The problem of classification of epoxy composites used for the manufacture of aircraft structures is solved by machine learning methods: neural network, reinforced trees and random forests. Classification metrics were obtained for each method used. Parameters such as precision, recall, F1 score and support were determined. The neural network classifier demonstrated the highest results. Boosted trees and random forests showed slightly lower results than the neural network method. At the same time, the classification metrics were high enough in each case. Therefore, machine learning methods effectively classify epoxy composites. The results obtained are in good agreement with the experimental ones. The prediction accuracy score obtained using each method was greater than 0.88.


    Access

    Download


    Export, share and cite



    Title :

    Artificial intelligence as applied to classifying epoxy composites for aircraft


    Contributors:


    Publication date :

    2025




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Classifying aircraft

    Engineering Index Backfile | 1940


    Artificial intelligence aircraft

    DING ZHIFENG | European Patent Office | 2020

    Free access


    Distributed Artificial Intelligence Applied to Design of Aircraft Fuselage and Wings

    Saggu, J. S. / International Council of Aeronautical Sciences | British Library Conference Proceedings | 1994


    Artificial intelligence low-altitude aircraft

    QU SONG | European Patent Office | 2021

    Free access