您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(工学版)》

山东大学学报 (工学版) ›› 2020, Vol. 50 ›› Issue (1): 101-108.doi: 10.6040/j.issn.1672-3961.0.2018.552

• 化学与环境 • 上一篇    下一篇

废水处理过程的典型相关分析建模方法研究

刘鸿斌1,2(),宋留1   

  1. 1. 南京林业大学林业资源高效加工利用协同创新中心, 江苏 南京 210037
    2. 华南理工大学制浆造纸工程国家重点实验室, 广东 广州 510640
  • 收稿日期:2018-12-24 出版日期:2020-02-20 发布日期:2020-02-14
  • 作者简介:刘鸿斌(1981—),男,山西大同人,主要研究方向为制浆造纸过程监测与控制研究. E-mail: hongbinliu@njfu.edu.cn
  • 基金资助:
    制浆造纸工程国家重点实验室开放基金资助项目(201813);南京林业大学高层次人才科研启动基金(GXL029)

Study on modeling methods of wastewater treatment processes with canonical correlation analysis

Hongbin LIU1,2(),Liu SONG1   

  1. 1. Co-Innovation Center of Efficient Processing and Utilization of Forest Resources, Nanjing Forestry University, Nanjing 210037, Jiangsu, China
    2. State Key Laboratory of Pulp and Paper Engineering, South China University of Technology, Guangzhou 510640, Guangdong, China
  • Received:2018-12-24 Online:2020-02-20 Published:2020-02-14
  • Supported by:
    制浆造纸工程国家重点实验室开放基金资助项目(201813);南京林业大学高层次人才科研启动基金(GXL029)

摘要:

随着公众环保意识的增强,废水达标排放成为工业生产中至关重要的一步。传统的污水出水水质预测模型是基于静态数据模型,这样不仅忽略了过程变量中的动态有效信息,还影响了模型预测的精度,降低了模型的泛化能力。在考虑了过程变量的时变与动态特性的基础上,将时间差分方法嵌入到典型相关分析模型中,分析了时间差分阶数变化对模型预测精度的影响。与传统的典型相关分析建模方法相比,基于时间差分的典型相关分析模型对出水化学需氧量的预测均方根误差由1.502 8下降至0.564 5,相关系数由0.422 7提高到0.847 0;对于出水总氮,其均方根误差由2.344 0下降到1.192 6,相关系数由0.405 9提高到0.793 6。模型的预测精度与泛化能力均得到提高。

关键词: 废水处理过程, 动态过程, 时间差分, 典型相关分析, 软测量

Abstract:

With the improvement of public awareness of environmental protection, the discharge of industrial wastewater became a crucial issue in industrial production. The typical water quality models were based on static models which ignored the dynamic information in process variables, resulting in the reduction in the accuracy of model prediction and the generalization ability of the models. Considering the time-varying and dynamic characteristics of process variables, a time difference model embedded into canonical correlation analysis was proposed in this paper. The effect of the order of the time difference model on the prediction accuracy was also analyzed. Compared with the traditional canonical correlation analysis, the root mean square error values of effluent chemical oxygen demand and effluent total nitrogen were reduced from 1.502 8 to 0.564 5 and from 2.344 0 to 1.192 6, respectively. The correlation coefficient values were increased from 0.422 7 to 0.847 0 and from 0.405 9 to 0.793 6, respectively. The results indicated that the prediction accuracy and generalization ability of the model were both improved.

Key words: wastewater treatment processes, dynamic processes, time difference, canonical correlation analysis, soft sensor

中图分类号: 

  • X703

图1

废水处理过程变量"

图2

TD-CCA软测量模型流程图"

图3

不同差分阶数的TD模型的预测误差"

图4

CCA预测结果"

图5

TD-CCA预测结果"

表1

CCA和TD-CCA的预测结果"

模型 集合 出水COD 出水TN
RMSE MAPE/% r RMSE MAPE/% r
CCA
训练集 0.822 9 11.16 0.765 9 1.510 7 15.610 0 0.566 5
测试集 1.502 8 13.74 0.422 7 2.344 0 20.28 0 0.405 9
TD-CCA
训练集 0.454 6 0.922 2 0.860 4 1.072 6 0.828 9 0.864 7
测试集 0.564 5 0.937 6 0.847 0 1.192 6 0.891 7 0.793 6

图6

CCA预测结果"

图7

TD-CCA预测结果"

