{"title":"An AK-Chart for the Non-Normal Data","authors":"Chia-Hau Liu, Tai-Yue Wang","volume":91,"journal":"International Journal of Economics and Management Engineering","pagesStart":1107,"pagesEnd":1113,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/9998681","abstract":"
Traditional multivariate control charts assume that measurement from manufacturing processes follows a multivariate normal distribution. However, this assumption may not hold or may be difficult to verify because not all the measurement from manufacturing processes are normal distributed in practice. This study develops a new multivariate control chart for monitoring the processes with non-normal data. We propose a mechanism based on integrating the one-class classification method and the adaptive technique. The adaptive technique is used to improve the sensitivity to small shift on one-class classification in statistical process control. In addition, this design provides an easy way to allocate the value of type I error so it is easier to be implemented. Finally, the simulation study and the real data from industry are used to demonstrate the effectiveness of the propose control charts.<\/p>\r\n","references":"[1] S. Bersimis, S. Psarakis, and J. Panaretos, \"Multivariate statistical process\r\ncontrol charts: an overview,\u201d Quality and Reliability Engineering\r\nInternational, vol. 23, no.5, pp. 517-543. Aug 2007.W.-K. Chen, Linear\r\nNetworks and Systems (Book style). Belmont, CA: Wadsworth, 1993,\r\npp. 123\u2013135.\r\n[2] H. Hotelling, \"Multivariate quality control-illustrated by the air testing of\r\nsample bombsight,\"Techniques of Statistical Analysis, McGraw-Hill:\r\nNew York, 1947, pp. 111-184.\r\n[3] R.B. Crosier, \"Multivariate generalizations of cumulative sum\r\nquality-control schemes,\u201d Technometrics, vol. 30, no. 3, pp. 291-303,\r\nAug 1988.\r\n[4] C. A.Lowry, W.H. Woodall, C.W. Champ, and S.E. Rigdon, \"A\r\nmultivariate exponentially weighted moving average control\r\nchart,\u201dTechnometrics, vol. 34, no. 1, pp. 46-53,Feb 1992.\r\n[5] R.Y.Liu, \"Control chart for multivariate process,\u201d Journal of the\r\nAmerican Statistical Association, vol. 90, no. 432, pp. 1380-1387, Dec\r\n1995.\r\n[6] R.Y.Liu and J. Tang, \"Control charts for dependent and independent\r\nmeasurements based on bootstrap methods,\u201dJournal of the American\r\nStatistical Association, vol. 91, no. 436, pp. 1694-1700,Dec 1996.\r\n[7] G.Z. Stoumbos and L. A. Jones, \"On the properties and design of\r\nindividuals control charts based on simplicial depth,\u201d Nonlinear Studies,\r\nvol. 7, no. 2, pp. 147-178, June2000.\r\n[8] P. QiuandD. Hawkins, \"A rank based multivariate CUSUM procedure,\u201d\r\nTechnometrics, vol. 43, no. 2, pp. 120-132,May 2001.\r\n[9] P. QiuandD. Hawkins, \"A nonparametric multivariate CUSUM procedure\r\nfor detecting shifts in all directions,\u201d Journal of the Royal Statistical\r\nSociety-D, vol. 52,pp. 151-164, 2003.\r\n[10] C. Zou and F. Tsung, \"A multivariate sign EWMA control chart,\u201d\r\nTechnometrics, vol. 53, no. 1, pp. 84-97,Feb 2011.\r\n[11] P. Qiu, \"Distribution-free multivariate process control based on log-linear\r\nmodeling,\u201d IIE Transactions, vol. 40, no. 7, pp. 664-677, 2008.\r\n[12] G.Z. Stoumbos and J.H. Sullivan, \"Robustness to non-normality of the\r\nmultivariate EWMA control chart.\u201d Journal of Quality Technology, vol.\r\n34, no. 3,pp. 260-276,Jul2002.\r\n[13] C.Zou, Z. Wang and F. Tsung, \"A spatial rank-based multivariate EWMA\r\ncontrol chart,\u201d Naval Research Logistics, vol. 59, pp. 91-110. Mar 2012.\r\n[14] R. Sun and F. Tsung, \"A kernel distance-based multivariate control chart\r\nusing support vector methods,\u201d InternationalJournal of Production\r\nResearch, vol. 41, no. 13, pp. 2975-2989. Sep 2003.\r\n[15] S.Kumar, A.K.Choudhary, M.Kumar, R. Shankar and M.K. Tiwari,\r\n\"Kernel distance-based robust support vector methods and its application\r\nin developing a robust K-chart,\u201d InternationalJournal of Production\r\nResearch, vol. 44, no. 1,pp. 77-96,Jan 2006.