Assessment of Outliers in Alloy Datasets Using Unsupervised Techniques

Wenzlick, Madison; Mamun, Osman; Devanathan, Ram; Rose, Kelly; Hawk, Jeffrey

doi:10.1007/s11837-022-05204-4

Title: Assessment of Outliers in Alloy Datasets Using Unsupervised Techniques

Journal Article · 18 May 2022 · JOM. Journal of the Minerals, Metals & Materials Society

DOI: https://doi.org/10.1007/s11837-022-05204-4 · OSTI ID:1876555

^[1]; Mamun, Osman ^[2];

^[2]; Rose, Kelly ^[3]; Hawk, Jeffrey ^[3]

National Energy Technology Lab. (NETL), Albany, OR (United States). Support Contractor
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
National Energy Technology Lab. (NETL), Albany, OR (United States)

We report advancements in data analytics techniques have enabled complex, disparate datasets to be leveraged for alloy design. Identifying outliers in a dataset can reduce noise, identify erroneous and/or anomalous records, prevent overfitting, and improve model assessment and optimization. In this work, two alloy datasets (9-12% Cr ferritic martensitic steels, and austenitic stainless steels) have been assessed for outliers using unsupervised techniques and supplemented with domain knowledge. Principal component analysis and k-means clustering were applied to the data, and points were assessed as outliers based on their distance away from other points in the cluster and from other points in the dataset. The outlier characteristics were investigated to determine both cluster-specific and overall trends in the properties of the outlier points. The approach demonstrated here is extensible to other alloy datasets for outlier identification and evaluation to improve the reliability of machine learning and modeling predictions for advanced alloy design.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: National Energy Technology Laboratory (NETL), Pittsburgh, PA, Morgantown, WV, and Albany, OR (United States); Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)

Sponsoring Organization:: USDOE Office of Fossil Energy (FE)

Grant/Contract Number:: 89243318CFE000003; AC05-76RL01830

OSTI ID:: 1876555

Report Number(s):: PNNL-SA-169146

Journal Information:: JOM. Journal of the Minerals, Metals & Materials Society, Journal Name: JOM. Journal of the Minerals, Metals & Materials Society Journal Issue: 7 Vol. 74; ISSN 1047-4838

Publisher:: SpringerCopyright Statement

Country of Publication:: United States

Language:: English

References (19)

