基于模糊神经网络的污水处理生化除磷过程控制

doi:10.11949/0438-1157.20191514

摘要/Abstract

摘要：

针对污水处理生化除磷过程中出水总磷难以实时达标的问题，提出了一种基于模糊神经网络(fuzzy neural network，FNN)的出水总磷控制方法。首先，通过分析污水处理生化除磷机理，确定了控制器的操作变量为生化反应池第五分区外部碳源(external carbon, EC)与溶解氧(dissolved oxygen, DO)传递系数。其次，设计了一种基于FNN的出水总磷控制器，采用梯度下降算法更新控制器参数；最后，将基于FNN的出水总磷控制器应用于污水处理过程基准仿真平台(benchmark simulation model No.1，BSM1)，实验结果表明，基于FNN的出水总磷控制器能够保证出水总磷的达标排放，具有较好的控制效果。

关键词: 污水处理过程, 生化除磷, 模糊神经网络, 过程控制

Abstract:

To make the effluent total phosphorus reach the real-time standard in wastewater treatment process (WWTP), an effluent total phosphorus control strategy, based on fuzzy neural network (FNN), is proposed to control the biochemical phosphorus in this paper. First, the manipulated variables, based on the mechanism analysis of biochemical phosphorus removal process, were considered as the external carbon (EC) and dissolved oxygen (DO) transfer coefficient. Second, an FNN-based process controller was designed to control the effluent total phosphorus. And a gradient descent algorithm was applied to adjust the parameters of controller. Finally, the proposed FNN-based process controller was tested on the benchmark simulation model No. 1 (BSM1) to evaluate its effectiveness. The results demonstrated that the proposed FNN-based process controller can guarantee the standard discharge of effluent total phosphorus. The results show that the FNN-based effluent total phosphorus controller can ensure that the total effluent total phosphorus is discharged and has a good control effect.

Key words: wastewater treatment process, phosphorus removal, fuzzy neural network, process control

中图分类号:

TP 173

张璐, 张嘉成, 韩红桂, 乔俊飞. 基于模糊神经网络的污水处理生化除磷过程控制[J]. 化工学报, 2020, 71(3): 1217-1225.

Lu ZHANG, Jiacheng ZHANG, Honggui HAN, Junfei QIAO. FNN-based process control for biochemical phosphorus in WWTP[J]. CIESC Journal, 2020, 71(3): 1217-1225.

图/表 8

图1 基于FNN的出水总磷控制系统架构图

Fig.1 Structure of effluent total phosphorus control system based on FNN

图2 FNN拓扑结构

Fig.2 Structure of FNN

图3 入水流量与总磷浓度

Fig.3 Inffluent flow and total phosphorus concentration

图4 总磷浓度控制效果

Fig.4 Control performance of total phosphorus concentration

图5 过程变量浓度

Fig.5 Concentration of process variable

图6 操作变量值

Fig.6 Value of process variable

表1 不同控制策略的出水总磷去除效果对比

Table 1 Comparison of phosphorus removal effects of various control strategies

控制策略	除磷效果
控制策略	去除率	平均值/(mg/L)	峰值/(mg/L)
A²/O-BAF	65%~82%	1.03	1.44
PID	71%~87%	0.71	1.04
MPC	76%~94%	0.32	0.48
FNN	87%~96%	0.29	0.32

表2 不同控制策略的控制效果对比

Table 2 Comparison of control performance of various control strategies

控制策略	控制效果
控制策略	ISE	RMSE	Dev_i^max
PID	0.72	1.03	1.44
MPC	0.49	0.71	1.04
BPNN	0.40	0.32	0.48
FNN	0.34	0.29	0.32

