Probabilistic neural network identification of an alloy for direct laser deposition
Accepted version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Abstract
A neural network tool was used to discover a new nickel-base alloy for direct laser deposition most likely to satisfy targets of processability, cost, density, phase stability, creep resistance, oxidation, fatigue life, and resistance to thermal stresses. The neural network tool can learn property-property relationships, which allows it to use a large database of thermal resistance measurements to guide the extrapolation of just ten data entries of alloy processability. The tool was used to propose a new alloy, and experimental testing confirms that the physical properties of the proposed alloy are better tailored to the target application than other available commercial alloys.
Description
Keywords
Nickel, Direct laser deposition, Alloy, Neural network
Journal Title
Materials and Design
Conference Name
Journal ISSN
0264-1275
1873-4197
1873-4197
Volume Title
168
Publisher
Elsevier BV
Publisher DOI
Sponsorship
The Royal Society (uf130122)
Royal Society (RGF/EA/180034)
Engineering and Physical Sciences Research Council (EP/H500375/1)
Engineering and Physical Sciences Research Council (EP/M005607/1)
Royal Society (IMF130944)
Technology Strategy Board (113072)
Engineering and Physical Sciences Research Council (EP/H022309/1)
Royal Society (RGF/EA/180034)
Engineering and Physical Sciences Research Council (EP/H500375/1)
Engineering and Physical Sciences Research Council (EP/M005607/1)
Royal Society (IMF130944)
Technology Strategy Board (113072)
Engineering and Physical Sciences Research Council (EP/H022309/1)