Method, computer program, and device for predicting tyre wear of a means of transport

Abstract

The present invention relates to a method, to a computer program comprising instructions, and to a device for predicting tyre wear of a means of transport. In a first step, wear models are assigned to the monitored tyres (S1). At a later point in time, tread depth measurement values are obtained for a subset of the monitored tyres (S2). All wear models are then calibrated on the basis of the tread depth measurement values (S4). For example, correction factors for the wear models may be determined for this purpose from the tread depth measurement values (S3). The wear of the monitored tyres is predicted on the basis of the wear models (S5).

Description

[0001] 202404087

[0002] 1

[0003] Description

[0004] Method, computer program and device for predicting tire wear of a means of transport

[0005] The present invention relates to a method, a computer program with instructions and a device for predicting tire wear of a means of transport.

[0006] To increase operational safety, it is desirable to monitor the wear of tires on a means of transport in order to be able to inform an operator of the means of transport in a timely manner about a necessary tire change.

[0007] There are approaches to determining the tread depth of a vehicle tire using a tire sensor. For example, DE 102008 002 722 A1 describes a method for determining changes in the tread depth of a vehicle tire. The method involves at least one accelerometer installed in the tire acquiring and outputting acceleration measurements while the tire is rotating. From these acceleration measurements, ratio values ​​are calculated, which represent a measure of the tire's contact patch. From a large number of ratio values, a subset is selected, to which a common, recurring load condition is assigned. Changes in the tread depth are then inferred from changes in the ratio values ​​of this subset over time.

[0008] However, due to various disadvantages or technical hurdles, such approaches have rarely been implemented in practice. 202404087

[0009] 2

[0010] An alternative approach is to predict the tread depth of a vehicle tire using a wear model. In this context, EP 4 129 714 A1 describes a method for predicting the tread depth profile of a vehicle tire. The method involves recording a large number of wear curves for specific vehicle tires. These wear curves are recorded for a variety of different parameters and stored on a data storage device. When predicting the future tread depth, this wear curve data can be used to forecast the future tread depth profile.

[0011] US 9,079,461 B2 describes a method for monitoring vehicle tires. This method reduces variations in tire condition data between vehicle tires by performing an individual self-comparison of the tire condition data for each tire. Additionally, variations in tire condition data within the tires themselves are reduced by performing a peer-based comparison of the tire condition data for each tire.

[0012] One challenge, particularly when using static wear models to predict tire wear, is the lack of knowledge about the vehicle's driving behavior, which directly impacts tire wear. Typically, static wear models only rely on tire information, vehicle information, and tire mileage. Operating parameters of the vehicle, such as speeds, accelerations, and cornering, are not considered. This leads to tire wear predictions diverging from actual wear as mileage increases.

[0013] To improve tire wear prediction, the tire tread depth can be manually measured after a certain period. The following measurement was taken: 202404087

[0014] The three measured values ​​obtained can then be used to recalibrate the wear models employed. However, this represents a considerable effort.

[0015] It is an object of the present invention to provide improved solutions for predicting tire wear of a means of transport.

[0016] This problem is solved by a method having the features of claim 1, by a computer program with instructions according to claim 9, and by a device having the features of claim 10. Preferred embodiments of the invention are the subject of the dependent claims.

[0017] According to a first aspect of the invention, a method for predicting tire wear of a means of transportation comprises the steps:

[0018] - Assigning wear patterns to the monitored tires;

[0019] - Obtaining tread depth measurements for a subset of the monitored tires;

[0020] - Calibrating all wear models using the tread depth measurements; and

[0021] - Predictions of the wear of the monitored tires based on the wear models.

