Principal component analysis-based image fusion routine with application to automotive stamping split detection

Yi Zhou, Abdel Mayyas, Mohammed A. Omar

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

This study discusses the development and implementation of noncontact split detection method, for automotive stamping press lines. The system features a novel fusion routine that combines thermal and visible images in real-time, assisted with principle component analysis (PCA) subroutine. The thermal detector scans the temperature maps of the highly reflective steel sheets in the die cavity to locate abnormal temperature readings that might be indicative of high local wrinkling pressure, while the visible vision system offsets the blurring effect caused by heat diffusion across the surface and provide a spatial reference. The employed PCA uses a new singular value decomposition (SVD) that is more efficient than standard SVD computations, enabling the PCA to be applied in real-time acquisitions (∼30Hz). The PCA affects the images by reducing the nonvalue data content (reduce redundancy, noise) while highlighting important features. The fusion is done using a pixel-level algorithm using different variations, where each is assessed for performance. The proposed detection system has been tested on an automotive pressline to assess the formability of complex-shaped panels and have shown high detection success rate. Different splits with variant shape, size, and severity have been detected under actual operating conditions.

Original languageEnglish (US)
Pages (from-to)76-91
Number of pages16
JournalResearch in Nondestructive Evaluation
Volume22
Issue number2
DOIs
StatePublished - Apr 2011
Externally publishedYes

Fingerprint

stamping
Image fusion
Stamping
principal components analysis
Principal component analysis
fusion
Singular value decomposition
Subroutines
Steel sheet
Formability
decomposition
wrinkling
subroutines
Redundancy
blurring
redundancy
Pixels
Detectors
acquisition
Temperature

Keywords

  • principal component analysis
  • sensor fusion
  • single value decomposition
  • thermo-plastic effect

ASJC Scopus subject areas

  • Condensed Matter Physics
  • Materials Science(all)
  • Mechanics of Materials
  • Mechanical Engineering

Cite this

Principal component analysis-based image fusion routine with application to automotive stamping split detection. / Zhou, Yi; Mayyas, Abdel; Omar, Mohammed A.

In: Research in Nondestructive Evaluation, Vol. 22, No. 2, 04.2011, p. 76-91.

Research output: Contribution to journalArticle

@article{2a04b7d2579d42f48874334d445878b9,
title = "Principal component analysis-based image fusion routine with application to automotive stamping split detection",
abstract = "This study discusses the development and implementation of noncontact split detection method, for automotive stamping press lines. The system features a novel fusion routine that combines thermal and visible images in real-time, assisted with principle component analysis (PCA) subroutine. The thermal detector scans the temperature maps of the highly reflective steel sheets in the die cavity to locate abnormal temperature readings that might be indicative of high local wrinkling pressure, while the visible vision system offsets the blurring effect caused by heat diffusion across the surface and provide a spatial reference. The employed PCA uses a new singular value decomposition (SVD) that is more efficient than standard SVD computations, enabling the PCA to be applied in real-time acquisitions (∼30Hz). The PCA affects the images by reducing the nonvalue data content (reduce redundancy, noise) while highlighting important features. The fusion is done using a pixel-level algorithm using different variations, where each is assessed for performance. The proposed detection system has been tested on an automotive pressline to assess the formability of complex-shaped panels and have shown high detection success rate. Different splits with variant shape, size, and severity have been detected under actual operating conditions.",
keywords = "principal component analysis, sensor fusion, single value decomposition, thermo-plastic effect",
author = "Yi Zhou and Abdel Mayyas and Omar, {Mohammed A.}",
year = "2011",
month = "4",
doi = "10.1080/09349847.2011.553348",
language = "English (US)",
volume = "22",
pages = "76--91",
journal = "Research in Nondestructive Evaluation",
issn = "0934-9847",
publisher = "Taylor and Francis Ltd.",
number = "2",

}

TY - JOUR

T1 - Principal component analysis-based image fusion routine with application to automotive stamping split detection

AU - Zhou, Yi

AU - Mayyas, Abdel

AU - Omar, Mohammed A.

PY - 2011/4

Y1 - 2011/4

N2 - This study discusses the development and implementation of noncontact split detection method, for automotive stamping press lines. The system features a novel fusion routine that combines thermal and visible images in real-time, assisted with principle component analysis (PCA) subroutine. The thermal detector scans the temperature maps of the highly reflective steel sheets in the die cavity to locate abnormal temperature readings that might be indicative of high local wrinkling pressure, while the visible vision system offsets the blurring effect caused by heat diffusion across the surface and provide a spatial reference. The employed PCA uses a new singular value decomposition (SVD) that is more efficient than standard SVD computations, enabling the PCA to be applied in real-time acquisitions (∼30Hz). The PCA affects the images by reducing the nonvalue data content (reduce redundancy, noise) while highlighting important features. The fusion is done using a pixel-level algorithm using different variations, where each is assessed for performance. The proposed detection system has been tested on an automotive pressline to assess the formability of complex-shaped panels and have shown high detection success rate. Different splits with variant shape, size, and severity have been detected under actual operating conditions.

AB - This study discusses the development and implementation of noncontact split detection method, for automotive stamping press lines. The system features a novel fusion routine that combines thermal and visible images in real-time, assisted with principle component analysis (PCA) subroutine. The thermal detector scans the temperature maps of the highly reflective steel sheets in the die cavity to locate abnormal temperature readings that might be indicative of high local wrinkling pressure, while the visible vision system offsets the blurring effect caused by heat diffusion across the surface and provide a spatial reference. The employed PCA uses a new singular value decomposition (SVD) that is more efficient than standard SVD computations, enabling the PCA to be applied in real-time acquisitions (∼30Hz). The PCA affects the images by reducing the nonvalue data content (reduce redundancy, noise) while highlighting important features. The fusion is done using a pixel-level algorithm using different variations, where each is assessed for performance. The proposed detection system has been tested on an automotive pressline to assess the formability of complex-shaped panels and have shown high detection success rate. Different splits with variant shape, size, and severity have been detected under actual operating conditions.

KW - principal component analysis

KW - sensor fusion

KW - single value decomposition

KW - thermo-plastic effect

UR - http://www.scopus.com/inward/record.url?scp=79953223759&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79953223759&partnerID=8YFLogxK

U2 - 10.1080/09349847.2011.553348

DO - 10.1080/09349847.2011.553348

M3 - Article

VL - 22

SP - 76

EP - 91

JO - Research in Nondestructive Evaluation

JF - Research in Nondestructive Evaluation

SN - 0934-9847

IS - 2

ER -