\r\n[16] F. Camci, R.B. Chinnam and R.D. Ellis, \"Robust kernel distance\r\nmultivariate control chart using support vector principles,\u201d\r\nInternationalJournal of Production Research, vol. 46, no. 18, pp.\r\n5075-5095, 2008.\r\n[17] C.S. Cheng and H.P. Cheng, \"Identifying the source of variance shifts in\r\nthe multivariate process using neural networks and support vector\r\nmachines,\u201d Expert Systems with Applications, vol. 35, no.1-2, pp.\r\n198-206, Jul-Aug 2008.\r\n[18] W.Gani, H. Taleb and M. Limam,\"An assessment of the\r\nkernel-distance-based multivariate control chart through an industrial\r\napplication,\u201d Quality and Reliability Engineering International, vol. 27,\r\nno. 4, pp. 391-401,Jun 2011.\r\n[19] X. Ning and F. Tsung, \"Improved design of kernel distance-based charts\r\nusing support vector method,\u201d IIE Transactions, vol. 45, no. 4, pp.\r\n467-476,Apr2013.\r\n[20] T.Sukchotrat, S.B. Kim and F. Tsung, \"One-class classification-based\r\ncontrol charts for multivariate process monitoring,\u201d IIE Transactions, vol.\r\n42, no. 2, pp. 107-120. 2009.\r\n[21] X. Ning and F. Tsung, \"A density-based statistical process control scheme\r\nfor high-dimensional and mixed-type observations,\u201d IIE Transactions,\r\nvol. 44, no. 4,pp. 301-311. 2012.\r\n[22] D. M. J. Tax and R. P. W. Duin, \"Data domain description using support\r\nvectors,\u201d European Symposium on Aritficial Neural Networks, pp.\r\n251-256. 1999.\r\n[23] C. Cortes and V. Vapnik, \"Support-vector networks,\u201d Machine Learning,\r\nvol. 20, no. 3, pp. 273-297,Sep 1995.\r\n[24] F. Aparisi, \"Hotelling\u2019s T2 control chart with adaptive sample size,\u201d\r\nInternationalJournal of Production Research, vol. 34, no. 10, pp.\r\n2853-2862,Oct 1996.\r\n[25] F. Aparisi and C.L. Haro, \"Hotelling\u2019s T2 control chart with sampling\r\nintervals,\u201dInternationalJournal of Production Research, vol. 39, no. 14,\r\npp. 3127-3140,Sep 2001.\r\n[26] F. Aparisi and C.L. Haro, \"A comparison of T2 control chart with\r\nvariable sampling schemes as opposed to MEWMA chart,\u201d\r\nInternationalJournal of Production Research, vol. 41, no. 10, pp.\r\n2169-2182,Jul 2003.\r\n[27] Y.K. Chen and K.C. Chiou, \"Adaptive sampling enhancement for\r\nHotelling\u2019s T2 charts,\u201d In: The 2005 International Conference in\r\nManagement Sciences and Decision Marking, Tamkang University, pp.\r\n281-296. 2005.\r\n[28] D. M. J. Tax and R. P. W. Duin, \"Uniform object generation for\r\noptimizing one-class classifiers,\u201d Journal of Machine Learning\r\nResearch,vol. 2, pp. 251-256, 2002.\r\n[29] Y.K. Chen and K.L. Hsieh, \"Hotelling\u2019s T2 charts with variable sample\r\nsize and control limit,\u201d European Journal of Operational Research, vol.\r\n182, no. 3,pp. 1251-1262,Nov 2007.\r\n[30] D. He and A. Grigoryan, \"Construction of double sampling S-control\r\ncharts for agile manufacturing,\u201d Quality and Reliability Engineering\r\nInternational, vol. 18, no. 4, pp. 343-355,Jul-Aug 2002.\r\n[31] D. He and A. Grigoryan, \"Multivariate multiple sampling charts,\u201d IIE\r\nTransactions, vol. 37, no. 6, pp. 509-521, 2005.\r\n[32] D. He and A. Grigoryan, \"Statistical design of joint double sampling X \u0305\r\nand s charts,\u201d European Journal of Operational Research, vol. 168, no. 1,\r\npp. 122-142,Jan 2006.\r\n[33] D.He, A. Grigoryan and M. Sigh, \"Design of double and triple sampling X \u0305 control charts using genetic algorithms,\u201d InternationalJournal of\r\nProduction Research, vol. 40, no. 6, pp. 1387-1404,Apr 2002.\r\n[34] Y.K. Chen, \"Economic design of X \u0305 control charts for non-normal data\r\nusing variable sampling policy,\u201d InternationalJournal of Production\r\nResearch, vol. 92, no. 1, pp. 61-74,Nov2004.\r\n[35] D.E.Goldberg, Genetic Algorithms on Search Optimization and Machine\r\nLearning Reading. Addison-Wesley, MA, 1989.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 91, 2014"}