K-均值聚类在CCERT系统流型辨识中的应用

李凯锋; 王保良; 黄志尧; 冀海峰; 李海青

doi:10.13700/j.bh.1001-5965.2017.0070

K-均值聚类在CCERT系统流型辨识中的应用

doi: 10.13700/j.bh.1001-5965.2017.0070

浙江大学控制科学与工程学院工业控制技术国家重点实验室, 杭州 310027

基金项目:

国家自然科学基金 61371161

详细信息

作者简介:
李凯锋男, 硕士研究生。主要研究方向:检测技术与自动化装置

王保良男, 博士, 教授, 博士生导师。主要研究方向:过程参数检测、嵌入式系统

通讯作者:
王保良, E-mail:wangbl@zju.edu.cn

中图分类号: TP212
计量
- 文章访问数: 624
- HTML全文浏览量: 67
- PDF下载量: 320
- 被引次数: 0
出版历程
- 收稿日期: 2017-02-15
- 录用日期: 2017-04-24
- 网络出版日期: 2017-11-20

Application of K-means clustering in flow pattern identification of CCERT system

State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China

Funds:

National Natural Science Foundation of China 61371161

More Information

Corresponding author: WANG Baoliang, E-mail:wangbl@zju.edu.cn

摘要

摘要:
流型是气水两相流的重要参数之一，对气水两相流的流动影响很大。基于电容耦合电阻层析成像（CCERT）系统，以水平管道气水两相流流型为研究对象，利用主成分分析（PCA）方法提取不同流型下采集到的电导率信息的主成分，消除不同电极对之间信号的冗余，进而结合K-均值聚类算法实现流型辨识。实验结果表明，该方法具有较高准确度，对于水平管道泡状流、层状流和环状流3种典型的气水两相流流型的静态辨识准确率可以分别达到97%、96%和99%，动态辨识准确率可以分别达到92%、90%和87%。
- 气水两相流 /
- CCERT系统 /
- 流型辨识 /
- K-均值聚类 /
- 主成分分析(PCA)
Abstract:
Flow pattern is one of the most important parameters of gas-liquid two-phase flow and has great influence on the flow of gas-liquid two-phase flow. In this paper, gas-liquid two-phase flow patterns in a horizontal pipe are analyzed with capacitively coupled electrical resistance tomography (CCERT) system. Principal component analysis (PCA) method is used to extract the principal components of the electrical conductivity information under different flow patterns, and thus the redundancy of signal between different electrode pairs can be eliminated. The three flow patterns are recognized by using K-means clustering algorithm. The experimental results show that this method has high accuracy. The static identification accuracy for bubble flow, stratified flow and annular flow is 97%, 96% and 99%, respectively, and the dynamic identification accuracy is 92%, 90% and 87%, respectively.
- gas-liquid two-phase flow /
- CCERT system /
- flow pattern identification /
- K-means clustering /
- principal component analysis (PCA)

HTML全文

图 1 CCERT系统结构图

Figure 1. Structure diagram of CCERT system

下载: 全尺寸图片幻灯片

图 2 CCERT传感器结构示意图

Figure 2. Structure diagram of CCERT sensor

下载: 全尺寸图片幻灯片

图 3 CCERT传感器等效电路图

Figure 3. Equivalent circuit diagram of CCERT sensor

下载: 全尺寸图片幻灯片

图 4 静态实验中不同流型下的电阻测量值

Figure 4. Resistance measurement results under different flow patterns in static experiments

下载: 全尺寸图片幻灯片

图 5 气水两相流动态实验装置实物图

Figure 5. Picture of gas-water two-phase flow's dynamic experimental device

下载: 全尺寸图片幻灯片

图 6 流型照片和管截面流型示意图

Figure 6. Photographs of different flow patterns and sketch map of different flow patterns at pipe section

下载: 全尺寸图片幻灯片

图 7 动态实验中不同流型下的电阻测量值

Figure 7. Resistance measurement results under different flow patterns in dynamic experiments

