NTRS - NASA Technical Reports Server

Back to Results
Design of Materials with AlchemiteMachine learning models that establish the relationships between materials processing and properties can enable inverse design of materials through active learning. Alchemite is a commercial software that can perform inverse materials design on sparse data. Here we evaluate Alchemite’s performance on a dataset of shape memory alloys and a dataset of heat exchangers compared to baseline random forest models. Alchemite had higher accuracy when making predictions on sparse data and was more accurate or nearly as accurate as random forests on complete datasets while also quantifying uncertainty. The software was also used to suggest processing steps and design parameters to optimize properties and performance; however, physical validation of the suggested design parameters was beyond the scope of this work. Several useful design insights were gained about the impact of the design parameters on properties and performance including the importance of dopant choice and amount for shape memory alloys and the importance of height and weight on the thermal resistance of heat exchangers.
Document ID
Acquisition Source
Glenn Research Center
Document Type
Technical Memorandum (TM)
Joshua Stuckner
(Glenn Research Center Cleveland, Ohio, United States)
Thomas M Whitehead
Robert C Parini
Gareth J Conduit
Othmane Benafan
(Glenn Research Center Cleveland, Ohio, United States)
Steven M Arnold
(Glenn Research Center Cleveland, Ohio, United States)
Date Acquired
May 31, 2022
Publication Date
July 15, 2022
Subject Category
Systems Analysis And Operations Research
Metals And Metallic Materials
Mathematical And Computer Sciences (General)
Report/Patent Number
Funding Number(s)
WBS: 109492.
Distribution Limits
Portions of document may include copyright protected material.
Technical Review
Single Expert
Machine learning
Active learning
Commercial software
Data science
No Preview Available