Abstract: A railway vehicle condition monitoring apparatus includes a detection device for detecting vehicle information represented by a wheel load or the like of a wheel included in a railway vehicle running on a railroad track, and a determination device including a classifier to which the vehicle information detected by the detection device is input and which outputs a vehicle condition such as the presence or absence of an abnormality of the railway vehicle. The classifier is generated by means of machine learning that uses training data of a railway vehicle of which the vehicle condition is known, the training data being the vehicle information and the vehicle condition which is known, the machine learning being performed so that when the vehicle information of the training data is input to the classifier, the classifier outputs the vehicle condition of the training data.

Abstract: A method of precisely measuring the track twist of a track on which a vehicle for commercial operation is travelling using this vehicle is to be provided. The method includes measuring a condition of a track (R) on which a vehicle for commercial operation (100) is travelling using this vehicle (100). The vehicle for commercial operation includes a bogie (10). The bogie includes four wheels (1) and primary springs (2) provided to correspond to the four wheels (1) and support the corresponding wheels (1), and is capable of measuring a wheel load of each of the four wheels (1). The method includes the steps of: measuring the wheel load of each wheel (1) (S13); calculating the displacement of each primary spring (2) based on the measured wheel load (S15); and calculating the track twist (h) of the track (R) based on the calculated displacements of the primary springs (2) (S18).

Abstract: A railway vehicle condition monitoring apparatus includes a detection device for detecting vehicle information represented by a wheel load or the like of a wheel included in a railway vehicle running on a railroad track, and a determination device including a classifier to which the vehicle information detected by the detection device is input and which outputs a vehicle condition such as the presence or absence of an abnormality of the railway vehicle. The classifier is generated by means of machine learning that uses training data of a railway vehicle of which the vehicle condition is known, the training data being the vehicle information and the vehicle condition which is known, the machine learning being performed so that when the vehicle information of the training data is input to the classifier, the classifier outputs the vehicle condition of the training data.

Abstract: A vehicle abnormality detecting apparatus 1 includes wheel load sensors 11 that are attached to right and left rails R constituting a track to measure wheel loads of wheels 3 provided in a vehicle 2; and a calculation unit 12 that is connected to the wheel load sensors 11. An index represented by wheel loads of a pair or more of right and left wheels 3 provided in at least one of bogies 4 and defined according to a type of vehicle abnormality as an index for detecting the vehicle abnormality is previously stored in the calculation unit 12. The calculation unit 12 calculates a value of the stored index from the wheel loads measured by the wheel load sensors 11 and transmitted from the wheel load sensors 11, and detects the abnormality of a running vehicle based on the calculated value of the index.

Abstract: A method of precisely measuring the track twist of a track on which a vehicle for commercial operation is travelling using this vehicle is to be provided. The method includes measuring a condition of a track (R) on which a vehicle for commercial operation (100) is travelling using this vehicle (100). The vehicle for commercial operation includes a bogie (10). The bogie includes four wheels (1) and primary springs (2) provided to correspond to the four wheels (1) and support the corresponding wheels (1), and is capable of measuring a wheel load of each of the four wheels (1). The method includes the steps of: measuring the wheel load of each wheel (1) (S13); calculating the displacement of each primary spring (2) based on the measured wheel load (S15); and calculating the track twist (h) of the track (R) based on the calculated displacements of the primary springs (2) (S18).

Abstract: A vehicle abnormality detecting apparatus 1 includes wheel load sensors 11 that are attached to right and left rails R constituting a track to measure wheel loads of wheels 3 provided in a vehicle 2; and a calculation unit 12 that is connected to the wheel load sensors 11. An index represented by wheel loads of a pair or more of right and left wheels 3 provided in at least one of bogies 4 and defined according to a type of vehicle abnormality as an index for detecting the vehicle abnormality is previously stored in the calculation unit 12. The calculation unit 12 calculates a value of the stored index from the wheel loads measured by the wheel load sensors 11 and transmitted from the wheel load sensors 11, and detects the abnormality of a running vehicle based on the calculated value of the index.