下载: 全尺寸图片幻灯片

表 1 K-均值聚类静态流型辨识结果

Table 1. Static flow pattern identification results of K-means clustering

流型测试组数正确组数准确率/%

泡状流 100 97 97

层状流 100 96 96

环状流 100 99 99

下载: 导出CSV

表 2 K-均值聚类动态流型辨识结果

Table 2. Dynamic flow pattern identification results of K-means clustering

流型测试组数正确组数准确率/%

泡状流 100 92 92

层状流 100 90 90

环状流 100 87 87

下载: 导出CSV

参考文献(20)

[1]	FARRALL M, HIBBERD S, SIMMONS K, et al.Prediction of air/oil exit flows in a commercial aero-engine bearing chamber[J].Proceedings of the Institution of Mechanical Engineers Part G:Journal of Aerospace Engineering, 2006, 220(3):197-202. doi: 10.1243/09544100JAERO40
[2]	李海青.两相流参数检测及应用[M].杭州:浙江大学出版社, 1991:9-12. LI H Q. Two-phase flow parameter measurement and applications[M].Hangzhou:Zhejiang University Press, 1991:9-12(in Chinese).
[3]	张彦俊. 电阻层析成像图像重建及流型辨识[D]. 哈尔滨: 哈尔滨理工大学, 2011. http://cdmd.cnki.com.cn/Article/CDMD-11914-1012256404.htm ZHANG Y J.Image reconstruction and flow regime identification of electrical resistance tomography[D].Harbin:Harbin University of Science and Technology, 2011(in Chinese). http://cdmd.cnki.com.cn/Article/CDMD-11914-1012256404.htm
[4]	孙斌, 周云龙.基于支持向量机的气液两相流流型识别新方法[J].应用基础与工程科学学报, 2007, 15(2):209-216. http://d.wanfangdata.com.cn/Periodical/yyjcygckxxb200702010 SUN B, ZHOU Y L.A novel identification method of gas-liquid two-phase flow regimes based on support vector machine[J]. Journal of Basic Science and Engineering, 2007, 15(2):209-216(in Chinese). http://d.wanfangdata.com.cn/Periodical/yyjcygckxxb200702010
[5]	ROMAN A J, KREITZER P J, ERVIN J S, et al.Flow pattern identification of horizontal two-phase refrigerant flow using neural networks[J].International Communications in Heat & Mass Transfer, 2016, 71:254-264. http://www.dtic.mil/cgi-bin/GetTRDoc?AD=ADA604486
[6]	CHEN D X, YANG W Q, PAN M C.Design of impedance measuring circuits based on phase-sensitive demodulation technique[J].IEEE Transactions on Instrumentation & Measurement, 2011, 60(4):1276-1282. http://ieeexplore.ieee.org/xpl/abstractAuthors.jsp?reload=true&arnumber=5618560&sortType%3Dasc_p_Sequence%26filter%3DAND%28p_Publication_Number%3A19%29%26pageNumber%3D56%26rowsPerPage%3D75
[7]	WANG B L, HU Y Y, JI H F, et al.A novel electrical resistance tomography system based on C⁴D technique[J].IEEE Transactions on Instrumentation & Measurement, 2013, 62(5):1017-1024. http://www.worldneurosurgery.org/article/S1878-8750(11)01088-6/references
[8]	ZEMANN A J, SCHNELL E, VOLGGER D, et al.Contactless conductivity detection for capillary electrophoresis[J].Analytical Chemistry, 1998, 70(3):563-567. doi: 10.1021/ac9707592
[9]	JI H F, LI Z Z, WANG B L, et al.Design and implementation of an industrial C⁴D sensor for conductivity detection[J].Sensors & Actuators A Physical, 2014, 213:1-8.
[10]	王保良, 张伟波, 黄志尧, 等.电容耦合电阻层析成像传感器结构优化设计研究[J].传感技术学报, 2012, 25(2):206-211. http://d.wanfangdata.com.cn/Periodical/cgjsxb201202013 WANG B L, ZHANG W B, HUANG Z Y, et al.Optimum design for capacitively coupled electrical resistance tomography sensor configuration[J].Chinese Journal of Sensors and Actuators, 2012, 25(2):206-211(in Chinese). http://d.wanfangdata.com.cn/Periodical/cgjsxb201202013
