JOURNAL OF LIGHT INDUSTRY

CN 41-1437/TS  ISSN 2096-1553

基于HCPS多层感知器的污水处理后氨氮浓度测量

高明 ,  崔钶 ,  李昊 ,  栗三一

downloadPDF
高明, 崔钶, 李昊, 等. 基于HCPS多层感知器的污水处理后氨氮浓度测量[J]. 轻工学报, 2018, 33(6): 92-100,108. doi: 10.3969/j.issn.2096-1553.2018.06.011
引用本文: 高明, 崔钶, 李昊, 等. 基于HCPS多层感知器的污水处理后氨氮浓度测量[J]. 轻工学报, 2018, 33(6): 92-100,108. doi: 10.3969/j.issn.2096-1553.2018.06.011
shu
GAO Ming, CUI Ke, LI Hao and et al. Measurement of ammonia nitrogen concentration after sewage treatment based on HCPS multilayer perceptrons[J]. Journal of Light Industry, 2018, 33(6): 92-100,108. doi: 10.3969/j.issn.2096-1553.2018.06.011
Citation: GAO Ming, CUI Ke, LI Hao and et al. Measurement of ammonia nitrogen concentration after sewage treatment based on HCPS multilayer perceptrons[J]. Journal of Light Industry, 2018, 33(6): 92-100,108. doi: 10.3969/j.issn.2096-1553.2018.06.011
shu

基于HCPS多层感知器的污水处理后氨氮浓度测量

  • 1. 黄河流域水环境监测中心 监测管理处, 河南 郑州 450004;

  • 2. 郑州轻工业学院 电气信息工程学院, 河南 郑州 450001

    • 作者简介: 高明(1986-),女,河南省宜阳县人,黄河流域水环境监测中心工程师,硕士,主要研究方向为水环境监测与研究.;

  • 基金项目: 国家自然科学基金项目（61603347）

  • 中图分类号: TP273;TS97;X703.1

Measurement of ammonia nitrogen concentration after sewage treatment based on HCPS multilayer perceptrons

  • 1. Monitoring Management Service, Yellow River Basin Water Environment Monitoring Center, Zhengzhou 450004, China;

  • 2. College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450001, China

  • Received Date: 2018-10-18

    CLC number: TP273;TS97;X703.1

  • 摘要: 针对现污水处理后出水氨氮预测模型中隐含层神经元存在过大冗余而浪费资源的问题，提出了一种基于敏感度和互信息的混合增加删减的神经网络结构调整算法（HCPS）.该算法重新定义了敏感度公式，利用敏感度和互信息自适应地调整网络结构，删除敏感度过低的隐含神经元，分裂过大的隐含层神经元，合并互信息过大的两个隐含层神经元.在污水处理基准仿真平台BSM1上的验证结果表明，HCPS算法可以获得更紧凑的网络结构，用于出水氨氮浓度预测精度较高.
    Abstract: In the existing prediction model of ammonia nitrogen in sewage treatment effluent, the hidden layer neurons excessively redundant, which wastes resources. A new structure adjustment algorithm (HCPS) based on sensitivity analysis (SA) and mutual information (MI) was proposed. The algorithm redefined the sensitivity formula, adaptively, adjusted the network structure by using sensitivity and mutual information, deleted hidden neurons with low sensitivity, divided hidden neurons with excessive sensitivity, and merged two hidden neurons with excessive mutual information. The results of verification on BSM1, a benchmark simulation platform for sewage treatment, showed that HCPS algorithm could obtain a more compact network structure, and the prediction accuracy of ammonia nitrogen concentration in effluent was higher.
    1. [1]

      DU R,PENG Y,CAO S,et al.Advanced nitrogen removal from wastewater by combining anammox with partial denitrification[J].Bioresource Technology,2015,179:497.

    2. [2]

      杨航涛,王双保,王成龙.基于分光光度法的水质氨氮检测系统设计[J].测控技术,2012,31(5):49.

    3. [3]

      乔俊飞,安茹,韩红桂.基于RBF神经网络的出水氨氮预测研究[J].控制工程,2016,23(9):1301.

    4. [4]

      ESFE M H,AFRAND M,WONGWISES S,et al.Applications of feedforward multilayer perceptron artificial neural networks and empirical correlation for prediction of thermal conductivity of Mg(OH)2-EG using experimental data[J].International Communications in Heat and Mass Transfer,2015,67(4):46.

    5. [5]

      ZHANG Y D,WANG S H,JI G L,et al.Fruit classification using computer vision and feedforward neural network[J].Journal of Food Engineering,2014,143(6):167.

    6. [6]

      FARAJZADEH J,FARD A F,LOTFI S.Modeling of monthly rainfall and runoff of Urmia lake basin using "feed-forward neural network" and "time series analysis" model[J].Water Resources and Industry,2014(7):38.

    7. [7]

      OONG T H,ISA N A.Adaptive evolutionary artificial neural networks for pattern classification[J].IEEE Trans Neural Netw,2011,22(11):1823.

    8. [8]

      WANG J H,WANG H Y,CHEN Y L,et al.A constructive algorithm for unsupervised learning with incremental neural network[J].Journal of Applied Research & Technology,2015,13(2):188.

    9. [9]

      PLATT J.A resource-allocating network for function interpolation[J].Neural Computation,1991,3(2):213.

    10. [10]

      LAURET P,FOCK E,MARA T A.A node pruning algorithm based on a Fourier amplitude sensitivity test method[J].IEEE Transactions on Neural Networks,2006,17(2):273.