[0022] According to another aspect of the invention, a computer program contains instructions which, when executed by a computer, cause the computer to perform the following steps to predict tire wear of a means of transportation:

[0023] - Assigning wear patterns to the monitored tires;

[0024] - Obtaining tread depth measurements for a subset of the monitored tires;

[0025] - Calibrating all wear models using the tread depth measurements; and

[0026] - Predictions of the wear of the monitored tires based on the wear models. 202404087

[0027] 4

[0028] The term "computer" is to be understood broadly. In particular, it also includes control units, embedded systems, smartphones, and other processor-based data processing devices. Furthermore, the individual steps are not necessarily performed directly by the computer. It is equally possible that the computer controls or relies on external components to carry out individual steps.

[0029] The computer program can, for example, be made available for electronic retrieval or be stored on a computer-readable storage medium.

[0030] According to a further aspect of the invention, a device for predicting tire wear of a means of transport comprises a memory containing instructions and a processor, wherein the processor is configured to perform the following steps for predicting the tire wear of the means of transport when the instructions are executed:

[0031] - Assigning wear patterns to the monitored tires;

[0032] - Obtaining tread depth measurements for a subset of the monitored tires;

[0033] - Calibrating all wear models using the tread depth measurements; and

[0034] - Predictions of the wear of the monitored tires based on the wear models.

[0035] Instead of manually measuring all monitored tires, the solution according to the invention only performs a manual measurement on a subset of the monitored tires of the same vehicle. The manual measurement on this subset of tires serves as a measure of the vehicle's driving intensity. This measure is used to calibrate the wear models for all tires of the vehicle. This approach is particularly advantageous for vehicles with multiple tires, such as trucks and buses, which often have six, eight, or ten tires. [The following appears to be unrelated and possibly a separate text fragment: 02404087 for the different tires 202404087]

[0036] 5 Depending on the implementation of the solution according to the invention, the same or different wear models may be used.

[0037] According to one aspect of the invention, the subset comprises exactly one tire. The minimum size of the subset is 1, meaning that a measurement is taken on only a single tire, e.g., the left front tire. This single measurement is then used to calibrate the wear models for all tires of the vehicle. In this way, the number of required manual measurements is minimized.

[0038] According to one aspect of the invention, the subset comprises at least two tires, preferably arranged on different sides and on different axles of the vehicle. In this embodiment, manual measurements are performed on at least two tires, the tires preferably being located on different sides of the vehicle, i.e., left and right, and on different axles, e.g., the first and the last axle. This allows for finer calibration of the wear models with only a slight additional effort for the manual measurements.

[0039] According to one aspect of the invention, correction factors for the wear models are determined from the tread depth measurements. The tread depth measurements taken on the tires, or the tire wear that can be determined from them, are preferably converted into one or more correction factors. These can be used particularly easily for calibrating the wear models. For example, a wear model can assume the value "1" for the correction factor as long as no manual measurement has been performed. After a manual measurement has been carried out, this value is then changed accordingly.

[0040] According to one aspect of the invention, the correction factors are specific to the means of transport. This allows for the properties of the means of transport to be determined.

[0041] 6. Factors such as mass, mass distribution, number of tires or axles, etc., should be taken into account in the correction factors.

[0042] According to one aspect of the invention, at least a subset of the correction factors is determined by interpolation, averaging, or weighted calculation. Since manual measurements are only performed on a subset of the monitored tires, tread depth measurements are not available for at least some of the monitored tires. Therefore, the correction factors must be determined from measurements taken on other tires, at least for these tires. The specific method for calculating the respective correction factors is at the discretion of the person skilled in the art.

[0043] According to one aspect of the invention, the wear models are based on analytical functions that use the correction factors as parameters. The use of analytical functions has the advantage that the wear models require only minimal computational effort and therefore correspondingly less processor power.

[0044] According to one aspect of the invention, the wear models are based on machine learning models that use the correction factors as input parameters. The use of machine learning models for the wear models has the advantage of enabling more accurate predictions of tire wear. In particular, predictions are also possible when tire wear cannot be described with sufficient accuracy using analytical functions.

[0045] Preferably, a solution according to the invention is used in a means of transport. The means of transport can be, for example, a commercial vehicle, a work machine, an agricultural vehicle, a motorcycle, a passenger car, or a trailer. 202404087

[0046] 7

[0047] Further features of the present invention will become apparent from the following description and the attached claims in conjunction with the figures.