参考文献 30

1	Sukacova K,Trtílek M,Rataj T.Phosphorus removal using a microalgal biofilm in a new biofilm photobioreactor for tertiary wastewater treatment[J].Water Research,2015,71:55-63.
2	张为堂,薛晓飞,庞洪涛,等.碳氮比对AAO-BAF工艺运行性能的影响[J].化工学报,2015,66(5):1925-1930.
	Zhang W T,Xue X F,Pang H T,et al.Effect of C/N on performance of AAO-BAF process[J].CIESC Journal,2015,66(5):1925-1930.
3	Bawiec A.Efficiency of nitrogen and phosphorus compounds removal in hydroponic wastewater treatment plant[J].Environmental Technology,2018,40(16):1-34.
4	Novikova A,Nazarenko O B,Vtorushina A N,et al.Characterization of Badinsk zeolite and its use for removal of phosphorus and nitrogen compounds from wastewater[J].Materials Science Forum,2019,970:7-16.
5	张建华,彭永臻,张淼,等.不同电子受体配比对反硝化除磷特性及内碳源转化利用的影响[J].化工学报,2015,66(12):5046-5053.
	Zhang J H,Peng Y Z,Zhang M,et al.Effect of different electron acceptor ratios on removal of nitrogen and phosphorus and conversion and utilization of internal carbon source[J].CIESC Journal,2015,66(12):5046-5053.
6	Chen Y,Lan S,Wang L,et al.A review: driving factors and regulation strategies of microbial community structure and dynamics in wastewater treatment systems[J].Chemosphere,2017,174:173-182.
7	Usach F G,Ribes J,Ferrera J,et al.Calibration of denitrifying activity of poly phosphate accumulating organisms in an extended ASM2d model[J].Water Research,2010,44(18):5284-5279.
8	Gernaey K V,Jorgensen S B.Benchmarking combined biological phosphorus and nitrogen removal wastewater treatment processes[J].Control Engineering Practice,2004,12(3):357-373.
9	Guerrero J,Guisasola A,Vilanova R,et al.Improving the performance of a WWTP control system by model-based setpoint optimization[J].Environmental Modelling & Software,2011,26(4):492-497.
10	马玉萍,陈立爱,叶勇,等.硫酸亚铁用于污水厂二沉池出水化学除磷[J].环境工程学报,2015(3):1303-1307.
	Ma Y P,Chen L A,Ye Y,et al.FeSO₄·7H₂O for chemical phosphorus removal from secondary sedimentation tank effluent of WWTP[J].Chinese Journal of Environmental Engineering,2015,9(3):1303-1307.
11	Solon K,Alsina X F,Mbamb C K,et al.Plant wide modelling of phosphorus transformations in wastewater treatment systems[J].Impacts of Control and Operational Strategies,2017,64(13):97-110.
12	Guerrero J,Guisasola A,Baeza J A,et al.Novel control strategy for efficient biological phosphorus removal with carbon-limited wastewaters[J].Water Science and Technology,2013,70(4):267-282.
13	Coats E R,Mockos A,Loge F J.Post-anoxic denitrification driven by PHA and glycogen within enhanced biological phosphorus removal[J].Bioresource Technology,2011,102(2):1019-1027.
14	Zhu G B,Peng Y Z,Zhai L M,et al.Performance and optimization of biological nitrogen removal process enhanced by anoxic/oxic step feeding[J].Biochemical Engineering Journal,2009,43(9):280-287.
15	Wang D,Zheng W,Liao D,et al.Effect of initial pH control on biological phosphorus removal induced by the aerobic/extended-idle regime[J].Chemosphere,2013,90(8):2279-2287.
16	Liu J J,Yuan Y,Li B K,et al.Enhanced nitrogen and phosphorus removal from municipal wastewater in an anaerobic-aerobic-anoxic sequencing batch reactor with sludge fermentation products as carbon source[J].Bioresource Technology,2017,244(13):1158-1165.
17	Ostace G S,Baeza J A,Guerrero J,et al.Development and economic assessment of different WWTP control strategies for optimal simultaneous removal of carbon, nitrogen and phosphorus[J].Computers & Chemical Engineering,2013,53:164-177.
18	Amand L,Olsson G,Carlsson B,et al.Aeration control— a review[J].Water Science & Technology,2013,67(11):2374-2397.
19	Chen Y Z,Li B,Yea L,et al.The combined effects of COD/N ratio and nitrate recycling ratio on nitrogen and phosphorus removal in anaerobic/anoxic/aerobic (A2/O) biological aerated filter (BAF) systems[J].Biochemical Engineering Journal,2015,93(18):235-242.
20	张为堂,侯锋,刘青松,等.HRT和曝气量对AAO-BAF系统反硝化除磷性能的影响[J].化工学报,2014,65(4):1436-1442.
	Zhang W T,Hou F,Liu Q S,et al.Effect of HRT and aeration rate on performance of AAO-BAF system for denitrifying phosphorus removal[J].CIESC Journal,2014,65(4):1436-1442.
21	Shen W H,Chen X Q,Pierre J,et al.Corriou application of model predictive control to the BSM1 benchmark of wastewater treatment process[J].Computers and Chemical Engineering,2018,32(12):2849-2856.
22	Sabahi K,Ghaemin S,Liu J X,et al.Indirect predictive type-2 fuzzy neural network controller for a class of nonlinear input-delay systems[J].ISA Transactions,2017,71(19):185-195.
23	Cristea V M,Pop C,Serban P,et al.Model predictive control of the waste water treatment plant based on the Benchmark Simulation Model No.1-BSM1[J].Computer Aided Chemical Engineering,2008,25(11):441-446.
24	Ruano M V,Ribes J,Sin G,et al.A systematic approach for fine-tuning of fuzzy controllers applied to WWTPs[J].Environmental Modelling & Software,2010,25(5):670-676.
25	Cai W,Zhang B,Jin Y,et al.Behavior of total phosphorus removal in an intelligent controlled sequencing batch biofilm reactor for municipal wastewater treatment[J].Bioresource Technology,2013,132:190-196.
26	Lochmatter S,Gonzalez-Gil G,Holliger C.Optimized aeration strategies for nitrogen and phosphorus removal with aerobic granular sludge[J].Water Research,2013,47(16):6187-6197.
27	Tavakoli A R,Seifi A R,Arefi M,et al.Designing a self-constructing fuzzy neural network controller for damping power system oscillations[J].Fuzzy Sets and System,2019,365(4):63-76.
28	Sartorius C,Von H J,Tettenborn F.Phosphorus recovery from wastewater—expert survey on present use and future potential[J].Water Environment Research,2012,84(4):313-322.
29	Sartorius C,Von H J,Tettenborn F.Phosphorus recovery from wastewater—state-of-the-art and future potential[J].Proceedings of the Water Environment Federation,2011,1:299-316.
30	Zhang X Y,Li X,Cao J,et al.Design of memory controllers for finite-time stabilization of delayed neural networks with uncertainty[J].Journal of the Franklin Institute,2018,355(13):5394-5413.

