• Login
    View Item 
    •   SMARTech Home
    • Georgia Tech Theses and Dissertations
    • Georgia Tech Theses and Dissertations
    • View Item
    •   SMARTech Home
    • Georgia Tech Theses and Dissertations
    • Georgia Tech Theses and Dissertations
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Data-driven Process-Structure-Property Models for Additive Manufactured Ni-base Superalloys

    Thumbnail
    View/Open
    GORGANNEJAD-DISSERTATION-2020.pdf (16.66Mb)
    Date
    2020-12-09
    Author
    GorganNejad, Sanam
    Metadata
    Show full item record
    Abstract
    The complexity of the selective laser melting (SLM) process, which has shown success for shaping advanced structural alloys, has concentrated most of the research efforts to develop process-structure-property (PSP) models for fostering our understanding of the process that can ultimately serve as predictive and optimization tools. The data-driven approach has shown to effectively alleviate the burden of cost- and time-intensive computational and experimental approaches. The aim of the present research is two-fold. Firstly, it attempts to introduce a systematic and robust workflow for characterization and quantification of the key structural attributes of the SLM'ed manufactured materials such as porosity and surface roughness. The merit of implementing the introduced workflow is to enable data fusion and to integrate structural data and knowledge from various length-scales and sources for the creation of a coherent database. Secondly, this work seeks to investigate the implementation of various statistical and Machine Learning (ML) approaches for the establishment of the PSP models. Both parametric and non-parametric regression techniques are employed to construct models to illustrate the suitability of the different ML methods. From well-established regression techniques, non-parametric support vector regression (SVR), and Gaussian-based modeling approaches featuring uncertainty quantification to novel multiple tensor-on-tensor regression method with the distinct capability of data fusion of high-dimensional data have been examined.
    URI
    http://hdl.handle.net/1853/64190
    Collections
    • Georgia Tech Theses and Dissertations [23877]
    • School of Mechanical Engineering Theses and Dissertations [4086]

    Browse

    All of SMARTechCommunities & CollectionsDatesAuthorsTitlesSubjectsTypesThis CollectionDatesAuthorsTitlesSubjectsTypes

    My SMARTech

    Login

    Statistics

    View Usage StatisticsView Google Analytics Statistics
    facebook instagram twitter youtube
    • My Account
    • Contact us
    • Directory
    • Campus Map
    • Support/Give
    • Library Accessibility
      • About SMARTech
      • SMARTech Terms of Use
    Georgia Tech Library266 4th Street NW, Atlanta, GA 30332
    404.894.4500
    • Emergency Information
    • Legal and Privacy Information
    • Human Trafficking Notice
    • Accessibility
    • Accountability
    • Accreditation
    • Employment
    © 2020 Georgia Institute of Technology