Tire changing system

Abstract

A replacement system for supporting tires of a vehicle includes a processor in electronic communication with an electronic system of the vehicle and electronic memory capacity for storing tire identification information. The processor receives tire identification information and vehicle data. A predictive model is in electronic communication with the processor and receives the tire identification information and vehicle data. An identification of a replacement tread depth of the tire is included in the predictive model and the model determines an estimate of a remaining available distance for the tire to reach the replacement tread depth. The model estimates a remaining available time to reach the replacement tread depth from the estimate of the remaining available distance. A residual correction module optimizes the estimate of the remaining available time for the tire to reach the replacement tread depth and a notification of a replacement lead time is generated by the system.

Description

Technical Field

[0001] This invention generally relates to tire monitoring systems. More specifically, this invention relates to a system for collecting tire parameter data to monitor tire wear. This invention also relates to a system for estimating tire wear rate and generating predictions for tire replacement. Background Technology

[0002] Tire wear refers to the loss of material on the tire tread, as indicated by tire tread depth. Measuring or predicting tire wear can be beneficial. For example, information about tire wear can be used to predict tire performance during vehicle braking and / or maneuvering, and to determine when tires should be replaced. Furthermore, tire wear rate, i.e., the wear of the tire over time, can be used to estimate tread depth as a function of time to predict tire performance and / or tire life.

[0003] Techniques have been developed to directly measure tire wear conditions using sensors attached to the tire. Direct techniques offer several advantages, such as the relative simplicity of methods for measuring pressure, temperature, and / or tread depth using sensors. However, direct techniques also present challenges, such as the proper installation of sensors without compromising tire integrity, sensor lifespan, and / or the transmission of sensor data in harsh tire environments.

[0004] Because of these challenges, indirect techniques have been developed. Indirect techniques take into account measurements from certain tire and / or vehicle sensors and then generate predictions or estimates of tire condition and / or tire wear rate. While indirect techniques may not necessarily encounter challenges related to sensor installation, sensor lifespan, and / or sensor data transmission, they do include challenges in achieving accuracy and repeatability in the generated estimates or predictions. For example, many indirect techniques have experienced drawbacks in the prior art due to the lack of optimal prediction techniques, which in turn reduces the accuracy and / or reliability of tread wear prediction.

[0005] As a result, there is a need in the art for a system that accurately and reliably estimates tire wear rate and generates predictions of tire replacement. Summary of the Invention

[0006] According to one aspect of an exemplary embodiment of the present invention, a tire changing system for supporting a vehicle's tires is provided. The system includes a processor that electronically communicates with the vehicle's electronic system, and an electronic memory capacity for storing tire identification information. The processor receives tire identification information from the electronic memory capacity and vehicle data from the vehicle's electronic system. A prediction model electronically communicates with the processor and receives the tire identification information and vehicle data. The identification of the tire's replacement tread depth is included in the prediction model, and an estimate of the remaining available distance for the tire to reach the replacement tread depth is determined by the prediction model. An estimate of the remaining available time to reach the replacement tread depth is determined by the prediction model based on the estimate of the remaining available distance for the tire to reach the replacement tread depth. A residual correction module electronically communicates with the processor and optimizes the estimate of the remaining available time for the tire to reach the replacement tread depth. A replacement lead time determination is generated by the tire changing system and corresponds to the estimate of the remaining available time for the tire to reach the replacement tread depth. A replacement lead time notification is generated by the tire changing system and transmitted to at least one of the vehicle's electronic system, a cloud-based server, and a display device.

[0007] This invention provides the following technical solutions:

[0008] 1. A tire changing system for supporting a vehicle, the vehicle including an electronic system comprising:

[0009] A processor that communicates electronically with the vehicle's electronic systems;

[0010] Electronic storage capacity for storing tire identification information;

[0011] The processor receives tire identification information from the electronic memory capacity and vehicle data from the vehicle's electronic systems.

[0012] A predictive model that communicates electronically with the processor and receives tire identification information and vehicle data;

[0013] Identification of tire replacement tread depth included in the prediction model;

[0014] An estimate of the remaining available distance for a tire to reach the replacement tread depth determined by the predictive model;

[0015] The remaining available time to reach the tire replacement depth is estimated by the predictive model based on the estimated remaining available distance to reach the tire replacement depth.

[0016] A residual correction module that communicates electronically with the processor to optimize the estimation of the remaining available time for the tire to reach the tread depth for replacement;

[0017] The replacement lead time is determined by an estimate generated by the tire replacement system and corresponding to the remaining available time for the tire to reach its replacement tread depth; and

[0018] A notification of the tire change lead time generated by the tire changing system, the notification being transmitted to at least one of the vehicle's electronic systems, a cloud-based server, and a display device.

