Every year there is a huge loss in production due to machines failure. Bearing defects are a popular and common problem that continues to occur in various industries. Defect detection in ball bearings is one of the challenges faced by various industries continuously. Hence it becomes very important to detect and diagnose all kinds of faults that may occur during or after the operation of the machine. A lot of research has been done in this area in the last 5–10 years. Several innovative techniques have been proposed for fault detection using vibration signals. Some of the purely mechanical techniques used in the past such as temperature monitoring, electric motor current monitoring, wear debris analysis, vibration measurement was reviewed. The main objective in this paper is to identify fault bearings through machine learning with better accuracy and the results showed that machine learning-based fault diagnosis will be very efficient in identifying bearing faults.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Fault Detection in Ball Bearing through Machine Learning Models


    Beteiligte:
    Hasan, Amir (Autor:in) / Singh, Jaspreet (Autor:in)


    Erscheinungsdatum :

    2022-12-01


    Format / Umfang :

    452802 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch