数据和知识驱动的城市污水处理过程多目标优化控制

韩红桂; 张琳琳; 伍小龙; 乔俊飞

doi:10.16383/j.aas.c210098

数据和知识驱动的城市污水处理过程多目标优化控制

doi: 10.16383/j.aas.c210098

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

基金项目: 国家重点研发项目(2018YFC1900800-5), 国家自然科学基金(61890930-5, 61903010, 62021003), 北京市卓越青年科学家计划项目(BJJWZYJH01201910005020), 北京市自然科学基金(KZ202110005009)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

张琳琳：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. E-mail: zhangllsy@163.com

伍小龙：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过程智能特征建模与智能控制. E-mail: lewis_wxl@sina.com

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: 2329
- HTML全文浏览量: 635
- PDF下载量: 827
- 被引次数: 0
出版历程
- 收稿日期: 2021-02-10
- 录用日期: 2021-05-28
- 网络出版日期: 2021-07-28
- 刊出日期: 2021-11-18

Data-knowledge Driven Multiobjective 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

Funds: Supported by National Key Research and Development Project (2018YFC1900800-5), National Natural Science Foundation of China (61890930-5, 61903010, 62021003), Beijing Outstanding Young Scientist Program (BJJWZYJH01201910005020), and Beijing Natural Science Foundation (KZ202110005009)

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

ZHANG Lin-Lin　Ph. D. candidate at the Faculty of Information Technology, Beijing University of Technology. Her main research interest is intelligent optimal control of municipal wastewater treatment process

WU Xiao-Long　Lecturer at the Faculty of Information Technology, Beijing University of Technology. His research interest covers intelligent feature modeling and intelligent control of municipal wastewater treatment process

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: 城市污水处理过程优化控制是降低能耗的有效手段, 然而, 如何提高出水水质的同时降低能耗依然是当前城市污水处理过程面临的挑战. 围绕上述挑战, 文中提出了一种数据和知识驱动的多目标优化控制(Data-knowledge driven multiobjective optimal control, DK-MOC)方法. 首先, 建立了出水水质、能耗以及系统运行状态的表达关系, 获得了运行过程优化目标模型. 其次, 提出了一种基于知识迁徙学习的动态多目标粒子群优化算法, 实现了控制变量优化设定值的自适应求解. 最后, 将提出的DK-MOC应用于城市污水处理过程基准仿真模型1 (Benchmark simulation model No. 1, BSM1). 结果表明该方法能够实时获取控制变量的优化设定值, 提高了出水水质, 并且有效降低了运行能耗.
- 城市污水处理过程 /
- 数据和知识驱动方法, 多目标优化控制 /
- 知识迁徙学习 /
- 动态多目标粒子群优化
Abstract: The optimal control is an effective method to reduce energy consumption for municipal wastewater treatment process. However, it is still a challenge to improve the effluent qualities and reduce energy consumption simultaneously for the municipal wastewater treatment process. To solve this problem, a data-knowledge driven multiobjective optimal control (DK-MOC) method is proposed in this paper. First, the expression relationship among effluent qualities, energy consumption and system operation state is established to obtain the operational optimal objective model. Second, a dynamic multiobjective particle swarm optimization algorithm, based on knowledge transfer learning method, is proposed to obtain the optimal set-points of control variables adaptively. Finally, the proposed DK-MOC method is applied to the benchmark simulation model No. 1 (BSM1) of the municipal wastewater treatment process. The results demonstrate that this proposed method can obtain the optimal set-points of control variables online, which not only improve the effluent qualities, but also reduce the operation energy consumption effectively.

HTML全文

图 1 DK-MOC的流程图

Fig. 1 The flow chart of DK-MOC

下载: 全尺寸图片幻灯片

图 2 控制变量设定值求解步骤

Fig. 2 The solution procedure of set values of control variables

下载: 全尺寸图片幻灯片

图 3 干旱天气下出水水质建模结果

Fig. 3 The modeling results of effluent quality in dry weather

下载: 全尺寸图片幻灯片

图 4 干旱天气下能耗建模结果

Fig. 4 The modeling results of energy consumption in dry weather

下载: 全尺寸图片幻灯片

图 5 干旱天气下平均出水水质值

Fig. 5 Average values of effluent quality in dry weather

下载: 全尺寸图片幻灯片

图 6 干旱天气下平均能耗值

Fig. 6 Average values of energy consumption in dry weather

下载: 全尺寸图片幻灯片

图 7 干旱天气下溶解氧浓度跟踪性能

Fig. 7 Tracking performance of S_O in dry weather

下载: 全尺寸图片幻灯片

图 8 干旱天气下硝态氮浓度跟踪性能

Fig. 8 Tracking performance of S_NO in dry weather

下载: 全尺寸图片幻灯片

图 9 干旱天气下硝态氮和溶解氧浓度跟踪误差

Fig. 9 Tracking errors of S_NO and S_O in dry weather

下载: 全尺寸图片幻灯片

表 1 干旱天气下能耗和出水水质的测量精度

Table 1 The measurement accuracy of energy consumption and effluent quality in dry weather