[0019] 2. The tire replacement system for supporting a vehicle according to Scheme 1, wherein the tire identification information includes the original tread depth of the tire, the rim size of the tire, the type of the tire, and the position of the tire on the vehicle.

[0020] 3. The tire replacement system for supporting a vehicle according to claim 1, wherein the vehicle data includes at least one of vehicle travel distance, vehicle speed, and vehicle load.

[0021] 4. The tire replacement system for supporting a vehicle according to claim 1, wherein the vehicle's electronic system includes at least one of a controlled area network bus and an electronic braking system.

[0022] 5. The tire replacement system for supporting a vehicle according to claim 1 further includes a sensor unit mounted to the tire and communicating electronically with the processor, the sensor unit measuring tire parameters including at least one of tire pressure, tire temperature and tire load, wherein the prediction model receives the tire parameters.

[0023] 6. The tire replacement system for supporting a vehicle according to Scheme 1, wherein the prediction model employs survival analysis technology.

[0024] 7. The tire replacement system for supporting a vehicle according to claim 1, wherein the prediction model generates at least one decay curve as a function of the remaining tread depth and the tire travel distance, wherein the at least one decay curve represents the tire wear rate.

[0025] 8. The tire replacement system for supporting a vehicle according to Scheme 7, wherein the prediction model generates a decay curve of typical tire wear rate, a decay curve of slow tire wear rate, and a decay curve of fast tire wear rate.

[0026] 9. The tire replacement system for supporting a vehicle according to claim 7, wherein the expected travel distance for the tire to reach the replacement tread depth is identified from the at least one decay curve.

[0027] 10. The tire replacement system for supporting a vehicle according to claim 9, wherein the estimate of the remaining available distance for the tire to reach the replacement tread depth is calculated by subtracting the travel distance experienced by the tire from the expected distance for the tire to reach the replacement tread depth.

[0028] 11. The tire replacement system for supporting a vehicle according to claim 7, wherein the accuracy of the at least one decay curve is improved by estimating the remaining tread depth of the tire using physical parameters of the tire, the physical parameters of the tire including at least one of tire travel distance, tire pressure and tire temperature.

[0029] 12. The tire replacement system for supporting a vehicle according to claim 7, wherein the prediction model includes shape parameters to modify the slope of the at least one decay curve.

[0030] 13. The tire replacement system for supporting a vehicle according to claim 12, wherein the estimate of the remaining tread depth of the tire is estimated as a size or percentage.

[0031] 14. The tire replacement system for supporting a vehicle according to Scheme 1, wherein the estimate of the remaining available distance is converted into an estimate of the remaining available time to reach the tire replacement depth by dividing the estimate of the remaining available distance by the average time-based distance traveled by the vehicle.

[0032] 15. The tire replacement system for supporting a vehicle according to Scheme 1, wherein the residual correction module includes a machine learning model.

[0033] 16. The tire replacement system for supporting a vehicle according to claim 15, wherein the machine learning model includes a predetermined percentile of absolute error.

[0034] 17. The tire replacement system for supporting a vehicle according to claim 16, wherein the machine learning model identifies confidence intervals around a center value, including observation points.

[0035] 18. The tire replacement system for supporting a vehicle according to claim 1 further includes a filter module that communicates electronically with the processor.

[0036] 19. The tire replacement system for supporting a vehicle according to claim 18, wherein the filter module allows the tire replacement system to use data when the tire is within a predetermined wear range.

[0037] 20. The tire replacement system for supporting a vehicle according to claim 19, wherein the filter module adopts a receiving area with respect to a slow wear curve and a fast wear curve, wherein the slow wear curve and the fast wear curve are functions of the remaining tread depth and the tire travel distance.

[0038] Brief description of the attached figures

[0039] The invention will be described by way of example and with reference to the accompanying drawings, wherein:

[0040] Figure 1 This is a schematic perspective view of a type of vehicle with a tire equipped with sensors, employing an exemplary embodiment of the tire changing system of the present invention.

