Master thesis: Sequential machine learning for applications to material dev
Swerim AB / Datajobb / Stockholm
Observera att sista ansökningsdag har passerat.
Visa alla datajobb i Stockholm,
Solna,
Lidingö,
Sundbyberg,
Danderyd eller i
hela Sverige Visa alla jobb hos Swerim AB i Stockholm,
Lysekil,
Luleå eller i
hela Sverige The research institute Swerim provides applied research within mining engineering, process metallurgy and materials and manufacturing engineering, mainly for the mining, steel and metals industry. Swerim has 190 co-workers in two locations in Sweden - Luleå and Stockholm.
Background
Development of metallic materials is in many aspects an iterative process involving a series of steps e.g. physically-based modelling, design of experimental heats, processing, characterization and material testing. There is a strong need to accelerate material development, for this reason faster and more accurate methods are being development to support the development cycle. Machine learning methods is likely to play a big role in how we develop materials in the future. One use case is to provide correlations between input-output space for which physically-based models are not available.
Project description
In your thesis, you will evaluate a sequential machine learning approach for applications within material development. The sequential machine learning approach is chosen because of the precious nature of experimental data. This will be done by defining a relevant input-output space where physical do exist, and sample data from this input-output space to train the machine learning model. An important goal of the project is to assess the amount of data needed to make a good representation of the input-output space, as well as to explore various sampling strategies. The work will be performed as a collaboration between Swerim, Högskolan i Skövde and companies represented by Swedish metal industry.
Objectives and learning outcome
• Literature survey including review of sequential machine learning methods, in particular for applications within material science.
• Implementation of sequential machine learning models using open-source tools.
• Evaluate best practice for relevant input-output space(es) i.e. type of model and sampling strategies.
• Scientific publication.
Required qualifications
Student in computer since, physics, material science or related area. Proficiency in coding is a must and hands-on experience using machine learning techniques is considered a merit.
The work should be initiated during the beginning of 2023. The master student performing the work will gain a large industry network. Swerim rewards the student with 50 000 SEK for an approved master thesis (30hp).
Interested?
Do you think it sounds interesting and want to know more? Feel free to contact one of us below, no later than December 20th, 2022. Please note that we fill the thesis as soon as we find a suitable applicant, which means we can fill the position before the deadline.
Contacts
For further information about project, please contact:
• David Lindell,
David.lindell@swerim.se• Gunnar Mathiason,
gunnar.mathiason@his.seVaraktighet, arbetstid
Heltid 3 - 6 månader
Publiceringsdatum2022-09-13ErsättningFast månads- vecko- eller timlön
Så ansöker duSista dag att ansöka är 2022-12-20
Klicka på denna länk för att göra din ansökanFöretagSWERIM AB
Omfattning Detta är ett heltidsjobb.
Arbetsgivare Swerim AB (org.nr 556585-4725),
http://swerim.se Arbetsplats Swerim AB
Jobbnummer 6977092
Observera att sista ansökningsdag har passerat.