Predicting flashover events is critical for safety in various electrical domains, particularly in designing medium and high-voltage systems. This paper presents an innovative approach to automating the prediction of flashover occurrences in medium-voltage connectors using machine learning techniques. The study involves the analysis of model-generated plots based on experimental flashover events, specifically focusing on the characterization of electrical parameters indicative of flashover. Leveraging machine learning models, such as convolutional neural networks and regression techniques, we demonstrate the ability to predict flashover and non-flashover at certain applied voltage level instances with high accuracy. The proposed methodology aims to streamline the identification process, eliminating the need for manual inspection and enhancing the efficiency of flashover prediction in diverse medium-voltage applications.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Predictive Modeling of Surface Flashover Using Deep Learning


    Beteiligte:
    Tewari, Vedant (Autor:in) / Al Sufi, Suaib (Autor:in) / Benet, Sean (Autor:in) / Park, Chanyeop (Autor:in)


    Erscheinungsdatum :

    19.06.2024


    Format / Umfang :

    3057015 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Inhibiting surface flashover with magnetic fields

    Korzekwa, R. / Lehr, M. / Krompholz, H. et al. | Tema Archiv | 1989


    Surface Flashover Triggering of Pseudospark Switchers

    Jianmin, X. / Yuchang, Q. / Jingliang, C. | British Library Online Contents | 2003



    Measurement of the effects of surface roughness on flashover

    Smith, J.D. / Hatfield, L.L. | Tema Archiv | 1988