[0041] Figure 2 yes Figure 1 A plan view of this type of vehicle is shown;

[0042] Figure 3 yes Figure 1 The schematic perspective view of this type of vehicle is shown, illustrating the transmission of data to a cloud-based server and to user equipment;

[0043] Figure 4 These are schematic diagrams illustrating various aspects of exemplary embodiments of the tire changing system of the present invention;

[0044] Figure 5 This is a graphical representation of one aspect of an exemplary embodiment of the tire changing system of the present invention;

[0045] Figure 6 This is a representation of an expression used in one aspect of an exemplary embodiment of the tire changing system of the present invention;

[0046] Figure 7 This is a representation of another expression used in one aspect of an exemplary embodiment of the tire changing system of the present invention;

[0047] Figure 8 This is a representation of another expression used in one aspect of an exemplary embodiment of the tire changing system of the present invention;

[0048] Figure 9 This is a representation of another expression used in one aspect of an exemplary embodiment of the tire changing system of the present invention;

[0049] Figure 10 This is a graphical representation of another exemplary embodiment of the tire changing system of the present invention;

[0050] Figure 11 This is a graphical representation of another exemplary embodiment of the tire changing system of the present invention;

[0051] Figure 12 This is a representation of another expression used in one aspect of an exemplary embodiment of the tire changing system of the present invention;

[0052] Figure 13 This is a representation of another expression used in one aspect of an exemplary embodiment of the tire changing system of the present invention;

[0053] Figure 14 This is a representation of another expression used in one aspect of an exemplary embodiment of the tire changing system of the present invention;

[0054] Figure 15 This is a representation of another expression used in one aspect of an exemplary embodiment of the tire changing system of the present invention;

[0055] Figure 16 This is a representation of another expression used in one aspect of an exemplary embodiment of the tire changing system of the present invention;

[0056] Figure 17 This is a graphical representation of another exemplary embodiment of the tire changing system of the present invention;

[0057] Figure 18 This is a schematic diagram of another exemplary embodiment of the tire changing system of the present invention; and

[0058] Figure 19 This is a graphical representation of another exemplary embodiment of the tire changing system of the present invention.

[0059] Similar numbers in all the accompanying figures refer to similar parts.

[0060] definition

[0061] An "ANN," or "Artificial Neural Network," is an adaptive tool for modeling nonlinear statistical data. It changes its structure based on external or internal information flowing through the network during the learning phase. ANNs are tools for modeling complex relationships between inputs and outputs or for finding patterns in data.

[0062] "Axial" and "axially" refer to a line or direction parallel to the axis of rotation of the tire.

[0063] "CAN bus" is an abbreviation for Controller Area Network.

[0064] "Circumferential" refers to a line or direction extending along the periphery of the surface of the annular tread that is perpendicular to the axial direction.

[0065] “Cloud computing” or “cloud” refers to computer processing involving computing power and / or data storage distributed across multiple data centers, typically facilitated by the use of internet access and communication.

[0066] "EBS" is an abbreviation for Electronic Braking System.

[0067] The “center plane (CP)” refers to the plane that is perpendicular to the tire’s axis of rotation and passes through the center of the tread.

[0068] "Imprint" refers to the contact surface or area formed between the tire tread and a flat surface when the tire rotates or rolls.

[0069] "Groove" refers to a narrow, elongated gap in the tread that can extend circumferentially or laterally around the tread in a straight or zigzag pattern.

[0070] "Inner side" refers to the side of the tire that is closest to the vehicle when the tire is mounted on the wheel and the wheel is mounted on the vehicle.

[0071] A Kalman filter is a set of mathematical equations that implements a predictor-corrector type estimator that is optimal in the sense of minimizing the covariance of the estimation error while satisfying certain assumptions.

[0072] "Horizontal" refers to the axial direction.

[0073] A Luenberger observer is a state observer or estimation model. A state observer is a system that provides an estimate of the internal state of a given real system from measurements of its inputs and outputs. It is typically implemented in a computer and provides the basis for many practical applications.

[0074] “MSE” is an abbreviation for mean square error, which is the error between the measured signal and the estimated signal minimized by the Kalman filter.

[0075] "Outer side" refers to the side of the tire that is furthest from the vehicle when the tire is mounted on the wheel and the wheel is mounted on the vehicle.

[0076] "PSD" stands for Power Spectral Density (a technical name synonymous with FFT (Fast Fourier Transform)).

[0077] "Radial" and "radially" refer to directions that are radially toward or away from the tire's axis of rotation.

[0078] "Tread stripe" refers to a circumferentially extending rubber strip on the tire tread that is defined by at least one circumferential groove and a second such groove or lateral edge, the strip not being separated laterally by grooves of full depth.

[0079] "Slits" refer to small grooves molded into the tire tread elements. These grooves subdivide the tread surface and improve traction. Slits are typically narrow and located close to the tire track, rather than being open recesses within the tire track.

[0080] "Tread" refers to the molded rubber component, which includes the part of the tire that comes into contact with the road under normal inflation and load.

[0081] "Tread depth" refers to the radial distance or dimension between the outermost radial surface of the tread element and the outermost radial surface of the deepest groove of the tire.