[1]	曹跃, 余冲, 李智, 杨明磊. 工业数据驱动的加氢裂化装置多工况切换过渡状态检测[J]. 化工学报, 2023, 74(9): 3841-3854.
[2]	康飞, 吕伟光, 巨锋, 孙峙. 废锂离子电池放电路径与评价研究[J]. 化工学报, 2023, 74(9): 3903-3911.
[3]	苏晓丹, 朱干宇, 李会泉, 郑光明, 孟子衡, 李防, 杨云瑞, 习本军, 崔玉. 湿法磷酸半水工艺考察与石膏结晶过程研究[J]. 化工学报, 2023, 74(4): 1805-1817.
[4]	张江淮, 赵众. 碳三加氢装置鲁棒最小协方差约束控制及应用[J]. 化工学报, 2023, 74(3): 1216-1227.
[5]	张中秋, 李宏光, 石逸林. 基于人工预测调控策略的复杂化工过程多任务学习方法[J]. 化工学报, 2023, 74(3): 1195-1204.
[6]	赵涛岩, 曹江涛, 李平, 冯琳, 商瑀. 区间二型模糊免疫PID在环己烷无催化氧化温度控制系统中的应用[J]. 化工学报, 2022, 73(7): 3166-3173.
[7]	王琨, 侍洪波, 谭帅, 宋冰, 陶阳. 局部时差约束邻域保持嵌入算法在故障检测中的应用[J]. 化工学报, 2022, 73(7): 3109-3119.
[8]	周乐, 沈程凯, 吴超, 侯北平, 宋执环. 深度融合特征提取网络及其在化工过程软测量中的应用[J]. 化工学报, 2022, 73(7): 3156-3165.
[9]	王建松, 许锋, 罗雄麟. 化工过程多回路PID控制系统模式切换参数自整定[J]. 化工学报, 2022, 73(4): 1647-1657.
[10]	张成, 潘立志, 李元. 基于加权统计特征KICA的故障检测与诊断方法[J]. 化工学报, 2022, 73(2): 827-837.
[11]	张兴硕, 罗雄麟, 许锋. 催化裂化装置反再系统动态模拟精细化与控制系统“工艺优先”配对设计[J]. 化工学报, 2022, 73(2): 747-758.
[12]	卢道铭, 唐钊艇, 范怡平, 卢春喜. 大差异颗粒分级再生设备的性能研究[J]. 化工学报, 2021, 72(8): 4184-4195.
[13]	王龙洋, 蒙西, 乔俊飞. 基于改进集合经验模态分解和深度信念网络的出水总磷预测[J]. 化工学报, 2021, 72(5): 2745-2753.
[14]	李元, 杨东昇, 赵丽颖, 张成. 层次变分高斯混合模型与主多项式分析的故障检测策略[J]. 化工学报, 2021, 72(3): 1616-1626.
[15]	谢苗苗, 张浪文, 谢巍. 复杂非线性系统的子系统分解方法[J]. 化工学报, 2021, 72(3): 1557-1566.