Please wait a minute...
JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE)
Energy and Mechanical Engineering     
F-MEWMA control chart for fuzzy hierarchical quantitative characteristics
ZHOU Juan, YU Zhonghua, HOU Zhi
Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province, Zhejiang University, Hangzhou 310027, China
Download:   PDF(705KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

Fuzzy multivariate exponentially weighted moving average control chart (F-MEWMA) was proposed in order to solve the problem of lower power when implementing statistical process control to the quality characteristic which was difficult to quantify but could be described in hierarchical levels. F-MEWMA tried to blur the hierarchical quantitative characteristics based on fuzzy theory. Since different α cut sets containing different amount of information, interval value of weighted fuzzy α cut set was proposed. Mathematical characterization and comparison of the quality characteristics for fuzzy univariate data and fuzzy multivariate data were conducted respectively, and the control limits for different weight coefficients and different dimensions were determined by Matlab simulation. Then F-EWMA and F-MEWMA were designed. The effect of F-MEWMA was analyzed by calculating probability of identifying variation by Matlab simulation. The implementation of the F-MEWMA on the electric energy meter running and starting quality characteristics showed good result.



Published: 23 July 2016
CLC:  O 213  
Cite this article:

ZHOU Juan, YU Zhonghua, HOU Zhi. F-MEWMA control chart for fuzzy hierarchical quantitative characteristics. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2016, 50(7): 1373-1380.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2016.07.021     OR     http://www.zjujournals.com/eng/Y2016/V50/I7/1373


面向模糊多级特征的F-MEWMA控制图研究

围绕难以定量测量、但可以分级量化的质量特性,在实施统计过程控制中所遇到的检出力受限问题展开讨论,提出模糊多变量指数加权移动平均控制图(F-MEWMA)方法.该方法借助于模糊理论,对分级量化特征进行模糊化处理. 针对不同α截集包含信息量多寡的问题,提出应用加权α截集模糊区间值来构造统计量,分别针对模糊单变量和模糊多变量质量特性进行数学表征与比较分析. 采用Matlab仿真的方式确定不同权重系数和不同维数下的控制限,完成F-EWMA、F-MEWMA的设计. 采用Matlab仿真的方法,以识别变异的概率为评价指标对F-MEWMA的监控效果进行分析. 以电能表潜动和起动的质量特性为例,对提出的方法进行应用,取得了较好的应用效果.

[1]ZARANDI H, MOHOHAMMAD H F. A general fuzzystatistical clustering approach for estimating the time of change in variable sampling control charts [J]. Information Sciences, 2010, 180(16): 3033-3044.
[2]GULBAY M, KAHRAMAN C. An alternative approach to fuzzy control charts: direct fuzzy approach [J]. Information Sciences, 2007, 177(8): 1463-1480.
[3]SENTURK S, ERGINEL N. Development of fuzzy R and s control charts using α cuts [J]. Information Sciences, 2009, 179(10): 1542-1551.
[4]SENTURK S. Fuzzy regression control chart based on αcut approximation [J]. International Journal of Computational Intelligence Systems, 2010, 3(1): 123-140.
[5]侯世旺,同淑荣. 基于模糊数的不确定质量控制图及选型[J]. 计算机集成制造系统,2012, 18(2): 415-421.
HOU Shiwang, TONG Shurong. Fuzzy numberbased uncertain quality control chart and type selection [J]. Computer Integrated Manufacturing Systems, 2012, 18(2): 415-421.
[6]SHAHRAM G, KAZEM N, RASSOUL N. Developing a multivariate approach to monitor fuzzy quality profiles [J]. Quality and Quantity, 2014, 48: 817-836.
[7]HOSSEIN A, RASSOUL N. Fuzzy multivariate exponentially weighted moving average control chart [J]. International Journal of Advanced Technology, 2010, 48(9):1001-1007.
[8]AHMADABADI M, FARJAMI Y, MOGHADAM M. A process control method based on fiveparameter generalized lambda distribution [J]. Quality and Quantity, 2012, 46: 1097-1111.
[9]葛志强,宋执环,杨春节. 基于MCUSUMICAPCA 的微小故障检测[J]. 浙江大学学报:工学版,2008,42(3):373-377.
GE Zhiqiang, SONG Zhihuan, YANG Chunjie. Small shift detection based on MCUSUMICAPCA [J]. Journal o f Zhejiang University: Engineering Science, 2008,42(3): 373-377.
[10]PILLET M, BOUKAR A, PAIREL E. Multivariate SPC for total inertial tolerancing [J]. International Journal of Metrology and Quality Engineering, 2013, 4(3): 169-175.
[11]TALEB H. Control charts applications for multivariate attribute processes [J]. Computers and Industrial Engineering, 2009, 56(1): 399-410.
[12]HRYNIEWICZ O. Statistics with fuzzy data in statistical quality control [J]. Soft Computing, 2008, 12(1): 229-234.
[13]RUNGER G C,PRABHU S S. A Markov chain model for the multivariate exponentially weighted moving averages control chart[ J] . Journal of the American Statistical Association, 1996, 91(436):1701-1706.
[14]LOWRY C A, WOODALL W H, CHAMP C. A multivariate exponentially weighted moving control average charts [J]. Technometrics, 1992, 34(1): 46-53.
[15] MOLNAU W E, RUNGER G C, MONTGOMERY D C. A program for ARL calculation for multivariate EWMA chart [J]. Journal of Quality Technology, 2001, 33(4): 515-521.
[16]杜褔洲,唐晓青,孙静.MEWMA控制图ARL计算及参数优化[J]. 北京航空航天大学学报,2006,32(8):974-978.
DU Fuzhou, TANG Xiaoqing, SUN Jing. ARL computation and parameters optimization for MEWMA control chart based on the Markov chain [J]. Journal of Beijing University of Aeronautics and Astronautics, 2006,32(8):974-978.

No related articles found!