[0082] "Tread element" or "traction element" refers to a pattern strip or block element defined by a shape having adjacent grooves. Detailed Implementation

[0083] Turn now Figures 1 to 19 An exemplary embodiment of the tire changing system of the present invention is shown as 10. (See also: Special Reference) Figure 1 System 10 estimates the wear rate of each tire 12 supporting vehicle 14 and predicts the replacement of each tire 12 supporting vehicle 14. Although vehicle 14 is described as a passenger car for convenience, the invention is not limited thereto. The principles of the invention can be applied to other vehicle categories, such as commercial trucks and trailers, off-road vehicles, etc., where the vehicle may be supported by more or fewer tires.

[0084] Each tire 12 includes a pair of bead regions 16 and a pair of sidewalls 18, wherein each sidewall extends radially outward from the corresponding bead region to the contact tread 20. The tire 12 is reinforced by a carcass 22 extending circumferentially from one bead region 16 to the other, as known to those skilled in the art. An inner liner 24 is formed on the inner surface of the carcass 22. The tire 12 is mounted on a wheel 26 in a manner known to those skilled in the art and, upon mounting, forms an inner cavity 28 filled with a pressurized fluid (such as air).

[0085] Sensor unit 30 can be attached to the inner liner 24 of each tire 12 by means such as adhesive and measures certain parameters or conditions of the tire 12, as will be described in more detail below. It should be understood that sensor unit 30 can be attached in this manner or to other parts of the tire 12, such as between layers of the carcass 22, on or in one of the sidewalls 18, on or in the tread 20, and / or combinations thereof. For convenience, this document will refer to the mounting of sensor unit 30 on the tire 12, and it should be understood that such mounting includes all such attachments.

[0086] Sensor unit 30 is mounted on each tire 12 to detect certain real-time tire parameters, such as tire pressure 52 ( Figure 4Temperature 54 and / or load 56. Preferably, sensor unit 30 is a tire pressure monitoring system (TPMS) module or sensor, which is a commercially available type and can be any known configuration. For convenience, sensor unit 30 is referred to as a TPMS sensor. Each TPMS sensor 30 preferably also includes electronic memory capacity for storing identification (ID) information for each tire 12, referred to as tire ID information 58. Alternatively, tire ID information 58 may be included in another sensor unit or in a separate tire ID storage medium, such as tire ID tag 34.

[0087] Tire ID information 58 may include manufacturing information of tire 12, such as: tire type 64, such as passenger tire, truck tire, trailer tire, steering tire, non-steering tire, etc.; tire model; original tread depth 60; size information, such as rim size 62, width and outer diameter; production location; production date; including compound identification or tread crown code associated with compound identification; including tread structure identification or model code associated with tread structure identification. Tire ID information 58 may also include service history or other information to identify specific characteristics and parameters of each tire 12, and the tire's location or position 66 on vehicle 14. In addition, Global Positioning System (GPS) capability may be included in TPMS sensor 30 and / or tire ID tag 34 to provide location tracking of tire 12 and / or vehicle 14 on which the tire is mounted during transportation.

[0088] It should be understood that the TMPS sensor 30 and the tire ID tag 34 can be separate units or can be integrated into a single sensor unit. Furthermore, other sensors known to those skilled in the art can be used in the tire 12 as integrated or separate units. For convenience, the TMPS sensor 30 and the tire ID tag 34 are referred to as separate units; it should be understood that they can be integrated into a single unit, and other sensors can be employed.

[0089] Turn now Figure 2 The TPMS sensor 30 and tire ID tag 34 each include an antenna for wirelessly transmitting measurement parameters 52 of tire pressure, 54 of tire temperature, and 56 of tire load, as well as tire ID information 58, to the processor 38. The processor 38 may be integrated into the TPMS sensor 30 or the tire ID tag 34, or it may be a remote processor that can be mounted on the vehicle 14 or be cloud-based. For convenience, the processor 38 will be described as a remote processor mounted on the vehicle 14; it should be understood that the processor may alternatively be cloud-based or integrated into the TPMS sensor unit 30 or the tire ID tag 34.

[0090] The processor 38 preferably communicates electronically with the electronic systems of the vehicle 14, such as the vehicle CAN bus system 42, which is referred to as the CAN bus or vehicle EBS. For convenience, reference will be made to the CAN bus 42, but it should be understood that such reference includes other electronic systems of the vehicle 14, such as the vehicle EBS.

[0091] Various aspects of the tire changing system 10 are preferably executed on a processor 38, which is capable of receiving input data from the TMPS sensor 30 and the tire ID tag 34, as well as data from sensors mounted on the vehicle 14 that communicate electronically with the CAN bus. For example, on-board or vehicle-based sensors include sensors indicating vehicle data such as vehicle speed 68, vehicle load 70, vehicle distance traveled 72 from the odometer, etc.

