Automated wheel profile wear determination

Abstract

A method for the automated determination of driving-related wear (V) of a wheel of a rail vehicle is described. In the method, the rail vehicle travels a measuring distance (MS) whose length (ZS) is known or determined with high precision. In addition, the required number (AU) of revolutions (U) of the wheel to travel the measuring distance (MS) is determined. Based on the length (ZS) and the determined number (AU) of revolutions (MS) of the wheel, a current diameter (Dm) of the rail vehicle wheel is determined. In addition, wear (V) of the wheel is determined by comparing the determined current diameter (Dm) with a reference value (Dn, Dm°). Furthermore, a method for training an artificial intelligence-based algorithm for determining a current value of a geometric parameter (Sd, Sh, qR, S, HL) of a wheel profile of a rail vehicle is described.A wear detection device (40) is also described.

Description

[0001] The invention relates to a method for the automated determination of driving-related wear on a wheel of a rail vehicle. The invention also relates to a method for training an artificial intelligence-based algorithm for determining a current value of a geometric parameter of a wheel profile of a rail vehicle. The invention further relates to a wear determination device.

[0002] Rail vehicles are subject to severe wear during operation due to the exceptionally large masses they move, the resulting high energy flow, and the pronounced dissipation resulting from this high energy flow. This particularly affects the contact between the wheels of a rail vehicle and the track being traveled on.

[0003] The wheel profile of rail vehicles, i.e., the part of a rail vehicle wheel that ensures stable contact with the rail, is manufactured by turning according to a standardized geometry (DIN EN 13715). Due to dynamic metal-to-metal contact, the wheel profile is subject to significant wear. This wear can be divided into two components.

[0004] Part of this is due to rolling during movement, which is always accompanied by slippage and micro-sliding. This wear manifests itself, on the one hand, in a geometric change in the profile, which is "deformed" compared to the profile prescribed by the standards.

[0005] On the other hand, wear is due to the correction of profile changes. This correction is achieved through underfloor wheelset rotation (reprofiling), which constantly removes material to restore the (standard-compliant) wheel profile, which naturally involves a reduction in the wheel diameter.

[0006] To determine when reprofiling is necessary, it is usually customary to perform periodic measurements of a wheel's diameter and profile using special equipment that measures certain geometric parameters of the wheel and its profile. When these parameters reach certain limits, reprofiling is scheduled. This is where the first problem lies: the use of most measuring instruments requires that the vehicle be stopped in a workshop suitable for wheel inspection (i.e., equipped with a suitable inspection pit) so that personnel trained in the use of these measuring instruments can intervene.

[0007] One of the required measurements is the diameter of the circle corresponding to point D0 (see Fig. 1) of the profile, which is located in the transverse center of the profile. When measuring the diameter, the measuring instruments currently in use provide results that are subject to measurement errors due to their operating principle. For example, some measuring instruments measure the diameter of the wheel flange (diameter at the location of the apex SP in Fig. 1), then measure the flange height (Sh in Fig. 1) and then estimate the measured diameter, which refers to the center of the profile.

[0008] Other bow-shaped instruments (see Fig. 2) are mounted on the wheel tread and allow indirect diameter measurement by measuring the curvature of the arc. In this case, small local deformations (flat spots), surface damage, contamination, etc., lead to measurement errors of a magnitude (millimeters) consistent with the operating limits.

[0009] The error inherent in these measurements can (and should) be reduced by taking measurements on the same wheel in different curve sectors and then averaging the results. However, this is particularly cumbersome because, at any given position in the workshop when the vehicle is stationary, only a limited sector of each wheel is almost always accessible. To gain access to other or larger sectors, the vehicle would have to be moved so that the wheels rotate by enough degrees to make different curve sectors accessible to the measuring device. This is almost never done in practice because it is often too costly and because railway workshops are not always equipped to carry out such movements safely.The measurement error is sometimes so large that when comparing the measurement reports of two consecutive inspections, the diameter assigned to one report is often larger than that assigned to the previous report, which of course cannot correspond to the facts due to the increasing wear of the wheels during operation.

