledge-data-driven cooperative optimal control

下载: 全尺寸图片幻灯片

图 2 KDDCOC流程图

Fig. 2 Flow chart of knowledge-data-driven cooperative optimal control

下载: 全尺寸图片幻灯片

图 3 干燥天气下$S_{NO}$的优化控制结果和$S_{NO}$的控制误差

Fig. 3 Optimal Control results of $S_{NO}$ and control errors of $S_{NO}$ in the dry weather

下载: 全尺寸图片幻灯片

图 4 干燥天气下的$Q_a$

Fig. 4 Optimal control results of $Q_a$ in the dry weather

下载: 全尺寸图片幻灯片

图 5 干燥天气下每天的EQ

Fig. 5 The values of EQ in the dry weather

下载: 全尺寸图片幻灯片

图 7 干燥天气下每天的TC

Fig. 7 The values of TC in the dry weather

下载: 全尺寸图片幻灯片

图 6 干燥天气下每天的PE

Fig. 6 The values of PE in the dry weather

下载: 全尺寸图片幻灯片

图 8 干燥天气下各出水组分的浓度

Fig. 8 Effluent parameters in the dry weather

下载: 全尺寸图片幻灯片

图 9 干燥天气下的$ N_{tot}$

Fig. 9 $ N_{tot}$ in the dry weather

下载: 全尺寸图片幻灯片

图 10 暴雨天气下$S_{NO}$的优化控制结果和$S_{NO}$的控制误差

Fig. 10 Optimal Control results of $S_{NO}$ and control errors of $S_{NO}$ in the storm weather

下载: 全尺寸图片幻灯片

图 16 暴雨天气下的$ N_{tot}$

Fig. 16 $ N_{tot}$ in the storm weather

下载: 全尺寸图片幻灯片

图 11 暴雨天气下的$Q_a$

Fig. 11 Optimal control results of $Q_a$ in the storm weather

下载: 全尺寸图片幻灯片

图 12 暴雨天气下每天的EQ

Fig. 12 The values of EQ in the storm weather

下载: 全尺寸图片幻灯片

图 13 暴雨天气下每天的PE

Fig. 13 The values of PE in the storm weather

下载: 全尺寸图片幻灯片

图 14 暴雨天气下每天的TC

Fig. 14 The values of TC in the storm weather

下载: 全尺寸图片幻灯片

图 15 暴雨天气下各出水组分的浓度

Fig. 15 Effluent parameters in the storm weather

下载: 全尺寸图片幻灯片

表 1 干燥天气下不同优化控制方法的详细性能

Table 1 Detailed performance of different optimal control methods in the dry weather

天气	方法	PE (kW$\cdot$h)	EQ (kg poll.units)	TC (€)	IAE
干燥	KDDCOC	237	6 543	700.99	0.043
	KDDCOC-$\lambda_1$	251	6 631	712.55	0.057
	KDDCOC-$\lambda_2$	262	6 595	711.11	0.061
	DMOPSO-OC^[20]	258	6 654	716.23	0.092
	DMOOC^[21]	284	6 619	717.85	0.142
	PID	295	6 768	734.92	0.210

下载: 导出CSV

表 2 暴雨天气下不同优化控制方法的详细性能

Table 2 Detailed performance of different optimal control methods in the storm weather

天气	方法	PE (kW$\cdot$h)	EQ (kg poll.units)	TC (€)	IAE
暴雨	KDDCOC	221	7 338	777.34	0.097
	KDDCOC-$\lambda_1$	232	7 449	790.60	0.112
	KDDCOC-$\lambda_2$	244	7 381	786.17	0.106
	DMOPSO-OC^[20]	239	7 645	811.58	0.123
	DMOOC^[21]	264	7 536	805.61	0.204
	PID	295	7 773	835.42	0.248

下载: 导出CSV

参考文献(32)

