Apparatus and method for calculating and / or monitoring tire wear rate on a vehicle

Abstract

A computer-implemented method for calculating a tire wear rate of a vehicle, the method comprising: acquiring technical data of at least one tire of the vehicle; acquiring technical data of the vehicle; acquiring telematics information of the vehicle; and calculating a tire wear rate based at least in part on the acquired technical data of the at least one tire of the vehicle, the acquired vehicle technical data, and the acquired vehicle telematics information according to a data-driven mathematical tire wear model.

Description

[Technical Field]

[0001] This disclosure is generally directed to computer-implemented methods and apparatus for calculating and / or monitoring tire wear rates on a vehicle. [Background technology]

[0002] Tire wear rate is an essential factor contributing to road safety. Replacing tires too late can lead to dangerous traffic situations or even accidents, potentially resulting in serious injury or death, as well as increased liability risk. Therefore, being able to replace tires in a timely manner is not only a safety issue, but also an economic one. Missing the right time to replace tires can result in significant costs due to potential accidents or damage, while replacing them too early can add to fleet costs. Proper tire lifecycle management is also a sustainability issue, as premature tire replacement can lead to the waste of valuable resources.

[0003] Determining the right time to change tires is also a critical success factor in vehicle logistics or fleet management. Scheduling tire changes on vehicles in a timely manner, or being able to schedule tire changes in conjunction with the maintenance of other vehicle components, can minimize downtime, resulting in cost savings and increased reliability, especially in commercial applications. For example, when changing tires, other vehicle components that have limited remaining life can also be replaced. Particularly when managing a fleet that includes multiple long-distance trucks, proper monitoring of tire wear rates is important, for example, to determine which of the available trucks is best suited for a particular route.

[0004] Therefore, being able to accurately predict the right time to change a tire is a key factor in making mobility and the transportation of goods safer, greener, more reliable and more economical.

[0005] Conventional methods for monitoring tire wear rates by estimating tire wear are based on purely static mathematical models or expensive dedicated sensors in the tires, or a combination of both. The use of purely static mathematical models leads to inaccuracies and therefore fails to achieve the goal of accurately predicting the appropriate time for tire replacement. To overcome the drawbacks inherent in purely static mathematical models, sensor-based methods have been developed. However, each sensor is expensive and requires additional effort when changing tires. Furthermore, proper communication between tire sensors and the vehicle's electronics involves additional factors that complicate the overall system. Furthermore, when changing tires, the tire sensors may also need to be replaced. This not only increases costs but also increases waste and, therefore, the environmental footprint.

[0006] Patent document 1 discloses a method for making available data relating to tires of a vehicle, where vehicle data and / or tire data are made available by a vehicle memory unit of the vehicle, where the vehicle data are acquired by sensors arranged on the vehicle. The vehicle data and / or tire data comprise information on at least one characteristic of the tires of the vehicle. A tire wear probability of the tires of the vehicle is obtained as a function of the vehicle data and / or tire data.

[0007] Patent Document 2 provides a tire wear estimation system based on sensor data. In the disclosed system, at least one sensor is attached to a tire to generate a first predictor variable. A lookup table or database stores data related to a second predictor variable. One of the predictor variables includes at least one vehicle effect. A model receives the predictor variables and generates an estimated wear rate for at least one tire.

[0008] U.S. Patent No. 6,277,999 discloses a vehicle-integrated predicted tread life indicator system and method of operation. In the disclosed method, data related to one or more tread depth measurements is received. The one or more tread depth measurements are taken by a measurement device external to the vehicle. The one or more tread depth measurements represent the tread depth of at least one tread of at least one tire of the vehicle. The method includes associating a respective distance value with each of the one or more tread depth measurements and accessing a model that correlates the one or more tread depth measurements to predicted tread depth. The method includes determining, based at least in part on the model, an estimated distance at which the predicted tread depth is expected to equal or exceed a tread depth threshold. The method includes providing the estimated distance to a notification system of the vehicle. [Prior art documents] [Patent documents]

[0009] [Patent Document 1] US Patent Application Publication No. 2017 / 0001482 [Patent Document 2] US Patent Application Publication No. 2018 / 0272813 [Patent Document 3] US Patent Application Publication No. 2019 / 0009618 Summary of the Invention [Problem to be solved by the invention]

[0010] With the advent of big data and machine learning, a more robust and versatile toolchain is now available than ever before. Based on these technologies, it is possible to monitor the rate of tire wear on a vehicle with greater precision, thereby enabling accurate predictions of remaining tread depth, remaining mileage, or remaining time until tire replacement. [Means for solving the problem]

[0011] The above objectives are achieved by the present disclosure of various computer-implemented methods and apparatus for calculating and / or monitoring the rate of tire wear on a vehicle.

[0012] According to a first aspect, the present disclosure provides a first computer-implemented method for calculating and / or monitoring a tire wear rate of a vehicle. The method includes acquiring technical data for at least one tire of the vehicle, acquiring the vehicle technical data, acquiring data of at least one in-operation measurement of at least one characteristic of the at least one tire of the vehicle, and calculating a tire wear rate based at least in part on the acquired technical data for the at least one tire of the vehicle, the acquired vehicle technical data, and the acquired vehicle telematics information according to a self-tuning mathematical tire wear model. The computer-implemented method enables an accurate representation of tire wear by the self-tuning mathematical tire wear model.

[0013] According to one example of the first aspect, the method may further include selecting one of a plurality of pre-stored algorithms for calculating the tire wear rate.

[0014] According to yet another example of the first aspect, the method may further include executing a plurality of pre-stored algorithms for calculating a tire wear rate, and selecting from the plurality of algorithms an algorithm that produces a tire wear rate calculation that is closest to a tire wear rate based on data from the at least one in-operation measurement obtained.

[0015] According to another example of the first aspect, the self-tuning mathematical tire wear model is tuned based on data from at least one in-operation measurement of at least one tire of the vehicle.

[0016] According to yet another example of the first aspect, the self-tuning mathematical tire wear model is tuned based on a plurality of calculated tire wear rates, the plurality of calculated tire wear rates being based on data acquired from a plurality of vehicles, the acquired data including technical data for at least one tire on each of the vehicles, technical data for each of the vehicles, and data of at least one in-operation measurement of at least one characteristic of the at least one tire on each of the vehicles.

[0017] According to another example of the first aspect, the method includes estimating a remaining tread depth and / or a remaining mileage of the tire and / or a remaining time until replacement according to a set minimum tread depth based on the calculated tire wear rate.

[0018] According to another example of the first aspect, the method includes reporting to a control system at least one of a calculated tire wear rate, an estimated remaining tread depth, a remaining mileage of the tire, and a remaining time until replacement according to a set minimum tread depth.

[0019] In one example of the first aspect, the control system is located in a vehicle.

[0020] In yet another example of the first aspect, the control system is located external to the vehicle and enables collection from a plurality of vehicles of at least calculated tire wear rates, estimated remaining tread depths, remaining mileage of the tires, and remaining time until replacement according to a set minimum tread depth.

[0021] In yet another example of the first aspect, performing an in-operation measurement of at least one characteristic of at least one tire of the vehicle includes measuring a remaining tread depth during operation, and preferably relating the measured remaining tread depth to an odometer wear rate of the vehicle.

