基于聚类的轮廓数据质量监控方法研究

doi:10.12005/orms.2017.0090

运筹与管理 ›› 2017, Vol. 26 ›› Issue (4): 112-117.DOI: 10.12005/orms.2017.0090

基于聚类的轮廓数据质量监控方法研究

聂斌, 姚雪海, 李京亚

天津大学管理与经济学部,天津 300072

收稿日期:2015-05-08 出版日期:2017-04-25
作者简介:聂斌,(1971-)男,副教授,主要研究方向为统计过程控制、实验设计和可靠性工程等;姚雪海(1989-),男,硕士研究生;李京亚(1990-),女,硕士研究生。

Profile Monitor Based on Clustering Method

NIE Bin, YAO Xue-hai, LI Jing-ya

College of Management and Economics, Tianjin University, Tianjin 300072, China

Received:2015-05-08 Online:2017-04-25

摘要/Abstract

摘要： 轮廓线的变点识别是质量管理的研究热点之一,当前研究多以轮廓整体变化为识别对象,而对局部变化问题研究相对较少,且更少有在发现变异时间的同时能够寻找到变化区域在个体轮廓曲线上位置的系统方法。本文针对轮廓线局部变化识别问题,提出基于小波变换和聚类分析的方法。通过仿真性能评价,并与现有方法进行比较,结果显示本方法能够在更小的差异度检测出变化并准确定位变化区域。在文章的末尾,本文采用了一个实例对该方法的效果进行验证。

关键词: 变点识别, 聚类分析, 小波变换, 轮廓线, 统计过程控制

Abstract: Change-point detection of profiles has been a hot topic in quality management. Most of the literatures focus on the global change detection while research on local change problem is relatively few, and the ones that find change time as well as change area are extremely less. To solve local change problem, our paper proposes a method based on wavelet transform and cluster method. In this paper, we do a performance evaluation using Matlab and compare its result with WANOVA method. It shows that our method can detect change-point and locate change area under smaller difference between profiles.

Key words: change-point detection, cluster analysis, wavelet transform, profile, SPC

中图分类号:

F222.3

聂斌, 姚雪海, 李京亚. 基于聚类的轮廓数据质量监控方法研究[J]. 运筹与管理, 2017, 26(4): 112-117.

NIE Bin, YAO Xue-hai, LI Jing-ya. Profile Monitor Based on Clustering Method[J]. Operations Research and Management Science, 2017, 26(4): 112-117.

参考文献

[1] E Walker, S P Wright. Comparing curves using additive models[J]. Journal of Quality Technology, 2002, 34(1): 118-129.
[2] 陈希孺.变点统计分析简介[J].数理统计与管理,1991,10(2):52-59.
[3] Hawkins D L, Gallant A R, Fuller W. A simple least squares method for estimating a change in mean[J]. Communications in Statistics-Simulation and Computation, 1986, 15(3): 523-530.
[4] Barry D, Hartigan J A. A Bayesian analysis for change point problems[J]. Journal of the American Statistical Association, 1993, 88(421): 309-319.
[5] Kokoszka P, Leipus R. Change-point estimation in ARCH models[J]. Bernoulli, 2000, 6(3): 513-539.
[6] Williams J D, Woodall W H, Brinch J B. Statistical monitoring of nonlinear product and process quality profiles[J]. Quality and reliability engineering international, 2007, 23: 925-941.
[7] Kang L, S Albin S. On-line monitoring when the process yields a linear[J]. Journal of Quality Technology, 2000, 32(4): 418-426.
[8] Ding Y, Zeng L, Zhou S. Phase Ⅰanalysis for monitoring nonlinear profiles in manufacturing process[J]. Journal of Quality Technology, 2006, 38(3): 199-216.
[9] Chang S I, Yadama S. Statistical process control for monitoring non-linear profiles using wavelet filtering and B-Spline approximation[J]. International Journal of Production Research, 2010, 48(4): 1049-1068.
[10] Zou C, Qiu P. Multivariate statistical process control using lasso[J]. Journal of the American statistical association, 2009, 104: 1586-1596.
[11] Girimurugan S, Chicken E, Pignatiello J, et al. Wavelet ANOVA for detection of local and global profile changes[C]//Proceedings of the 2013 Industrial and Systems Engineering Research Conference, A. Krishnamurthy and WKV Chan, eds. 3235-3244.
[12] 潘泉,张磊,孟晋丽.小波滤波方法与应用[M].北京:清华大学出版社,2005.
[13] Meyer Y. Wavelets-algorithms and applications[J]. Wavelets-Algorithms and applications Society for Industrial and Applied Mathematics Translation, 1993, 1: 142.
[14] 余晃晶.小波降噪阈值选取的研究[J].绍兴文理学院学报,2004,24(19):34-38.
[15] 何晓群.多元统计分析[M].北京:中国人民大学出版社,2004.
[16] 李飞,薛彬,黄亚楼.初始中心优化的K-Means聚类算法[J].计算机科学,2002,29(7):94-96.

基于聚类的轮廓数据质量监控方法研究

Profile Monitor Based on Clustering Method

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

[1]	聂斌, 叶文静, 刘迪青, 刘晓卉. 基于B样条和聚类分析的非参数轮廓监控方法研究[J]. 运筹与管理, 2021, 30(5): 79-87.
[2]	冯爱兰, 张小青, 孔继利. 基于聚类和动态规划的组合路径策略[J]. 运筹与管理, 2019, 28(8): 86-92.
[3]	聂斌, 王曦, 胡雪. 非正态变异下的非线性轮廓异常点识别方法研究[J]. 运筹与管理, 2019, 28(1): 101-107.
[4]	刘宏涛, 赵希男. 基于客体优势识别的自主式竞优评析方法[J]. 运筹与管理, 2017, 26(3): 131-137.
[5]	马越峰, 卢虎生, 甄建静. 稀土分离联产品质量控制研究[J]. 运筹与管理, 2017, 26(3): 165-171.
[6]	张红, 于渤, 鞠立新. 基于GIS的长三角城市群经济空间集聚特征研究[J]. 运筹与管理, 2015, 24(6): 184-191.
[7]	鲍新中, 傅宏宇. 基于变精度加权平均粗糙度决策树的财务预警研究[J]. 运筹与管理, 2015, 24(3): 189-196.
[8]	李鹏, 朱建军. 基于新直觉模糊相似度的大规模群决策方法[J]. 运筹与管理, 2014, 23(2): 167-174.
[9]	苏木亚, 郭崇慧. 基于主成分分析的单变量时间序列聚类方法[J]. 运筹与管理, 2011, 20(6): 66-72.
[10]	张目, 周宗放. 基于投影寻踪和最优分割的企业信用评级模型[J]. 运筹与管理, 2011, 20(6): 226-231.