模型	EC		EQ
模型	RMSE	PA	RMSE	PA
AKF	0.0082	98.71 %	0.0079	97.06 %
GA-ANN	0.0123	93.36 %	0.0124	95.52 %
LSSVM	0.0115	96.21 %	0.0139	94.31 %
AFNN	0.0079	98.99 %	0.0070	98.73 %

下载: 导出CSV

表 2 阴雨天气下能耗和出水水质的测量精度

Table 2 The measurement accuracy of energy consumption and effluent quality in rainy weather

模型	EC		EQ
模型	RMSE	PA	RMSE	PA
AKF	0.0093	96.60 %	0.0833	97.37 %
GA-ANN	0.0146	95.72 %	0.1002	94.32 %
LSSVM	0.0138	95.74 %	0.0940	96.76 %
AFNN	0.0089	98.88 %	0.0776	98.89 %

下载: 导出CSV

表 3 DK-MOC的出水水质结果

Table 3 Effluent quality results obtained by DK-MOC

水质指标	干旱天气	阴雨天气	排放标准
S_NH(mg·L⁻¹)	3.44	3.89	<4
N_tot (mg·L⁻¹)	17.41	17.01	<18
TSS (mg·L⁻¹)	12.57	13.51	<30
COD (mg·L⁻¹)	47.75	46.53	<100
BOD (mg·L⁻¹)	2.71	2.93	<10

下载: 导出CSV

表 4 不同优化控制策略的比较结果

Table 4 Comparison results of different optimal control strategies

优化控制策略	干旱天气		阴雨天气
优化控制策略	EC (kW·h)	EQ (kg poll. units)	EC (kW·h)	EQ (kg poll. units)
AFNN+NSGAII+PID	4015	8867	4969	9049
AFNN+CMOPSO+PID	4770	8915	4869	9293
AFNN+AMOPSO+PID	3848	7695	3870	7 944
AFNN+KT-DSOPSO+PID	3727	9062	3892	9479
DK-MOC	3 641	7 179	3 821	8106

下载: 导出CSV

参考文献(30)

