Confidence assessment of quality prediction from process measurement in sequential manufacturing processes

Nong Ye, Qiu Zhong, Gregory E. Rahn

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Sequential manufacturing processes are common in many manufacturing industries. We can use an artificial neural network (ANN) technique to build a model of manufacturing processes to capture the relationship between process measures and production unit quality. Using the ANN model, the quality value of a production unit can be predicted for its process measures. In addition to the predicted quality value, we need to assess our confidence in the predicted quality value through a confidence interval (prediction interval). Little work exists to assess the confidence in ANN outputs. This paper presents a comparative study of several methods in assessing the confidence in ANN outputs for quality prediction. We investigate two new methods: the variance estimation method and the distribution estimation method, in comparison with two existing methods: the error estimation method and the linear regression method. With respect to prediction accuracy and power, our results show that the distribution estimation method appears very promising among the four methods. However, the distribution estimation method requires much computation and storage during training and prediction, which may create difficulty in real-time quality monitoring and control. For the consideration of computation and storage requirement, the variance estimation method provides an acceptable solution. The error estimation method produces the worst performance among the four methods.

Original languageEnglish (US)
Pages (from-to)177-184
Number of pages8
JournalIEEE Transactions on Electronics Packaging Manufacturing
Volume23
Issue number3
DOIs
StatePublished - Jul 2000

Fingerprint

Neural networks
Error analysis
Linear regression
Monitoring
Industry

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Confidence assessment of quality prediction from process measurement in sequential manufacturing processes. / Ye, Nong; Zhong, Qiu; Rahn, Gregory E.

In: IEEE Transactions on Electronics Packaging Manufacturing, Vol. 23, No. 3, 07.2000, p. 177-184.

Research output: Contribution to journalArticle

@article{5ac453d6b6124b488c7c02bf3338566c,
title = "Confidence assessment of quality prediction from process measurement in sequential manufacturing processes",
abstract = "Sequential manufacturing processes are common in many manufacturing industries. We can use an artificial neural network (ANN) technique to build a model of manufacturing processes to capture the relationship between process measures and production unit quality. Using the ANN model, the quality value of a production unit can be predicted for its process measures. In addition to the predicted quality value, we need to assess our confidence in the predicted quality value through a confidence interval (prediction interval). Little work exists to assess the confidence in ANN outputs. This paper presents a comparative study of several methods in assessing the confidence in ANN outputs for quality prediction. We investigate two new methods: the variance estimation method and the distribution estimation method, in comparison with two existing methods: the error estimation method and the linear regression method. With respect to prediction accuracy and power, our results show that the distribution estimation method appears very promising among the four methods. However, the distribution estimation method requires much computation and storage during training and prediction, which may create difficulty in real-time quality monitoring and control. For the consideration of computation and storage requirement, the variance estimation method provides an acceptable solution. The error estimation method produces the worst performance among the four methods.",
author = "Nong Ye and Qiu Zhong and Rahn, {Gregory E.}",
year = "2000",
month = "7",
doi = "10.1109/6104.873245",
language = "English (US)",
volume = "23",
pages = "177--184",
journal = "IEEE Transactions on Electronics Packaging Manufacturing",
issn = "1521-334X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Confidence assessment of quality prediction from process measurement in sequential manufacturing processes

AU - Ye, Nong

AU - Zhong, Qiu

AU - Rahn, Gregory E.

PY - 2000/7

Y1 - 2000/7

N2 - Sequential manufacturing processes are common in many manufacturing industries. We can use an artificial neural network (ANN) technique to build a model of manufacturing processes to capture the relationship between process measures and production unit quality. Using the ANN model, the quality value of a production unit can be predicted for its process measures. In addition to the predicted quality value, we need to assess our confidence in the predicted quality value through a confidence interval (prediction interval). Little work exists to assess the confidence in ANN outputs. This paper presents a comparative study of several methods in assessing the confidence in ANN outputs for quality prediction. We investigate two new methods: the variance estimation method and the distribution estimation method, in comparison with two existing methods: the error estimation method and the linear regression method. With respect to prediction accuracy and power, our results show that the distribution estimation method appears very promising among the four methods. However, the distribution estimation method requires much computation and storage during training and prediction, which may create difficulty in real-time quality monitoring and control. For the consideration of computation and storage requirement, the variance estimation method provides an acceptable solution. The error estimation method produces the worst performance among the four methods.

AB - Sequential manufacturing processes are common in many manufacturing industries. We can use an artificial neural network (ANN) technique to build a model of manufacturing processes to capture the relationship between process measures and production unit quality. Using the ANN model, the quality value of a production unit can be predicted for its process measures. In addition to the predicted quality value, we need to assess our confidence in the predicted quality value through a confidence interval (prediction interval). Little work exists to assess the confidence in ANN outputs. This paper presents a comparative study of several methods in assessing the confidence in ANN outputs for quality prediction. We investigate two new methods: the variance estimation method and the distribution estimation method, in comparison with two existing methods: the error estimation method and the linear regression method. With respect to prediction accuracy and power, our results show that the distribution estimation method appears very promising among the four methods. However, the distribution estimation method requires much computation and storage during training and prediction, which may create difficulty in real-time quality monitoring and control. For the consideration of computation and storage requirement, the variance estimation method provides an acceptable solution. The error estimation method produces the worst performance among the four methods.

UR - http://www.scopus.com/inward/record.url?scp=0034223257&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034223257&partnerID=8YFLogxK

U2 - 10.1109/6104.873245

DO - 10.1109/6104.873245

M3 - Article

VL - 23

SP - 177

EP - 184

JO - IEEE Transactions on Electronics Packaging Manufacturing

JF - IEEE Transactions on Electronics Packaging Manufacturing

SN - 1521-334X

IS - 3

ER -