    11. [11]

      ISLAM M M,SATTAR M A,AMIN M F,et al.A new adaptive merging and growing algorithm for designing artificial neural networks[J].IEEE Transactions on Systems Man and Cybernetics Part B,2009,39(3):705.

    12. [12]

      HAN H G,QIAO J F.A structure optimisation algorithm for feedforward neural network construction[J].Neurocomputing,2013,99:347.

    13. [13]

      GUO W,WEI H,ZHAO J,et al.Theoretical and numerical analysis of learning dynamics near singularity in multilayer perceptrons[J].Neurocomputing,2015,151:390.

    14. [14]

      HACINE-GHARBI A,RAVIER P,HARBA R,et al.Low bias histogram-based estimation of mutual information for feature selection[J].Pattern Recognition Letters,2012,33(10):1302.

    15. [15]

      GUO Y M,LIU Y G,ZENG G M,et al.An integrated treatment of domestic wastewater using sequencing batch biofilm reactor combined with vertical flow constructed wetland and its artificial neural network simulation study[J].Ecological Engineering,2014,64:18.

    16. [16]

      MIRBAGHERI B,EHTESHAMI M,BAGHERI Z.Modeling of a sequencing batch reactor treating municipal wastewater using multi-laye perceptron and radial basis function artificial neural networks[J].Process Safety and Environmental Protection,2015,93:111.

    17. [17]

      VIVIANO G,SALERNO F,CHIARA E,et al.Surrogate measures for providing high frequency estimates of total phosphorus concentrations in urban watersheds[J].Water Research,2014,64:265.

    18. [18]

      JEPPSSON U,PONS M N.The COST benchmark simulation model-current state and future perspective[J].Control Engineering Practice,2004,12(3):299.

    19. [19]

      HAN H G,QIAO J F.A structure optimization algorithm for feedforward neural network construction[J].Neurocomputing,2013,1(99):347.

    20. [20]

      CHEN C,YAN X.Optimization of a multilayer neural network by using minimal redundancy maximal relevance-partial mutual information clustering with least square regression[J].IEEE Transactions on Neural Networks and Learning Systems,2015,26(6):1177.

    1. [1]

      胡新楠 , 朱成凯 , 胡中泽 , 纪执立 , 金伟平 , 郭城 , 沈汪洋 . 复配比对明胶-羟丙基甲基纤维素双水相体系微观结构和流变特性的影响. 轻工学报, 2024, 0(0): -.

    2. [2]

      贾尚羲 , 张怡雪 , 石盼盼 , 王昱 , 李可 . 不同时长超声波处理对鹰嘴豆分离蛋白乳化液稳定性的影响. 轻工学报, 2024, 39(5): 40-49. doi: 10.12187/2024.05.005

    3. [3]

      费致根 , 鲁豪 , 宋晓晓 , 赵鑫昌 , 郭兴 , 肖艳秋 . 基于改进ResNet网络的烟丝输送带洁净度分类模型. 轻工学报, 2024, 39(5): 71-77. doi: 10.12187/2024.05.008

  • 加载中
WeChat 点击查看大图
计量
  • PDF下载量:  4
  • 文章访问数:  1048
  • 引证文献数: 0
文章相关
  • 收稿日期:  2018-10-18
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索
高明, 崔钶, 李昊, 等. 基于HCPS多层感知器的污水处理后氨氮浓度测量[J]. 轻工学报, 2018, 33(6): 92-100,108. doi: 10.3969/j.issn.2096-1553.2018.06.011
引用本文: 高明, 崔钶, 李昊, 等. 基于HCPS多层感知器的污水处理后氨氮浓度测量[J]. 轻工学报, 2018, 33(6): 92-100,108. doi: 10.3969/j.issn.2096-1553.2018.06.011
shu
GAO Ming, CUI Ke, LI Hao and et al. Measurement of ammonia nitrogen concentration after sewage treatment based on HCPS multilayer perceptrons[J]. Journal of Light Industry, 2018, 33(6): 92-100,108. doi: 10.3969/j.issn.2096-1553.2018.06.011
Citation: GAO Ming, CUI Ke, LI Hao and et al. Measurement of ammonia nitrogen concentration after sewage treatment based on HCPS multilayer perceptrons[J]. Journal of Light Industry, 2018, 33(6): 92-100,108. doi: 10.3969/j.issn.2096-1553.2018.06.011
shu

基于HCPS多层感知器的污水处理后氨氮浓度测量

    作者简介:高明(1986-),女,河南省宜阳县人,黄河流域水环境监测中心工程师,硕士,主要研究方向为水环境监测与研究.
  • 1. 黄河流域水环境监测中心 监测管理处, 河南 郑州 450004;
  • 2. 郑州轻工业学院 电气信息工程学院, 河南 郑州 450001
  • 收稿日期: 2018-10-18
基金项目:  国家自然科学基金项目（61603347）

摘要: 针对现污水处理后出水氨氮预测模型中隐含层神经元存在过大冗余而浪费资源的问题，提出了一种基于敏感度和互信息的混合增加删减的神经网络结构调整算法（HCPS）.该算法重新定义了敏感度公式，利用敏感度和互信息自适应地调整网络结构，删除敏感度过低的隐含神经元，分裂过大的隐含层神经元，合并互信息过大的两个隐含层神经元.在污水处理基准仿真平台BSM1上的验证结果表明，HCPS算法可以获得更紧凑的网络结构，用于出水氨氮浓度预测精度较高.

English Abstract

参考文献 (20) 相关文章 (3)

目录

/

返回文章

网站版权 © 轻工学报编辑部

地址：河南省郑州市科学大道136号邮编：450001

本系统由北京仁和汇智信息技术有限公司开发 技术支持： info@rhhz.net