Numerical Design Of High Entropy Super Alloy Using Multiscale Materials Modeling And Deep Learning

Tom Andersson (Corresponding author), Anssi Laukkanen, Tomi Suhonen, Matti Lindroos, Tatu Pinomaa, Joni Kaipainen

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

A new alloy designed for application, which require high strength materials even in elevated temperatures, with multiscale material modelling and deep learning is presented. Calphad type of analysis are combined with DFT simulations and tied together with machine learning tools are utilized in order to find the most promising alloy composition. Designed alloy will be synthesized and test specimens are produced with laser powder bed fusion. Experimental material and mechanical characterization methods are combined with simulation tools to create a micromechanical model that is used for mechanical property and performance simulations. A workflow is created to combine the different length scales in order to assess the performance of the final component already in alloy design phase in such a way that the alloying components can be fine-tuned to fulfil the design requirements of the respective products.
Original languageEnglish
Title of host publicationWorld PM2022 Congress Proceedings
PublisherEuropean Powder Metallurgy Association (EPMA)
ISBN (Electronic)978-1-899072-55-2
Publication statusPublished - Oct 2022
MoE publication typeA4 Article in a conference publication
EventWorld PM2022 Congress & Exhibition - Lyon, France
Duration: 9 Oct 202213 Oct 2022

Conference

ConferenceWorld PM2022 Congress & Exhibition
Country/TerritoryFrance
CityLyon
Period9/10/2213/10/22

Fingerprint

Dive into the research topics of 'Numerical Design Of High Entropy Super Alloy Using Multiscale Materials Modeling And Deep Learning'. Together they form a unique fingerprint.

Cite this