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.

A system for simulating a railroad track. The system comprises one or more modular track simulation units that are smaller than conventional track simulators and are easy to use with and be connected to a device being tested (e.g., grade crossing predictor). Each track simulation unit may have one of a plurality of impedances associated with a corresponding railroad track length. The units are combinable such that the system can simulate multiple, different track lengths. Each unit has a plurality of test points that can be connected to the device under test and/or used to alter conditions of the simulated track.

A system controls a level crossing of a railway track installation. The railway track installation includes at least one track. The system includes at least two magnetometers associated with the at least one track and placed at corners of a crossing area between the at least one track and a road. The system also includes a level crossing control unit configured for receiving data from the magnetometers. Each magnetometer is arranged to detect a respective magnetic field vector of the earth's magnetic field and to send data representative of the magnetic field vector to the control unit. The control unit is configured to elaborate the data to detect changes in the magnetic field vectors due to the presence of a train in the crossing area and to control the level crossing as a function of the detected changes.

A grade crossing control system includes a controller that receives start and end inputs corresponding to a train traversing an outer approach, determines the difference in time between the start and end inputs, and uses the difference in time to determine a delay period by which activation of a grade crossing warning system will be delayed following detection of the train by a track occupancy circuit in an inner approach in order to compensate for slow moving trains. The start and end inputs for the outer approach may be supplied in different ways including a separate track occupancy circuit for the outer approach, by train detection devices unconnected to the track at the start and end of the outer approach, or by overlapping track occupancy circuits positioned at the start of the outer and inner approaches.

To locate a shunt, the shunt includes an RF transmitter configured to wirelessly transmit an identifier of the shunt such as the configured shunt frequency. The shunt may include switches or memory locations that may be configured by an installer to correspond to the configured shunt frequency. Other embodiments employ switches or sensors influenced by jumpers installed in the shunt to configure the frequency of the shunt. A portable device receives a transmission including the identifier and displays it along with an indication of the received signal strength of the transmission, and maintenance personnel move the portable device along the track to locate the highest received signal strength, which indicates the location of the shunt. The shunt may also include a test circuit that may be configurable to generate a test frequency, determine a parameter indicative of shunt performance, and output a signal based on the parameter.

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.

An improved safety system used to determine the present position of road vehicles with rubber tires that are outfitted with railgear to be able to ride on railroad tracks that provides data to control signals, such as flashing lights, and crossing gates at railroad grade crossings in order to prevent accidents with vehicles or persons.

Systems and methods for detecting the dynamic train-to-rail shunting performance of a train as it is moving along the rails of a railroad track. The systems and methods use portable equipment temporarily installed at a site where it is desired to test the shunting of one or more trains or the electrical equipment installed at the track. The systems and method use sensor plates and a high speed recording system to simultaneously capture measured train-to-rail shunting characteristics and the positioning of a train's axles and any rail conditions impacting the measurements. The captured information can be used to fine tune the train, the electrical equipment installed at the track and/or to design new devices.

A railroad measurement system includes a railroad track powered measurement device providing measurement signals of electrical quantities across rails of a railroad track; a wayside control device adapted to receive the measurement signals provided by the railroad track powered measurement device; and a communication network interfacing with the railroad track powered measurement device and adapted to transmit data, wherein the railroad track powered measurement device is adapted to transmit the measurement signals of the electrical quantities via the communication network, and the wayside control device is adapted to receive the measurement signals.

A system controls a level crossing of a railway track installation. The railway track installation includes at least one track. The system includes at least two magnetometers associated with the at least one track and placed at corners of a crossing area between the at least one track and a road. The system also includes a level crossing control unit configured for receiving data from the magnetometers. Each magnetometer is arranged to detect a respective magnetic field vector of the earth's magnetic field and to send data representative of the magnetic field vector to the control unit. The control unit is configured to elaborate the data to detect changes in the magnetic field vectors due to the presence of a train in the crossing area and to control the level crossing as a function of the detected changes.