[0092] refer to Figure 3 When the aforementioned tire data, tire ID information, and vehicle data are collected and associated for each tire 12, the data can be retrieved from the processor 38 on the vehicle 14. Figure 2 The data can be wirelessly transmitted 40 to a processor in a cloud-based server 44. The data can be stored and / or remotely analyzed on the cloud-based server 44, and can also be wirelessly transmitted 46 to a display device 50 for use in a display visible to the user, technician, or fleet manager of vehicle 14, such as a smartphone or computer. Alternatively, the data can be wirelessly transmitted 48 directly 48 from the processor 38 on vehicle 14 to the display device 50.

[0093] Turn Figure 4 The tire changing system 10 includes the transmission of data 74 to the processor 38. Preferably, the data 74 includes tire ID information 58, specifically the original tread depth 60, rim size 62, tire type 64, and tire position 66 on the vehicle 14, which are transmitted from the ID tag 34 to the processor 38. Alternatively, some or all of the tire ID information 58 may be stored in a database that communicates electronically with the processor 38. The transmitted data 74 also includes vehicle data, such as the vehicle distance traveled 72 from the odometer, which is transmitted from the CAN bus 42 to the processor 38.

[0094] To improve the accuracy of the tire changing system 10, the transmitted data 74 may include additional data transmitted to the processor 38. For example, tire pressure 52, tire temperature 54, and / or tire load 56 may be transmitted from the TPMS sensor 30 to the processor 38. Vehicle speed 68 and / or vehicle load 70 may be transmitted from the CAN bus 42 to the processor 38. It should be understood that other types of information may be included in the transmitted data 74, such as traffic conditions, road conditions, weather, etc. Each set of transmitted data 74 is timestamped, making the transmitted data correlated with a specific measurement time. In this way, multiple sets of transmitted data 74, each with a specific timestamp, can be generated.

[0095] The tire changing system 10 includes a prediction model 76, which is stored on or in electronic communication with the processor 38. The prediction model 76 receives transmitted data 74 and generates the remaining available distance 100 and remaining available time 102 for the tire 12 that will reach the replacement tread depth 82, as will be described in more detail below. Preferably, the prediction model 76 employs survival analysis techniques, which are statistical techniques that analyze data inputs (e.g., transmitted data 74) to estimate the remaining duration for a given component (e.g., each tire 12) until the event occurs.

[0096] The survival analysis technique employed in predictive model 76 is preferably a parametric model, which uses a fixed mathematical form to calculate the output. The residuals, which are the differences between observed and predicted values, are then adjusted using a nonparametric model. Results are generated in various forms, such as plots, documents, and variables in an interactive environment. The survival analysis technique and the nonparametric model take multiple continuous and categorical parameters as input.

[0097] Each tire 12 includes the original tread depth of 60, such as Figure 1 As shown. Reference Figure 4 and Figure 5 As tire 12 wears, the tread depth decreases and is represented as the remaining tread depth 80. The remaining tread depth 80 can be expressed as the size or percentage of the original tread depth 60. The replacement tread depth 82 is identified, which can be a specific size or a specific percentage of the original tread depth 60. Figure 5 In this case, the replacement tread depth 82 is set to 20% (20%) of the original tread depth 60.

[0098] The survival analysis technique in prediction model 76 generates a central decay curve 86 as a function of the remaining tread depth 80 and the distance 84 traveled by tire 12. The central decay curve 86 represents the typical expected wear rate of tire 12. An upper decay curve 90, representing a slower wear rate of tire 12, can also be generated. A lower decay curve 92, representing a faster wear rate of tire 12, can be further generated.

[0099] For a typical expected wear rate 86, the expected distance 84 for tire 12 to reach replacement tread depth 82 is indicated at point 94. For example, when the replacement tread depth 82 is set to 20% of the original tread depth 60, the expected distance 94 for tire 12 to reach replacement tread depth is 270,000 kilometers (km). For a slower wear rate 90, the expected distance for tire 12 to reach replacement tread depth 82 is indicated at point 96, which is 320,000 km. For a faster wear rate 92, the expected distance for tire 12 to reach replacement tread depth 82 is indicated at point 98, which is 220,000 km.

[0100] Since the expected distance 94 for tire 12 to reach the replacement tread depth 82 has been identified, the remaining usable distance 100 that the tire can travel can be generated. Figure 6 Tire ID information 58 provides the distance traveled by vehicle 14 when tire 12 was new and at its original tread depth of 60. The current vehicle distance traveled 72 can be obtained from the odometer. The distance traveled 84 by tire 12 can be determined by subtracting the distance traveled by vehicle 14 when tire 12 was new from the vehicle's current distance traveled.

