Please wait a minute...
浙江大学学报(理学版)  2018, Vol. 45 Issue (4): 468-475    DOI: 10.3785/j.issn.1008-9497.2018.04.014
环境科学     
基于BP神经网络的城镇污水厂活性炭自动投加系统研究
方荣业1, 史宇滨2, 蒋婷1, 李威1, 史惠祥1
1. 浙江大学 环境与资源学院, 浙江 杭州 310058;
2. 华东勘测设计研究院有限公司, 浙江 杭州 310014
A study on the activated carbon intelligent dosing system for urban sewage treatment plants based on BP neural network.
FANG Rongye1, SHI Yubin2, JIANG Ting1, LI Wei1, SHI Huixiang1
1. College of Environmental & Resource Sciences, Zhejiang University, Hangzhou 310058, China;
2. Huadong Engineering Corporation Limited, Hangzhou 310014, China
 全文: PDF(2266 KB)   HTML  
摘要: 近年来,活性炭吸附技术逐渐成为深度处理的主流技术,但粉末活性炭投加系统仍处于人工控制阶段,现场需要技术人员依靠经验确定活性炭投加量,易造成出水水质不稳定、活性炭药耗大等问题.以浙江省嘉善县某城镇污水处理厂的深度处理工艺为研究背景,以粉末活性炭投加系统为研究对象,针对活性炭投加控制系统滞后、非线性、复杂等问题,建立了BP神经网络前馈预测-PID反馈控制的自动投加控制系统.实践证明,该系统具有较强的自适应能力和较高的控制精度,出水COD达标率较人工控制提高了8.88%,活性炭日均消耗量削减了16.61%,取得了较好的经济效益.
关键词: 深度处理粉末活性炭投加系统BP神经网络投药复合控制    
Abstract: In recent years, adsorption of contaminants by activated carbon has become a predominant technology for intensive treatment of wastewater. However, the operation system is yet controlled manually. And the dose of activated carbon is determined by experience, resulting in instability of effluent COD value and excessive use of activated carbon. In order to solve the problems of long time lag, nonlinearity and complexity of the dosing system of activated carbon, based on BP network prediction plus PID feedback control, we developed an automatic dosing system of activated carbon as an intensive treatment technology of a municipal wastewater treatment factory in Jiashan county. The composite control system exhibits good self-adaptability and great control precision. The qualification percentage is enhanced by 8.88% than manual control, and consumption of activated carbon is decreased by 16.61% per day.
Key words: advanced treatment    powder activated carbon dosing system    BP neural network    compound dosing control
收稿日期: 2017-06-14 出版日期: 2018-07-12
CLC:  X505  
基金资助: 环保部水体污染控制与治理科技重大专项(2017ZX07206).
通讯作者: 史惠祥,通信作者,ORCID:http://orcid.org/0000-0002-5704-4229,E-mail:shhx188@163.com.     E-mail: shhx188@163.com
作者简介: 方荣业(1994-),ORCID:http://orcid.org/0000-0001-6799-5565,男,硕士,主要从事水污染治理研究,E-mail:391172012@qq.com.
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
方荣业
史宇滨
蒋婷
李威
史惠祥

引用本文:

方荣业, 史宇滨, 蒋婷, 李威, 史惠祥. 基于BP神经网络的城镇污水厂活性炭自动投加系统研究[J]. 浙江大学学报(理学版), 2018, 45(4): 468-475.

FANG Rongye, SHI Yubin, JIANG Ting, LI Wei, SHI Huixiang. A study on the activated carbon intelligent dosing system for urban sewage treatment plants based on BP neural network.. Journal of Zhejiang University (Science Edition), 2018, 45(4): 468-475.

链接本文:

https://www.zjujournals.com/sci/CN/10.3785/j.issn.1008-9497.2018.04.014        https://www.zjujournals.com/sci/CN/Y2018/V45/I4/468

[1] 巴能军,周志伟,董俊,等. 助滤和再生粉末活性炭吸附技术用于工业废水深度处理[J]. 给水排水,2017,43(2):71-74. BA N J,ZHOU Z W,DONG J,et al. Filtration and regeneration powdered activated carbon adsorption technology for advanced treatment of industrial wastewater[J]. Water & Wastewater Engineering,2017,43(2):71-74.
[2] 司景萍,马继昌,牛家骅,等. 基于模糊神经网络的智能故障诊断专家系统[J]. 振动与冲击,2017,36(4):164-171. SI J P,MA J C,NIU J Y,et al. An intelligent fault diagnosis expert system based on fuzzy neural network[J]. Journal of Vibration and Shock,2017,36(4):164-171.
[3] 张延风. 烧杯搅拌试验条件的最优化[J]. 企业技术开发,2014,33(4):44-45. ZHANG Y F. Optimization of jar test conditions[J]. Technological Development of Enterprise,2014,33(4):44-45.
[4] 蒋绍阶,仇洪建,段果,等. 基于短程反馈BP神经网络的混凝投药控制中试[J]. 中国给水排水,2013,29(11):26-29. JIANG S J,QIU H J,DUAN G,et al. Coagulant dosage control based on short range feedback BP neural network[J]. China Water & Wastewater,2013,29(11):26-29.
[5] 陈金辉,赵雷振,杨宗宵. 改进的BP神经网络在故障诊断中的应用[J]. 河北科技大学学报,2011,32(5):455-459. CHEN J H,ZHAO L Z,YANG Z X. Application of improved BP neural network in fault diagnosis[J]. Journal of Hebei University of Science and Technology,2011,32(5):455-459.
[6] 焦斌,叶明星. BP神经网络隐层单元数确定方法[J]. 上海电机学院学报,2013,16(3):113-116. JIAO B,YE M X. Determination of hidden unit number in a BP neural network[J]. Journal of Shanghai Dianji University,2013,16(3):113-116.
[7] 李友坤. BP神经网络的研究分析及改进应用[D]. 合肥:安徽理工大学,2012. LI Y K. Analysis and Improvement Applications of BP Neural Network[D]. Hefei:Anhui University of Science and Technology,2012.
[8] DHARMAN S, CHANDRAMOULI V, LINGIREDDY S. Predicting total organic carbon removal efficiency and coagulation dosage using artificial neural networks[J]. Environmental Engineering Science, 2012, 29(8):743-750.
[9] NAUCK D, KRUSE R. A fuzzy neural network learning fuzzy control rules and membership functions by fuzzy error back propagation[J]. IEEE International Conference on Neural Networks, 1996, 2(2):1022-1027.
[10] MARTELLI G. Stability of PID-controlled second-order time-delay feedback systems[J]. Automatica, 2009, 45(11):2718-2722.
[11] 王素青,姜维福. 基于MATLAB/Simulink的PID参数整定[J]. 自动化技术与应用,2009,28(3):24-26. WANG S Q,JIANG W F. PID tuning based on MATLAB/Simulink[J]. Techniques of Automation and Applications,2009,28(3):24-26.
[12] 雷斌,吕凤玉,马殷元. 基于PLC和组态王的农村水厂监控系统设计[J]. 自动化技术与应用,2010,29(12):100-102. LEI B,LYU F Y,MA Y Y. Design of supervision system based on PLC and king view for the rural waterworks[J]. Techniques of Automation and Applications,2010,29(12):100-102.
[13] 许甜. 城市水处理厂自动化系统的研究与设计[D]. 西安:西安建筑科技大学,2015. XU T. Research and Design of Municipal Water Treatment Plant Automation System[D]. Xi'an:Xi'an University of Architecture and Technology,2015.
[14] 蔡先峰. WinCC组态软件在大足选煤厂的应用[J]. 选煤技术,2011(1):56-58. CAI X F. Application of WinCC configuration software in Dazu coal preparation plant[J]. Coal Preparation Technology,2011(1):56-58.
[1] 张贝娜, 冯震华, 张丰, 杜震洪, 刘仁义, 周芹. 基于时空多视图BP神经网络的城市空气质量数据补全方法研究[J]. 浙江大学学报(理学版), 2019, 46(6): 737-744.
[2] 赵涛涛, 白建军, 尚忠慧. 基于BP神经网络的陕西省县域乡村性分异研究[J]. 浙江大学学报(理学版), 2016, 43(2): 203-210.