1 黄道平, 刘乙奇, 李艳. 软测量在污水处理过程中的研究与应用[J]. 化工学报, 2011, 62 (1): 1- 9.
HUANG Daoping , LIU Yiqi , LI Yan . Soft sensor research and its application in wastewater treatment[J]. CIESC Jorunal, 2011, 62 (1): 1- 9.
2 杨浩, 莫卫林, 熊智新, 等. 基于RPLS的造纸废水处理过程软测量建模[J]. 中国造纸, 2016, 35 (10): 31- 35.
doi: 10.11980/j.issn.0254-508X.2016.10.007
YANG Hao , MO Weilin , XIONG Zhixin , et al. Soft sensor modeling of papermaking effluent treatment processes using RPLS[J]. China Pulp & Paper, 2016, 35 (10): 31- 35.
doi: 10.11980/j.issn.0254-508X.2016.10.007
3 徐龙琴, 刘双印. 基于APSO-WLSSVR的水质预测模型[J]. 山东大学学报(工学版), 2012, 42 (5): 80- 86.
XU Longqin , LIU Shuangyin . Water quality prediction model based on APSO-WLSSVR[J]. Journal of Shandong University of Technology (Engineering Science), 2012, 42 (5): 80- 86.
4 汪瑶, 徐亮, 殷文志, 等. 基于ANN和LSSVR的造纸废水处理过程软测量建模[J]. 中国造纸学报, 2017, 32 (1): 50- 54.
WANG Yao , XU Liang , YIN Wenzhi , et al. Soft sensor modeling of papermaking treatment processes based on ANN and LSSVR[J]. Transactions of China Pulp and Paper, 2017, 32 (1): 50- 54.
5 王欣, 宋翼颉, 秦斌, 等. 基于LSSVM的污水处理过程建模[J]. 湖南工业大学学报, 2016, 30 (1): 59- 63.
doi: 10.3969/j.issn.1673-9833.2016.01.011
WANG Xin , SONG Yijie , QIN Bin , et al. Modeling of sewage treatment process based on MIMO-LSSVM[J]. Journal of Hunan University of Technology, 2016, 30 (1): 59- 63.
doi: 10.3969/j.issn.1673-9833.2016.01.011
6 邱禹, 刘乙奇, 吴菁, 等. 基于深层神经网络的多输出自适应软测量建模[J]. 化工学报, 2018, 69 (7): 3101- 3113.
QIU Yu , LIU Yiqi , WU Jing . A self-adaptive multi-output soft sensor modeling based on deep neural network[J]. CIESC Jorunal, 2018, 69 (7): 3101- 3113.
7 宋留, 杨冲, 张辉, 等. 造纸废水处理过程的高斯过程回归软测量建模[J]. 中国环境科学, 2018, 38 (7): 2564- 2571.
doi: 10.3969/j.issn.1000-6923.2018.07.023
SONG Liu , YANG Chong , ZHANG Hui , et al. Soft-sensor modeling of papermaking wastewater treatment process based on Gaussian process[J]. China Environmental Science, 2018, 38 (7): 2564- 2571.
doi: 10.3969/j.issn.1000-6923.2018.07.023
8 柴伟, 纪镐南. 污水处理出水BOD区间预测建模[J]. 哈尔滨工业大学学报, 2018, 50 (2): 71- 76.
CHAI Wei , JI Haonan . Interval predictor models for effluent BOD of wastewater treatment[J]. Journal of Harbin Institute of Technology, 2018, 50 (2): 71- 76.
9 车笑卿, 熊伟丽. 基于仿射传播聚类的局部TDGPR的自适应软测量建模[J]. 计算机与应用化学, 2017, 34 (11): 850- 857.
CHE Xiaoqing , XIONG Weili . Self-adaptive soft sensor based on affine propagation clustering of local TDGPR models[J]. Computers and Applied Chemistry, 2017, 34 (11): 850- 857.
10 LIU Ziwei , GE Zhiqiang , CHEN Guangjie , et al. Adaptive soft sensors for quality prediction under the framework of Bayesian network[J]. Control Engineering Practice, 2018, 72, 19- 28.
doi: 10.1016/j.conengprac.2017.10.018
11 王通, 高宪文, 刘文芳. 基于改进即时学习算法的动液面软测量建模[J]. 东北大学学报(自然科学版), 2015, 36 (7): 918- 922.
doi: 10.3969/j.issn.1005-3026.2015.07.002