[0022] According to another / second aspect, the present disclosure provides a second computer-implemented method for calculating and / or monitoring a tire wear rate of a vehicle, the method including the steps of transmitting technical data of at least one tire of the vehicle, transmitting the vehicle technical data, transmitting data of at least one in-operation measurement of at least one characteristic of the at least one tire of the vehicle, and obtaining a calculated tire wear rate based at least in part on the transmitted technical data of the at least one tire of the vehicle, the transmitted vehicle technical data, and the transmitted data of the at least one in-operation measurement of the at least one characteristic of the at least one tire of the vehicle, wherein the calculated tire wear rate is calculated according to a self-tuning mathematical tire wear model.

[0023] According to one example of the second aspect, the method includes estimating the remaining tread depth and / or the remaining mileage of the tire and / or the remaining time until replacement according to a set minimum tread depth based on the calculated tire wear rate.

[0024] According to another example of the second aspect, the method includes reporting to a control system at least one of a calculated tire wear rate, an estimated remaining tread depth, a remaining mileage of the tire, and a remaining time until replacement according to a set minimum tread depth.

[0025] In one example of the second aspect, the control system is located in a vehicle.

[0026] In yet another example of the second aspect, the control system is located external to the vehicle and enables collection from a plurality of vehicles of at least calculated tire wear rates, estimated remaining tread depths, remaining mileage of the tires, and remaining time until replacement according to a set minimum tread depth.

[0027] In one example of the second aspect, the technical data for at least one tire of the vehicle includes at least one of a tire manufacturer, a tire model, a tire pattern, a tire specification, a tire size, a tire mounting position, retread information, and a tire batch number.

[0028] In yet another example of the second aspect, performing an in-operation measurement of at least one characteristic of at least one tire of the vehicle includes measuring a remaining tread depth during operation, and preferably relating the measured remaining tread depth to an odometer wear rate of the vehicle.

[0029] According to another / third aspect, the present disclosure provides a third computer-implemented method for calculating and / or monitoring a tire wear rate of a vehicle. The method includes acquiring technical data for at least one tire of the vehicle, acquiring the vehicle technical data, acquiring vehicle telematics information, and calculating a tire wear rate based at least in part on the acquired technical data for the at least one tire of the vehicle, the acquired vehicle technical data, and the acquired vehicle telematics information according to a data-driven mathematical tire wear model. The computer-implemented method enables an accurate representation of tire wear by the data-driven mathematical tire wear model.

[0030] According to one example of the third aspect, the method can further include obtaining data of at least one in-service measurement of at least one characteristic of at least one tire of the vehicle, wherein calculating the tire wear rate further includes calculating the tire wear rate based at least in part on the obtained data of the at least one in-service measurement of the at least one characteristic of the at least one tire of the vehicle. The in-service measurements further enable the present invention to more accurately assess tire wear and, as described in more detail below, to more accurately predict total tire life into the future.

[0031] Advantageously, the step of calculating the tire wear rate further comprises the step of selecting one of a plurality of pre-stored algorithms for calculating tire wear after obtaining data of at least one in-operation measurement of at least one characteristic of at least one tire of the vehicle, Preferably, the pre-stored algorithm represents an algorithm that performs satisfactorily for calculating tire wear under predetermined conditions.

[0032] According to yet another example of the third aspect, the step of selecting one of a plurality of pre-stored algorithms for calculating a tire wear rate includes the steps of executing a plurality of algorithms for calculating tire wear, and selecting an algorithm from the plurality of algorithms that produces a tire wear calculation that is closest to a tire wear value obtained in at least one operational measurement.

[0033] According to yet another example of the third aspect, the step of calculating the tire wear rate further includes calculating the tire wear rate according to a self-tuning model, the self-tuning model being tuned based on data from at least one in-operation measurement of at least one tire of the vehicle.

[0034] According to yet another example of the third aspect, the data-driven mathematical tire wear model can be trained based on a plurality of calculated tire wear rates, the plurality of calculated tire wear rates being based on data acquired from a plurality of vehicles, the acquired data including technical data for at least one tire of each of the vehicles, technical data for each of the vehicles, and telematics information for each of the vehicles. Thus, according to this aspect, the data-driven mathematical tire wear model is continuously adapted according to data provided by the plurality of vehicles.

[0035] According to yet another / fourth aspect, the present invention provides a fourth computer-implemented method for calculating and / or monitoring a tire wear rate of a vehicle, the method comprising the steps of transmitting technical data of at least one tire of the vehicle, transmitting the vehicle technical data, transmitting vehicle telematics information, and obtaining a calculated tire wear rate based at least in part on the transmitted technical data of the at least one tire of the vehicle, the transmitted vehicle technical data, and the transmitted vehicle telematics information, wherein the calculated tire wear rate is calculated according to a data-driven mathematical tire wear model.

[0036] In one example of the fourth aspect, the computer-implemented method for calculating and / or monitoring a tire wear rate of a vehicle further includes transmitting data of at least one in-operation measurement of at least one characteristic of at least one tire of the vehicle, wherein the calculated tire wear rate is further calculated based at least in part on the at least one in-operation measurement of the at least one characteristic of the at least one tire of the vehicle.

[0037] According to yet another example of the fourth aspect, a computer-implemented method for calculating and / or monitoring tire wear rates for a vehicle may include estimating, based on the calculated tire wear rates, a remaining tread depth and / or a remaining mileage of the tire and / or a remaining time until replacement according to a set minimum tread depth.

[0038] According to yet another example of the fourth aspect, a computer-implemented method for calculating and / or monitoring a tire wear rate of a vehicle may include reporting to a control system at least one of the calculated tire wear rate, an estimated remaining tread depth, a remaining mileage of the tire, and a remaining time until replacement according to a set minimum tread depth.

[0039] In one example of the fourth aspect, the control system may be located in a vehicle.

[0040] In yet another example of the fourth aspect, the control system is located external to the vehicle and enables collection from a plurality of vehicles of at least calculated tire wear rates, estimated remaining tread depths, remaining mileage of the tires, and remaining time until replacement according to a set minimum tread depth.

[0041] According to yet another example of the fourth aspect, the technical data for at least one tire of the vehicle includes at least one of a tire manufacturer, a tire model, a tire pattern, a tire specification, a tire size, a tire mounting position, retread information, and a tire batch number.

[0042] According to yet another example of the fourth aspect, the computer-implemented method for calculating and / or monitoring tire wear rate of a vehicle as described above, comprising performing in-operation measurements of at least one characteristic of at least one tire of the vehicle, further comprises measuring remaining tread depth during operation, and preferably relating the measured remaining tread depth to the odometer wear rate of the vehicle.

[0043] According to yet another example of the fourth aspect, the vehicle information from the vehicle includes at least one of vehicle manufacturer, vehicle chassis, vehicle usage, tractor load, region, country, longitudinal acceleration, lateral acceleration, speed, GPS coordinates, odometer, road type, load, tire pressure, gear shift, engine RPM, wheel speed, throttle / brake pedal position, tire temperature, outside air temperature, and steering wheel angle.

[0044] In a further fifth aspect, there is provided a first apparatus comprising: means for acquiring technical data of at least one tire of a vehicle; means for acquiring the technical data of the vehicle; means for acquiring data of at least one measurement of at least one characteristic of at least one tire of the vehicle; and means for calculating a tire wear rate based at least in part on the acquired technical data of the at least one tire of the vehicle, the acquired technical data of the vehicle, and the acquired data of the at least one measurement of the at least one characteristic of the at least one tire of the vehicle according to a self-tuning mathematical tire wear model.