[0048] Figure overview

[0049] Fig. 1 schematically shows a method for predicting tire wear on a means of transport;

[0050] Fig. 2 shows an embodiment of a device for predicting tire wear of a means of transport;

[0051] Fig. 3 shows a first example of the progression of predicted tire wear over mileage;

[0052] Fig. 4 shows a second example of the progression of predicted tire wear over mileage; and

[0053] Fig. 5 schematically shows a means of transport in which a solution according to the invention is implemented.

[0054] Character description

[0055] To better understand the principles of the present invention, embodiments of the invention are explained in more detail below with reference to the figures. The same reference numerals are used in the figures for identical or equivalently acting elements and are not necessarily described again for each figure. It is understood that the invention is not limited to the embodiments shown and that the described features can also be combined or modified without limiting the scope of the invention.

[0056] 8

[0057] to leave the scope of protection of the invention as defined in the attached claims.

[0058] Fig. 1 schematically shows a method for predicting tire wear on a vehicle. In a first step, wear models S1 are assigned to the monitored tires. Subsequently, tread depth measurements S2 are obtained for a subset of the monitored tires. This subset can comprise exactly one tire. Alternatively, the subset can comprise at least two tires, preferably located on different sides and axles of the vehicle. All wear models are then calibrated using the tread depth measurements S4. For example, correction factors for the wear models can be determined from the tread depth measurements S3. These correction factors can be specific to the vehicle. At least a subset of the correction factors can be determined by interpolation, averaging, or weighted calculation.The wear of the monitored tires is predicted using wear models (S5). These wear models can be based, for example, on analytical functions that use correction factors as parameters. Alternatively, the wear models can be based on machine learning models that use correction factors as input parameters.

[0059] Fig. 2 shows a simplified schematic representation of an embodiment of a device 10 for predicting tire wear A of a means of transportation. The device 10 has a memory 11 and a processor 12. For example, the device 10 is a computer, a control unit, an embedded system, or a smartphone. Instructions are stored in the memory 11 which, when executed by the processor 12, cause the device 10 to perform the steps according to one of the described methods. The 202404087 stored in the memory 11

[0060] 9

[0061] Instructions thus embody a program executable by the processor 12, which implements the method according to the invention. The device 10 has an input 13 for receiving information, for example, tread depth measurements Mp. Data generated by the processor 12, e.g., correction factors for wear models AMi for the tires, can be stored in memory 11. The wear Ai of the monitored tires predicted by the processor 12 can also be provided via an output 14. The input 13 and the output 14 can be combined into a bidirectional interface.

[0062] The processor 12 can comprise one or more processor units, such as microprocessors, digital signal processors, or combinations thereof.

[0063] Memory 11 can contain both volatile and non-volatile memory areas and can include a wide variety of storage devices and media, such as hard disks, optical storage media, or semiconductor memory.

[0064] Fig. 3 shows a first example of the progression of predicted tire wear over a mileage L. The predicted wear is represented as a remaining tread depth PT for four different tires. In this example, the predicted tire wear is generated using wear models based on analytical functions. After a certain mileage LM, a manual tread depth measurement is taken for the first time on a single tire. The measured tread depth, marked by a circle in Fig. 3, is used to calibrate the wear models of all four tires.

[0065] Fig. 4 shows a second example of the progression of predicted tire wear over mileage. Again, the predicted wear is shown as the remaining tread depth PT for four 202404087 tires.

[0066] Ten different tires. In this example, tire wear is also predicted using wear models based on analytical functions. After a certain mileage (LM), the tread depth is measured manually for the first time on two different tires located on opposite sides and axles of the vehicle. The measured tread depths, marked by circles in Fig. 4, are used to calibrate the wear models of the four tires. In this example, the wear models for the different tires are calibrated differently based on the measured tread depths, which is clearly visible in the varying step heights in the curve.

