Control chart pattern recognition of manufacturing process using wavelet feature-based artificial neural networks

Jun Seok Kim; Sang Hoon Park; Cheong Sool Park; Hyo Heon Ko; Sung Shick Kim; Jun Geol Baek

doi:10.1166/asl.2012.3904

Control chart pattern recognition of manufacturing process using wavelet feature-based artificial neural networks

Jun Seok Kim, Sang Hoon Park, Cheong Sool Park, Hyo Heon Ko, Sung Shick Kim, Jun Geol Baek

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

Control chart pattern recognition is one of the most important tools in the identification of process problems in modern manufacturing industries. Abnormal patterns including systematic, cyclic, drift, and shift could be involved with certain assignable causes. Conventional control charts could not inherently recognize these patterns. In this paper, multi-resolution wavelet analysis is used to extract features. A self-organizing map then generates cluster vectors with wavelet coefficients. Using these features, a back-propagation network classifies unnatural patterns. The performance evaluation result is better than those of other competitive methods.

Original language	English
Pages (from-to)	863-866
Number of pages	4
Journal	Advanced Science Letters
Volume	13
DOIs	https://doi.org/10.1166/asl.2012.3904
Publication status	Published - 2012 Jun

Keywords

Artificial neural network
Control charts
Feature extraction
Multi-class classification
Pattern recognition
Wavelet analysis

ASJC Scopus subject areas

General Computer Science
Health(social science)
General Mathematics
Education
General Environmental Science
General Engineering
General Energy

Access to Document

10.1166/asl.2012.3904

Cite this

@article{515f8dd942b048b0b914b8cd6c2648c6,

title = "Control chart pattern recognition of manufacturing process using wavelet feature-based artificial neural networks",

abstract = "Control chart pattern recognition is one of the most important tools in the identification of process problems in modern manufacturing industries. Abnormal patterns including systematic, cyclic, drift, and shift could be involved with certain assignable causes. Conventional control charts could not inherently recognize these patterns. In this paper, multi-resolution wavelet analysis is used to extract features. A self-organizing map then generates cluster vectors with wavelet coefficients. Using these features, a back-propagation network classifies unnatural patterns. The performance evaluation result is better than those of other competitive methods.",

keywords = "Artificial neural network, Control charts, Feature extraction, Multi-class classification, Pattern recognition, Wavelet analysis",

author = "Kim, {Jun Seok} and Park, {Sang Hoon} and Park, {Cheong Sool} and Ko, {Hyo Heon} and Kim, {Sung Shick} and Baek, {Jun Geol}",

year = "2012",

month = jun,

doi = "10.1166/asl.2012.3904",

language = "English",

volume = "13",

pages = "863--866",

journal = "Advanced Science Letters",

issn = "1936-6612",

publisher = "American Scientific Publishers",

}

TY - JOUR

T1 - Control chart pattern recognition of manufacturing process using wavelet feature-based artificial neural networks

AU - Kim, Jun Seok

AU - Park, Sang Hoon

AU - Park, Cheong Sool

AU - Ko, Hyo Heon

AU - Kim, Sung Shick

AU - Baek, Jun Geol

PY - 2012/6

Y1 - 2012/6

N2 - Control chart pattern recognition is one of the most important tools in the identification of process problems in modern manufacturing industries. Abnormal patterns including systematic, cyclic, drift, and shift could be involved with certain assignable causes. Conventional control charts could not inherently recognize these patterns. In this paper, multi-resolution wavelet analysis is used to extract features. A self-organizing map then generates cluster vectors with wavelet coefficients. Using these features, a back-propagation network classifies unnatural patterns. The performance evaluation result is better than those of other competitive methods.

AB - Control chart pattern recognition is one of the most important tools in the identification of process problems in modern manufacturing industries. Abnormal patterns including systematic, cyclic, drift, and shift could be involved with certain assignable causes. Conventional control charts could not inherently recognize these patterns. In this paper, multi-resolution wavelet analysis is used to extract features. A self-organizing map then generates cluster vectors with wavelet coefficients. Using these features, a back-propagation network classifies unnatural patterns. The performance evaluation result is better than those of other competitive methods.

KW - Artificial neural network

KW - Control charts

KW - Feature extraction

KW - Multi-class classification

KW - Pattern recognition

KW - Wavelet analysis

UR - http://www.scopus.com/inward/record.url?scp=84863311060&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863311060&partnerID=8YFLogxK

U2 - 10.1166/asl.2012.3904

DO - 10.1166/asl.2012.3904

M3 - Article

AN - SCOPUS:84863311060

SN - 1936-6612

VL - 13

SP - 863

EP - 866

JO - Advanced Science Letters

JF - Advanced Science Letters

ER -

Control chart pattern recognition of manufacturing process using wavelet feature-based artificial neural networks

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this