Data Science Techniques, Assumptions, and Challenges in Alloy Clustering and Property Prediction Wenzlick, Madison; Mamun, Osman; Devanathan, Ram Journal of Materials Engineering and Performance, Vol. 30, Issue 2 https://doi.org/10.1007/s11665-020-05340-5	journal	January 2021
Data Assessment Method to Support the Development of Creep-Resistant Alloys Wenzlick, Madison; Bauer, Jennifer R.; Rose, Kelly Integrating Materials and Manufacturing Innovation, Vol. 9, Issue 1 https://doi.org/10.1007/s40192-020-00167-3	journal	January 2020
A Comprehensive Survey of Clustering Algorithms Xu, Dongkuan; Tian, Yingjie Annals of Data Science, Vol. 2, Issue 2 https://doi.org/10.1007/s40745-015-0040-1	journal	June 2015
Principal component analysis Wold, Svante; Esbensen, Kim; Geladi, Paul Chemometrics and Intelligent Laboratory Systems, Vol. 2, Issue 1-3 https://doi.org/10.1016/0169-7439(87)80084-9	journal	August 1987
Silhouettes: A graphical aid to the interpretation and validation of cluster analysis Rousseeuw, Peter J. Journal of Computational and Applied Mathematics, Vol. 20 https://doi.org/10.1016/0377-0427(87)90125-7	journal	November 1987
Predictions of long-term creep life for the family of 9–12 wt% Cr martensitic steels Verma, Amit K.; Hawk, Jeffrey A.; Romanov, Vyacheslav Journal of Alloys and Compounds, Vol. 815 https://doi.org/10.1016/j.jallcom.2019.152417	journal	January 2020
Detection of outliers in gas emissions from urban areas using functional data analysis Torres, J. Martínez; Nieto, P. J. Garcia; Alejano, L. Journal of Hazardous Materials, Vol. 186, Issue 1 https://doi.org/10.1016/j.jhazmat.2010.10.091	journal	February 2011
Screening of heritage data for improving toughness of creep-resistant martensitic steels Verma, Amit K.; Huang, Wei-Heng; Hawk, Jeffrey A. Materials Science and Engineering: A, Vol. 763 https://doi.org/10.1016/j.msea.2019.138142	journal	August 2019
Data clustering: 50 years beyond K-means Jain, Anil K. Pattern Recognition Letters, Vol. 31, Issue 8 https://doi.org/10.1016/j.patrec.2009.09.011	journal	June 2010
Coupling physics in machine learning to predict properties of high-temperatures alloys Peng, Jian; Yamamoto, Yukinori; Hawk, Jeffrey A. npj Computational Materials, Vol. 6, Issue 1 https://doi.org/10.1038/s41524-020-00407-2	journal	September 2020
Machine learning augmented predictive and generative model for rupture life in ferritic and austenitic steels Mamun, Osman; Wenzlick, Madison; Sathanur, Arun npj Materials Degradation, Vol. 5, Issue 1 https://doi.org/10.1038/s41529-021-00166-5	journal	April 2021
Array programming with NumPy Harris, Charles R.; Millman, K. Jarrod; van der Walt, Stéfan J. Nature, Vol. 585, Issue 7825 https://doi.org/10.1038/s41586-020-2649-2	journal	September 2020
A machine learning aided interpretable model for rupture strength prediction in Fe-based martensitic and austenitic alloys Mamun, Osman; Wenzlick, Madison; Hawk, Jeffrey Scientific Reports, Vol. 11, Issue 1 https://doi.org/10.1038/s41598-021-83694-z	journal	March 2021
Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science Agrawal, Ankit; Choudhary, Alok APL Materials, Vol. 4, Issue 5 https://doi.org/10.1063/1.4946894	journal	April 2016
Matplotlib: A 2D Graphics Environment Hunter, John D. Computing in Science & Engineering, Vol. 9, Issue 3 https://doi.org/10.1109/MCSE.2007.55	journal	January 2007
Materials Data Science: Current Status and Future Outlook Kalidindi, Surya R.; De Graef, Marc Annual Review of Materials Research, Vol. 45, Issue 1 https://doi.org/10.1146/annurev-matsci-070214-020844	journal	July 2015
The utility of multivariate outlier detection techniques for data quality evaluation in large studies: an application within the ONDRI project Sunderland, Kelly M.; Beaton, Derek; Fraser, Julia BMC Medical Research Methodology, Vol. 19, Issue 1 https://doi.org/10.1186/s12874-019-0737-5	journal	May 2019
Materials science with large-scale data and informatics: Unlocking new opportunities Hill, Joanne; Mulholland, Gregory; Persson, Kristin MRS Bulletin, Vol. 41, Issue 5 https://doi.org/10.1557/mrs.2016.93	journal	May 2016
seaborn: statistical data visualization Waskom, Michael Journal of Open Source Software, Vol. 6, Issue 60 https://doi.org/10.21105/joss.03021	journal	April 2021

Similar Records

Bulk Nanostructured FCC Steels With Enhanced Radiation Tolerance

Technical Report · 2012 · OSTI ID:1054231

Zhang, Xinghang; Hartwig, K. Ted; Allen, Todd; +1 more

Influence of Various Material Design Parameters on Deformation Behaviors of TRIP Steels

Journal Article · 2010 · Computational Materials Science, 50(2):720-730 · OSTI ID:1222175

Choi, Kyoo Sil; Soulami, Ayoub; Liu, Wenning N.; +2 more

Corrosion of austenitic and ferritic-martensitic steels exposed to supercritical carbon dioxide

Journal Article · 2010 · Corrosion Science · OSTI ID:1023326

Tan, Lizhen; Anderson, Mark; Taylor, D; +1 more

Related Subjects

36 MATERIALS SCIENCE
ML
alloy design
machine learning
outlier detection

Title: Assessment of Outliers in Alloy Datasets Using Unsupervised Techniques

Citation Formats

References (19)

Similar Records

Related Subjects