[0010] The wheel diameter is important for vehicle safety and reliability. Since it contributes to determining instantaneous speed using displacement sensors, the problem arises of reducing these measurement errors, verifying the accuracy of measurements taken using conventional methods, and possibly applying more precise innovative methods. Other geometric parameters of the wheel profile (which are also relevant to vehicle safety) also change constantly during vehicle operation and usually approach their operating limits. Since these parameters (e.g. Sh = wheel flange height, Sd = wheel flange thickness, qR = wheel flange flank dimension) are also only determined during workshop inspections, the problem arises of estimating them more frequently using innovative methods.

[0011] The task is therefore to develop a method and a device for the simplified determination of wheel wear on a wheel of a rail vehicle.

[0012] This object is achieved by a method for the automated determination of the driving-related wear of a wheel of a rail vehicle according to patent claim 1, a method for training an algorithm based on artificial intelligence for determining a current value of a geometric parameter of a wheel profile of a rail vehicle according to patent claim 12 and a wear determination device according to patent claim 13.

[0013] In the method according to the invention for the automated determination of driving-related wear on a wheel of a rail vehicle, the rail vehicle travels a measuring distance whose length is known or determined with high precision. As explained in more detail later, there are various methods for precisely measuring a distance. In the simplest case, the distance has markings whose spacing is precisely known. When the rail vehicle passes the marking, the counting of revolutions is started or stopped. Alternatively, an exact position measurement of a rail vehicle can also be carried out based on a satellite navigation system, whose measurement errors are corrected using additional information.

[0014] As explained in more detail later, a differential satellite navigation system is particularly well suited for highly accurate measurement of a measuring distance traveled by a rail vehicle. If the length of the measuring distance is determined by an internal measuring device of the rail vehicle, wheel wear can be determined automatically, independent of the measurements taken by an infrastructure operator. However, with a one-time measurement, particularly by the infrastructure operator, the accuracy of the wear determination can be advantageously increased in areas where an exact measurement of the length of a measuring distance using an internal measuring device is not possible. For example, such a case can arise if no differential satellite navigation system is available in an area and the measurement of a simple satellite navigation system needs to be refined.

[0015] Furthermore, the required number of wheel revolutions to travel the test section is determined. To measure the required number of revolutions, a position encoder is preferably used, which is fitted to an axle of a modern rail vehicle, particularly a modern locomotive. Such a position encoder transmits, among other things, the instantaneous angular velocity of each axle to the safety systems as well as to the anti-skid and anti-skid systems. A modern rail vehicle includes a computing system that can determine the number of revolutions of each axle, and even fractions thereof, with high accuracy within a predetermined time interval or over a predetermined distance.

[0016] Based on the length ZS of the track and the determined number AU of wheel revolutions, the current diameter Dm of the rail vehicle wheel is determined. The wheel diameter Dm is defined as the diameter in a measuring circle plane. The measuring circle plane is preferably located 70 mm from the inner face of the wheel.

[0017] The diameter Dm of the wheel is calculated using the following formula: Dm=zsAU⋅π.

[0018] A rail vehicle wheel has a wheel profile with a generative curve defined by standards, viewed in the cross-sectional direction. The generative curve exhibits a bulge on the part facing the inside of the track and a slight taper on the part facing the outside of the track, the wheel flange. For simplification, this body can be approximated by a truncated cone.

[0019] This special geometry of the wheels in a rail vehicle wheelset means that when one axle moves slightly in an axial direction, for example to the left, the left wheel ideally rolls on a disc with a slightly larger diameter than the right wheel. However, since both wheels are rigidly attached to the same axle and must therefore rotate in unison, i.e. by the same angle at the same time, contact with the rail creates a restoring moment that lies in the running plane and returns the wheelset to the track center. During rectilinear movement, this essentially results in an oscillating, almost sinusoidal movement of the axle in the rolling plane. On the other hand, each individual wheel rolls moment by moment over an ideal point, the rail contact point, which is at a distance from the axle center that varies between a minimum and a maximum.

[0020] The point of contact, or more precisely the very small contact area, between the wheel and the rail therefore describes an open curve with each revolution, since the end point of a revolution does not usually coincide exactly with its starting point. This is due to the "truncated cone" geometry of the wheel and the resulting transverse movements. However, the point at which the revolution begins and the point at which the revolution ends are very close to each other. Therefore, it can be assumed that the wheel travels a distance with each revolution equal to the length of the open curve described above. This applies under the assumption that the wheel rolls without creep. This length can be related to the average diameter of the open curve associated with each revolution.

