Information-based inspection allocation for real-time inspection systems

Adan Verduzco, Jesus Villalobos, Benjamin Vega

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

The use of real-time Automated Visual Inspection (AVI) in the electronics assembly industry is subject to cycle time constraints determined by the manufacturing system. These constraints must be met to maintain the nominal production rate. A problem thus created is determining which components to inspect at each one of the AVI stations such that the inspection time available is used in an optimal way. This paper presents a real-time inspection allocation that is based on the information gained by inspecting one additional component. The selection of which components to inspect is modeled as an information maximization problem. A modified Knapsack greedy heuristic is used to find near-optimal solutions to this optimization problem within the required time constraints.

Original languageEnglish (US)
Pages (from-to)13-22
Number of pages10
JournalJournal of Manufacturing Systems
Volume20
Issue number1
StatePublished - 2001

Fingerprint

Inspection
Electronic equipment
Industry
Time constraints

Keywords

  • Automated Visual Inspection
  • Flexible Inspection Systems
  • Information Gain
  • Inspection Allocation

ASJC Scopus subject areas

  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering

Cite this

Information-based inspection allocation for real-time inspection systems. / Verduzco, Adan; Villalobos, Jesus; Vega, Benjamin.

In: Journal of Manufacturing Systems, Vol. 20, No. 1, 2001, p. 13-22.

Research output: Contribution to journalArticle

@article{9be95946f93d4405b2ee722236c87d95,
title = "Information-based inspection allocation for real-time inspection systems",
abstract = "The use of real-time Automated Visual Inspection (AVI) in the electronics assembly industry is subject to cycle time constraints determined by the manufacturing system. These constraints must be met to maintain the nominal production rate. A problem thus created is determining which components to inspect at each one of the AVI stations such that the inspection time available is used in an optimal way. This paper presents a real-time inspection allocation that is based on the information gained by inspecting one additional component. The selection of which components to inspect is modeled as an information maximization problem. A modified Knapsack greedy heuristic is used to find near-optimal solutions to this optimization problem within the required time constraints.",
keywords = "Automated Visual Inspection, Flexible Inspection Systems, Information Gain, Inspection Allocation",
author = "Adan Verduzco and Jesus Villalobos and Benjamin Vega",
year = "2001",
language = "English (US)",
volume = "20",
pages = "13--22",
journal = "Journal of Manufacturing Systems",
issn = "0278-6125",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Information-based inspection allocation for real-time inspection systems

AU - Verduzco, Adan

AU - Villalobos, Jesus

AU - Vega, Benjamin

PY - 2001

Y1 - 2001

N2 - The use of real-time Automated Visual Inspection (AVI) in the electronics assembly industry is subject to cycle time constraints determined by the manufacturing system. These constraints must be met to maintain the nominal production rate. A problem thus created is determining which components to inspect at each one of the AVI stations such that the inspection time available is used in an optimal way. This paper presents a real-time inspection allocation that is based on the information gained by inspecting one additional component. The selection of which components to inspect is modeled as an information maximization problem. A modified Knapsack greedy heuristic is used to find near-optimal solutions to this optimization problem within the required time constraints.

AB - The use of real-time Automated Visual Inspection (AVI) in the electronics assembly industry is subject to cycle time constraints determined by the manufacturing system. These constraints must be met to maintain the nominal production rate. A problem thus created is determining which components to inspect at each one of the AVI stations such that the inspection time available is used in an optimal way. This paper presents a real-time inspection allocation that is based on the information gained by inspecting one additional component. The selection of which components to inspect is modeled as an information maximization problem. A modified Knapsack greedy heuristic is used to find near-optimal solutions to this optimization problem within the required time constraints.

KW - Automated Visual Inspection

KW - Flexible Inspection Systems

KW - Information Gain

KW - Inspection Allocation

UR - http://www.scopus.com/inward/record.url?scp=0040028632&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0040028632&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0040028632

VL - 20

SP - 13

EP - 22

JO - Journal of Manufacturing Systems

JF - Journal of Manufacturing Systems

SN - 0278-6125

IS - 1

ER -