[0067] Fig. 5 schematically shows a means of transport 20 in which a solution according to the invention is implemented. In this example, the means of transport 20 is a commercial vehicle. The means of transport 20 has three axles with a total of ten tires 21. Furthermore, the means of transport 20 has a device 10 according to the invention for predicting tire wear Ai. The predicted wear Ai is evaluated by an assistance system 22, which, if necessary, can issue warnings or instructions to an operator of the means of transport 20 by means of a display device 23. For example, a prompt to perform a manual tread depth measurement can be issued, or excessive wear and a recommended tire change can be indicated. The device 10 according to the invention is shown in Fig. 5 as a separate component.Alternatively, it can also be integrated into the assistance system 22 or another component of the means of transport 20. Communication between the components in the means of transport 20 takes place, for example, via a network 24.

[0068] Preferably, the prediction of wear and tear Ai and the provision of displays do not take place in the means of transport 20, but centrally in a 202404087

[0069] 11

[0070] Database and corresponding server structures. For example, an internet-based service can be implemented that determines the profile depths, calculates and applies the correction factors, and then displays and warns users via a web portal or app. Additionally, warnings can be sent via email, SMS, or similar services if the profile depth becomes too small or if manual calibration is required.

[0071] 202404087

[0072] 12

[0073] Reference symbol list

[0074] 10 Device

[0075] 11 storage

[0076] 12 processor

[0077] 13 Entrance

[0078] 14 Exit

[0079] 20 means of transport

[0080] 21 tires

[0081] 22 Assistance systems

[0082] 23 Display device

[0083] 24 network

[0084] A wear and tear

[0085] AMi wear and tear model

[0086] Ki correction factor

[0087] L mileage

[0088] LM mileage at the time of measurement

[0089] MP profile depth measurement

[0090] PT profile depth

[0091] 51 Assigning wear models

[0092] 52 Obtaining profile depth measurements

[0093] 53 Determining correction factors for the wear and tear models

[0094] 54 Calibrating the wear models

[0095] 55 predictions of wear and tear

Claims

202404087 13 Patent claims 1. Method for predicting the wear (Ai) of tires (21) of a means of transport (20), comprising the steps: - Assigning (S1) wear models (AMi) to the monitored tires (21); - Obtain (S2) tread depth measurements (Mp) for a subset of the monitored tires (21 ); - Calibrating (S4) all wear models (AMi) based on the tread depth measurements (Mp); and - Predictions (S5) of the wear (Ai) of the monitored tires (21) based on the wear models (AMi).

2. Method according to claim 1, wherein the subset comprises exactly one tire (21).

3. Method according to claim 1, wherein the subset comprises at least two tires (21) arranged on different sides and on different axes of the means of transport (20).

4. Method according to one of the preceding claims, wherein correction factors (K) for the wear models (AMi) are determined from the profile depth measurements (Mp) (S3).

5. Method according to claim 4, wherein the correction factors (K) are specific for the means of transport (20).

6. Method according to claim 4 or 5, wherein at least a subset of the correction factors (K) is determined by interpolation, averaging, or weighted calculation (S3). 202404087 14 7. A method according to any one of claims 4 to 6, wherein the wear models (AMi) are based on analytical functions that use the correction factors (K) as parameters.

8. A method according to any one of claims 4 to 6, wherein the Wear models (AMi) are based on machine learning models that use correction factors (K) as input parameters.

9. Computer program with instructions which, when executed by a computer, cause the computer to perform the steps of a method according to any one of claims 1 to 8 for predicting wear (Ai) of tires (21) of a means of transport (20).

10. Device (10) for predicting the wear of tires (21) of a means of transport (20), comprising a memory (11) in which instructions are stored, and a processor (12), wherein the processor (12) is configured to execute the steps of a method according to any one of claims 1 to 8 for predicting the wear (Ai) of tires (21) of a means of transport (20) when the instructions are executed.

Images