[0045] In a further sixth aspect, there is provided a second apparatus comprising: means for transmitting technical data of at least one tire of a vehicle; means for transmitting the vehicle technical data; means for transmitting data of at least one measurement of at least one characteristic of the at least one tire of the vehicle; and means for obtaining a calculated tire wear rate based at least in part on the transmitted technical data of the at least one tire of the vehicle, the transmitted vehicle technical data, and the transmitted data of the at least one measurement of the at least one characteristic of the at least one tire of the vehicle, wherein the calculated tire wear rate is calculated according to a self-tuning mathematical tire wear model.

[0046] In a further seventh aspect, a third apparatus is provided, comprising: means for acquiring technical data of at least one tire of a vehicle; means for acquiring technical data of the vehicle; means for acquiring telematics information of the vehicle; and means for calculating a tire wear rate based at least in part on the acquired technical data of the at least one tire of the vehicle, the acquired technical data of the vehicle, and the acquired vehicle telematics information of the vehicle according to a data-driven mathematical tire wear model.

[0047] In a further eighth aspect, there is provided a fourth apparatus comprising: means for transmitting technical data of at least one tire of a vehicle; means for transmitting the vehicle technical data; means for transmitting vehicle telematics information; and means for obtaining a calculated tire wear rate based at least in part on the transmitted technical data of the at least one tire of the vehicle, the transmitted vehicle technical data, and the transmitted vehicle telematics information of the vehicle, wherein the calculated tire wear rate is calculated according to a data-driven mathematical tire wear model.

[0048] Still other benefits and advantages of the present invention will become apparent upon perusal of the detailed description, with appropriate reference to the accompanying drawings. [Brief explanation of the drawings]

[0049] [Figure 1]FIG. 1 illustrates an exemplary calculated tire wear chart for tires of a vehicle according to a self-tuning tire wear model based on a combination of tire information for at least one tire of the vehicle, vehicle technical information, and at least one in-operation measurement of tire wear, in accordance with the present disclosure. [Figure 2] Figure 2a illustrates in the form of three charts an exemplary pre-stored algorithm used during the process for accurately calculating tire wear according to the present disclosure, and Figure 2b illustrates in the form of another exemplary tire wear chart for a vehicle the functional aspects of a self-tuning mathematical model for increasing the accuracy of calculated tire wear rates according to the present disclosure. [Figure 3] 3a shows yet another chart of exemplary tire wear for a tire of a vehicle for a data-driven tire wear model based on a combination of tire information for at least one tire of the vehicle, vehicle technical information, and vehicle telematics information in accordance with the present disclosure. FIG. 3b shows yet another chart of exemplary tire wear for a tire of a vehicle for a data-driven tire wear model based on a combination of tire information for at least one tire of the vehicle, vehicle technical information, vehicle telematics information, and data of at least one in-operation measurement of remaining tread depth in accordance with the present disclosure. [Figure 4] Figure 4a illustrates various exemplary scenarios, including loading conditions and road types, that are the basis for the development of a data-driven mathematical tire wear model in accordance with the present disclosure. Figure 4b illustrates exemplary values ​​determined for maximum distance traveled per mm of truck tread wear (km / mm) for various road types and loading conditions in accordance with the present disclosure. Figure 4c illustrates the relative difference between exemplary values ​​determined for maximum distance traveled per mm of truck tread wear (km / mm) for various road types and loading conditions in accordance with the present disclosure. [Figure 5]Figure 5A shows an example data flow between a vehicle and a cloud for calculating tire wear and possible reporting of the calculated tire wear, including estimated remaining tread depth, remaining mileage of the tire, and / or remaining time until replacement according to a set minimum tread depth, in accordance with the present disclosure. Figure 5B shows an example data flow between a vehicle, a cloud, and a user computing device for calculating tire wear and possible reporting of the calculated tire wear, including estimated remaining tread depth, remaining mileage of the tire, and / or remaining time until replacement according to a set minimum tread depth, in accordance with the present disclosure. Figure 5C shows an example data flow between a vehicle, a cloud, and a control system for calculating tire wear and possible reporting of the calculated tire wear, including estimated remaining tread depth, remaining mileage of the tire, and / or remaining time until replacement according to a set minimum tread depth, in accordance with the present disclosure. [Figure 6] 1 illustrates an exemplary fleet manager platform that may receive reports of calculated tire wear rates according to the present disclosure. [Figure 7] 7 shows a flowchart illustrating a computer-implemented method 700 for calculating and / or monitoring tire wear rates for a vehicle according to the present disclosure. [Figure 8] 8 shows a flowchart illustrating a computer-implemented method 800 for calculating and / or monitoring tire wear rates for a vehicle according to the present disclosure. [Figure 9] 9 shows a flowchart illustrating a computer-implemented method 900 for calculating and / or monitoring tire wear rates for a vehicle according to the present disclosure. [Figure 10] 1 shows a flowchart illustrating a computer-implemented method 1000 for calculating and / or monitoring tire wear rates for a vehicle according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0050] The present disclosure provides a computer-implemented method and apparatus for calculating and / or monitoring the rate of tire wear on a vehicle. The computer-implemented method and apparatus according to the present disclosure provide many advantages. The present invention allows for the determination of the optimal time to change a vehicle's tires, thus making personal mobility and the transportation of goods safer, greener, more reliable, and more economical.

[0051] Self-tuning mathematical tire wear models versus purely statistical models FIG. 1 shows a chart illustrating an exemplary tire wear profile for a vehicle tire. Along the horizontal axis, the tire's mileage is shown. Along the vertical axis, tire characteristics such as remaining tread depth and RTD are shown. In the upper left corner, the tire is in a new condition, i.e., in this example, the tire has a remaining tread depth of 13 mm and 0 km of mileage. A remaining tread depth of 3 mm indicates the tire's end of life in this example. The dashed and dotted lines represent estimated tire wear calculated using a purely statistical model based on tire parameters such as tire size and tire position. In this example, the average tire mileage calculated using a purely statistical model is approximately 180,000 kilometers (shown by the dashed and dotted line), with a deviation of approximately 80,000 kilometers in both directions, suggesting that the statistical mileage ranges from 100,000 kilometers to 260,000 kilometers (shown by the thin dashed line). Therefore, it can be seen that the exact point in time when the minimum tread depth is reached cannot be accurately assessed.

[0052] Figure 1 further illustrates that conventional purely statistical methods can be improved by taking a measurement of remaining tread depth at a point in time and considering that measurement when calculating the tire wear rate. In the illustrated example, an in-service measurement is performed at approximately 110,000 kilometers (shown by the solid triangle). The in-service measurement indicates that the tire wear is below average; in other words, the current tire wear rate (in this case, remaining tread depth) is above average.

[0053] To assess the tire's end-of-life, i.e., when it reaches a remaining tread depth of 3 mm, a self-tuning mathematical tire wear model is applied according to the present disclosure. The self-tuning mathematical tire wear model is provided with tire characteristics measured at a specific mileage (here, the RTD measured at 110,000 kilometers), as well as input data related to the vehicle's tire and vehicle's technical data. Using these data, the self-tuning mathematical model calculates the expected future tire wear, for example, until the tire reaches the end-of-life (e.g., until it reaches a certain minimum RDT, e.g., 3 mm). Therefore, it is possible to calculate how the tire's remaining tread depth varies with mileage. The calculated tire's remaining tread depth is shown by a solid black line, and its deviation is shown by a dash-dot line. As can be seen, the average mileage of the example tire is approximately 200,000 kilometers, with only a deviation of approximately 40,000 kilometers in either direction, improving the statistical mileage to a range of 160,000 kilometers to 240,000 kilometers. Therefore, the deviation range is reduced by 50%, allowing a more accurate assessment of the exact point in time when minimum tread depth is reached.