[1]	韩红桂, 张璐, 卢薇, 乔俊飞. 城市污水处理过程动态多目标智能优化控制研究. 自动化学报, 2021, 47(3): 620-629 Han Hong-Gui, Zhang Lu, Lu Wei, Qiao Jun-Fei. Research on dynamic multiobjective intelligent optimal control for municipal wastewater treatment process. Acta Automatica Sinica, 2021, 47(3): 620-629
[2]	杜睿, 彭永臻. 城市污水生物脱氮技术变革: 厌氧氨氧化的研究与实践新进展. 中国科学: 技术科学, 2022, 52(3): 389-402 doi: 10.1360/SST-2020-0407 Du Rui, Peng Yong-Zhen. Technical revolution of biological nitrogen removal from municipal wastewater: recent advances in anammox research and application. Scientia Sinica Technologica, 2022, 52(3): 389-402 doi: 10.1360/SST-2020-0407
[3]	韩红桂, 张琳琳, 伍小龙, 乔俊飞. 数据和知识驱动的城市污水处理过程多目标优化控制. 自动化学报, 2021, 47(11): 2538-2546 Han Hong-Gui, Zhang Lin-Lin, Wu Xiao-Long, Qiao Jun-Fei. Data-knowledge driven multiobjective optimal control for municipal wastewater treatment process. Acta Automatica Sinica, 2021, 47(11): 2538-2546
[4]	杨翠丽, 武战红, 韩红桂, 乔俊飞. 城市污水处理过程优化设定方法研究进展. 自动化学报, 2020, 46(10): 2092-2108 Yang Cui-Li, Wu Zhan-Hong, Han Hong-Gui, Qiao Jun-Fei. Perspectives on optimal setting methods for municipal wastewater treatment processes. Acta Automatica Sinica, 2020, 46(10): 2092-2108
[5]	阳春华, 孙备, 李勇刚, 黄科科, 桂卫华. 复杂生产流程协同优化与智能控制. 自动化学报, 2023, 49(3): 528-539 Yang Chun-Hua, Sun Bei, Li Yong-Gang, Huang Ke-Ke, Gui Wei-Hua. Cooperative optimization and intelligent control of complex production processes. Acta Automatica Sinica, 2023, 49(3): 528-539
[6]	韩红桂, 秦晨辉, 孙浩源, 乔俊飞. 城市污水处理过程自适应滑模控制. 自动化学报, 2023, 49(5): 1010-1018 Han Hong-Gui, Qin Chen-Hui, Sun Hao-Yuan, Qiao Jun-Fei. Adaptive sliding mode control for municipal wastewater treatment process. Acta Automatica Sinica, 2023, 49(5): 1010-1018
[7]	Borja S, Albert G, Xavier F, Ulf J, Juan A B. A plant-wide model describing GHG emissions and nutrient recovery options for water resource recovery facilities. Water Research, 2022, 215: 118223 doi: 10.1016/j.watres.2022.118223
[8]	Reifsnyder S, Garrido-Baserba M, Cecconi F, Wong L, Ackman P, Melitas N, et al. Relationship between manual air valve positioning, water quality and energy usage in activated sludge processes. Water Research, 2020, 173: 115537 doi: 10.1016/j.watres.2020.115537
[9]	Plosz B G. Optimization of the activated sludge anoxic reactor configuration as a means to control nutrient removal kinetically. Water Research, 2007, 41(8): 1763-1773 doi: 10.1016/j.watres.2007.01.007
[10]	Borzooei S, Campo G, Cerutti A, Meucci L, Panepinto D, Riggio V, et al. Optimization of the wastewater treatment plant: From energy saving to environmental impact mitigation. Science of the Total Environment, 2019, 691: 1182-1189 doi: 10.1016/j.scitotenv.2019.07.241
[11]	Abba S I, Pham Q B, Usman A G, Linh N T T, Aliyu D S, Nguyen Q, et al. Emerging evolutionary algorithm integrated with kernel principal component analysis for modeling the performance of a water treatment plant. Journal of Water Process Engineering, 2020, 33: 101081 doi: 10.1016/j.jwpe.2019.101081
[12]	Feng J, Song W Z, Zhang H G, Wang W. Data-driven robust iterative learning consensus tracking control for MIMO multiagent systems under fixed and iteration-switching topologies. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2022, 52(2): 1331-1344 doi: 10.1109/TSMC.2020.3017289
[13]	Santoso F, Finn A. A data-driven cyber–physical system using deep-learning convolutional neural networks: study on false-data injection attacks in an unmanned ground vehicle under fault-tolerant conditions. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2023, 53(1): 346-356 doi: 10.1109/TSMC.2022.3170071
[14]	Zhang H, Yang C, Shi X Q, Liu H B. Effluent quality prediction in papermaking wastewater treatment processes using dynamic Bayesian networks. Journal of Cleaner Production, 2021, 282: 125396 doi: 10.1016/j.jclepro.2020.125396
[15]	Zeng Y H, Zhang Z J, Kusiak A, Tang F, Wei X P. Optimizing wastewater pumping system with data-driven models and a greedy electromagnetism-like algorithm. Stochastic Environmental Research and Risk Assessment, 2016, 30: 1263-1275 doi: 10.1007/s00477-015-1115-4
