Analysis of degradation process with measurement errors

Rong Pan, Wendai Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Degradation tests are often applied on highly reliable products when the product performance can be repeatedly measured. In this paper, we compare two common types of degradation models - a nonlinear regression model and a stochastic process model. Particularly, we discuss the effects of measurement error on model parameter estimation and model selection. Using an example of photovoltaic product degradation, we (1) demonstrate the use of linear models for estimating model parameters, and (2) provide a hypothesis test for the statistical significance of product performance degradation. It shows that some forms of measurement errors, such as the drifting error of tester, can be easily incorporated into the analysis of stochastic degradation models.

Original languageEnglish (US)
Title of host publicationProceedings - Annual Reliability and Maintainability Symposium
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479928477
DOIs
StatePublished - 2014
Event60th Annual Reliability and Maintainability Symposium, RAMS 2014 - Colorado Springs, CO, United States
Duration: Jan 27 2014Jan 30 2014

Other

Other60th Annual Reliability and Maintainability Symposium, RAMS 2014
CountryUnited States
CityColorado Springs, CO
Period1/27/141/30/14

Fingerprint

Measurement errors
Measurement Error
Degradation
Nonlinear Regression Model
Hypothesis Test
Statistical Significance
Model Selection
Model
Process Model
Stochastic Model
Parameter Estimation
Stochastic Processes
Linear Model
Random processes
Parameter estimation
Demonstrate

Keywords

  • Degradation modeling
  • Hypothesis test
  • Linear models
  • Wiener process

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality
  • Mathematics(all)
  • Computer Science Applications

Cite this

Pan, R., & Wang, W. (2014). Analysis of degradation process with measurement errors. In Proceedings - Annual Reliability and Maintainability Symposium [6798513] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RAMS.2014.6798513

Analysis of degradation process with measurement errors. / Pan, Rong; Wang, Wendai.

Proceedings - Annual Reliability and Maintainability Symposium. Institute of Electrical and Electronics Engineers Inc., 2014. 6798513.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Pan, R & Wang, W 2014, Analysis of degradation process with measurement errors. in Proceedings - Annual Reliability and Maintainability Symposium., 6798513, Institute of Electrical and Electronics Engineers Inc., 60th Annual Reliability and Maintainability Symposium, RAMS 2014, Colorado Springs, CO, United States, 1/27/14. https://doi.org/10.1109/RAMS.2014.6798513
Pan R, Wang W. Analysis of degradation process with measurement errors. In Proceedings - Annual Reliability and Maintainability Symposium. Institute of Electrical and Electronics Engineers Inc. 2014. 6798513 https://doi.org/10.1109/RAMS.2014.6798513
Pan, Rong ; Wang, Wendai. / Analysis of degradation process with measurement errors. Proceedings - Annual Reliability and Maintainability Symposium. Institute of Electrical and Electronics Engineers Inc., 2014.
@inproceedings{939a98ed523c413a96ac5be72c5cd4b7,
title = "Analysis of degradation process with measurement errors",
abstract = "Degradation tests are often applied on highly reliable products when the product performance can be repeatedly measured. In this paper, we compare two common types of degradation models - a nonlinear regression model and a stochastic process model. Particularly, we discuss the effects of measurement error on model parameter estimation and model selection. Using an example of photovoltaic product degradation, we (1) demonstrate the use of linear models for estimating model parameters, and (2) provide a hypothesis test for the statistical significance of product performance degradation. It shows that some forms of measurement errors, such as the drifting error of tester, can be easily incorporated into the analysis of stochastic degradation models.",
keywords = "Degradation modeling, Hypothesis test, Linear models, Wiener process",
author = "Rong Pan and Wendai Wang",
year = "2014",
doi = "10.1109/RAMS.2014.6798513",
language = "English (US)",
isbn = "9781479928477",
booktitle = "Proceedings - Annual Reliability and Maintainability Symposium",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Analysis of degradation process with measurement errors

AU - Pan, Rong

AU - Wang, Wendai

PY - 2014

Y1 - 2014

N2 - Degradation tests are often applied on highly reliable products when the product performance can be repeatedly measured. In this paper, we compare two common types of degradation models - a nonlinear regression model and a stochastic process model. Particularly, we discuss the effects of measurement error on model parameter estimation and model selection. Using an example of photovoltaic product degradation, we (1) demonstrate the use of linear models for estimating model parameters, and (2) provide a hypothesis test for the statistical significance of product performance degradation. It shows that some forms of measurement errors, such as the drifting error of tester, can be easily incorporated into the analysis of stochastic degradation models.

AB - Degradation tests are often applied on highly reliable products when the product performance can be repeatedly measured. In this paper, we compare two common types of degradation models - a nonlinear regression model and a stochastic process model. Particularly, we discuss the effects of measurement error on model parameter estimation and model selection. Using an example of photovoltaic product degradation, we (1) demonstrate the use of linear models for estimating model parameters, and (2) provide a hypothesis test for the statistical significance of product performance degradation. It shows that some forms of measurement errors, such as the drifting error of tester, can be easily incorporated into the analysis of stochastic degradation models.

KW - Degradation modeling

KW - Hypothesis test

KW - Linear models

KW - Wiener process

UR - http://www.scopus.com/inward/record.url?scp=84900024021&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900024021&partnerID=8YFLogxK

U2 - 10.1109/RAMS.2014.6798513

DO - 10.1109/RAMS.2014.6798513

M3 - Conference contribution

SN - 9781479928477

BT - Proceedings - Annual Reliability and Maintainability Symposium

PB - Institute of Electrical and Electronics Engineers Inc.

ER -