[0021] If we also assume a sufficiently large number of revolutions AU and know that the wheel rotates on circles with alternating larger and smaller diameters, we can approximately assume that the average of the length of the curves described at each revolution is equal to the circumference of the circle corresponding to the point D0 of the wheel profile in the measuring circle plane.

[0022] In reality, the contact between wheel and rail is not point-like, but occurs over a small contact surface. The dimensions of this surface, for the materials in question, are very small compared to the surface of a wheel with a diameter of more than one meter. It can therefore be assumed that this surface can be approximated to a point and that, after a very large number AU of revolutions, the distance traveled by rolling on a circle with a diameter between a minimum and a maximum is practically identical to the distance that would have been traveled if rolling had occurred only on a disc of negligible thickness and a diameter Dm.

[0023] Assuming that the traveled measuring distance or path ZS is many orders of magnitude larger than the diameter of a wheel, which is about one meter, i.e. that the number AU of revolutions is so large that the average of the circles on which the path ZS is traveled practically coincides with the diameter Dm of the reference circle for the measurements, the value of the diameter Dm can be calculated according to formula (1).

[0024] Finally, wheel profile wear is determined based on a comparison, preferably by comparison, of the determined current diameter with a reference value of the wheel diameter. Wear is understood to be the wear of the tread of a rail vehicle wheel that leads to a change in the wheel profile. As explained in more detail later, wear is characterized in particular by the variables wheel flange height Sh, wheel flange thickness Sd, wheel flange flank angle qR, and rollover S. The knowledge that these variables are related to changes in the wheel diameter is used here. For example, the wheel flange height Sh increases when the diameter in the center of the wheel is reduced due to wear, since the point D0 in the center of the track profile is used as the reference point for determining the wheel flange height Sh.The flange thickness Sd, on the other hand, decreases as the wheel diameter decreases due to wear. The flank angle qR also decreases with increasing wear. The roll over S, on the other hand, increases with increasing wear.

[0025] Furthermore, a so-called hollow run HL can also be determined as wear based on the diameter Dm.

[0026] If significant wear is detected in the area of point D0, this is referred to as a “false flange” or “hollow runout” according to standard EN 15313:2016 (D) - §C.2.14.

[0027] A hollow run (HL) in the form of a false wheel flange occurs when the outer tread area is higher than the tread in the measuring circle plane. A hollow run develops when significant tread wear occurs in the area of the measuring circle plane. Therefore, based on the measurement according to the invention, an estimate of the hollow run, which according to the standard must not exceed 2 mm, can also be made.

[0028] Advantageously, wheel tread wear is determined while the rail vehicle is in motion, eliminating the need for the vehicle to visit a workshop for wear assessment. A visit to the workshop is only required when one of the automated wear measurements indicates that a wear limit has been reached. Advantageously, the number of visits to the workshop can be reduced compared to the conventional approach, in which wheel tread wear is determined in a workshop itself. The method according to the invention allows the current values characterizing wheel wear to be continuously estimated, and timely notification of an inspection can be provided.

[0029] The method according to the invention for training an algorithm based on artificial intelligence for determining a current value of a geometric parameter of a wheel profile of a rail vehicle is preferably intended to be used in the method according to the invention for the automated determination of the driving-related wear of a wheel of a rail vehicle in order to determine the wear on the basis of the determined current diameter of the wheel.

[0030] In the method according to the invention for training an artificial intelligence-based algorithm for determining a current value of a geometric parameter of a wheel profile of a rail vehicle, labeled training data is provided, which comprises a wheel diameter value as input data and a target value of an additional parameter of the wheel profile as output data. Such an additional parameter or its value characterizes the shape of the wheel profile and thus also the rolling properties of the wheel. These additional parameters characterize the wear condition of the wheel. As already briefly explained, wear is characterized in particular by the variables wheel flange height Sh, wheel flange thickness Sd, wheel flange flank angle qR, and the rollover S and hollow run HL.Labeled data is understood here as training data that includes target data that can be compared with the algorithm's result data once the input data of the training data has been entered into the algorithm. The artificial intelligence-based algorithm preferably has an artificial neural network that is subject to adaptation to the training data used for training during the training process.

