A train control system may include a data acquisition hub connected to a database and sensors associated with one or more locomotives, systems, or components of a train and configured to acquire data in association with inputs derived from contextual data relating to a plurality of trains being operated by experienced train engineers under a variety of different conditions and in different geographical areas for use as training data. A machine learning engine of the train control system may receive the training data from the data acquisition hub, encode a modified learning function as a statistical model of desirable train handling behavior, evaluate train handling behavior by comparing to the statistical model, and update a certification of one or more of a train engineer, a semi-autonomous control system, or a fully autonomous control system.


    Access

    Download


    Export, share and cite



    Title :

    MACHINE LEARNING BASED TRAIN HANDLING EVALUATION


    Contributors:
    HOWARD BRADLEY (author) / BRAND JOHN (author)

    Publication date :

    2021-04-15


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    B61L Leiten des Eisenbahnverkehrs , GUIDING RAILWAY TRAFFIC / G05B Steuer- oder Regelsysteme allgemein , CONTROL OR REGULATING SYSTEMS IN GENERAL / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Machine learning based train handling evaluation

    HOWARD BRADLEY / BRAND JOHN | European Patent Office | 2022

    Free access

    Train handling

    Wood, G.H. | Engineering Index Backfile | 1917


    Train handling

    Wood, G.H. | Engineering Index Backfile | 1917


    Train handling

    Wood, G.H. | Engineering Index Backfile | 1918


    Passenger train handling

    Engineering Index Backfile | 1924