基于模糊神经网络的出水总磷软测量方法研究被引量：3

Effluent total phosphorus detecting method and its application based on soft-sensor and FNN techniques

导出

摘要在污水处理过程中,出水总磷(Total Phosphorus,TP)是衡量污水处理效果的关键参数之一。本文针对目前出水TP难以实时测量的问题,提出了一种基于模糊神经网络(FNN)的出水TP软测量方法。该软测量方法通过实际运行数据,利用偏最小二乘法(Partial Least Squares,PLS)筛选出与出水TP相关性强的过程变量;同时,利用FNN建立了出水TP与相关性变量之间的软测量模型,并将该方法嵌入到污水处理运行系统。实验结果显示该软测量方法能够实现出水TP的实时预测,并且具有较好的预测精度。 Total Phosphorus （TP） is a key parameter to evaluate the performance of a wastewater treatment plant （WWTP）. A soft-sensor monitoring method modelling by fuzzy neural network （FNN） was proposed in this paper to solve the problem of time-delay in TP measurement. To ensure accuracy and computing efficiency of soft-sensor model, the data used in this paper was obtained from a WWTP in China and Partial Least Squares （PLS） technique was utilized to suppress the irrelevant process variables with effluent TP. The soft-sensor system was embedded in wastewater treatment process and tested with satisfactory results.

作者郭民张一弛韩红桂

机构地区北京工业大学电子信息与控制工程学院数字社区教育部工程研究中心计算智能与智能系统北京市重点实验室

出处《计算机与应用化学》 CAS 2016年第2期223-227,共5页 Computers and Applied Chemistry

基金国家自然科学基金(61203099 61225016) 北京市科技计划课题(Z141100001414005 Z141101004414058) 中国博士后科学基金资助项目(2014M550017 XJ2013018) 北京市科技新星计划(Z131104000413007) 教育部博士点基金项目(20121103120020 20131103110016) 北京市教委项目(km201410005001 KZ201410005002) 北京市朝阳区博士后资助项目(2014ZZ-05) 北京市朝阳区协同创新项目(ZH14000177)

关键词污水处理出水TP 偏最小二乘法神经网络软测量技术 wastewater treatment process total phosphorus measurement PLS FNN soft-sensor technique

分类号 TQ015.9 [化学工程]

引文网络
相关文献

参考文献29

1Strokal M, He Y and Zhang Y C. Increasing eutrophication in the coastal seas of China from 1970 to 2050[J]. Marine Pollution Bulletin, 2014, 85(1): 123-140.
2Chang N N, Shiaoa J C and Gong G C. Diversity of demersal fish in the east China sea: implication of eutrophication and fishery[J]. Continental Shelf Research, 2012, 47(1):42-54.
3Hu J F, Zhang G and Li K C. Increased eutrophication offshore Hong Kong, China during the past 75 years: evidence from high-resolution sedimentary records[J]. Marine Chemistry, 2008, 110(1-2):7-17.
4Rémi D, Magalie D and Dorioz J M. Assessing the impact of agricultural pressures on N and P loads and eutrophication risk[J]. Ecological Indicators, 2015, 48(1):396-407.
5Bucholc K, Szymczak-Zyla M and Lubecki L. Nutrient content in Macrophyta collected from southern Baltic sea beaches in relation to eutrophication and biogas production[J]. Science of the Total Environment, 2014, 473-474:298-307.
6Nyenje P M, Foppena J W and Uhlenbrook S. Eutrophication and nutrient release in urban areas of sub-Saharan africa-a review[J]. Science of the Total Environment, 2010, 408(3):337-455.
7Olsson G. Instrumentation, control and automation in the water industry: state-of-the-art and new challenges CD[J]. Water Science and Technology, 2006, 53(4-5):1-16.
8Jin L Y, Zhang G M and Tian H F. Current state of sewagetreatment in China[J]. Water Research, 2014, 66(1):85-98.
9Zhang Y, Thepsithar P and Jiang X. Direct determination of phosphate in raw Jatropha Curcas oil by ion chromatography[J]. Industrial Crops and Products, 2013, 44(1):459-464.
10Olsson G. ICA and me - a subjective review[J]. Water Research, 2012, 46(6):1585-1624.

二级参考文献34

1王小艺,刘载文,苏震.基于神经网络的污水BOD软测量补偿方法研究[J].系统仿真学报,2009,21(S2):83-85. 被引量：5
2冉维丽,乔俊飞.基于PCA-GABP神经网络的BOD软测量方法[J].控制工程,2004,11(3):212-215. 被引量：21
3冉维丽,乔俊飞.基于PCA时间延迟神经网络的BOD在线预测软测量方法[J].电工技术学报,2004,19(12):78-82. 被引量：12
4席剑辉,韩敏.多重分支时间延迟神经网络的混沌预测研究[J].信息与控制,2007,36(2):181-186. 被引量：6
5宋贤民,衷卫声.曝气池SVI软测量建模研究[J].工矿自动化,2007,33(3):27-29. 被引量：2
6Gruber N,Galloway J N.Nature,2008,45l:293～296.
7Elena Bennett,Steve R.Carpenter.World Watch,2002,15(2):24～32.
8齐文启陈光孙宗光王光席俊清马秋香.中国环境监测,2007,:32-33.
9Herve S,de Traversay C,Cost M.Water Science and Technology,2004,49(4):227～233.
10Hart Honggui, Qiao Junfei, Chen Qili. Model predictive control of dissolved oxygen concentration based on a self-organizing RBF neural network. Control Engineering Practice, 2012, 20(4): 465-476.