[0031] Furthermore, the algorithm determines a value of an additional parameter of the wheel profile based on the input data.

[0032] The algorithm is adapted based on the output data or result data of the algorithm and the output data or target data of the training data. If an artificial neural network is used to implement the algorithm, the weights of the artificial neural network are updated using an error function that incorporates the result of the algorithm and the corresponding target value of the labeled training data. The "comparison" is therefore carried out in such a way that the target value and the result of the algorithm are used as input values for the error function during a training step, and the result of the error function determines the change in the weights of the artificial neural network.

[0033] The artificial intelligence-based algorithm is trained through the training process to estimate the additional wheel profile parameters based on labeled training data, which includes both measured wheel diameters as input data for the algorithm and target values of an additional wheel profile parameter as the desired output values of the algorithm. The training process can also be performed based on measurements of the additional parameters taken in the workshop during an inspection, so that the algorithm becomes increasingly more reliable and accurate over time.

[0034] The wear determination device according to the invention has a track length determination unit for the highly accurate determination of a length of a measuring track to be traveled by a rail vehicle.

[0035] Part of the wear detection device according to the invention is also a rotation speed detection unit for determining the required number of wheel revolutions to travel the measuring distance. Such a rotation speed detection unit comprises a tachometer or angle sensor.

[0036] The wear determination device according to the invention also comprises a diameter determination unit for determining a current diameter of the wheel of the rail vehicle on the basis of the length and the determined number of revolutions of the wheel.

[0037] Furthermore, the wear detection device according to the invention comprises a wear detection unit for determining the wear by comparing the determined current diameter with a reference value. The wear detection device according to the invention shares the advantages of the method according to the invention for the automated determination of driving-related wear of a wheel of a rail vehicle.

[0038] Some of the aforementioned components of the wear detection device according to the invention can be implemented entirely or partially in the form of software modules in a processor of a corresponding computer system. A largely software-based implementation has the advantage that even computer systems already used in the control of rail vehicles can be easily retrofitted with a software update to operate in the manner according to the invention.

[0039] In this respect, the object is also achieved by a corresponding computer program product with a computer program that can be loaded directly into a computer system, with program sections for executing the steps of the method according to the invention for the automated determination of the driving-related wear of a wheel of a rail vehicle, optionally using suitable additional measuring sensors, when the program is executed in the computer system. Advantageously, such a computer program product can, in addition to the computer program, optionally comprise additional components, such as documentation, and / or additional components, including hardware components, such as hardware keys (dongles, etc.) for using the software.

[0040] A computer-readable medium, e.g., a memory stick, a hard disk, or another portable or permanently installed data storage device, on which the program sections of the computer program that can be read and executed by a computer system are stored, can be used for transport to the computer system and / or for storage on or in the computer system. For this purpose, the computer system can, for example, have one or more cooperating microprocessors or the like.

[0041] The dependent claims and the following description each contain particularly advantageous embodiments and developments of the invention. In particular, the claims of one claim category can also be developed analogously to the dependent claims of another claim category and their description parts. Furthermore, within the scope of the invention, the various features of different embodiments and claims can also be combined to form new embodiments.

[0042] In a variant of the method according to the invention for the automated determination of driving-related wear on a rail vehicle wheel, the length of the measuring section is measured in advance with high precision. As already mentioned, such an approach is particularly advantageous when access to a differential satellite navigation system is not possible.

[0043] Alternatively, the length of the test section is measured with high precision using a differential satellite navigation system while the vehicle is being driven. A differential satellite navigation system is capable of determining the position of a rail vehicle with an error of a few centimeters, or even a few millimeters with optimal signal reception. Particularly precise differential satellite navigation systems also evaluate the phase shift of the carrier wave, thus achieving accuracies of a few millimeters. Therefore, if the starting point and end point of the route or test section lie on a straight line entirely within an area covered by a high-quality differential satellite navigation system, it is possible to determine the distance ZS between the starting point and the end point with high accuracy, which can then be used to calculate the diameter Dm of a wheel.The accuracy of the position determination depends on the distance of the satellite navigation system's receiver from the reference station. As already mentioned, the length of the measuring section should be orders of magnitude greater than the diameter of the rail vehicle's wheels, preferably several kilometers. This ensures that the number of revolutions is high enough that the effects of lateral movement of the axles, also known as "snaking," can be neglected. Preferably, the measuring section is traveled multiple times, and the measured distances are averaged.

