A new technique for the prediction of non-linear material behavior

J. A. Wang; N. S. Rao

doi:10.1016/S0022-3115(01)00750-4

A new technique for the prediction of non-linear material behavior

J. A. Wang, N. S. Rao

Autonomous and Complex Systems

Oak Ridge National Laboratory

Research output: Contribution to journal › Article › peer-review

7 Scopus citations

Abstract

A new methodology is developed for the prediction of material behavior, such as aging processes, by utilizing a combination of domain models and non-linear estimators including neural networks and nearest neighbor regressions. This methodology is applied to the problem of predicting embrittilement levels in light-water reactors by combining the existing models with the conventional non-linear estimators. The Power Reactor Embrittlement Database is used in this study. The results indicate that the combined embrittlement predictor achieved about 56.5% and 32.8% reductions in the uncertainties for General Electric Boiling Water Reactor plate and weld data compared to Regulatory Guide 1.99, Revision 2, respectively. The implications of irradiation temperature effect to the development of radiation embrittlement model are then discussed.

Original language	English
Pages (from-to)	193-202
Number of pages	10
Journal	Journal of Nuclear Materials
Volume	301
Issue number	2-3
DOIs	https://doi.org/10.1016/S0022-3115(01)00750-4
State	Published - Mar 2002

Funding

The authors gratefully acknowledge the efforts of R.K. Nanstad for his valuable comments on this research. This research is sponsored by the R&D Seed Money Program of Oak Ridge National Laboratory, and by Engineering Research Program of Office of Basic Energy Sciences of US Department of Energy, under contract DE-AC05-00OR22725 with UT-Battelle, LLC.

Funders	Funder number
Basic Energy Sciences of US Department of Energy	DE-AC05-00OR22725
Oak Ridge National Laboratory

Access to Document

10.1016/S0022-3115(01)00750-4

Cite this

@article{4e7bb62e30f14bc59a2f01ddce8786a0,

title = "A new technique for the prediction of non-linear material behavior",

abstract = "A new methodology is developed for the prediction of material behavior, such as aging processes, by utilizing a combination of domain models and non-linear estimators including neural networks and nearest neighbor regressions. This methodology is applied to the problem of predicting embrittilement levels in light-water reactors by combining the existing models with the conventional non-linear estimators. The Power Reactor Embrittlement Database is used in this study. The results indicate that the combined embrittlement predictor achieved about 56.5% and 32.8% reductions in the uncertainties for General Electric Boiling Water Reactor plate and weld data compared to Regulatory Guide 1.99, Revision 2, respectively. The implications of irradiation temperature effect to the development of radiation embrittlement model are then discussed.",

author = "Wang, {J. A.} and Rao, {N. S.}",

year = "2002",

month = mar,

doi = "10.1016/S0022-3115(01)00750-4",

language = "English",

volume = "301",

pages = "193--202",

journal = "Journal of Nuclear Materials",

issn = "0022-3115",

publisher = "Elsevier",

number = "2-3",

}

TY - JOUR

T1 - A new technique for the prediction of non-linear material behavior

AU - Wang, J. A.

AU - Rao, N. S.

PY - 2002/3

Y1 - 2002/3

N2 - A new methodology is developed for the prediction of material behavior, such as aging processes, by utilizing a combination of domain models and non-linear estimators including neural networks and nearest neighbor regressions. This methodology is applied to the problem of predicting embrittilement levels in light-water reactors by combining the existing models with the conventional non-linear estimators. The Power Reactor Embrittlement Database is used in this study. The results indicate that the combined embrittlement predictor achieved about 56.5% and 32.8% reductions in the uncertainties for General Electric Boiling Water Reactor plate and weld data compared to Regulatory Guide 1.99, Revision 2, respectively. The implications of irradiation temperature effect to the development of radiation embrittlement model are then discussed.

AB - A new methodology is developed for the prediction of material behavior, such as aging processes, by utilizing a combination of domain models and non-linear estimators including neural networks and nearest neighbor regressions. This methodology is applied to the problem of predicting embrittilement levels in light-water reactors by combining the existing models with the conventional non-linear estimators. The Power Reactor Embrittlement Database is used in this study. The results indicate that the combined embrittlement predictor achieved about 56.5% and 32.8% reductions in the uncertainties for General Electric Boiling Water Reactor plate and weld data compared to Regulatory Guide 1.99, Revision 2, respectively. The implications of irradiation temperature effect to the development of radiation embrittlement model are then discussed.

UR - http://www.scopus.com/inward/record.url?scp=0036499017&partnerID=8YFLogxK

U2 - 10.1016/S0022-3115(01)00750-4

DO - 10.1016/S0022-3115(01)00750-4

M3 - Article

AN - SCOPUS:0036499017

SN - 0022-3115

VL - 301

SP - 193

EP - 202

JO - Journal of Nuclear Materials

JF - Journal of Nuclear Materials

IS - 2-3

ER -

A new technique for the prediction of non-linear material behavior

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Cite this