System for determining adhesion value for between railway vehicle wheel and rail

Abstract

To provide a system for determining an adhesion value between a railway vehicle wheel and a rail which is capable of self-calibrating during use of the system.SOLUTION: A system for determining an adhesion value between a railway vehicle wheel and a rail includes: optical information acquisition means provided to acquire optical information from the rail; a database provided to store the acquired optical information in at least a learning phase and associate the stored optical information with a relevant actual adhesion value between the wheel and the rail measured at the time of acquisition of the optical information; and a control unit provided to determine the current adhesion value between the wheel and the rail on the basis of a comparison between the acquired current optical information and the optical information previously stored in the database. The control unit determines that the current adhesion value between the wheel and the rail associated with the acquired optical information corresponds to the adhesion value associated with the optical information having the highest degree of similarity with the current acquired optical information among the optical information stored in the database.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates generally to the field of railway vehicles, and more particularly to a system for determining a wheel-rail adhesion value for a railway vehicle. [Background technology]

[0002] Conventional techniques for measuring wheel-rail adhesion are essentially based on "indirect" solutions based on vision or reflection optical sensors, or "direct" solutions that implement dedicated brake or traction controls to estimate adhesion. This second category ("direct" solutions) includes, for example, solutions that apply a known braking force to one or more axles and detect the axle's response with respect to rotational speed. Using the braking force and angular acceleration, it is easy to estimate the available adhesion at the wheel-rail contact.

[0003] However, optical solutions based on vision or reflection have the disadvantage that they must be properly pre-calibrated through complex calibration procedures, and yet they are generally not used because they are sensitive to the environmental conditions of visibility and lighting in which the system operates.

[0004] On the other hand, direct adhesion measurements are reliable, but can only be performed when a braking torque is applied to the axles. Therefore, this measurement can only be performed during braking phases, unless, for example, a dedicated brake control is implemented, which periodically applies a known braking force and detects the axle's response in terms of angular acceleration. A dedicated control solution makes it possible to measure adhesion with the desired spatial-temporal resolution, but disadvantageously requires the periodic application of a braking force to at least one axle of the rail vehicle, which is not necessary for the vehicle to run. Summary of the Invention [Problem to be solved by the invention]

[0005] The object of the present invention is to provide a system for determining adhesion values between a wheel and a rail of a railway vehicle, which is capable of self-calibrating during use of the system, for example, based on artificial intelligence techniques. The system for determining adhesion values between a wheel and a rail of a railway vehicle calibrates the results from an optical sensor based on direct adhesion measurements. The system accumulates the results of the direct adhesion measurements throughout the system's processing, making the interpretation of indirect measurements based on the optical sensor increasingly reliable. The reliability of the results of the indirect measurements obtained by a properly calibrated system allows for reliable continuous measurement of the adhesion between the wheel and the rail. At the same time, the increased reliability of the results of the indirect measurements obtained by a properly calibrated system can reduce or eliminate the need to apply a dedicated brake just for adhesion measurements.

[0006] According to one aspect of the present invention, the above and other objects and advantages are achieved by a system for determining an adhesion value between a wheel of a railway vehicle and a rail, having the features defined in claim 1. Preferred embodiments of the invention are defined in the dependent claims, the contents of which should be understood as an essential part of this description. [Brief explanation of the drawings]

[0007] Next, functional and structural features of some preferred embodiments of a system for determining an adhesion value between a wheel of a railway vehicle and a rail according to the present invention will be described in detail with reference to the accompanying drawings. [Figure 1] FIG. 1 illustrates one embodiment of a system for determining adhesion values between a rail vehicle wheel and a rail. [Figure 2] FIG. 2 shows a further embodiment of a system for determining an adhesion value between a wheel of a railway vehicle and a rail. [Figure 3A] FIG. 3A shows an example of the results of direct adhesion measurements by applying a braking force to an axle. [Figure 3B] FIG. 3B shows a further example of the results of direct adhesion measurements by applying a braking force to an axle. DETAILED DESCRIPTION OF THE INVENTION

[0008] Before describing several embodiments of the present invention in detail, it should be made clear that the present invention is not limited in its application to the details of construction and arrangement of components set forth in the following description or illustrated in the drawings. The present invention is capable of other embodiments and may actually be practiced or constructed in a variety of different ways. Also, it is to be understood that the phraseology and terminology are for the purpose of description and should not be construed as limiting. The use of "include," "comprise," or variations thereof means the inclusion of the elements described below and equivalents thereof, as well as additional elements and equivalents thereof.

[0009] Reference is first made to Figure 1, which shows a system for determining adhesion values between wheels W and rails R for a rail vehicle RV.

[0010] The system includes optical information acquisition means 3 arranged to acquire optical information from the rail R, and a database 5 arranged to store the optical information, at least during a learning phase, and to associate the stored optical information with each actual adhesion value between the wheel W and the rail R, which was substantially measured at the time of acquisition of the optical information by the optical information acquisition means 3. It is clear that the database 5 may also be arranged to store the optical information during use immediately after the initial learning phase, and to associate the optical information with each actual adhesion value between the wheel W and the rail R, which was substantially measured at the time of acquisition of the optical information by the optical information acquisition means 3. This allows the system to continue training even while it is in use.