[0044] In this case, the test section is preferably repeated several times. A statistical mean of the length of the test section is then determined. The measured values of the number of revolutions that deviate from a statistical mean by more than a predetermined threshold are discarded. Finally, an average of the number of revolutions is determined based on the remaining measured values, and this average is used as the basis for determining the statistically corrected current diameter Dm* of the rail vehicle wheel. The accuracy of the measurement result is advantageously further improved by averaging and discarding "outliers." This is because the determination of a wheel diameter can be affected by a systematic error, which is mainly due to micro-sliding and slippage of the motorized axles.

[0045] As already explained above, the diameter of the wheel preferably refers to the center of the wheel profile at point D0 in the center plane of the wheel. The term "point" here refers to a projection or sectional view of a wheel. In three-dimensional terms, the "point" D0 corresponds to a circle that revolves around the wheel profile in the center plane of the wheel. The center of the wheel profile is approximately in the area where a wheel of a rail vehicle is in contact with the rail. The wheel diameter Dm at the center of the wheel profile can advantageously be determined based on the number of wheel revolutions and the length of the distance traveled or measured distance.

[0046] More precisely, the "point" D0 can be defined as a small, elliptically shaped area slightly elongated in the direction of travel. The geometry of this contact area varies dynamically during rolling and is strongly influenced by the physical properties of the contacting metals (wheel / rail) and the mutual dynamic interactions due to the ride.

[0047] Preferably, a correction value after replacing or reprofiling a wheel is determined by first determining a first value Dm* of a current diameter immediately after the wheel's replacement or reprofiling, and then comparing the current diameter Dm* with the wheel's diameter value Dn listed in the design documents as a reference value. If necessary, an offset |Dn - Dm*| of the first value Dm* relative to the value Dn listed in the design documents is determined as the correction value. It is expedient to use this offset to correct any error that may have influenced the diameter estimate.This offset, whose value is calculated once as described, is then applied to all subsequent diameter estimates Dm, which are made using formula (1) and the statistical correction already mentioned, to eliminate the systematic error affecting the first value Dm* for this and all subsequent measurements. The first value of a current diameter corrected by this offset is also referred to as Dm° and corresponds to the value Dn from the design documents.

[0048] Alternatively, the reference value can be corrected by the correction value to account for the systematic measurement error. This means that in this case, the first value Dm* is used as the reference value, and the wear is determined based on the difference between subsequent values Dm of the wheel diameter and the first value Dm*. This advantageously compensates for a systematic measurement error.

[0049] Also preferably, a current diameter value corrected by the correction value |Dn - Dm*| is compared with the data entered for the safety systems and drive control systems of the rail vehicle and / or measurements performed during the last inspection, and corrections are made to these data if necessary. Advantageously, further measurement errors that have occurred in connection with measurements performed using methods other than the method according to the invention are also detected and corrected if necessary. In particular, safety-relevant and reliability-relevant errors can be corrected in this way.

[0050] Furthermore, a current value of at least one of the following additional geometric parameters of the wheel profile is preferably determined by an algorithm based on artificial intelligence on the basis of the determined current diameter Dm: - the flange thickness Sd, - the flange height Sh, - the flange dimension qR, - the overrolling S, - the hollow barrel HL.

[0051] Once the wear condition of the profile of a rail vehicle wheel on the rolled strip has been determined using the current diameter value Dm, i.e., at point D0 of the profile, which is located in the transverse center of the profile, this information can be used to determine additional wheel profile parameters. It is advantageous to determine additional wheel profile wear parameters, based on which a maintenance strategy can be defined.

[0052] In addition to the current value Dm of the diameter, preferably in addition to the deviation of the current value Dm of the diameter from a reference value Dm°, the determined operating conditions of the rail vehicle are also used as input data for the algorithm.