[0054] The input data regarding technical data of the vehicle's tires may include one or more of: tire manufacturer, tire pattern, tire specification, tire size, tire mounting location, retread information, country, or region.

[0055] The input data regarding the vehicle's technical data may include one or more of the vehicle manufacturer, the vehicle chassis, the vehicle usage, and / or the tractor load.

[0056] Additionally, the self-tuning mathematical model uses as input data from at least one in-service measurement of at least one characteristic of the tire, such as the actual remaining tread depth of the tire and the mileage reading from an odometer.

[0057] By executing a computer-implemented method for calculating and / or monitoring the tire wear rate of a vehicle, technical data of at least one tire of the vehicle and data of at least one in-operation measurement of at least one characteristic of at least one tire of the vehicle are obtained, and the tire wear rate is calculated according to a self-tuning mathematical model based on the obtained technical data of the at least one tire of the vehicle and the obtained data of at least one in-operation measurement of at least one characteristic of the at least one tire of the vehicle.

[0058] The above steps can be repeated with further in-service measurements after the tire has traveled further miles (as described in more detail below). Typically, each iteration of in-service measurements and new calculations of tire wear rate will provide greater precision as to when a tire will reach end of life, and therefore greater predictability for, for example, truck route planning.

[0059] 2a illustrates an example embodiment of a self-tuning mathematical model that a computer-implemented method for calculating and / or monitoring tire wear rate of a vehicle may follow to calculate tire wear and / or tire wear rate. In one embodiment, the calculation of tire wear rate may be performed after obtaining data from an in-service measurement of at least one tire characteristic, such as remaining tread depth combined with respective mileage readings from the vehicle's odometer.

[0060] In one embodiment, calculating the tire wear rate may involve the execution of multiple pre-stored algorithms. Figure 2a shows three different charts for three different pre-stored algorithms. For each of the three graphs, the vertical axis shows the remaining tread depth (RTD) and the horizontal axis shows the distance traveled (KM) of at least one tire as read from the vehicle's odometer. The upper left corner of each graph represents the state of the remaining tread depth according to the technical data of the tire at the time of sale when the tire is new, i.e., when the tire has zero mileage. As the mileage increases, the remaining tread depth decreases.

[0061] Each filled circle on the graph represents a remaining tread depth measurement associated with the vehicle's odometer status. For example, in the first graph, two previous in-service measurements have been taken, in the second graph, six previous in-service measurements have been taken, and in the third graph, six previous in-service measurements have also been taken. Each open circle on the graph represents a calculated RTD for a particular mileage for which further in-service measurements have been scheduled based on previous measurements (filled circles) and the applied algorithm. Each cross (X) on the graph represents the most recent in-service measurement of RTD at a particular mileage. For ease of illustration, each graph shows a cross (X) over an open circle.

[0062] The three graphs show three algorithms that can be run in parallel to find the best algorithm for prediction. In this example, the first graph shows a significant offset between the calculated RTD (open circles) and the RTD measurements (crosses). Therefore, applying the "three-point" algorithm, which uses the last two measurements to calculate future RTD, would be inaccurate in this case. The second graph, showing a linear regression model, shows a small offset between the calculated RTD (open circles) and the RTD measurements (crosses). Therefore, in this case, this algorithm may be preferable to the first algorithm for calculating future RTD, and the current measurement is used as an additional measurement point for calculating future RTD. Finally, the third graph, showing an exponential regression model, shows an even smaller offset between the calculated RTD (open circles) and the RTD measurements (crosses). Therefore, in this case, this may be the most preferable algorithm for calculating future RTD. Again, the current measurement (open circle) is used as an additional measurement point for calculating future RTD.

[0063] More generally, the example shown in Figure 2a illustrates that various pre-stored algorithms, such as three-point, linear regression, exponential regression, logarithmic regression, or neural network algorithms, may be executed after obtaining data from at least one measurement of remaining tread depth associated with the vehicle's odometer status. The pre-stored and executed algorithm that produces a calculated tire wear rate (e.g., RTD) for a particular mileage that most closely matches the measured tire wear rate (e.g., RTD) at that particular mileage is selected for calculating the tire wear rate over the tire's life.

[0064] Algorithms can utilize all available in-service measurements of tire characteristics and, in combination with other input information provided to the model, such as tire manufacturer, tire pattern, tire specification, tire size, tire mounting position, retread information, vehicle manufacturer, vehicle chassis, vehicle usage, tractor load, country, or region, to estimate which pre-stored algorithm best describes each characteristic of the tire in service. In one aspect, curve-fitting techniques can be applied. Each tire characteristic is then extrapolated using the algorithm that produces the best fit to each value of one or more in-service measurements. Based on this extrapolation, the remaining life of the tire can be determined. The tire's end-of-life value can be defined as 3 mm tread depth or any other value defined by the user.

[0065] In one aspect, the pre-stored algorithms of the self-tuning mathematical models may be continually modified, improved, or replaced / updated by respective providers.

[0066] 2b shows a graph illustrating yet another aspect of the self-tuning mathematical model. The horizontal axis shows the distance traveled by the vehicle's tires in km and three tests performed at a particular odometer state. The vertical axis shows the remaining tread depth in the form of a discrete value for a new tire ("New Tire"). Additionally, three remaining tread depth states ("RTD1", "RTD2", "RTD3") for the three tests performed, as well as another discrete value of the remaining tread depth at the end of the tire's life (TWI, Tread Wear Indicator).

[0067] When a tire is new, the self-tuning model can be fed tire and vehicle data at 1, and a trend in tire wear and remaining tread depth can be calculated (shown by dashed line A). A first inspection is scheduled at a specific mileage. At this mileage, the self-tuning model calculated a specific RTD (shown by 2). An actual in-service measurement of remaining tread depth performed at this specific mileage yields a lower value than that calculated. This value is shown as "RTD1" at 3. As a result, the self-tuning model adjusts its prediction, as indicated by the downward arrow, and the calculated tire wear is greater than originally predicted.

[0068] Thus, if the calculated value of a tire characteristic, e.g., "RTD1," deviates from the actual measured value of each tire characteristic, the mathematical model self-corrects, i.e., the mathematical model is tuned. Tuning the mathematical model involves making the calculated value of the tire characteristic equal to the actual measured value of that characteristic for the mileage at which the measurement is taken. Tuning the model may further include fitting the model to the most recent actual measured value of each tire characteristic and at least one previous measured value of each tire characteristic, if available.

[0069] The above procedure can be repeated for each additional in-service measurement of each tire property, thus for the second and third test and measurements, "RTD2" and "RTD3," respectively. These values ​​are also designated by odd numbers, 5 and 7 (and 9, indicating TWI). Furthermore, calculated values ​​are designated by even numbers, here 4, 6, and 8. This allows for continuous self-tuning of the model. The more measurements performed, the more accurate the model and the smaller the calculation error.

[0070] In one aspect, the self-tuning mathematical model for calculating tire wear rate can be continuously modified / improved through the application of big data methods and / or machine learning techniques. For example, the self-tuning mathematical tire wear model can be trained based on a plurality of calculated tire wear rates, the plurality of calculated tire wear rates based on data acquired from a plurality of vehicles, the acquired data including technical data of at least one tire on each of the vehicles, the technical data of each of the vehicles, and data of at least one in-operation measurement of at least one characteristic of the at least one tire on each of the vehicles.