[16]	Han H G, Chen C, Sun H Y, Qiao J F. Multiobjective integrated optimal control for nonlinear systems. IEEE Transactions on Cybernetics, 2023, 53(12): 7712-7722 doi: 10.1109/TCYB.2022.3204030
[17]	王凌, 王晶晶. 考虑运输时间的分布式绿色柔性作业车间调度协同群智能优化. 中国科学: 技术科学, 2023, 53(02): 243-257 doi: 10.1360/SST-2021-0355 Wang Lin, Wang Jing-Jing. A cooperative memetic algorithm for the distributed green flexible job shop with transportation time. Scientia Sinica Technologica, 2023, 53(02): 243-257 doi: 10.1360/SST-2021-0355
[18]	Santín I, Pedret C, Vilanova R, Meneses M. Advanced decision control system for effluent violations removal in wastewater treatment plants. Control Engineering Practice, 2016, 49: 60-75 doi: 10.1016/j.conengprac.2016.01.005
[19]	Han H G, Zhang L, Qiao J F. Dynamic optimal control for wastewater treatment process under multiple operating conditions. IEEE Transactions on Automation Science and Engineering, 2023, 20(3): 1907-1919 doi: 10.1109/TASE.2022.3189048
[20]	Han H G, Liu Z, Lu W, Hou Y, Qiao J F. Dynamic MOPSO-based optimal control for wastewater treatment process. IEEE Transactions on Cybernetics, 2021, 51(5): 2518-2528 doi: 10.1109/TCYB.2019.2925534
[21]	Qiao J F, Zhang W. Dynamic multi-objective optimization control for wastewater treatment process. Neural Computing and Applications, 2018, 29: 1261-1271 doi: 10.1007/s00521-016-2642-8
[22]	张伟, 黄卫民. 基于种群分区的多策略自适应多目标粒子群算法. 自动化学报, 2022, 48(10): 2585-2599 Zhang Wei, Huang Wei-Min. Multi-strategy adaptive multi-objective particle swarm optimization algorithm based on swarm partition. Acta Automatica Sinica, 2022, 48(10): 2585-2599
[23]	Watari D, Taniguchi I, Goverde H, Manganiello P, Shirazi E, Catthoor F, et al. Multi-time scale energy management framework for smart PV systems mixing fast and slow dynamics. Applied Energy, 2021, 289: 116671 doi: 10.1016/j.apenergy.2021.116671
[24]	Han H G, Fu S J, Sun H Y, Qiao J F. Data-driven model-predictive control for nonlinear systems with stochastic sampling interval. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2023, 53(5): 3019-3030 doi: 10.1109/TSMC.2022.3220550
[25]	Jiang Y, Li X Y, Qin C W, Xing X Y, Chen Z Y. Improved particle swarm optimization based selective harmonic elimination and neutral point balance control for three-level inverter in low-voltage ride-through operation. IEEE Transactions on Industrial Informatics, 2022, 18(1): 642-652 doi: 10.1109/TII.2021.3062625
[26]	Han H G, Zhang L, Liu H X, Yang C L, Qiao J F. Intelligent optimal control system with flexible objective functions and its applications in wastewater treatment process. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019, 51(6): 3464-3476
[27]	Song M, Sun W, Shahidehpour M, Yan M Y, Cao C C. Multi-time scale coordinated control and scheduling of inverter-based TCLs with variable wind generation. IEEE Transactions on Sustainable Energy, 2021, 12(1): 46-57 doi: 10.1109/TSTE.2020.2971271
[28]	Han H G, Zhang L, Zhang L L, He Z, Qiao J F. Cooperative optimal controller and its application to activated sludge process. IEEE Transactions on Cybernetics, 2021, 51(8): 3938-3951 doi: 10.1109/TCYB.2019.2925143
[29]	Zhou P, Wang X, Chai T Y. Multiobjective operation optimization of wastewater treatment process based on reinforcement self-learning and knowledge guidance. IEEE Transactions on Cybernetics, 2023. 53(11): 6896-6909 doi: 10.1109/TCYB.2022.3164476
[30]	桂卫华, 曾朝晖, 陈晓方, 谢永芳, 孙玉波. 知识驱动的流程工业智能制造. 中国科学: 信息科学, 2020, 50(9): 1345-1360 doi: 10.1360/SSI-2020-0211 Gui Wei-Hua, Zeng Zhao-Hui, Chen Xiao-Fang, Xie Yong-Fang, Sun Yu-Bo. Knowledge-driven process industry smart manufacturing. Scientia Sinica Informationis, 2020, 50(9): 1345-1360 doi: 10.1360/SSI-2020-0211
[31]	Ji M D, Wang J, Samir K K, Wang S Q, Zhang J, Liang S, et al. Water-energy-greenhouse gas nexus of a novel high-rate activated sludge-two-stage vertical up-flow constructed wetland system for low-carbon wastewater treatment. Water Research, 2023, 229: 119491 doi: 10.1016/j.watres.2022.119491
[32]	Han H G, Liu Z, Liu H X, Qiao J F. Knowledge- data-driven model predictive control for a class of nonlinear systems. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021, 51(7): 4492-4504 doi: 10.1109/TSMC.2019.2937002