Akademska digitalna zbirka SLovenije - logo
ALL libraries (COBIB.SI union bibliographic/catalogue database)
  • Big-data analytics for the modelling of wrought aluminium alloys [Elektronski vir]
    Kevorkijan, Varužan ...
    The widespread usability of post-consumer scrap in the production of wrought aluminium alloys for standard or required quality depends on a fundamental ability to be able to formulate new alloys with ... sufficiently wider concentration intervals. An industrial tool developed within the Impol Aluminium Group for such a modelling of wrought aluminium alloys is OPTIAl - the algorithm for correlating the properties of wrought aluminium alloys, the chemical composition and the processing parameters. The learning of the algorithm was performed by applying the experimentally confirmed equivalency of different technological paths (the chemical composition of the alloy and the main processing parameters), able to provide the same combination of properties. In the first step, through a process of data mining, a data matrix was created, consisting of the results of standard, room-temperature tensile tests and the corresponding technological paths for different production lots of the AA 6110 alloy. Next, based on the accumulated data, the most probable technological path-property correlations were identified. Finally, various standard and some non-standard alloy compositions, derived from the alloy AA 6110, and the processing parameters were inducted to provide the desired combination of properties. The validation of the above-described methodology was performed through regular production of a limited number of cognitively computed alloys and their characterization. It was found that by applying the above methodology on proper experimentally determined values, either the chemical composition or the mechanical properties can be predicted with high accuracy, sufficient for most industrial applications.
    Source: Program in knjiga povzetkov [Elektronski vir] = Program and book of abstracts (Str. 92)
    Type of material - conference contribution
    Publish date - 2017
    Language - english
    COBISS.SI-ID - 93482753

    Link(s):

    http://icmt25.com/e_files/content/Preliminary_BookOfAbstracts_25ICM&T.pdf

Shelf entry