[0101] The remaining usable distance of 100 at a typical expected wear rate of 86 is calculated by subtracting the distance traveled by tire 12 from the expected distance of 94 when the tire reaches a replacement tread depth of 82 at a typical expected wear rate. The remaining usable distance of 100 at a slower wear rate of 90 is calculated by subtracting the distance traveled by tire 12 from the expected distance of 96 when the tire reaches a replacement tread depth of 82 at a slower wear rate. The remaining usable distance of 100 at a faster wear rate of 92 is calculated by subtracting the distance traveled by tire 12 from the expected distance of 98 when the tire reaches a replacement tread depth of 82 at a faster wear rate.

[0102] like Figure 6 As shown, the remaining usable distance 100 can be converted into the remaining usable time 102 to reach the tire replacement tread depth 82. The average weekly distance 104 traveled by vehicle 14 can be monitored via the vehicle distance 72 from the odometer. The remaining usable time 102 to reach the tire replacement tread depth 82 is determined by dividing the remaining usable distance 100 by the average weekly distance 104.

[0103] To provide greater accuracy for the tire changing system 10, the accuracy of the decay curves 86, 90, and 92 can be improved. One way to improve this accuracy is to estimate the tread depth 80 using the physical parameters of the tire 12. For example, using... Figure 7 Equation 106 shown, the first function 110, expresses the estimate of the tread depth 80 as a minimum tread depth 112 that depends on several parameters x1, x2, x3. Figure 8Equation 108 shown, the second function 114 expresses the estimate of tread depth 80 as a maximum tread depth 116 depending on parameters x1, x2, x3.

[0104] In each function 110 and 114, parameters x1, x2, and x3 include available parameters selected from the transmitted data 74, such as tire pressure 52, tire temperature 54, and tire load 56. Tire travel distance 84 is a parameter that is always available, as determined above. In this way, the accuracy of the decay curves 86, 90, and 92 is improved because when the travel distance 84 of tire 12 is zero (0), function 110 should return the maximum value 112 of the tread depth, which is the original depth 60. When the travel distance 84 of tire 12 is at its maximum value, function 114 should return the minimum value 116 of the tread depth, i.e., the tread depth 82 is changed.

[0105] Figure 9 Equation 118 shown preferably improves the accuracy of the decay curves 86, 90, and 92 by estimating the tread depth 80, which is an exponential decay function incorporating the limiting values ​​of equations 106 and 108. In equation 118, TD is the remaining tread depth 80 to be predicted, preferably in millimeters. original The original tread depth of tire 12 is 60. min The tread depth is 82, the distance is the tire travel distance 84, preferably in kilometers, and alpha (α) is the shape parameter that modifies the slope of the attenuation curves 86, 90, and 92.

[0106] Figure 10 The modified prediction model 120 is shown in Figure 11, and the adjustment of the attenuation curve 122 from the original attenuation curves 86, 90, and 92 is illustrated based on the shape parameter alpha α. An additional modified prediction model 124 is shown in Figure 11, which illustrates a further adjustment of the attenuation curve 126 based on the original tread depth 60 and the replacement tread depth 82 of the tire 12.

[0107] To consider as many variables or parameters as possible, equation 118 can be modified as follows: Figure 12 The final equation is shown in equation 128. In final equation 128, the shape parameter alpha (α) is replaced by matrix A, and the tire travel distance 84 is replaced by the parameter matrix P. The dot product of matrices A and P can be read as a linear transformation, such as... Figure 13 As shown in 130. An example of a linear transformation including specific parameters from the transmitted data 74 is as follows. Figure 14As shown in 132. The linear transformation 132 includes the travel distance 84 of tire 12, tire pressure 52, and tire temperature 54. Additional parameters from the transmitted data 74 can be added to further increase the accuracy of the attenuation curves 86, 90, and 92, and thus improve the accuracy of the tire changing system 10.

[0108] Another method to improve the accuracy of the decay curves 86, 90, and 92 to provide greater accuracy for the tire changing system 10 includes estimating the tread depth 80 as a percentage. In this case, Figure 9 Equation 118 shown has lost its geometric elements and adopted Figure 15 The form of Equation 134. In Equation 134, TD is the remaining tread depth 80 to be predicted as a percentage, MinTreadDepth% is the replacement tread depth 82 of tire 12 as a percentage, distance is the tire travel distance 84, preferably in kilometers, and alpha (α) is a shape parameter that modifies the slope of the decay curves 86, 90, and 92.