WANG Tong , GAO Xianwen , LIU Wenfang . Soft sensor for determination of dynamic fluid levels based on enhanced Just-in-Time learning algorithm[J]. Journal of Northeastern University(Natural Science), 2015, 36 (7): 918- 922.
doi: 10.3969/j.issn.1005-3026.2015.07.002
12 汪世杰, 王振雷, 王昕. 基于JIT-MOSVR的软测量方法及应用[J]. 化工学报, 2017, 68 (3): 947- 955.
WANG Shijie , WANG Zhenlei , WANG Xin . Soft-sensor method based on JIT-MOSVR and its application[J]. CIESC Jorunal, 2017, 68 (3): 947- 955.
13 袁小锋, 葛志强, 宋执环. 基于时间差分和局部加权偏最小二乘算法的过程自适应软测量建模[J]. 化工学报, 2016, 67 (3): 724- 728.
YUAN Xiaofeng , GE Zhiqiang , SONG Zhihuan . Adaptive soft sensor based on time difference model and locally weighted partial least squares regression[J]. CIESC Jorunal, 2016, 67 (3): 724- 728.
14 FU Y , YANG W , XU O , et al. Soft sensor modelling by time difference, recursive partial least squares and adaptive model updating[J]. Measurement Science & Technology, 2017, 28 (4): 45101- 45108.
15 KANEKO H , FUNATSU K . Discussion on time difference models and intervals of time difference for application of soft sensors[J]. Industrial and Engineering Chemistry Research, 2013, 52 (3): 1322- 1334.
doi: 10.1021/ie302582v
16 SHI Honglan , KIM M J , LIU Hongbin , et al. Process modeling based on nonlinear PLS models using a prior knowledge-driven time difference method[J]. Journal of the Taiwan Institute of Chemical Engineers, 2016, 69, 93- 105.
doi: 10.1016/j.jtice.2016.10.013
17 李珊, 饶文碧. 基于视频的矿井中人体运动区域检测[J]. 计算机科学, 2018, 45 (4): 291- 295.
LI Shan , RAO Wenbi . Video-based detection of human motion area in mine[J]. Computer Science, 2018, 45 (4): 291- 295.
18 ZHU Qinqin , LIU Qiang , QIN S J . Concurrent quality and process monitoring with canonical correlation analysis[J]. Journal of Process Control, 2017, 60, 95- 103.
doi: 10.1016/j.jprocont.2017.06.017
19 WEI Zhihui , WANG Liqian , LIANG Xiao . Image dehazing using two-dimensional canonical correlation analysis[J]. Computer Vision Iet, 2015, 9 (6): 903- 913.
doi: 10.1049/iet-cvi.2014.0324
[1] 李广丽,刘斌,朱涛,殷依,张红斌. 基于优选典型相关分量的跨媒体检索模型[J]. 山东大学学报 (工学版), 2018, 48(5): 38-46.
[2] 陈志文, 彭涛, 阳春华, 何章鸣,杨超, 杨笑悦. 基于改进的典型相关分析的故障检测方法[J]. 山东大学学报(工学版), 2017, 47(5): 44-50.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 浦剑1 ,张军平1 ,黄华2 . 超分辨率算法研究综述[J]. 山东大学学报(工学版), 2009, 39(1): 27 -32 .
[2] 刘文亮,朱维红,陈涤,张泓泉. 基于雷达图像的运动目标形态检测及跟踪技术[J]. 山东大学学报(工学版), 2010, 40(3): 31 -36 .
[3] 王丽君,黄奇成,王兆旭 . 敏感性问题中的均方误差与模型比较[J]. 山东大学学报(工学版), 2006, 36(6): 51 -56 .
[4] 孙炜伟,王玉振. 考虑饱和的发电机单机无穷大系统有限增益镇定[J]. 山东大学学报(工学版), 2009, 39(1): 69 -76 .
[5] 孙殿柱,朱昌志,李延瑞 . 散乱点云边界特征快速提取算法[J]. 山东大学学报(工学版), 2009, 39(1): 84 -86 .
[6] 岳远征. 远离平衡态玻璃的弛豫[J]. 山东大学学报(工学版), 2009, 39(5): 1 -20 .
[7] 赵然杭,陈守煜 . 水资源数量与质量联合评价理论模型研究[J]. 山东大学学报(工学版), 2006, 36(3): 46 -50 .
[8] 程代展,李志强. 非线性系统线性化综述(英文)[J]. 山东大学学报(工学版), 2009, 39(2): 26 -36 .
[9] 薛翊国,李术才,赵岩,苏茂鑫,李为腾,丁志海. 青岛胶州湾海底隧道F44含水断层注浆前后TSP探测分析[J]. 山东大学学报(工学版), 2009, 39(2): 108 -112 .
[10] 陈华鑫, 陈拴发, 王秉纲. 基质沥青老化行为与老化机理[J]. 山东大学学报(工学版), 2009, 39(2): 125 -130 .