[0071] Over time, a wealth of data can be acquired representing countless driving scenarios involving many different vehicles under a variety of different traffic conditions. Each piece of data can be used to continuously train a self-tuning mathematical method for calculating tire wear rates, thereby generating added value. Based on all the available data, machine learning techniques can determine the wear pattern for a particular scenario.

[0072] In another aspect, the self-tuning mathematical model can be manually modified, for example, if a particular tire product is found to behave differently than previously expected under certain scenarios. The large number of inputs to the model can even limit modifications to a particular batch of tire models from a particular manufacturing facility. For example, a particular batch of tire models manufactured at a particular facility may be found to perform differently than other batches from other facilities. In such cases, the behavior of a single batch of tires can be taken into account by the model.

[0073] Another important factor that influences tire wear is the country in which the vehicle equipped with the monitored tires is driven. Some countries may have flat, wide roads, while others may have narrow, curvy roads associated with mountain ranges. Another national factor that influences tire wear is climate, which may make a difference, for example, whether a particular country has long summers and warm winters or cold winters and short summers.

[0074] Additionally, other factors such as humidity or dryness can affect tire wear.

[0075] Tire wear can also vary depending on the quality of infrastructure a country has to offer. Some countries may invest heavily in road infrastructure, while others may invest less. In the latter, lack of maintenance can lead to road surface damage, which can further contribute to a shorter tire lifespan. Another factor that can affect tire lifespan can be the quality of driver education in each country. Yet another factor to consider can be the different driving rules in different countries. Some countries, such as the Netherlands, have very strict speed limits even on highways, while other countries, such as Germany, have no speed limits on highways. This can result in very different stresses on tires depending on the country.

[0076] Furthermore, it must be taken into account that boundary conditions in different countries may not be very uniform. Therefore, regions may also be used to calculate tire wear as accurately as possible. In many countries, the quality of infrastructure in large economic centers may differ from rural areas. Additionally or alternatively, some areas of a country may be flat, while others may be mountainous. In either case, tire wear patterns may vary greatly. Therefore, regional data may be considered more precise than national data.

[0077] Data-driven mathematical modeling of tire wear with and without in-motion measurements Figures 3a and 3b show other charts of an exemplary calculated tire wear profile for a vehicle tire. Corresponding to Figure 1, along the horizontal axis the tire's mileage is shown. Along the vertical axis the remaining tread depth is shown. In the upper left corner the tire is in a new condition, i.e. (in this example) 0 km mileage and 13 mm remaining tread depth. When the remaining tread depth reaches a value of (in this example) 3 mm, the tire reaches the end of its life.

[0078] The dashed lines represent the range of tire mileage calculated according to a purely statistical model. The two sets of dash-dot and dash-dot lines represent the predicted range of tire mileage according to a data-driven mathematical model taking into account vehicle telematics information. In particular, vehicle telematics information may include data on the vehicle load (e.g., empty or loaded) and vehicle usage (regional or long-distance scenario).

[0079] Vehicle telematics information allows for even more accurate calculation of tire wear rates. For example, tire wear may differ depending on whether the vehicle is used for short distances with heavy traffic or primarily for long-distance travel, where trucks, in particular, often have a constant speed for long periods of time. Furthermore, the measured tire pressure can be taken into account as an additional factor contributing to tire wear. If the pressure is, for example, too low (i.e., deviating from the recommended tire pressure), the tire's contact area with the road increases. As a result, tire wear accelerates. Information about the measured tire pressure is even more important in relation to the vehicle's tractor load. As is known, the recommended tire pressure varies depending on the vehicle's load. Thus, if the vehicle is heavily loaded but the measured tire pressure is within the recommended tire pressure range for an unladen vehicle, tire wear will still increase.

[0080] Generally, that is, without considering tire pressure, load affects tire wear, so that heavily loaded vehicles will experience more tire wear than unloaded vehicles.

[0081] The predicted remaining mileage of a tire varies greatly depending on the vehicle load and use case. When a vehicle is loaded and used in a local scenario, the remaining mileage is much shorter than when the vehicle is empty and used in a long-distance scenario. Taking into account the vehicle's telematics information can clearly improve the remaining mileage prediction accuracy.

[0082] For example, if a vehicle is used in a long distance scenario in an unladen state (see dash-dotted and double-dashed lines with wide dots), the average tire mileage is approximately 235,000 kilometers (see dash-dotted line with wide dots), with a deviation of approximately 20,000 kilometers in both directions, resulting in a statistical mileage range of 215,000 kilometers to 255,000 kilometers (see double-dashed line with wide dots).

[0083] Similarly, when the vehicle is loaded and used in a regional scenario (see dash-dotted and dash-double-dot lines with small dots), the average mileage of the tires is 120,000 kilometers (see dash-dotted line with small dots), with a deviation of about 20,000 kilometers in both directions, resulting in a statistical mileage range of 100,000 kilometers to 140,000 kilometers (see dash-dotted line with small dots).

[0084] As a result, the exact point in time at which the minimum tread depth is reached or the distance traveled can be more accurately assessed, as the deviation range is 75% smaller compared to the state of the art (e.g., purely statistical models) and 50% smaller compared to using a self-tuning mathematical model that does not take into account vehicle telematics information, as shown in Figure 1.

[0085] Vehicle telematics information may include at least one of vehicle usage, tire pressure, tractor load, longitudinal acceleration, lateral acceleration, speed, GPS coordinates, odometer, road type, load, tire pressure, gear shift, engine RPM, wheel speed, throttle / brake pedal position, tire temperature, outside air temperature, and steering wheel angle.

[0086] As shown in FIG. 3b, in some embodiments, the advantages of the data-driven mathematical model can be combined with in-operational measurements corresponding to those described for the self-tuning mathematical model. For example, the second computer-implemented method can include acquiring data from at least one in-operational measurement. In this case, the calculated tire wear based on the data-driven model can be improved by the mechanisms of the self-tuning model described in connection with FIGS. 2a and 2b. When an in-operational measurement of at least one characteristic of the tire, such as remaining tread depth, is performed, the measured value of remaining tread depth is compared with the calculated value of tread depth, i.e., this measurement is used to correct the data-driven mathematical model. Considering that the process of performing in-operational measurements and fitting the model corresponds to the measurement and fitting for the self-tuning model, for simplicity, these features will not be described more extensively than above. However, it should be understood that these features described above are also applicable here.

[0087] As can be seen in Figure 3b, when the vehicle is used in a long distance scenario in an unladen state (see dash-dotted and double-dashed lines with wide dots), the average tire mileage is approximately 240,000 kilometers (see dash-dotted line with wide dots), with a deviation of approximately 10,000 kilometers in both directions, resulting in a statistical mileage range of 230,000 kilometers to 250,000 kilometers (see dash-dotted line with wide dots).

[0088] When the vehicle is loaded and used in a regional scenario (see dash-dotted and dash-double-dot lines with small dots), the average mileage of the tires is 160,000 kilometers (see dash-dotted line with small dots), with a deviation of about 10,000 kilometers in both directions, resulting in a statistical mileage range of 150,000 kilometers to 170,000 kilometers (see dash-dotted line with small dots).