[0011] In other words, the optical information may be catalogued in the database 5 according to the respective actual adhesion values between the wheels W and the rails R.

[0012] The actual adhesion value measured between the wheels W and the rails R can be determined by braking an axle of the rail vehicle RV and analyzing the behavior of that axle. Braking only one axle does not affect the behavior of the rail vehicle RV, since braking one axle does not affect the dynamics of the rail vehicle RV. In this way, it is possible to measure the actual adhesion value between the wheels W and the rails R without negatively affecting the speed of the rail vehicle RV and the comfort of passengers on board the rail vehicle RV. Preferably, the brakes are applied until the axle of the rail vehicle RV begins to skid or up to a predetermined limit value.

[0013] 3A and 3B show two examples of direct adhesion measurements when a (dedicated) braking force 302 is applied to the axle.

[0014] In the graph, 300 indicates the maximum braking force at the axle level that may be required by the exemplary railcar RV under discussion. Typically, maximum braking force 300 is the braking force applied during emergency braking.

[0015] The procedure for direct adhesion measurement involves applying a braking force 302 to one or more axles. The braking force 302 has an increasing ramp. When the maximum braking force 300 is reached, as shown in Figure 3A, or when the axle in question begins to slip, i.e., when the axle's tangential speed 304 deviates from the vehicle's travel speed 306, as shown in Figure 3B, the braking force 302 is returned to zero, thereby interrupting the upward slope of the braking force 302 graph.

[0016] In the case of Figure 3A, it is not possible to quantify the adhesion force between the wheel W and the rail R, but it can be said that the adhesion force between the wheel W and the rail R is sufficient to apply maximum braking force (e.g., to apply an emergency brake). Typically, the adhesion force engaged by an emergency brake is about 0.15. Therefore, in the case of Figure 3A, it can be said, for example, that the adhesion force between the wheel W and the rail R is greater than 0.15.

[0017] In any case, measuring adhesion beyond that required for emergency braking is not particularly important.

[0018] Alternatively, in Figure 3B, the adhesion between the wheel W and the rail R is not large enough to apply the maximum braking force 300. When a certain braking force value 303, shown by the dashed line, is reached, the axle begins to slip. At this point, the braking force 302 is immediately reset to zero and the axle regains vehicle speed.

[0019] The adhesion force can be calculated using the following relationship: TIFF2025122082000002.tif12170 where, μ: Adhesion force between wheel W and rail R; F brake : Braking force applied to the axle; R: Radius of wheel W; J: axle inertia; ω: angular acceleration of the axle; M: mass weighing on the axle; G: Gravitational acceleration.

[0020] As seen in Figure 1, the database 5 may be acquired on board the railcar RV, or as seen in Figure 2, the database 5 may be located at a remote location away from the railcar RV. If the database 5 is located at a remote location, the system may communicate with the database 5 via suitable wireless communication.

[0021] The system according to the invention further comprises a control unit 7 arranged to determine a current adhesion value between the wheel W and the rail R based on a comparison between the acquired current optical information and optical information pre-stored in the database 5.

[0022] Advantageously, suggestions can be provided to the driver via a suitable human-machine interface provided in the cabin taking into account the determined current adhesion value between the wheel W and the rail R. Alternatively or additionally, a braking system of the rail vehicle RV, a Wheel Slide Protection (WSP) system of the rail vehicle RV and / or an acceleration level of the rail vehicle RV can be automatically controlled taking into account the determined current adhesion value between the wheel W and the rail R.

[0023] The control unit 7 may be, for example, a PLC, a microprocessor, a microcontroller, or an FPGA.

[0024] As can be seen from Figures 1 and 2, the optical information acquisition means 3 may be provided on the railway vehicle RV so as to acquire optical information about the rail R located in front of the first axle A1 of the railway vehicle RV according to the direction of travel V of the railway vehicle RV.

[0025] Such an arrangement allows optical information about the rail R to be obtained without being disturbed by the passage of the wheels W of the rail vehicle RV, which would tend to clean the rail R or in any way change the condition of the rail R.

[0026] The control unit 7 is configured to determine whether the current adhesion value between the wheel W and the rail R associated with the current optical information acquired by the optical information acquisition means 3 corresponds to an adhesion value associated with optical information stored in the database 5 that has a higher degree of similarity to the current optical information.

[0027] Obviously, this similarity may be determined by the control unit 7 via deep learning algorithms.

[0028] "Deep learning" refers to the field of machine learning and artificial intelligence that relies on different levels of representation. Deep learning is a set of techniques based on artificial neural networks built with multiple distinct layers. In an artificial neural network, each layer calculates values for the subsequent layer so that information is processed more completely.

[0029] Image recognition is a branch of computer science called "computer vision."

[0030] Image recognition algorithms may be used to determine similarity. Broadly speaking, automatically recognizing an image means using an algorithm that can receive an input image and extract various information from it. The extracted information may be arranged at several levels: low level (statistics about the presence of various shades of gray or other colors, statistics about abrupt changes in brightness, etc.), intermediate level (characteristics related to image regions and relationships between regions), or high level (identification of objects with semantic significance). Two images can be recognized as similar based solely on low-level, intermediate-level, or high-level characteristics.

