Automatic train operation assistance device, automatic train operation assistance system, and automatic train operation assistance method

Abstract

An automatic train operation assistance device includes a data extraction unit that acquires operation data including the operation of a train and load factors of the vehicles of the train from a data collection device that collects equipment data on the train, a feature extraction unit that extracts, using the operation data, operation data on an inter-station including a travel time taken by the train to travel from a first station to a second station and a stoppage time for which the train is stopped at the first station or the second station, as features, and an operation prediction unit that constructs a prediction model using the features, and predicts the future operating conditions of the train including the future position of the train, using the prediction model and current features.

1 . An automatic train operation assistance device, comprising:
 processing circuitry   to acquire operation data including an operation of a train and load factors of vehicles of the train from a data collection device to collect equipment data on the train;   to extract, using the operation data, operation data on an inter-station including a travel time taken by the train to travel from a first station to a second station and a stop time for which the train is stopped at the first station or the second station, as features; and   to construct a prediction model using the features, and predict future operating conditions of the train including a future position of the train, using the prediction model and current features.   
     
     
         2 . The automatic train operation assistance device according to  claim 1 ,
 wherein the processing circuitry creates operation time-series data by combining the features on two or more different inter-stations in chronological order, wherein   the processing circuitry constructs the prediction model by machine learning with the operation time-series data as explanatory variables and the future operating conditions of the train as objective variables.   
     
     
         3 . The automatic train operation assistance device according to  claim 2 , wherein
 the processing circuitry creates the operation time-series data by combining the features on a specified number of the nearest inter-stations with the current features on the train for which prediction is performed.   
     
     
         4 . The automatic train operation assistance device according to  claim 1 , wherein
 the load factors of the vehicles of the train included in the operation data include, for each vehicle of the train, a load factor when the train is stopped at a station and passengers are getting on and off, and a load factor when the train is traveling, and   the processing circuitry extracts the features including at least one of a maximum load factor, a minimum load factor, an average load factor, or a standard deviation that indicates variations in the load factor during a time of getting on and off of the passengers when the train is stopped at the station, the standard deviation being a standard deviation in the load factor when the passengers are getting on and off.   
     
     
         5 . The automatic train operation assistance device according to  claim 4 , wherein
 the processing circuitry uses the features on a vehicle with a longest time of getting on and off, a vehicle with a largest number of passengers who get off the vehicle, a vehicle with a largest number of passengers who get on the vehicle, or a vehicle with a greatest standard deviation, of the vehicles included in the train, to predict the future operating conditions of the train including the vehicle.   
     
     
         6 . The automatic train operation assistance device according to  claim 1 , wherein
 the processing circuitry outputs the predicted future operating conditions of the train to an automatic train operation system installed on the train.   
     
     
         7 . The automatic train operation assistance device according to  claim 1 , wherein
 the automatic train operation assistance device is installed on the train.   
     
     
         8 . The automatic train operation assistance device according to  claim 1 , wherein
 the automatic train operation assistance device is installed in an operation control apparatus to control the operation of the train or in a cloud.   
     
     
         9 . The automatic train operation assistance device according to  claim 8 , wherein
 the operation control apparatus or the cloud performs wireless communications with a plurality of the trains, and   the processing circuitry acquires the operation data on the plurality of trains from the data collection device installed in the operation control apparatus or in the cloud.   
     
     
         10 . The automatic train operation assistance device according to  claim 8 , wherein
 the processing circuitry acquires the operation data from the data collection device installed on the train via communication.   
     
     
         11 . The automatic train operation assistance device according to  claim 8 , wherein
 the processing circuitry predicts, for a plurality of the trains, the future operating conditions of each train.   
     
     
         12 . The automatic train operation assistance device according to  claim 8 , wherein
 the processing circuitry extracts, as the features, first features on the train for which prediction is performed and, in addition, second features on a preceding train of the train for which prediction is performed.   
     
     
         13 . An automatic train operation assistance system, comprising:
 a first automatic train operation assistance device installed in an operation control apparatus to control an operation of a train or in a cloud; and   a second automatic train operation assistance device installed on the train, wherein   the first automatic train operation assistance device includes   first processing circuitry   to acquire operation data including an operation of the train and load factors of vehicles of the train from a data collection device that collects equipment data on the train,   to extract, using the operation data, operation data on an inter-station including a travel time taken by the train to travel from a first station to a second station and a stop time for which the train is stopped at the first station or the second station, as features, and   to construct a prediction model using the features, and   the second automatic train operation assistance device includes   second processing circuitry   to acquire operation data including an operation of the train and load factors of vehicles of the train from a data collection device that collects equipment data on the train,   to extract, using the operation data, operation data on an inter-station including a travel time taken by the train to travel from a first station to a second station and a stop time for which the train is stopped at the first station or the second station, as features, and   to predict future operating conditions of the train including a future position of the train, using the prediction model and current features.   
     
     
         14 . The automatic train operation assistance system according to  claim 13 , wherein
 the first processing circuitry creates operation time-series data by combining the features on two or more different inter-stations in chronological order, and   constructs the prediction model by machine learning with the operation time-series data as explanatory variables and the future operating conditions of the train as objective variables.   
     
     
         15 . The automatic train operation assistance system according to  claim 14 , wherein
 the first processing circuitry creates the operation time-series data by combining the features on a specified number of the nearest inter-stations with the current features on the train for which prediction is performed.   
     
     
         16 . The automatic train operation assistance system according to  claim 13 , wherein
 the load factors of the vehicles of the train included in the operation data include, for each vehicle of the train, a load factor when the train is stopped at a station and passengers are getting on and off, and a load factor when the train is traveling, and   the first processing circuitry and the second processing circuitry extract the features including at least one of a maximum load factor, a minimum load factor, an average load factor, or a standard deviation that indicates variations in the load factor during a time of getting on and off of the passengers when the train is stopped at the station, the standard deviation being a standard deviation in the load factor when the passengers are getting on and off.   
     
     
         17 . The automatic train operation assistance system according to  claim 16 , wherein
 the second processing circuitry uses the features on a vehicle with a longest time of getting on and off, a vehicle with a largest number of passengers who get off the vehicle, a vehicle with a largest number of passengers who get on the vehicle, or a vehicle with a greatest standard deviation, of the vehicles included in the train, to predict the future operating conditions of the train including the vehicle.   
     
     
         18 . The automatic train operation assistance system according to  claim 13 , wherein
 the second processing circuitry outputs the predicted future operating conditions of the train to an automatic train operation system installed on the train.   
     
     
         19 . An automatic train operation assistance method, comprising:
 acquiring operation data including an operation of a train and load factors of vehicles of the train from a data collection device to collect equipment data on the train;   extracting using the operation data, operation data on an inter-station including a travel time taken by the train to travel from a first station to a second station and a stop time for which the train is stopped at the first station or the second station, as features;   constructing a prediction model using the features; and   predicting future operating conditions of the train including a future position of the train, using the prediction model and current features.