Patent classifications
B61L13/042
ANOMALY DETECTION USING MACHINE LEARNING
Examples of techniques for anomaly detection in a grade crossing prediction system are disclosed. Aspects include receiving a training data set comprising a plurality of labelled time series of signal values from a track circuit in a grade crossing predictor system, removing one or more non-unique values from each labelled time series of signal values in the plurality of labelled time series of signal values, extracting a plurality of features from the plurality of labelled time series of signal values, the plurality of features comprising: a number of signal values for each labeled time series of signal values in the plurality of labelled time series of signal values that are larger than a first threshold and a standard deviation for each labelled time series of signal values in the plurality of labelled time series of signal values, and training a machine learning algorithm utilizing the plurality of features.
Anomaly detection using machine learning
Examples of techniques for anomaly detection in a grade crossing prediction system are disclosed. Aspects include receiving a training data set comprising a plurality of labelled time series of signal values from a track circuit in a grade crossing predictor system, removing one or more non-unique values from each labelled time series of signal values in the plurality of labelled time series of signal values, extracting a plurality of features from the plurality of labelled time series of signal values, the plurality of features comprising: a number of signal values for each labeled time series of signal values in the plurality of labelled time series of signal values that are larger than a first threshold and a standard deviation for each labelled time series of signal values in the plurality of labelled time series of signal values, and training a machine learning algorithm utilizing the plurality of features.
RAILWAY DETECTION SYSTEM, RAILWAY INFRASTRUCTURE AND METHOD FOR DETECTING THE PRESENCE OF A RAILWAY VEHICLE
Railway detection system for detecting the presence of a railway vehicle on a railway track section comprising at least two rails, the railway track section comprising a first end and a second end opposite to the first end in a longitudinal direction of the railway track section, the railway detection system comprising a track circuit system comprising a signal generator electrically coupled to the first end of the railway track section, the signal generator being configured for generating a first track circuit signal to be injected into the railway track section at the first end, wherein the signal generator is adapted to generate a first component of the first track circuit signal comprising at least one DC pulse; generate a second component of the first track circuit signal, and add the first and the second component so as to obtain the first track circuit signal.
Fixed block track circuit
An active fixed block track circuit comprises at least a fixed block section, comprising at least two rails corresponding to each other, each having an isolation connector at two ends thereof and connected to a power supply unit and a traffic signal; a short driving unit, connected to each of the two rails within the fixed block section; and a detection unit, connected to the short driving unit. In this manner, not only the previous rail traffic signal circuit function where no more than one train may be allowed into the same fixed block section is maintained, but also another train approaching from the rear may be prevented from entering the fixed block section when the detection unit at the fixed block section detects an exceptional case happening at a neighboring fixed block section so that the traffic signal unit is switched into a stop traffic signal.