[0053] A correlation between the development of overroll S due to wear, in conjunction with the change in other parameters (due to the same wear), can be statistically determined during the algorithm training phase and subsequently further refined during algorithm implementation. This makes the wear determination even more precise.

[0054] The operating conditions preferably include at least one of the following types of operating conditions: - the average speed of the rail vehicle, - the curve profile of the routes travelled by the rail vehicle since the last test measurement, - the gradient profile of the routes travelled by the rail vehicle since the last test measurement, - weather conditions during operation of the rail vehicle, in particular snow or ice, - the general condition of the track used, - temperatures prevailing during operation.

[0055] Advantageously, these influencing factors affecting wheel wear can be taken into account by the algorithm for determining the additional parameters that characterize wheel wear, making the final result for determining the wheel wear of a rail vehicle more precise and reliable.

[0056] The invention is explained in more detail below with reference to exemplary embodiments in the accompanying figures. They show: Fig. 1 a sectional view of a wheel profile of a rail vehicle, Fig. 2 a conventional curved measuring device for indirectly measuring the diameter of a wheel of a railway vehicle by measuring the curvature of the wheel profile in the circumferential direction, Fig. 3 is a flowchart illustrating a method for the automated determination of the driving-related wear of a wheel of a rail vehicle, Fig. 4 a schematic representation of a wear detection device according to an embodiment of the invention, Fig. 5 is a flowchart illustrating a method for training an artificial intelligence-based algorithm for determining a current value of a geometric parameter of a wheel profile of a rail vehicle, Fig. 6 a schematic representation of a training device according to an embodiment of the invention.

[0057] In Fig. Figure 1 shows a sectional view 10 of a wheel profile of a rail vehicle, with the "length" L plotted against the "height" H of the wheel profile (each in mm). The "length" L here refers to the radial extension of the wheel, and the "height" H refers to the axial extension of the wheel. More precisely, Fig. 1 shows two wheel profiles, a wheel profile N (shown as a solid line) of a new wheel and a wheel profile W (shown as a dashed line) of a worn wheel. As a parameter of the wheel profile, a wheel flange height Sh is shown for the wheel profile N of the new wheel, which shows the height of the highest point of the wheel flange above the height of the wheel profile in the wheel center at point D0. Furthermore, in Fig. 1 shows the flange thickness Sd. The flange flank dimension qR is also shown, which represents the flank width of the flange. Furthermore, Fig. 1 illustrates a depression or hollow HL of the wheel profile of the worn wheel. In addition, Fig. 1 The overroll S is shown on the right side of the image. The overroll S represents a material redistribution of the wheel material from the center of the wheel profile to the edge.

[0058] In Fig. 2 shows two representations 20 of a conventional arc-shaped measuring device for indirectly measuring the diameter of a wheel of a rail vehicle by measuring the curvature of the wheel profile in the circumferential direction.

[0059] In Fig. 3 shows a flowchart 300 which describes a method for the automated determination of the driving-related wear of a wheel of a rail vehicle.

[0060] In step 3.I, the rail vehicle travels along a measuring section MS, whereby the length ZS of the rail section or the measuring section MS is determined with high precision by a differential satellite navigation system.

[0061] In step 3.II, the required number AU of revolutions U of the wheel for traveling the measuring distance is determined.

[0062] In step 3.III, a current diameter Dm of the wheel of the rail vehicle is determined based on the length ZS and the determined number AU of revolutions of the wheel.

[0063] In step 3.IV, the determined current diameter Dm is compared with a reference value Dn. In the event that the difference between the two values exceeds a predetermined threshold, which is Fig. 1 is marked with “y”, the process proceeds to step 3.V and a plurality of wear parameters V of the wheel are determined by an algorithm based on artificial intelligence.

[0064] In case the threshold value is not exceeded in step 3.IV, which is Fig. 3 is marked with “n”, the process proceeds to step 3.I and the process is repeated after a certain period of time.

[0065] In Fig. 4 shows a schematic representation of a wear detection device 40 according to an embodiment of the invention.

[0066] The wear determination device 40 has a route length determination unit 41 for highly accurate determination of a length of a measuring route to be traveled by a rail vehicle on the basis of satellite navigation data SND.

