US 11,676,009 B2
Machine learning based rotor alloy design system
Nagendra Somanath, South Windsor, CT (US); Ryan B. Noraas, Hartford, CT (US); Michael J Giering, Bolton, CT (US); and Olusegun T Oshin, Middletown, CT (US)
Assigned to Raytheon Technologies Corporation, Farmington, CT (US)
Filed by United Technologies Corporation, Farmington, CT (US)
Filed on Oct. 4, 2019, as Appl. No. 16/593,328.
Prior Publication US 2021/0103805 A1, Apr. 8, 2021
Int. Cl. G06N 3/08 (2023.01); B64F 5/00 (2017.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)
CPC G06N 3/08 (2013.01) [B64F 5/00 (2013.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)] 17 Claims
OG exemplary drawing
 
1. A method for designing a material for an aircraft component comprising:
training a neural network to correlate microstructural features of an alloy with material properties of the alloy by at least providing a set of images of the alloy, each of the images in the set of images having varied constituent compositions and at least one patch of corresponding data embedded into the image, and determining non-linear relationships between the microstructural features and corresponding empirically determined material properties via a machine learning algorithm;
receiving a set of desired material properties of the alloy for aircraft component; and
determining a set of microstructural features capable of achieving the desired material properties of the alloy based on the determined non-linear relationships and based on the received set of desired material properties.