Statistical process control using kernel PCA

被引：0

作者：

Stefatos, George ^{[1
]}

Hamza, A. Ben ^{[1
]}

机构：

[1] Concordia Univ, Concordia Inst Informat Syst Engn, Montreal, PQ, Canada

来源：

2007 MEDITERRANEAN CONFERENCE ON CONTROL & AUTOMATION, VOLS 1-4 | 2007年

关键词：

kernel PCA; process control; multivariate chart;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we present a robust multivariate statistical process control chart using kernel principal component analysis. The proposed control chart is effective in the detection of outliers, and its control limits are derived from the eigenanalysis of the Gaussian kernel matrix in the Hilbert feature space. Our experimental results show the much improved performance of the proposed control chart in comparison with existing multivariate monitoring and controlling charts.

引用

页码：1418 / 1423

页数：6

共 10 条

[1]

ALQALLAF PA, 2002, P ACM SIGKDD INT C K, P14

[2]

CHEN KH, 2001, P S INT COMP SCI STA

[3]

Haykin S, 1998, Neural networks: a comprehensive foundation

[4]

Jolliffe I. T., 1986, PRINCIPAL COMPONENT, DOI DOI 10.1016/0169-7439(87)80084-9

[5]

Montgomery DC, 2019, INTRO STAT QUALITY C

[6] Nonlinear component analysis as a kernel eigenvalue problem [J].

Scholkopf, B ;

Smola, A ;

Muller, KR .

NEURAL COMPUTATION, 1998, 10 (05) :1299-1319

[7] A comparison of multivariate control charts for individual observations [J].

Sullivan, JH ;

Woodall, WH .

JOURNAL OF QUALITY TECHNOLOGY, 1996, 28 (04) :398-408

[8] MULTIVARIATE CONTROL CHARTS FOR INDIVIDUAL OBSERVATIONS [J].

TRACY, ND ;

YOUNG, JC ;

MASON, RL .

JOURNAL OF QUALITY TECHNOLOGY, 1992, 24 (02) :88-95

[9] Robust estimation in multivariate control charts for individual observations [J].

Vargas, NJA .

JOURNAL OF QUALITY TECHNOLOGY, 2003, 35 (04) :367-376

[10]

Yang K., 2004, MULTIVARIATE STAT ME

← 1 →