[0067] Part of the wear determination device 40 is also a revolution number determination unit 42 for determining the required number AU of revolutions U of the wheel for traveling the measuring distance.

[0068] The wear determination device 40 comprises a diameter determination unit 43 for determining a current diameter Dm of the wheel of the rail vehicle on the basis of the length ZS and the determined number AU of revolutions of the wheel.

[0069] The wear determination device 40 also has a wear determination unit 44 for determining the wear V by comparing the determined current diameter Dm with a reference value Dn.

[0070] In Fig. 5 shows a flowchart 500 illustrating a method for training an artificial intelligence-based algorithm for determining a current value of a geometric parameter of a wheel profile of a rail vehicle characterizing the wear V of a wheel.

[0071] In step 5.I, labeled training data TD are provided, which comprise as input data a value Dm of a wheel diameter and as output data a target value of an additional parameter Sd, Sh, qR, S, HL of the wheel profile characterizing the wear V of a wheel.

[0072] In step 5.II, a value Dm of a wheel diameter is entered as the input value for the ALG algorithm. Furthermore, based on the input data Dm, the ALG algorithm determines an additional parameter ZP of the wheel profile as the output value.

[0073] In step 5.III, the algorithm ALG is adapted based on the value of the determined additional parameter ZP and the corresponding value ZP L this additional parameter, which is assigned to the labeled training data TD.

[0074] In step 5.IV, a difference ΔZ between the determined additional parameter ZP and the corresponding parameter ZP L of the labeled training data TD.

[0075] In step 5.V it is determined whether the difference ΔZ falls below a predetermined threshold value SW.

[0076] In the event that the threshold value SW is undershot, which is Fig. 5 is marked with "y", the algorithm for calculating additional wear parameters ZP is provided as part of the procedure for the automated determination of the driving-related wear of a wheel of a rail vehicle. In the event that the threshold value SW is exceeded, which is Fig. 5 is marked with “n”, the process proceeds to step 5.I and the algorithm ALG is further adapted to the training data TD.

[0077] In Fig. 6 is a schematic representation of a training device 60 according to an embodiment of the invention.

[0078] The training device 60 has an AI unit 61, which is configured to determine additional parameters ZP based on input data Dm from labeled training data TD. The additional parameters ZP as well as the additional parameters ZP assigned to the labeled training data TD L are transmitted to an adaptation unit 62, which adapts the ALG algorithm of the AI unit 61 to the received data ZP, ZPL. For example, the ALG algorithm is based on an artificial neural network with weights that are adapted to the target values. The received data ZP, ZP Lare also transmitted to a difference-forming unit 63, which determines a difference value ΔZP from it. Part of the training device 60 is also a testing unit 64, which, based on the difference value ΔZP, checks whether the ALG algorithm has already been sufficiently adapted to the training data TD. If this is the case, the algorithm is made available for the calculation of additional parameters ZP. Otherwise, the ALG algorithm is returned to the AI unit 61, and the adaptation process continues.

[0079] Finally, it is pointed out once again that the methods and devices described above are merely preferred embodiments of the invention and that the invention can be varied by a person skilled in the art without departing from the scope of the invention, insofar as it is defined by the claims. For the sake of completeness, it is also pointed out that the use of the indefinite articles “a” or “an” does not exclude the possibility that the features in question may be present in multiple units. Likewise, the term “unit” does not exclude the possibility that it consists of several components, which may also be spatially distributed. Regardless of the grammatical gender of a particular term, persons with male, female or other gender identities are included. QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited non-patent literature

[0000] Standard EN 15313:2016 (D) - §C.2.14

[0026]

