Title: Enriching Materials Databases with Machine Learning

Authors: Moncef. Salmi, Pierre-Yves. Lavertu, Thierry. Malo

DOI: 10.33599/nasampe/c.22.0054

Abstract: While the pace of innovation is constantly accelerating, product development budgets remain limited and development cycles are shortening. Under those conditions, an efficient material data management system can be key to respect the increasingly demanding constraints. This is especially true when the characterization of composites materials requires a myriad of coupon tests to be performed for the different test types and testing conditions. Hence, those test campaigns quickly become very expensive and time-consuming. The goal of this presentation is to show how a central material database alongside machine learning (ML) can be used to accelerate data generation and mitigate physical testing leading to significant time and cost savings. In this framework, all physical and virtual testing data are all stored within the centralized materials data management system simplifying the implementation and training of machine learning algorithms. ML algorithms can be trained to detect correlations among large datasets and then enrich the initial material database. The same machine learning algorithms can also be trained to help determine how to optimize the experimental tests needed to be performed with the objective again to save time and money. Based on this methodology, the generation of data is accelerated, and significant time and cost savings can be achieved.

References: 1. J. Allison, Integrated Computational Materials Engineering (ICME): The Next Big Thing in Material. in Accelerating Materials and Manufacturing Innovation for Global Competitiveness. 2011 Materials Information Luncheon.” Washington, D.C. 2011. [Online] Available: https://www.youtube.com/watch?v=Zpk_z5H-82Q 2. J. Allison, D. Backman and L. Christodoulou. Integrated Computational Materials Engineering: A New Paradigm for the Global Materials Profession. JOM, vol. 58, pp. 25–27, Nov. 2006. 3. N. Chopra, Integrated Computational Materials Engineering: A Multi-Scale Approach. JOM, vol. 67, pp. 118–119, Jan. 2015 4. B.A. Cowles and D. Backman, Advancement, and implementation of integrated computational materials engineering (ICME) for aerospace applications. (Preprint), AFRL/RXLMP, Ohio, 2010 5. I. Doghri and L. Adam, Integrated Computational Material Engineering (ICME) for beginners. [Online] 2020, Available https://www.e-xstream.com/whitepaper-icme-for-beginners 6. E. Alpaydin, Introduction to Machine Learning, 4th ed. Cambridge, MA, MIT Press, 2020. 7. S. Arthur, Some Studies in Machine Learning Using the Game of Checkers. IBM Journal of Research and Development, Vol. 3, Issue 3, July 1959. 8. C.M Bishop, Pattern Recognition and Machine Learning. New York, Springer-Verlag New York, 2006 9. R. Kohavi and F. Provost, Glossary of terms. Machine Learning, vol.30, pp. 271-274,1998.

Conference: CAMX 2022

Publication Date: 2022/10/17

SKU: TP22-0000000054

Pages: 10

Price: $20.00