System for determining a wheel-rail adhesion value for a railway vehicle

Patent metadata

Field	Value
Publication number	US-12345639-B2
Application number	US-202017756308-A
Country	US
Kind code	B2
Filing date	Nov 20, 2020
Priority date	Nov 22, 2019
Publication date	Jul 1, 2025
Grant date	Jul 1, 2025

Abstract

A system for determining an adhesion value between wheel and rail for a railway vehicle is described, comprising an optical information acquisition means arranged to acquire optical information from the rail, a database arranged to store the acquired optical information in at least a learning phase and to associate said information with a relevant real wheel-rail adhesion value measured at the moment of acquisition of the optical information, a control unit arranged to determine the current wheel-rail adhesion value on the basis of a comparison between current acquired optical information and the optical information previously stored in the database. The control unit determines that the current wheel-rail adhesion value associated with the current acquired optical information corresponds to the adhesion value associated with the optical information stored in the database having the highest degree of similarity with the current acquired optical information.

First claim

The invention claimed is:

1. A system for determining an adhesion value between wheel and rail for a railway vehicle, comprising:
an optical sensor arranged to acquire optical information from the rail;
a database arranged, at least in a learning phase, to store the acquired optical information and match the acquired optical information to a corresponding wheel-rail adhesion value, wherein each wheel-rail adhesion value is derived from a braking force measured during braking at an axel of the railway vehicle and concurrent with the of acquisition of the corresponding optical information acquired by the optical sensor;
a control unit arranged to determine a current wheel-rail adhesion value from current optical information acquired by the optical sensor based on identifying the wheel-rail adhesion value that is matched with the optical information stored in the database having the highest degree of similarity with the current acquired optical information.

2. The system according to claim 1 , wherein the optical sensor is a vision sensor.

3. The system according to claim 2 , wherein the vision sensor includes a video camera or a camera.

4. The system according to claim 1 , wherein the optical sensor is an optical sensor based on reflection.

5. The system according to claim 4 , wherein the optical sensor based on reflection is arranged to send a light signal towards the rail and to detect a quantity and/or a distribution of the light signal reflected by the rail indicative of a condition of the rail surface.

6. The system according to claim 1 , wherein the control unit is configured to identify the wheel-rail adhesion value that is matched with the optical information stored in the database having the highest degree of similarity with the current optical information through image recognition algorithms based on artificial intelligence and/or machine learning.

7. The system according to claim 1 , wherein the database is remote with respect to the railway vehicle.

8. The system according to claim 1 , wherein the optical sensor is arranged in the railway vehicle so as to acquire the optical information of the rail which is placed in front of a first axle of the railway vehicle, according to the direction of travel of the railway vehicle.

9. The system according to claim 1 , wherein the database is arranged to store a predetermined quantity of known optical information that is matched with respective known adhesion values, the correctness of which has been verified beforehand.

10. The system according to claim 1 , wherein the real wheel-rail adhesion value is measured by analyzing the behavior of an axle of the railway vehicle during a braking phase.

11. The system according to claim 10 , wherein the axle of the railway vehicle is braked until such axle begins to skid or up to a predetermined limit value.

Assignees

• Faiveley Transport Italia Spa

Inventors

• Frea Matteo

Classifications

• G06T2207/30252

  Vehicle exterior; Vicinity of vehicle · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title

• G06T7/0002

  Inspection of images, e.g. flaw detection · CPC title

• B61L15/0081

  On-board diagnosis or maintenance · CPC title

• B61L15/0072

  On-board train data handling · CPC title