Investigating Practical Orthogonality Deviations in RSM for Improved Predictive Reliability Modeling
M. Arndt, and M. Dazer. RAMS 2024 Proceedings of Annual Reliability and Maintainablity Symposium, (2024)peer-review.
Abstract
Response Surface Methodology (RSM) models may encounter limitations when incorporated with non-orthogonalities in the design matrix. This holds especially when performing end-of-life tests or demonstrating multivariate reliability. Exemplarily applied to CCDs, unexpectedly inexecutable test runs, variations in test point settings, and further factor level shifts can lead to impairments in the design model and prediction capability. This issue is addressed within this work. The consequences of common orthogonality offsets and their implications for predictive modeling relevant to multivariate reliability estimation with confidence intervals are discussed in here. By analyzing selected orthogonality disparities, trends in variance shaping in the parameter space and beyond are captured and described. For this purpose, visualizations like contours and variance dispersions of the test designs are interpreted. Considering the marginal range of predicted values, this approach thus serves to evaluate effects relevant for extrapolation from accelerated parameter ranges with respect to an estimate of their confidence intervals. In this way, the results show that experimental design manipulations justified from practical application exemplarily in a k=2 CCD lead to a more manageable handling of variances in the prediction of model values – which is lastly illustrated in an exemplary layout.
%0 Conference Paper
%1 arndt2024investigating
%A Arndt, Marco
%A Dazer, Martin
%B RAMS 2024 Proceedings of Annual Reliability and Maintainablity Symposium
%D 2024
%K zuverlässigkeitstechnik dissertation LebensdauermodellZahnriemen M_Dazer M_Arndt
%T Investigating Practical Orthogonality Deviations in RSM for Improved Predictive Reliability Modeling
%U https://www.xcdsystem.com/rams/proceedings2024/
%X Response Surface Methodology (RSM) models may encounter limitations when incorporated with non-orthogonalities in the design matrix. This holds especially when performing end-of-life tests or demonstrating multivariate reliability. Exemplarily applied to CCDs, unexpectedly inexecutable test runs, variations in test point settings, and further factor level shifts can lead to impairments in the design model and prediction capability. This issue is addressed within this work. The consequences of common orthogonality offsets and their implications for predictive modeling relevant to multivariate reliability estimation with confidence intervals are discussed in here. By analyzing selected orthogonality disparities, trends in variance shaping in the parameter space and beyond are captured and described. For this purpose, visualizations like contours and variance dispersions of the test designs are interpreted. Considering the marginal range of predicted values, this approach thus serves to evaluate effects relevant for extrapolation from accelerated parameter ranges with respect to an estimate of their confidence intervals. In this way, the results show that experimental design manipulations justified from practical application exemplarily in a k=2 CCD lead to a more manageable handling of variances in the prediction of model values – which is lastly illustrated in an exemplary layout.
%@ 978-8-3503-0769-6
@inproceedings{arndt2024investigating,
abstract = {Response Surface Methodology (RSM) models may encounter limitations when incorporated with non-orthogonalities in the design matrix. This holds especially when performing end-of-life tests or demonstrating multivariate reliability. Exemplarily applied to CCDs, unexpectedly inexecutable test runs, variations in test point settings, and further factor level shifts can lead to impairments in the design model and prediction capability. This issue is addressed within this work. The consequences of common orthogonality offsets and their implications for predictive modeling relevant to multivariate reliability estimation with confidence intervals are discussed in here. By analyzing selected orthogonality disparities, trends in variance shaping in the parameter space and beyond are captured and described. For this purpose, visualizations like contours and variance dispersions of the test designs are interpreted. Considering the marginal range of predicted values, this approach thus serves to evaluate effects relevant for extrapolation from accelerated parameter ranges with respect to an estimate of their confidence intervals. In this way, the results show that experimental design manipulations justified from practical application exemplarily in a k=2 CCD lead to a more manageable handling of variances in the prediction of model values – which is lastly illustrated in an exemplary layout.},
added-at = {2024-02-09T11:47:19.000+0100},
author = {Arndt, Marco and Dazer, Martin},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2f26392b01e49de7baaa015bca48f16d3/ima-publ},
booktitle = {RAMS 2024 Proceedings of Annual Reliability and Maintainablity Symposium},
eventdate = {22.-25.01.2024},
eventtitle = {2024 Annual Reliability and Maintainablity Symposium (RAMS 2024)},
interhash = {2a8ca850d3e69884a77deeaf0dfe43cd},
intrahash = {f26392b01e49de7baaa015bca48f16d3},
isbn = {978-8-3503-0769-6},
issn = {2577-0993},
keywords = {zuverlässigkeitstechnik dissertation LebensdauermodellZahnriemen M_Dazer M_Arndt},
note = {peer-review},
timestamp = {2024-02-09T11:47:19.000+0100},
title = {Investigating Practical Orthogonality Deviations in RSM for Improved Predictive Reliability Modeling},
url = {https://www.xcdsystem.com/rams/proceedings2024/},
venue = {Albuquerque, NM, USA},
year = 2024
}
