Abnormal control chart pattern classification optimisation using multi layered perceptron

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In today's industry, control charts are widely used to monitor production process. The abnormal patterns of a quality control chart could reveal problems that occur in the process. In the recent years, as an alternative of the traditional process quality management methods, such as Shewhart Statistical Process Control (SPC), Artificial Neural Networks (ANN) have been widely used to recognize the abnormal pattern of control charts. Various types of patterns are observed in control charts. Identification of these Control Chart Patterns (CCPs) can provide clues to potential quality problems in the manufacturing process. Each type of control chart pattern has its own geometric shape and various related features can represent this shape. Feature-based approaches can facilitate efficient pattern recognition since extracted shape features represent the main characteristics of the patterns in a condensed form. The objective of this study was to evaluate the relative performance of a feature-based CCP recognizer compared with the raw data-based recognizer. The study focused on recognition of six commonly researched CCPs plotted on the Shewhart X-bar chart. The ANN-based CCP recognizer trained using the nine shape features resulted in significantly better performance and generalization compared with the raw data-based recognizer.

Original languageEnglish
Pages (from-to)4690-4695
Number of pages6
JournalResearch Journal of Applied Sciences, Engineering and Technology
Volume7
Issue number22
Publication statusPublished - 2014

Fingerprint

Pattern recognition
Neural networks
Control charts
Statistical process control
Quality management
Quality control
Industry

Keywords

  • Artificial neural networks
  • Control chart patterns
  • Shape features
  • Statistical process control

ASJC Scopus subject areas

  • Engineering(all)
  • Computer Science(all)

Cite this

@article{20ada29e653a425f9c617342e1b59331,
title = "Abnormal control chart pattern classification optimisation using multi layered perceptron",
abstract = "In today's industry, control charts are widely used to monitor production process. The abnormal patterns of a quality control chart could reveal problems that occur in the process. In the recent years, as an alternative of the traditional process quality management methods, such as Shewhart Statistical Process Control (SPC), Artificial Neural Networks (ANN) have been widely used to recognize the abnormal pattern of control charts. Various types of patterns are observed in control charts. Identification of these Control Chart Patterns (CCPs) can provide clues to potential quality problems in the manufacturing process. Each type of control chart pattern has its own geometric shape and various related features can represent this shape. Feature-based approaches can facilitate efficient pattern recognition since extracted shape features represent the main characteristics of the patterns in a condensed form. The objective of this study was to evaluate the relative performance of a feature-based CCP recognizer compared with the raw data-based recognizer. The study focused on recognition of six commonly researched CCPs plotted on the Shewhart X-bar chart. The ANN-based CCP recognizer trained using the nine shape features resulted in significantly better performance and generalization compared with the raw data-based recognizer.",
keywords = "Artificial neural networks, Control chart patterns, Shape features, Statistical process control",
author = "Mitra Mahdiani and {Mohamad Judi}, Hairulliza and {Sahari @ Ashaari}, Noraidah",
year = "2014",
language = "English",
volume = "7",
pages = "4690--4695",
journal = "Research Journal of Applied Sciences, Engineering and Technology",
issn = "2040-7459",
publisher = "Maxwell Scientific Publications",
number = "22",

}

TY - JOUR

T1 - Abnormal control chart pattern classification optimisation using multi layered perceptron

AU - Mahdiani, Mitra

AU - Mohamad Judi, Hairulliza

AU - Sahari @ Ashaari, Noraidah

PY - 2014

Y1 - 2014

N2 - In today's industry, control charts are widely used to monitor production process. The abnormal patterns of a quality control chart could reveal problems that occur in the process. In the recent years, as an alternative of the traditional process quality management methods, such as Shewhart Statistical Process Control (SPC), Artificial Neural Networks (ANN) have been widely used to recognize the abnormal pattern of control charts. Various types of patterns are observed in control charts. Identification of these Control Chart Patterns (CCPs) can provide clues to potential quality problems in the manufacturing process. Each type of control chart pattern has its own geometric shape and various related features can represent this shape. Feature-based approaches can facilitate efficient pattern recognition since extracted shape features represent the main characteristics of the patterns in a condensed form. The objective of this study was to evaluate the relative performance of a feature-based CCP recognizer compared with the raw data-based recognizer. The study focused on recognition of six commonly researched CCPs plotted on the Shewhart X-bar chart. The ANN-based CCP recognizer trained using the nine shape features resulted in significantly better performance and generalization compared with the raw data-based recognizer.

AB - In today's industry, control charts are widely used to monitor production process. The abnormal patterns of a quality control chart could reveal problems that occur in the process. In the recent years, as an alternative of the traditional process quality management methods, such as Shewhart Statistical Process Control (SPC), Artificial Neural Networks (ANN) have been widely used to recognize the abnormal pattern of control charts. Various types of patterns are observed in control charts. Identification of these Control Chart Patterns (CCPs) can provide clues to potential quality problems in the manufacturing process. Each type of control chart pattern has its own geometric shape and various related features can represent this shape. Feature-based approaches can facilitate efficient pattern recognition since extracted shape features represent the main characteristics of the patterns in a condensed form. The objective of this study was to evaluate the relative performance of a feature-based CCP recognizer compared with the raw data-based recognizer. The study focused on recognition of six commonly researched CCPs plotted on the Shewhart X-bar chart. The ANN-based CCP recognizer trained using the nine shape features resulted in significantly better performance and generalization compared with the raw data-based recognizer.

KW - Artificial neural networks

KW - Control chart patterns

KW - Shape features

KW - Statistical process control

UR - http://www.scopus.com/inward/record.url?scp=84905665921&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905665921&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84905665921

VL - 7

SP - 4690

EP - 4695

JO - Research Journal of Applied Sciences, Engineering and Technology

JF - Research Journal of Applied Sciences, Engineering and Technology

SN - 2040-7459

IS - 22

ER -