[11]	王保良, 徐升继, 冀海峰, 等.电容耦合电阻层析成像并行电阻测量原理研究[J].传感技术学报, 2013, 26(5):660-665. http://d.wanfangdata.com.cn/Periodical/cgjsxb201305013 WANG B L, XU S J, JI H F, et al.Research on parallel resistance measurement principle for capacitively coupled electrical resistance tomography[J].Chinese Journal of Sensors and Actuators, 2013, 26(5):660-665(in Chinese). http://d.wanfangdata.com.cn/Periodical/cgjsxb201305013
[12]	HOTELLING H.Analysis of a complex of statistical variables into principal components[J].Journal of Educational Psychology, 2010, 24(6):417-441. doi: 10.1037/h0070888
[13]	赵广社, 张希仁.基于主成分分析的支持向量机分类方法研究[J].计算机工程与应用, 2004, 40(3):37-38. http://d.wanfangdata.com.cn/Periodical/jsjgcyyy200403012 ZHAO G S, ZHANG X R.Research of support vector machine classified method based on principal component analysis[J]. Computer Engineering and Applications, 2004, 40(3):37-38(in Chinese). http://d.wanfangdata.com.cn/Periodical/jsjgcyyy200403012
[14]	汪阳, 黄天戍, 杜广宇.一种基于聚类和主成分分析的异常检测方法[J].计算机工程与应用, 2006, 42(21):21-24. doi: 10.3321/j.issn:1002-8331.2006.21.006 WANG Y, HUANG T S, DU G Y.An anomaly detection method based on clustering and principal component analysis[J].Computer Engineering and Applications, 2006, 42(21):21-24(in Chinese). doi: 10.3321/j.issn:1002-8331.2006.21.006
[15]	QIN S J, DUNIA R.Determining the number of principal components for best reconstruction[J].Journal of Process Control, 2000, 10(10):245-250. http://d.wanfangdata.com.cn/NSTLQK_NSTL_QKJJ024067618.aspx
[16]	王丽珍.数据仓库与数据挖掘原理及应用[M].北京:科学出版社, 2005:106-108. WANG L Z.Theory and application of data warehouse and data mining[M].Beijing:Science Press, 2005:106-108(in Chinese).
[17]	周爱武, 于亚飞.K-means聚类算法的研究[J].计算机技术与发展, 2011, 21(2):62-65. http://d.wanfangdata.com.cn/Periodical/jsjxb200305012 ZHOU A W, YU Y F.The research about clustering algorithm of K-means[J].Computer Technology and Development, 2011, 21(2):62-65(in Chinese). http://d.wanfangdata.com.cn/Periodical/jsjxb200305012
[18]	王涛, 陈国定, 张永红.基于聚类分析的航空发动机轴承腔油气两相流型辨识[J].机械科学与技术, 2013, 32(3):328-332. http://d.wanfangdata.com.cn/Periodical/jxkxyjs201303004 WANG T, CHEN G D, ZHANG Y H.The oil/air two phase flow pattern recognition in bearing chamber of aircraft engine based on clustering analysis[J].Mechanical Science and Technology for Aerospace Engineering, 2013, 32(3):328-332(in Chinese). http://d.wanfangdata.com.cn/Periodical/jxkxyjs201303004
[19]	黄韬, 刘胜辉, 谭艳娜.基于K-means聚类算法的研究[J].计算机技术与发展, 2011, 21(7):54-57. HUANG T, LIU S H, TAN Y N.Research of clustering algorithm based on K-means[J].Computer Technology and Development, 2011, 21(7):54-57(in Chinese).
[20]	李霞. 基于数据挖掘的两相流参数测量新方法研究[D]. 杭州: 浙江大学, 2009. http://cdmd.cnki.com.cn/Article/CDMD-10335-2010067774.htm LI X.Study on new measurement methods of two-phase flow parameters based on data mining[D].Hangzhou:Zhejiang University, 2009(in Chinese). http://cdmd.cnki.com.cn/Article/CDMD-10335-2010067774.htm