[0109] To account for as many variables or parameters as possible, equation 134 can be modified as follows: Figure 16 The final equation 136 is shown. In the final equation 136, the shape parameter alpha (α) is replaced by matrix A, and the tire travel distance 84 is replaced by the parameter matrix P. The modified prediction model 138 is... Figure 17 The diagram shows the adjustment of the decay curve 140 from the original decay curves 86, 90, and 92 based on the replacement tread depth 82 of the tire 12 as a percentage, according to the shape parameter alpha α.

[0110] like Figure 4 As shown, the tire changing system 10 preferably includes a residual or error correction module 142 to optimize the estimate of the remaining available time 102 for the tire 12 to reach the replacement tread depth 82. More specifically, the residual correction module 142 preferably includes a machine learning model, such as a random forest model or a neural network model, used to train the analysis model to minimize statistical errors and thus optimize the estimate of the remaining available time 102 for the tire 12 to reach the replacement tread depth 82.

[0111] The model of the residual correction module 142 is preferably trained using approximately 60% (60%) of the tires 12 that have received the transmitted data 74, while the remaining 40% is used to estimate the remaining available time 102 to reach the replacement tread depth 82. Preferably, the division between 60% and 40% is determined using tire ID information 58 to ensure that the tires 12 used during model training are not used to test the model to further optimize the accuracy of the tire changing system 10.

[0112] The metrics used in the model of residual correction module 142 preferably include adjusted R. 2 It is a corrected coefficient of determination for the proportion of change in the dependent variable, which is predicted based on the number of predicted values ​​in the model. The metric preferably also includes the mean absolute error (MAE) between paired observations. Adjusted R0 2 MAE and α are traditional metrics in model error calculation.

[0113] The metrics in the model of the residual correction module 142 preferably also include a predetermined percentile of the absolute error, such as... Figure 18 As shown in the diagram. For example, these measures preferably include 75%, 90%, and 95% of the absolute error. The predicted center value 146 may not return a perfect match to the actual observations, so it is preferable to identify a confidence interval 144 around the center value, which will include the observed points. The confidence interval 144 is the range of estimates defined by a lower and upper bound and refers to the level of accuracy in the prediction. The larger the confidence interval 144, the larger the number of points included in the interval. The goal is to include the largest possible number of points within a smaller confidence interval 144.

[0114] For representativeness, it is preferable to calculate confidence intervals 144 that include errors of 75%, 90%, and 95%. For example, the remaining usable time 102 for tire 12 to reach the replacement tread depth 82 + / - interval [95%] represents 95% of the estimated remaining usable time in the time it will reach the end of its life. Confidence intervals 144 are preferably determined by calculating the absolute error for each point in the test database and generating a list, with the expected percentile on the list generated at the previous point. Confidence intervals 144 can be adjusted to any expected percentage, such as 50%, 75%, and 95%.

[0115] It should be understood that since the replacement tread depth 82 of tire 12 is expressed as a percentage, the error near the center value is also expressed as a percentage of the original tread depth 60. To convert the error to a size, the error can be multiplied by the original tread depth 60 size. For example, if the 95th percentile of the error is 10%, then to convert to a size, when tire 12 is at an original tread depth of 16mm for 60, 10% * 16mm equals 1.6mm. Therefore, the 95th percentile point will be contained within the range between the center value provided by the model and 1.6mm.

[0116] refer to Figure 4 and Figure 19Optional filter module 148 is stored on or in electronic communication with processor 38. More specifically, filtering certain data 74 is beneficial to improve the accuracy of tire changing system 10. For example, data for certain tires 12 can be filtered out, such as tires without identifiable ID information 58, tires that have been retreaded as indicated by the tire ID information, and tires that have experienced significant tread wear before the implementation of tire changing system 10, such as tread loss exceeding approximately 0.5 mm.

[0117] The filter module 148 preferably also filters out data 74 of tires 12 with insufficient data points so that the tire changing system 10 can accurately analyze trends in the data transmitted to the processor 38. Furthermore, the filter module 148 preferably manages outliers in the transmitted data 74. Specifically, to manage outliers, the filter module 148 removes isolated points or points with abnormal tread depth, such as tires 12 that show no wear after 100,000 km or tires that are completely worn after 5,000 km. Preferred techniques employed by the filter module 148 include using only the transmitted data 74 of tires 12 with a predetermined wear rate range, such as a wear rate greater than 0.3 mm per 10,000 km and less than 4 mm per 10,000 km of tire travel distance 84.

[0118] like Figure 19 As shown, in filter module 148, slow wear curve 150 and fast wear curve 152 can be determined. A data receiving area 154 can be generated by shifting the slow wear curve 150 upwards by a predetermined amount, for example, approximately 10%, and by shifting the fast wear curve 152 downwards by a predetermined amount, for example, approximately 10%. The data in receiving area 154 is thus received and used in tire changing system 10.