[0031] Preferably, the optical information acquisition means 3 is a visual sensor, such as a video camera or a camera, or an image acquisition sensor.

[0032] Alternatively, the optical information acquisition means 3 may be a reflective optical sensor. In this case, the reflective optical sensor is configured to emit an optical signal toward the rail R and detect the amount and / or distribution of the optical signal reflected from the rail R, which indicates the surface condition of the rail R.

[0033] To calibrate the system, the database 5 may pre-store predetermined amounts of known optical information. Each of these predetermined amounts of known optical information is associated with a known adhesion value, and the accuracy of the association between the predetermined amounts of known optical information and the known adhesion values is verified in advance. The stored optical information is then subsequently enhanced and updated during normal operation of the railcar RV. For example, the optical information may be acquired by the optical information acquisition means 3 at predetermined intervals or when a degraded adhesion condition is detected.

[0034] Next, an example will be described. In a first step of populating the database 5 using the optical information acquisition means 3, a determined amount of optical information is obtained. The determined amount of optical information is measured substantially at the moment of acquiring each optical information from the optical information acquisition means 3 and is associated with each actual adhesion value between the actual wheel W and the rail R. In a second step, the optical information acquisition means 3 picks up one or more additional items of optical information. This additional item of optical information is used to determine the current adhesion value between the wheel W and the rail R by comparing the additional optical information with optical information previously stored in the database 5. Specifically, it is determined that the current adhesion value between the wheel W and the rail R corresponds to an adhesion value associated with optical information stored in the database 5 that has a higher similarity to the added current optical information.

[0035] The advantage achieved by the present invention is therefore that a system can be provided for determining adhesion values between the wheels W of a railway vehicle RV and the rail R. This system is self-calibrating, since it stores a series of past results, and can therefore self-calibrate in an increasingly reliable manner. With a properly calibrated system, the interpretation of indirect measurements based on optical sensors can be more reliably performed, thus reducing or eliminating the need for dedicated brakes used solely for adhesion measurements.

[0036] Various aspects and embodiments of the system for determining the adhesion value between a wheel of a railway vehicle and a rail according to the present invention have been described in detail. It is understood that each embodiment can be combined with any other embodiment. Furthermore, the present invention is not limited to the described embodiments, but may be modified within the scope defined by the appended claims.

Claims

1. A system for determining an adhesion value between a wheel (W) and a rail (R) for a railway vehicle (RV), comprising: an optical information acquisition means (3) provided to acquire optical information from the rail (R); a database (5) for storing the acquired optical information at least during a learning phase and for associating the acquired optical information with actual adhesion values between the wheels (W) and the rails (R) measured substantially at the time of acquisition of the optical information by the optical information acquisition means (3); a control unit (7) arranged to determine a current adhesion value between the wheel (W) and the rail (R) based on a comparison between the acquired current optical information and the optical information previously stored in the database (5), The control unit (7) is configured to determine whether the current adhesion value between the wheel (W) and the rail (R) associated with the current optical information acquired by the optical information acquisition means (3) corresponds to the adhesion value associated with the optical information stored in the database (5) that has the highest similarity to the acquired current optical information.

2. 2. The system according to claim 1, wherein said optical information acquisition means (3) is a visual sensor.

3. The system of claim 2 , wherein the visual sensor comprises a video camera or a camera.

4. 2. The system according to claim 1, wherein the optical information acquisition means (3) is a reflective optical sensor.

5. The system according to claim 4, wherein the optical information acquisition means (3) of reflective type is configured to emit an optical signal to the rail (R) and further to detect the amount and / or distribution of the optical signal reflected by the rail (R), which indicates the surface condition of the rail (R).

6. 6. The system according to claim 1, wherein the control unit (7) is configured to determine, via an image recognition algorithm based on artificial intelligence and / or machine learning, which of the optical information stored in the database (5) has the highest degree of similarity to the current optical information.

7. 7. A system according to any one of claims 1 to 6, wherein the database (5) is located at a remote location away from the railway vehicle (RV).

8. 8. A system as claimed in any one of claims 1 to 7, wherein the optical information acquisition means (3) is provided on the railway vehicle (RV) so as to acquire the optical information of the rail (R) located in the direction of travel (V) of the railway vehicle (RV) and therefore in front of a first axle (A1) of the railway vehicle (RV).

9. 9. The system of claim 1, wherein the database (5) is configured to store predetermined amounts of known optical information, each of which is associated with a known adhesive strength value, and the accuracy of the association between the predetermined amounts of known optical information and the known adhesive strength value is verified in advance.

10. 10. The system according to any one of claims 1 to 9, wherein the actual adhesion value between the wheels (W) and the rails (R) is measured by analyzing the behavior of the axles of the railway vehicle (RV) during a braking phase.

11. 11. The system of claim 10, wherein the axles of the RV are braked until the axles begin to slip or up to a predetermined limit.

Images