A yield forecast model for pilot products using support vector regression and manufacturing experience-the case of large-size polariser

Der-Chiang Li, Chiao Wen Liu, Yao Hwei Fang, Cheng Chien Chen

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

To build up a manufacturing management model for a newly developed product is fundamentally a difficult problem, because the collected data in the early manufacturing stages is usually insufficient when data size is small. There are several researches on this topic, and most of them focus on the original data analysis such as building up virtual samples to increase the data number. As to other approaches, the usage of old or similar manufacturing experience may be an alternative approach to help in modelling a small data set, by taking advantage of the fact that the new product's manufacturing process could be based on the experience of the old one. This research proposes a combination of support vector regression (SVR) and the manufacturing experience to build up the manufacturing knowledge model for a new product. A real-problem of a new product yield forecast model in a polariser manufacturing company is demonstrated, where two approaches are proposed, and the results show that the presented approach is superior to the performance of a linear regression and back-propagation neural network. The case study shows that the input of the old or similar manufacturing experience into the forecast model can reduce the error rate and enhance the model forecasting ability.

Original languageEnglish
Pages (from-to)5481-5496
Number of pages16
JournalInternational Journal of Production Research
Volume48
Issue number18
DOIs
Publication statusPublished - 2010 Jan 1

Fingerprint

Support vector regression
Manufacturing
Backpropagation
Linear regression
New products
Neural networks
Industry
Modeling
Knowledge model
Manufacturing companies
Management model
Manufacturing process
Manufacturing management
Back-propagation neural network

All Science Journal Classification (ASJC) codes

  • Strategy and Management
  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering

Cite this

@article{d5ac3b1e555242efb22e302b236ae117,
title = "A yield forecast model for pilot products using support vector regression and manufacturing experience-the case of large-size polariser",
abstract = "To build up a manufacturing management model for a newly developed product is fundamentally a difficult problem, because the collected data in the early manufacturing stages is usually insufficient when data size is small. There are several researches on this topic, and most of them focus on the original data analysis such as building up virtual samples to increase the data number. As to other approaches, the usage of old or similar manufacturing experience may be an alternative approach to help in modelling a small data set, by taking advantage of the fact that the new product's manufacturing process could be based on the experience of the old one. This research proposes a combination of support vector regression (SVR) and the manufacturing experience to build up the manufacturing knowledge model for a new product. A real-problem of a new product yield forecast model in a polariser manufacturing company is demonstrated, where two approaches are proposed, and the results show that the presented approach is superior to the performance of a linear regression and back-propagation neural network. The case study shows that the input of the old or similar manufacturing experience into the forecast model can reduce the error rate and enhance the model forecasting ability.",
author = "Der-Chiang Li and Liu, {Chiao Wen} and Fang, {Yao Hwei} and Chen, {Cheng Chien}",
year = "2010",
month = "1",
day = "1",
doi = "10.1080/00207540903100051",
language = "English",
volume = "48",
pages = "5481--5496",
journal = "International Journal of Production Research",
issn = "0020-7543",
publisher = "Taylor and Francis Ltd.",
number = "18",

}

A yield forecast model for pilot products using support vector regression and manufacturing experience-the case of large-size polariser. / Li, Der-Chiang; Liu, Chiao Wen; Fang, Yao Hwei; Chen, Cheng Chien.

In: International Journal of Production Research, Vol. 48, No. 18, 01.01.2010, p. 5481-5496.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A yield forecast model for pilot products using support vector regression and manufacturing experience-the case of large-size polariser

AU - Li, Der-Chiang

AU - Liu, Chiao Wen

AU - Fang, Yao Hwei

AU - Chen, Cheng Chien

PY - 2010/1/1

Y1 - 2010/1/1

N2 - To build up a manufacturing management model for a newly developed product is fundamentally a difficult problem, because the collected data in the early manufacturing stages is usually insufficient when data size is small. There are several researches on this topic, and most of them focus on the original data analysis such as building up virtual samples to increase the data number. As to other approaches, the usage of old or similar manufacturing experience may be an alternative approach to help in modelling a small data set, by taking advantage of the fact that the new product's manufacturing process could be based on the experience of the old one. This research proposes a combination of support vector regression (SVR) and the manufacturing experience to build up the manufacturing knowledge model for a new product. A real-problem of a new product yield forecast model in a polariser manufacturing company is demonstrated, where two approaches are proposed, and the results show that the presented approach is superior to the performance of a linear regression and back-propagation neural network. The case study shows that the input of the old or similar manufacturing experience into the forecast model can reduce the error rate and enhance the model forecasting ability.

AB - To build up a manufacturing management model for a newly developed product is fundamentally a difficult problem, because the collected data in the early manufacturing stages is usually insufficient when data size is small. There are several researches on this topic, and most of them focus on the original data analysis such as building up virtual samples to increase the data number. As to other approaches, the usage of old or similar manufacturing experience may be an alternative approach to help in modelling a small data set, by taking advantage of the fact that the new product's manufacturing process could be based on the experience of the old one. This research proposes a combination of support vector regression (SVR) and the manufacturing experience to build up the manufacturing knowledge model for a new product. A real-problem of a new product yield forecast model in a polariser manufacturing company is demonstrated, where two approaches are proposed, and the results show that the presented approach is superior to the performance of a linear regression and back-propagation neural network. The case study shows that the input of the old or similar manufacturing experience into the forecast model can reduce the error rate and enhance the model forecasting ability.

UR - http://www.scopus.com/inward/record.url?scp=77954580900&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954580900&partnerID=8YFLogxK

U2 - 10.1080/00207540903100051

DO - 10.1080/00207540903100051

M3 - Article

VL - 48

SP - 5481

EP - 5496

JO - International Journal of Production Research

JF - International Journal of Production Research

SN - 0020-7543

IS - 18

ER -