[1]	Tang R, Wang Y, Yuan S, Wang W, Yue Z, Zhan X, et al. Organoarsenic feed additives in biological wastewater treatment processes: Removal, biotransformation, and associated impacts. Journal of Hazardous Materials, 2021, 406: 124789. doi: 10.1016/j.jhazmat.2020.124789
[2]	Iratni A, Chang N. Advances in control technologies for wastewater treatment processes: Status, challenges, and perspectives. IEEE/CAA Journal of Automatica Sinica, 2019, 6(2): 337-363. doi: 10.1109/JAS.2019.1911372
[3]	权利敏, 杨翠丽, 乔俊飞. 数据驱动的溶解氧浓度在线自组织控制方法. 自动化学报, DOI: 10.16383/j.aas.c210041 Quan Lin-Min, Yang Cui-Li, Qiao Jun-Fei. Data-driven online self-organizing control for dissolved oxygen concentration, Acta Automatica Sinica, DOI: 10.16383/j.aas.c210041
[4]	Chistiakova T, Wigren T, Carlsson B. Combined L2 -stable feedback and feedforward aeration control in a wastewater treatment plant. IEEE Transactions on Control Systems Technology, 2020, 28(3): 1017-1024. doi: 10.1109/TCST.2019.2891410
[5]	Ben-David E A, Habibi M, Haddad E, Hasanin M, Angel D L, Booth A M, et al. Microplastic distributions in a domestic wastewater treatment plant: Removal efficiency, seasonal variation and influence of sampling technique. Science of The Total Environment, 2021, 752: 141880. doi: 10.1016/j.scitotenv.2020.141880
[6]	Borzooei S, Amerlinck Y, Panepinto D, Abolfathi S, Nopens I, Nopens G, et al. Energy optimization of a wastewater treatment plant based on energy audit data: small investment with high return. Environmental Science and Pollution Research, 2020, 27: 17972–17985. doi: 10.1007/s11356-020-08277-3
[7]	Sun J Y, Liang P, Yan X X, Zuo K C, Xiao K, Xia J L, et al. Reducing aeration energy consumption in a large-scale membrane bioreactor: Process simulation and engineering application. Water Research, 2016, 93: 205−213. doi: 10.1016/j.watres.2016.02.026
[8]	De Gussem K, Fenu A, Wambecq T, Weemaes M. Energy saving on wastewater treatment plants through improved online control: Case study wastewater treatment plant antwerp-south. Water Science &Technology, 2014, 69(5): 1074−1079.
[9]	Zonta Z J, Kocijan J, Flotats X, Vrečko D. Multi-criteria analyses of wastewater treatment bio-processes under an uncertainty and a multiplicity of steady states. Water Research, 2012, 46(18): 6121-6131. doi: 10.1016/j.watres.2012.08.035
[10]	Godini K, Azarian G, Kimiaei A, Dragoi E N, Curteanu S. Modeling of a real industrial wastewater treatment plant based on aerated lagoon using a neuro-evolutive technique. Process Safety and Environmental Protection, 2021, 148: 114-124. doi: 10.1016/j.psep.2020.09.057
[11]	Qiu Y, Li J, Huang X, Shi H. A feasible data-driven mining system to optimize wastewater treatment process design and operation. Water, 2018, 10(10): 1342. doi: 10.3390/w10101342
[12]	Zeng Y, Zhang Z, Kusiak A, Tang F, Wei X. Optimizing wastewater pumping system with data-driven models and a greedy electromagnetism-like algorithm. Stochastic En- vironmental Research and Risk Assessment, 2016, 30: 1263−1275. doi: 10.1007/s00477-015-1115-4
[13]	Filipe J, Bessa R J, Reis M, Alves R, Póvoa P. Data-driven predictive energy optimization in a wastewater pumping station. Applied Energy, 2019, 252: 113423. doi: 10.1016/j.apenergy.2019.113423
[14]	Canete J F, Saz-Orozco P, Gabriel J G, Baratti R, Ruano A, Rivas-Blanco I. Control and soft sensing strategies for a wastewater treatment plant using a neuro-genetic approach. Computers & Chemical Engineering, 2021, 144: 107146.
[15]	Han H G, Zhang L, Liu H X, Qiao J F. Multiobjective design of fuzzy neural network controller for wastewater treatment process. Applied Soft Computing, 2018, 67: 467–478. doi: 10.1016/j.asoc.2018.03.020
[16]	栗三一, 乔俊飞, 李文静, 顾锞. 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, Gu Ke. Advanced decision and optimization control for wastewater treatment plants. Acta Automatica Sinica, 2018, 44(12): 2198-2209.
[17]	Vega P, Revollar S, Francisco M, Martín J M. Integration of set point optimization techniques into nonlinear MPC for improving the operation of WWTPs. Computers and Chemical Engineering, 2014, 68: 78-95. doi: 10.1016/j.compchemeng.2014.03.027
[18]	Zhang R, Xie W M, Yu H Q, Li W W. Optimizing municipal wastewater treatment plants using an improved multi-objective optimization method. Bioresource Technology, 2014, 157: 161-165. doi: 10.1016/j.biortech.2014.01.103
[19]	Mooselu M G, Nikoo M R, Latifi M, Sadegh M, Al-Wardy M, Al-Rawas G A. A multi-objective optimal allocation of treated wastewater in urban areas using leader-follower game. Journal of Cleaner Production, 2020, 267: 122189. doi: 10.1016/j.jclepro.2020.122189
[20]	Tejaswini E S S, Panjwani S, Gara U B B, Ambati S R. Multi-objective optimization based controller design for improved wastewater treatment plant operation. Environmental Technology & Innovation, 2021, 23: 101591
[21]	De Faria A B B, Ahmadi A, Tiruta-Barna L, Spérandio M. Feasibility of rigorous multi-objective optimization of wastewater management and treatment plants. Chemical Engineering Research and Design, 2016, 155(Part B): 394-406.
[22]	Qiao J F, Hou Y, Zhang L, Han H G. Adaptive fuzzy neural network control of wastewater treatment process with multiobjective operation. Neurocomputing, 2018, 275: 383-393. doi: 10.1016/j.neucom.2017.08.059
[23]	Huang M, Han W, Wan J, Ma Y, Chen X. Multi-objective optimisation for design and operation of anaerobic digestion using GA-ANN and NSGA-II. Journal of Chemical Technology & Biotechnology, 2016, 91(1): 226-233.
[24]	李永明, 史旭东, 熊伟丽. 基于工况识别的污水处理过程多目标优化控制. 化工学报, 2019, 70(11): 4325-4336. Li Yong-Ming, Shi Xu-Dong, Xiong Wei-Li. Condition recognition based intelligent multi-objective optimal control for wastewater treatment. CIESC Journal, 2019, 70(11): 4325-4336.
[25]	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.
[26]	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.
[27]	Newhart K B, Holloway R W, Hering A S, Cath T Y. Data-driven performance analyses of wastewater treatment plants: A review. Water research, 2019, 157: 498-513. doi: 10.1016/j.watres.2019.03.030
[28]	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.
[29]	Christine S, Fu G, Butler D. Multi-objective optimization of wastewater treatment plant control to reduce greenhouse gas emissions. Water Research, 2014, 55: 52-62. doi: 10.1016/j.watres.2014.02.018
[30]	Jeppsson U, Pons M N. The COST benchmark simulation model—current state and future perspective. Control Engineering Practice, 2004, 12(3): 299-304. doi: 10.1016/j.conengprac.2003.07.001