TY - GEN
T1 - Advanced statistical tools for modelling of composition and processing parameters for alloy development
AU - Zrazhevsky, Greg
AU - Golodnikov, Alex
AU - Uryasev, Stan
AU - Zrazhevsky, Alex
N1 - Publisher Copyright:
© Springer International Publishing Switzerland 2015.
PY - 2015
Y1 - 2015
N2 - The paper presents new statistical approaches for modeling highly variable mechanical properties and screening specimens in development of new materials. Particularly, for steels, Charpy V-Notch (CVN) exhibits substantial scatter which complicates prediction of impact toughness. The paper proposes to use Conditional Value-at-Risk (CVaR) for screening specimens with respect to CVN. Two approaches to estimation of CVaR are discussed. The first approach is based on linear regression coming from the Mixed-Quantile Quadrangle, and the second approach builds CVN distribution with percentile regression, and then directly calculates CVaR. The accuracy of estimated CVaR is assessed with some variant of the coefficient of multiple determination. We estimated discrepancy between estimates derived by two approaches with the Mean Absolute Percentage error. We compared VaR and CVaR risk measures in the screening process. We proposed a modified procedure for ranking specimens, which takes into account the uncertainty in estimates of CVaR.
AB - The paper presents new statistical approaches for modeling highly variable mechanical properties and screening specimens in development of new materials. Particularly, for steels, Charpy V-Notch (CVN) exhibits substantial scatter which complicates prediction of impact toughness. The paper proposes to use Conditional Value-at-Risk (CVaR) for screening specimens with respect to CVN. Two approaches to estimation of CVaR are discussed. The first approach is based on linear regression coming from the Mixed-Quantile Quadrangle, and the second approach builds CVN distribution with percentile regression, and then directly calculates CVaR. The accuracy of estimated CVaR is assessed with some variant of the coefficient of multiple determination. We estimated discrepancy between estimates derived by two approaches with the Mean Absolute Percentage error. We compared VaR and CVaR risk measures in the screening process. We proposed a modified procedure for ranking specimens, which takes into account the uncertainty in estimates of CVaR.
KW - CVaR
KW - Samples
KW - Screening
KW - Statistical Modeling
KW - Steel
KW - Toughness
UR - https://www.scopus.com/pages/publications/84947430553
U2 - 10.1007/978-3-319-18567-5_21
DO - 10.1007/978-3-319-18567-5_21
M3 - Conference contribution
AN - SCOPUS:84947430553
SN - 9783319185668
T3 - Springer Proceedings in Mathematics and Statistics
SP - 393
EP - 413
BT - Optimization, Control, and Applications in the Information Age - In Honor of Panos M. Pardalos’s 60th Birthday
A2 - Migdalas, Athanasios
A2 - Karakitsiou, Athanasia
PB - Springer New York LLC
T2 - Conference on Optimization, Control and Applications in the Information Age, 2014
Y2 - 15 June 2014 through 20 June 2014
ER -