Probabilistic neural network identification of an alloy for direct laser deposition

Probabilistic neural network identification of an alloy for direct laser deposition

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-p...

Full description

Bibliographic Details
Main Authors: B.D. Conduit, T. Illston, S. Baker, D. Vadegadde Duggappa, S. Harding, H.J. Stone, G.J. Conduit
Format: Article
Language:English
Published: Elsevier 2019-04-01
Series:Materials & Design
Online Access:http://www.sciencedirect.com/science/article/pii/S0264127519300814
id doaj-ed8638293a124c11b43ba00e48cbdd06
record_format Article
spelling doaj-ed8638293a124c11b43ba00e48cbdd062020-11-25T00:37:08ZengElsevierMaterials & Design0264-12752019-04-01168Probabilistic neural network identification of an alloy for direct laser depositionB.D. Conduit0T. Illston1S. Baker2D. Vadegadde Duggappa3S. Harding4H.J. Stone5G.J. Conduit6Rolls-Royce plc, Derby, PO Box 31DE24 8BJ, United KingdomMaterials Solutions, Worcester, WR4 9GN, United KingdomMaterials Solutions, Worcester, WR4 9GN, United KingdomRolls-Royce India Private Limited, Manyata Tech Park, Bangalore 560024, IndiaRolls-Royce plc, Bristol, PO Box 3, BS34 7QE, United KingdomDepartment of Materials Science & Metallurgy, University of Cambridge, 27 Charles Babbage Road, Cambridge CB3 0FS, United KingdomCavendish Laboratory, University of Cambridge, J.J. Thomson Avenue, Cambridge CB3 0HE, United Kingdom; Corresponding author.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. Keywords: Nickel, Direct laser deposition, Alloy, Neural networkhttp://www.sciencedirect.com/science/article/pii/S0264127519300814
collection DOAJ
language English
format Article
sources DOAJ
author B.D. Conduit
T. Illston
S. Baker
D. Vadegadde Duggappa
S. Harding
H.J. Stone
G.J. Conduit
spellingShingle B.D. Conduit
T. Illston
S. Baker
D. Vadegadde Duggappa
S. Harding
H.J. Stone
G.J. Conduit
Probabilistic neural network identification of an alloy for direct laser deposition
Materials & Design
author_facet B.D. Conduit
T. Illston
S. Baker
D. Vadegadde Duggappa
S. Harding
H.J. Stone
G.J. Conduit
author_sort B.D. Conduit
title Probabilistic neural network identification of an alloy for direct laser deposition
title_short Probabilistic neural network identification of an alloy for direct laser deposition
title_full Probabilistic neural network identification of an alloy for direct laser deposition
title_fullStr Probabilistic neural network identification of an alloy for direct laser deposition
title_full_unstemmed Probabilistic neural network identification of an alloy for direct laser deposition
title_sort probabilistic neural network identification of an alloy for direct laser deposition
publisher Elsevier
series Materials & Design
issn 0264-1275
publishDate 2019-04-01
description 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. Keywords: Nickel, Direct laser deposition, Alloy, Neural network
url http://www.sciencedirect.com/science/article/pii/S0264127519300814
work_keys_str_mv AT bdconduit probabilisticneuralnetworkidentificationofanalloyfordirectlaserdeposition
AT tillston probabilisticneuralnetworkidentificationofanalloyfordirectlaserdeposition
AT sbaker probabilisticneuralnetworkidentificationofanalloyfordirectlaserdeposition
AT dvadegaddeduggappa probabilisticneuralnetworkidentificationofanalloyfordirectlaserdeposition
AT sharding probabilisticneuralnetworkidentificationofanalloyfordirectlaserdeposition
AT hjstone probabilisticneuralnetworkidentificationofanalloyfordirectlaserdeposition
AT gjconduit probabilisticneuralnetworkidentificationofanalloyfordirectlaserdeposition
_version_ 1725302283609047040

Similar Items