[0089] As a result, the deviation range is approximately 90% smaller compared to the state of the art, allowing for a more accurate assessment of the exact point in time or distance traveled until minimum tread depth is reached. Furthermore, the deviation range is 75% smaller compared to a method using a self-tuning mathematical model that does not take into account vehicle telematics information, as shown in Figure 1. Finally, by combining the advantages of the second computer-implemented method including a data-driven mathematical model with the advantages of obtaining data from at least one in-operation measurement, the deviation range can be further reduced by 50% compared to when a data-driven mathematical model is used without additional measurement data.

[0090] Development of a data-driven mathematical tire wear model Figure 4a shows different conditions that are the basis for the development of a data-driven mathematical tire wear model. Vehicle telematics information such as speed, acceleration, gear shift, engine RPM, wheel speed, brake / throttle pedal position, tire pressure, tire temperature, outside temperature, or steering angle can be taken into consideration to play an important role in predicting tire wear more accurately.

[0091] A series of experiments correlated each vehicle's telematics with tire wear. This series of experiments was performed on multiple tires, focusing on the main drivers of tire wear, including load, acceleration, and temperature. Load conditions were defined as minimum and maximum loads so that fully loaded travel could be studied for acceleration. Similarly, curved and highway routes were defined to maximize the difference in lateral and longitudinal acceleration.

[0092] In a series of experiments, multiple trucks were driven side by side on two different types of roads, including a curved road and a highway, in summer and winter, with different loading conditions for the trucks. At regular intervals, tread wear measurements based on 3D scanning were performed to define the 360° profile of the tire. Based on the measurements, a relationship between tire wear per kilometer and vehicle telematics information was extracted.

[0093] The maximum distance traveled before reaching the end of tire life was determined for each vehicle load scenario, i.e., empty and loaded, on different road types, i.e., highway and curved road, as shown in Figure 4b. Based on the maximum distance traveled before reaching the end of tire life on different road types, the distance traveled per mm of tire tread wear was determined. This value is also expressed in kilometers per mm (KPM). The table shown in Figure 4b shows the KPM for different axles of the truck for each road condition.

[0094] Figure 4c shows the percentage results from Figure 4b. For example, as can be seen here, for a curved road, the KPM of the steer axle of an empty truck is expected to be 80% of the KPM of an empty truck driving on a highway. For a drive axle on a curved road, the KPM value of the loaded truck is only 37% of the KPM of an empty truck on a highway.

[0095] The resulting general formula for remaining tread depth can be expressed as follows: Remaining tread depth = F (mileage, tire technical data, vehicle technical data, A x ,A y ,Load,IP} where A x is the longitudinal acceleration, A y is the lateral acceleration and IP is the tire pressure.

[0096] The data-driven mathematical tire wear model provided by the present invention also estimates, among other features, the wear energy due to longitudinal acceleration. The wear energy is calculated by the longitudinal force (F x ) and slip (S x ), and slip can be calculated based on the wheel speed (V x ) and vehicle speed (V v ) δWE=FxdSx=Fx(Vx-Vv)dt Each slip ratio (SR) can be expressed as follows:

[0097]

number

[0098] Then, the wear energy equation is: δWE=FxVv SR dt This becomes:

[0099] When the slip ratio (SR) is small, the longitudinal force (F x ) and braking slip ratio (B p It is possible to find a linear correlation with SR. F x =ZBpSR

[0100] Using this relationship, the wear energy can be expressed as follows:

[0101]

number

[0102] where m is the mass of each tire on the vehicle. The above formula represents the wear energy over a specific time interval. By integrating the above formula over a fixed period, the total wear energy due to longitudinal forces can be calculated as follows:

[0103]

number

[0104] B p can vary according to the wear stage, the tires can be divided into different wear stages and the wear energy can be recalculated accordingly.

[0105] A similar calculation can be performed for the wear energy due to lateral force (index y), taking into account that at small slip angles there is a linear correlation between lateral force and slip angle α.

[0106]

number

[0107] From the data-driven experiments, residuals of longitudinal and lateral accelerations are determined for different road and load scenarios. In a further step, weighting factors (a1, b1, etc.) that can be used to scale the general formula for tire wear energy to obtain a data-driven wear rate based on load and acceleration are derived from the residuals as follows:

[0108]

number

[0109] In the above formula, m tire is the mass acting on each tire, V v is the vehicle speed, a y is the lateral acceleration, a xneg is the deceleration (negative acceleration), a xposvisc is the acceleration (positive acceleration) used to increase speed, taking into account the component due to air resistance.

[0110] Calculating and reporting tire wear rates 5A, 5B, and 5C show different ways in which the calculated tire wear rate can be reported. The black arrows indicate the transmission of data such as tire technical data, vehicle technical data, and vehicle telematics information. If the calculation is performed on the vehicle or in a component external to the vehicle not shown in FIG. 5, the black arrows may alternatively or additionally indicate the transmission of the calculated tire wear rate, in other words, the transmission of the output of the applied mathematical model. In any case, the dotted arrows indicate the reporting of the calculated tire wear rate or model output.

[0111] 5A, in one embodiment, the tire wear rate may be calculated external to the vehicle, for example, on a cloud computing device. In this example, technical data for at least one tire of the vehicle, technical data for the vehicle, and telematics information for the vehicle may be transmitted to the cloud computing device. The tire wear calculation may be performed within the cloud computing device, and the calculated tire wear may be reported to at least the vehicle.

[0112] Additionally or alternatively, the reports may be sent to a user computing device, such as a smartphone, notebook, PC, or tablet, or to a fleet management platform, as shown in FIGS. 5B and 5C.

[0113] 5B and 5C, the tire wear rate is calculated at the vehicle, in which case the calculated tire wear can be reported from the vehicle to a user computing device or fleet management platform.

[0114] FIG. 6 shows a screenshot of an example fleet management application based on a computer-implemented method for calculating and / or monitoring the wear rate of a vehicle's tires according to the present disclosure. The fleet management platform / software may be stored and executed on a cloud computing device / server. Each fleet management software may have a digital representation of each vehicle in a fleet of at least one vehicle. The digital representation of the vehicle may include technical data for the vehicle, such as brand, vehicle model, number of axles, tires used, etc. Once the tire wear rate of a vehicle is calculated using one of the methods according to the present disclosure, the calculated tire wear rate can be reported to the fleet management application. Within the fleet management application, the calculated tire wear rate can be associated with the digital representation of the vehicle. This association can be performed on a tire-by-tire basis.

[0115] As a result, the application may be able to display the tire wear rate for each tire of the vehicle. In some aspects, the remaining time or mileage for each tire of the vehicle may be displayed. Based on the displayed information, a user of the fleet management platform may be provided with detailed information regarding at least one of the calculated tire wear rate, remaining tread depth, remaining mileage, and remaining life for each tire of the vehicle. If certain conditions are met, a warning message may be issued to, for example, the driver, fleet manager, or any other user.

[0116] Computer-Implemented Method for Calculating and / or Monitoring Tire Wear Rate 7 shows a flow chart illustrating a computer-implemented method 900 for calculating and / or monitoring tire wear rates for a vehicle. The operations of the computer-implemented method 700 may be implemented by a computing device.

[0117] At 710, technical data for at least one tire of the vehicle is obtained.

[0118] At 720, vehicle technical data is obtained.

[0119] At 730, data is obtained for at least one measurement of at least one characteristic of at least one tire of the vehicle.