Claims

[1] Method for the automated determination of the driving-related wear of a wheel of a rail vehicle, comprising the steps: - Driving along a measuring section (MS) by the rail vehicle, the length (ZS) of which is known with high precision or is determined with high precision, - Determine the required number (AU) of revolutions (U) of the wheel to travel the measuring distance (MS), - Determination of a current diameter (Dm) of the wheel of the rail vehicle based on the determined length (ZS) of the measuring section (MS) and the determined number (AU) of revolutions of the wheel, - Determination of the wear (V) of the wheel based on a comparison of the determined current diameter (Dm) with a reference value (Dn, Dm°) of the diameter. [2] Method according to claim 1, wherein the length (ZS) of the measuring section (MS) is measured in advance with high precision. [3] Method according to claim 1, wherein the length (ZS) of the measuring section (MS) is measured with high precision by a differential satellite navigation system while traveling along the measuring section (MS). [4] Method according to claim 3, wherein - the test section (MS) is repeated several times, - a statistical mean value of the length (ZS) of the measuring section (MS) is determined, - Measured values of the number (AU) of revolutions (U) which deviate from a statistical mean value by more than a predetermined threshold value (SW) are rejected, - on the basis of the remaining measured values, an average value of the number (AU) of revolutions (U) is determined and this average value is used as the basis for determining the current diameter (Dm) of the wheel of the rail vehicle. [5] Method according to one of the preceding claims, wherein the current diameter (Dm) of the wheel refers to the center (D0) of the wheel profile. [6] Method according to one of the preceding claims, wherein a correction value after the replacement or reprofiling of a wheel is determined by a first determination of a first value (Dm*) of a current diameter directly after the replacement or reprofiling of the wheel and by a comparison of the first value (Dm*) with the value (Dn) of the diameter of the wheel listed in design documents as a reference value and this correction value is taken into account in the later measurement of a current diameter (Dm) for determining the current wear (V). [7] Method according to claim 6, wherein a value of the diameter of the wheel corrected by the correction value is compared with the data entered for the safety systems and driving control systems of the rail vehicle and / or measurements carried out during the last inspection and, if necessary, corrections are made to these data. [8] Method according to one of the preceding claims, wherein a current value of at least one of the following geometric additional parameters (Sd, Sh, qR, S, HL) of the wheel profile is determined by an algorithm based on artificial intelligence on the basis of the determined current diameter (Dm): - the flange thickness (Sd), - the flange height (Sh), - wheel flange dimension (qR), - the overrolling (S), - the hollow barrel (HL). [9] Method according to claim 8, wherein, in addition to the current diameter (Dm), the determined operating conditions of the rail vehicle are also used as input data for the algorithm. [10] The method of claim 9, wherein the operating conditions comprise at least one of the following types of operating conditions: - the average speed of the rail vehicle, - the curve profile of the routes traveled, - the gradient profile of the routes traveled, - weather conditions during operation of the rail vehicle, - the condition of the track being used, - temperatures prevailing during operation. [11] Method for training an artificial intelligence-based algorithm for determining a current value of a geometric parameter (Sd, Sh, qR, S, HL) of a wheel profile of a rail vehicle, comprising the steps: - Providing labeled training data (TD), which contains as input data a value (Dm) of a wheel diameter and as output data a target value (ZP L ) of an additional parameter (Sd, Sh, qR, S, HL) of the wheel profile, - Determining a value (ZP) of an additional parameter (Sd, Sh, qR, S, HL) of the wheel profile by the algorithm (ALG) based on the input data as output data, - Adapting the algorithm (ALG) based on the output data (ZP) of the algorithm (ALG) and the output data (ZP L ) of the labeled training data (TD). [12] The method of claim 11, wherein the input data comprises operating conditions encountered during use of the rail vehicle. [13] Wear detection device (40), comprising: - a track length determination unit (41) for the highly accurate determination of a length (ZS) of a measuring track (MS) to be traveled by a rail vehicle, - a revolution number determination unit (42) for determining the required number (AU) of revolutions of the wheel for traveling the measuring distance (MS), - a diameter determination unit (43) for determining a current diameter (Dm) of the wheel of the rail vehicle on the basis of the length (ZS) of the measuring section (MS) and the determined number (AU) of revolutions (U) of the wheel, - a wear determination unit (44) for determining the wear (V) of the wheel by comparing the determined current diameter (Dm) with a reference value (Dn, Dm°) of the diameter. [14] Computer program product comprising a computer program which can be loaded directly into a memory unit of a computer system, with program sections for carrying out a method according to one of claims 1 to 12 when the computer program is executed in the computer system. [15] Computer-readable medium on which program sections executable by a computer unit are stored in order to carry out a method according to one of claims 1 to 12 when the program sections are executed by the computer unit.

Images