Experimental design and regression analysis in simulation

An automated flowline case study

Chinho Lin, Christian N. Madu, Chu Hua Kuei

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

This paper uses an experimental design and regression metamodels to evaluate the relationships between the throughput of an automated flowline and other system parameters such as the number of machines in the flowline, machine processing times, capacity of the buffer, mean time between failure, and the mean time to repair. The Taguchi approach is used in the experimental design. Sixteen simulation runs are generated to test the significance of the main effects and the two-factor interactions. Consequently, Kleijnen's regression metamodel approach is used to develop predictor models for the automated flowline throughput. Finally, a decision model is formulated to determine the optimum design level of each factor.

Original languageEnglish
Pages (from-to)845-861
Number of pages17
JournalMicroelectronics Reliability
Volume34
Issue number5
DOIs
Publication statusPublished - 1994 Jan 1

Fingerprint

Flowlines
design analysis
Regression analysis
Design of experiments
regression analysis
MTBF
Throughput
simulation
Buffers
Repair
buffers
Processing
predictions
flowable hybrid composite
interactions

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Condensed Matter Physics
  • Safety, Risk, Reliability and Quality
  • Surfaces, Coatings and Films
  • Electrical and Electronic Engineering

Cite this

@article{6a6e8c29ff374c07a10e40de38cf1360,
title = "Experimental design and regression analysis in simulation: An automated flowline case study",
abstract = "This paper uses an experimental design and regression metamodels to evaluate the relationships between the throughput of an automated flowline and other system parameters such as the number of machines in the flowline, machine processing times, capacity of the buffer, mean time between failure, and the mean time to repair. The Taguchi approach is used in the experimental design. Sixteen simulation runs are generated to test the significance of the main effects and the two-factor interactions. Consequently, Kleijnen's regression metamodel approach is used to develop predictor models for the automated flowline throughput. Finally, a decision model is formulated to determine the optimum design level of each factor.",
author = "Chinho Lin and Madu, {Christian N.} and Kuei, {Chu Hua}",
year = "1994",
month = "1",
day = "1",
doi = "10.1016/0026-2714(94)90009-4",
language = "English",
volume = "34",
pages = "845--861",
journal = "Microelectronics Reliability",
issn = "0026-2714",
publisher = "Elsevier Limited",
number = "5",

}

Experimental design and regression analysis in simulation : An automated flowline case study. / Lin, Chinho; Madu, Christian N.; Kuei, Chu Hua.

In: Microelectronics Reliability, Vol. 34, No. 5, 01.01.1994, p. 845-861.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Experimental design and regression analysis in simulation

T2 - An automated flowline case study

AU - Lin, Chinho

AU - Madu, Christian N.

AU - Kuei, Chu Hua

PY - 1994/1/1

Y1 - 1994/1/1

N2 - This paper uses an experimental design and regression metamodels to evaluate the relationships between the throughput of an automated flowline and other system parameters such as the number of machines in the flowline, machine processing times, capacity of the buffer, mean time between failure, and the mean time to repair. The Taguchi approach is used in the experimental design. Sixteen simulation runs are generated to test the significance of the main effects and the two-factor interactions. Consequently, Kleijnen's regression metamodel approach is used to develop predictor models for the automated flowline throughput. Finally, a decision model is formulated to determine the optimum design level of each factor.

AB - This paper uses an experimental design and regression metamodels to evaluate the relationships between the throughput of an automated flowline and other system parameters such as the number of machines in the flowline, machine processing times, capacity of the buffer, mean time between failure, and the mean time to repair. The Taguchi approach is used in the experimental design. Sixteen simulation runs are generated to test the significance of the main effects and the two-factor interactions. Consequently, Kleijnen's regression metamodel approach is used to develop predictor models for the automated flowline throughput. Finally, a decision model is formulated to determine the optimum design level of each factor.

UR - http://www.scopus.com/inward/record.url?scp=0028426538&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028426538&partnerID=8YFLogxK

U2 - 10.1016/0026-2714(94)90009-4

DO - 10.1016/0026-2714(94)90009-4

M3 - Article

VL - 34

SP - 845

EP - 861

JO - Microelectronics Reliability

JF - Microelectronics Reliability

SN - 0026-2714

IS - 5

ER -