[0120] At 740, a tire wear rate based at least in part on the obtained technical data of the at least one tire of the vehicle and the obtained data of the at least one measurement of the at least one characteristic of the at least one tire of the vehicle is calculated according to a self-tuning mathematical tire wear model.

[0121] In another aspect, calculating the tire wear rate may include selecting one of a plurality of pre-stored algorithms for calculating the tire wear rate after performing at least one in-operation measurement of at least one characteristic of at least one tire of the vehicle.

[0122] In yet another aspect, selecting one of a plurality of pre-stored algorithms for calculating a tire wear rate after performing at least one in-operation measurement of at least one characteristic of at least one tire of the vehicle according to the self-tuning mathematical tire wear model may include executing a plurality of algorithms for calculating tire wear, and selecting one algorithm from the plurality of pre-stored algorithms that produces a tire wear calculation that is closest to the tire wear obtained in the at least one in-operation measurement.

[0123] In yet another aspect, the self-tuning model is tuned based on data from at least one in-service measurement of at least one tire of the vehicle.

[0124] In yet another aspect, the self-tuning mathematical tire wear model is trained based on a plurality of calculated tire wear rates, the plurality of calculated tire wear rates being based on data acquired from a plurality of vehicles, the acquired data including technical data for at least one tire of each of the vehicles, technical data for each of the vehicles, and telematics information for each of the vehicles.

[0125] In yet another aspect, the remaining tread depth and / or remaining mileage of the tire and / or remaining time to replacement according to a set minimum tread depth is estimated based on the calculated tire wear rate.

[0126] In yet another aspect, at least one of the calculated tire wear rate, the estimated remaining tread depth, the remaining mileage of the tire, and the remaining time until replacement according to a set minimum tread depth is reported to the control system.

[0127] In yet another aspect, the control system is located in a vehicle.

[0128] In another aspect, the control system is located external to the vehicle and enables collection from a plurality of vehicles of at least calculated tire wear rates, estimated remaining tread depths, remaining mileage of the tires, and remaining time until replacement according to a set minimum tread depth.

[0129] 8 shows a flowchart illustrating a computer-implemented method 800 for calculating and / or monitoring tire wear rates for a vehicle. The operations of the computer-implemented method 800 may be implemented by a computing device.

[0130] At 810, technical data for at least one tire of the vehicle is transmitted.

[0131] At 820, vehicle technical data is transmitted.

[0132] At 830, data of at least one measurement of at least one characteristic of at least one tire of the vehicle is transmitted.

[0133] At 840, a calculated tire wear rate is obtained that is calculated according to a self-tuning mathematical tire wear model and is based in part on the transmitted technical data of at least one tire of the vehicle and the obtained vehicle telematics information.

[0134] In yet another aspect, the remaining tread depth and / or remaining mileage of the tire and / or remaining time to replacement according to a set minimum tread depth is estimated based on the calculated tire wear rate.

[0135] In yet another aspect, at least one of the calculated tire wear rate, the estimated remaining tread depth, the remaining mileage of the tire, and the remaining time until replacement according to a set minimum tread depth is reported to the control system.

[0136] In yet another aspect, the control system is located in a vehicle.

[0137] In another aspect, the control system is located external to the vehicle and enables collection from a plurality of vehicles of at least calculated tire wear rates, estimated remaining tread depths, remaining mileage of the tires, and remaining time until replacement according to a set minimum tread depth.

[0138] 9 shows a flowchart illustrating a computer-implemented method 900 for calculating and / or monitoring tire wear rates for a vehicle. The operations of the computer-implemented method 900 may be implemented by a computing device.

[0139] At 910, technical data for at least one tire of the vehicle is obtained.

[0140] At 920, vehicle technical data is obtained.

[0141] At 930, vehicle telematics information is obtained.

[0142] At 940, a tire wear rate based at least in part on the obtained technical data of at least one tire of the vehicle and the obtained vehicle telematics information is calculated according to a data-driven mathematical tire wear model.

[0143] In yet another aspect, data from at least one in-service measurement of at least one characteristic of at least one tire of the vehicle can be obtained, and calculating the tire wear rate further includes calculating the tire wear rate based at least in part on the obtained data of the at least one in-service measurement of the at least one characteristic of the at least one tire of the vehicle.

[0144] In another aspect, calculating a tire wear rate based at least in part on data obtained from at least one in-operation measurement of at least one characteristic of at least one tire of the vehicle may include selecting one of a plurality of pre-stored algorithms for calculating the tire wear rate after performing at least one in-operation measurement of at least one characteristic of at least one tire of the vehicle.

[0145] In yet another aspect, selecting one of a plurality of pre-stored algorithms for calculating a tire wear rate after performing at least one in-operation measurement of at least one characteristic of at least one tire of the vehicle according to the self-tuning mathematical tire wear model may include executing a plurality of algorithms for calculating tire wear, and selecting one algorithm from the plurality of pre-stored algorithms that produces a tire wear calculation that is closest to the tire wear obtained in the at least one in-operation measurement.

[0146] In yet another aspect, calculating the tire wear rate further includes calculating the tire wear rate according to a self-tuning model, the self-tuning model being tuned based on data from at least one in-operation measurement of at least one tire of the vehicle.

[0147] In yet another aspect, the data-driven mathematical tire wear model is trained based on a plurality of calculated tire wear rates, the plurality of calculated tire wear rates being based on data acquired from a plurality of vehicles, the acquired data including technical data for at least one tire of each of the vehicles, technical data for each of the vehicles, and telematics information for each of the vehicles.

[0148] In yet another aspect, the remaining tread depth and / or remaining mileage of the tire and / or remaining time to replacement according to a set minimum tread depth is estimated based on the calculated tire wear rate.

[0149] In yet another aspect, at least one of the calculated tire wear rate, the estimated remaining tread depth, the remaining mileage of the tire, and the remaining time until replacement according to a set minimum tread depth is reported to the control system.

[0150] In yet another aspect, the control system is located in a vehicle.

[0151] In another aspect, the control system is located external to the vehicle and enables collection from a plurality of vehicles of at least calculated tire wear rates, estimated remaining tread depths, remaining mileage of the tires, and remaining time until replacement according to a set minimum tread depth.

[0152] 10 shows a flowchart illustrating a computer-implemented method 1000 for calculating and / or monitoring tire wear rates for a vehicle. The operations of the computer-implemented method 1000 may be implemented by a computing device.

[0153] At 1010, technical data for at least one tire of the vehicle is transmitted.

[0154] At 1020, vehicle technical data is transmitted.

[0155] At 1030, vehicle telematics information is transmitted.

[0156] At 1040, a calculated tire wear rate is obtained that is calculated according to a data-driven mathematical tire wear model and is based at least in part on the transmitted technical data of at least one tire of the vehicle and the obtained vehicle telematics information.

[0157] In yet another aspect, data from at least one in-service measurement of at least one characteristic of at least one tire of the vehicle can be transmitted, and the calculated tire wear rate is further calculated based at least in part on the at least one in-service measurement of the at least one characteristic of the at least one tire of the vehicle.

[0158] In yet another aspect, the remaining tread depth and / or remaining mileage of the tire and / or remaining time to replacement according to a set minimum tread depth is estimated based on the calculated tire wear rate.

[0159] In yet another aspect, at least one of the calculated tire wear rate, the estimated remaining tread depth, the remaining mileage of the tire, and the remaining time until replacement according to a set minimum tread depth is reported to the control system.

[0160] In yet another aspect, the control system is located in a vehicle.

[0161] In another aspect, the control system is located external to the vehicle and enables collection from a plurality of vehicles of at least calculated tire wear rates, estimated remaining tread depths, remaining mileage of the tires, and remaining time until replacement according to a set minimum tread depth.

Claims

1. 1. A computer-implemented method (900) for calculating tire wear rate for a vehicle, comprising: Obtaining (910) technical data of at least one tire of a vehicle; Obtaining (920) technical data of the vehicle; obtaining (930) telematics information for the vehicle; calculating (940) a tire wear rate based at least in part on the acquired technical data of at least one tire of the vehicle, the acquired technical data of the vehicle, and the acquired telematics information of the vehicle according to a data-driven mathematical tire wear model; obtaining data of at least one in-service measurement of at least one characteristic of at least one tire of the vehicle; Including, calculating the tire wear rate based at least in part on acquired data of at least one in-operation measurement of at least one characteristic of at least one tire of the vehicle; selecting one of a plurality of pre-stored algorithms for calculating a tire wear rate after obtaining data of at least one in-service measurement of at least one characteristic of at least one tire of the vehicle; selecting one of a plurality of pre-stored algorithms for calculating the tire wear rate, executing a plurality of algorithms for calculating the tire wear rate; selecting an algorithm from the plurality of algorithms that produces a tire wear rate calculation that most closely matches a tire wear rate based on data from the at least one in-operation measurement obtained.

2. 2. The method of claim 1, wherein the step of calculating the tire wear rate comprises: Calculating the tire wear rate according to a self-tuning mathematical model wherein the self-tuning mathematical model is tuned based on data from at least one in-operation measurement of at least one tire of the vehicle.

3. 2. The method of claim 1, wherein the data-driven mathematical tire wear model is trained based on a plurality of calculated tire wear rates, the plurality of calculated tire wear rates being based on data acquired from a plurality of vehicles, the acquired data including technical data for at least one tire of each of the vehicles, technical data for each of the vehicles, and telematics information for each of the vehicles.

4. 1. A computer-implemented method (1000) for calculating tire wear rate for a vehicle, comprising: - transmitting (1010) technical data of at least one tire of a vehicle; transmitting (1020) technical data of said vehicle; transmitting (1030) telematics information of the vehicle; obtaining (1040) a calculated tire wear rate based at least in part on the transmitted technical data of at least one tire of the vehicle, the transmitted technical data of the vehicle, and the transmitted telematics information of the vehicle, the calculated tire wear rate being calculated according to a data-driven mathematical tire wear model; transmitting data of at least one in-service measurement of at least one characteristic of at least one tire of the vehicle; Including, the calculated tire wear rate is further calculated based at least in part on at least one in-operation measurement of at least one characteristic of at least one tire of the vehicle; The step of calculating the tire wear rate includes: selecting one of a plurality of pre-stored algorithms for calculating a tire wear rate after obtaining data of at least one in-service measurement of at least one characteristic of at least one tire of the vehicle; selecting one of a plurality of pre-stored algorithms for calculating the tire wear rate, executing a plurality of algorithms for calculating the tire wear rate; selecting an algorithm from the plurality of algorithms that produces a tire wear rate calculation that most closely matches a tire wear rate based on data from the at least one in-operation measurement obtained.

5. 5. The method of claim 4, estimating the remaining tread depth and / or the remaining distance traveled by the tire and / or the remaining time until replacement according to a set minimum tread depth based on the calculated tire wear rate. The method further comprises:

6. 6. The method of claim 5, reporting to a control system at least one of the calculated tire wear rate, the estimated remaining tread depth, the remaining mileage of the tire, and the remaining time until replacement according to the set minimum tread depth. The method further comprises:

7. 7. The method of claim 6, wherein the control system is located in the vehicle.

8. 7. The method of claim 6, wherein the control system is located external to the vehicle and enables collection from a plurality of vehicles of at least the calculated tire wear rate, the estimated remaining tread depth, the remaining mileage of the tire, and the remaining time until replacement according to the set minimum tread depth.

9. 10. The method of claim 1, wherein the technical data for the at least one tire of the vehicle includes at least one of a tire manufacturer, a tire model, a tire pattern, a tire specification, a tire size, a tire mounting position, retread information, and a batch number for the tire.

10. 10. The method of claim 1, wherein performing an in-service measurement of at least one characteristic of at least one tire of the vehicle comprises measuring remaining tread depth during operation.

11. 2. The method of claim 1, wherein the telematics information for the vehicle includes at least one of vehicle usage, tire pressure, tractor load, region, country, longitudinal acceleration, lateral acceleration, speed, GPS coordinates, odometer, road type, load, tire pressure, gear shift, engine RPM, wheel speed, throttle / brake pedal position, tire temperature, outside air temperature, and steering wheel angle.

12. 1. An apparatus for monitoring the rate of tire wear on a vehicle, the apparatus comprising: means for obtaining technical data of at least one tire of a vehicle; means for obtaining technical data of said vehicle; means for acquiring telematics information of the vehicle; means for calculating a tire wear rate based at least in part on the acquired technical data of at least one tire of the vehicle, the acquired technical data of the vehicle, and the acquired telematics information of the vehicle according to a data-driven mathematical tire wear model; means for obtaining data of at least one in-service measurement of at least one characteristic of at least one tire of said vehicle; Including, the means for calculating the tire wear rate is based at least in part on acquired data of at least one in-operation measurement of at least one characteristic of at least one tire of the vehicle; means for selecting one of a plurality of pre-stored algorithms for calculating a tire wear rate after obtaining data of at least one in-service measurement of at least one characteristic of at least one tire of the vehicle; The means for selecting one of a plurality of pre-stored algorithms for calculating the tire wear rate comprises: means for executing a plurality of algorithms for calculating the tire wear rate; means for selecting from the plurality of algorithms an algorithm that produces a tire wear rate calculation that most closely matches a tire wear rate based on data from the at least one in-operation measurement obtained.

13. 1. An apparatus for monitoring the rate of tire wear on a vehicle, the apparatus comprising: means for transmitting technical data of at least one tire of the vehicle; means for transmitting technical data of said vehicle; means for transmitting telematics information of the vehicle; means for obtaining a calculated tire wear rate based at least in part on the transmitted technical data of at least one tire of the vehicle, the transmitted technical data of the vehicle, and the transmitted telematics information of the vehicle, the calculated tire wear rate being calculated according to a data-driven mathematical tire wear model; means for transmitting data of at least one in-service measurement of at least one characteristic of at least one tire of said vehicle; Including, the calculated tire wear rate is further calculated based at least in part on at least one in-operation measurement of at least one characteristic of at least one tire of the vehicle; The means for calculating the tire wear rate includes: means for selecting one of a plurality of pre-stored algorithms for calculating a tire wear rate after obtaining data of at least one in-service measurement of at least one characteristic of at least one tire of the vehicle; The means for selecting one of a plurality of pre-stored algorithms for calculating the tire wear rate comprises: means for executing a plurality of algorithms for calculating the tire wear rate; means for selecting from the plurality of algorithms an algorithm that produces a tire wear rate calculation that most closely matches a tire wear rate based on data from the at least one in-operation measurement obtained.

14. Apparatus according to claim 12, arranged to carry out any one of the methods according to any one of claims 2-3 or 5-11 when dependent on claim 1.

15. Apparatus according to claim 13, arranged to carry out any one of the methods according to any one of claims 5 to 11 when dependent on claim 4.

Images