[0119] return Figure 4 After the transmitted data 74 is processed by the prediction model 76, model modifications 120, 124, and / or 138 are performed, error correction is performed in the residual correction module 142, and the data is filtered in the filter module 148. The tire replacement system 10 then generates a replacement lead time determination 156. The replacement lead time determination 156 corresponds to the remaining available time 102 for the tire 12 to reach the replacement tread depth 82 at the determined time.

[0120] A notification 158 determining the replacement lead time 156 is generated by the tire replacement system 10 and transmitted to the CAN bus 42 or other vehicle electronic control systems, a cloud-based server 44, and / or a display device 50. Thus, the notification 158 determining the replacement lead time 156 is transmitted to the user, technician, and / or fleet manager of the vehicle 14. The notification 158 is preferably sent at a predetermined lead time, for example, approximately three (3) months before the replacement tread depth 82 of the fast-wearing tire 12. The number and frequency of the notifications 158 can be adjusted as needed, for example, to 12 months, 6 months, 3 months, and 1 month before the tire 12 reaches the replacement tread depth 82.

[0121] In this way, the tire changing system 10 of the present invention accurately and reliably estimates the wear rate of tire 12 and generates a prediction of tire replacement. Based on the availability of parameters and the accuracy of the generated estimates, parameters can be added or suppressed for use in system 10. Tire changing system 10 focuses on the remaining time available for tire 12 before reaching the replacement tread depth 82. Tire changing system 10 is applied to tires 12, vehicles 14, and fleets with different characteristics and uses, such as long-haul trucks, regional transport trucks, mixed-service trucks, buses, and passenger vehicle fleets.

[0122] The present invention also includes a method for estimating the wear rate of tire 12 and a method for generating a prediction of tire replacement. Each method includes the methods described above and... Figures 1 to 19 The steps described are shown.

[0123] It should be understood that the structure and method of the above-described tire changing system can be altered or rearranged, or components or steps known to those skilled in the art can be omitted or added without affecting the overall concept or operation of the invention. For example, although vehicle 14 is described as a passenger car for convenience, the invention can be applied to other vehicle categories, such as commercial trucks and trailers, off-road vehicles, etc., where the vehicle may be supported by more or fewer tires.

[0124] The invention has been described with reference to preferred embodiments. Others will conceive of possible modifications and alterations upon reading and understanding this specification. It should be understood that all such modifications and alterations are included within the scope of the invention as set forth in the appended claims or their equivalents.

Claims

1. A tire changing system for supporting a vehicle, the vehicle including an electronic system, characterized in that... The system includes: A processor that communicates electronically with the vehicle's electronic systems; Electronic storage capacity for storing tire identification information; The processor receives tire identification information from the electronic memory capacity and vehicle data from the vehicle's electronic systems. A predictive model that communicates electronically with the processor and receives tire identification information and vehicle data; Identification of tire replacement tread depth included in the prediction model; An estimate of the remaining available distance for a tire to reach the replacement tread depth determined by the predictive model; The remaining available time to reach the tire replacement depth is estimated by the predictive model based on the estimated remaining available distance to reach the tire replacement depth. A residual correction module that communicates electronically with the processor to optimize the estimation of the remaining available time for the tire to reach the tread depth for replacement; The replacement lead time is determined by the tire replacement system and corresponds to the estimated remaining available time for the tire to reach the replacement tread depth. A filter module in electronic communication with the processor, wherein the filter module allows the tire changing system to use data when the tire is within a predetermined wear range; and A notification of the tire change lead time generated by the tire changing system, the notification being transmitted to at least one of the vehicle's electronic systems, a cloud-based server, and a display device.

2. The tire changing system for supporting a vehicle according to claim 1, wherein, The tire identification information includes the tire's original tread depth, tire rim size, tire type, and tire position on the vehicle.

3. The tire changing system for supporting a vehicle according to claim 1, wherein, The vehicle data includes at least one of the following: vehicle distance traveled, vehicle speed, and vehicle load.

4. The tire replacement system for supporting a vehicle according to claim 1 further includes a sensor unit mounted to the tire and communicating electronically with the processor, the sensor unit measuring tire parameters including at least one of tire pressure, tire temperature, and tire load, wherein the prediction model receives the tire parameters.

5. The tire changing system for supporting a vehicle according to claim 1, wherein, The prediction model employs survival analysis techniques.

6. The tire changing system for supporting a vehicle according to claim 1, wherein, The prediction model generates at least one decay curve as a function of remaining tread depth and tire travel distance, wherein the at least one decay curve represents the tire wear rate.

7. The tire changing system for supporting a vehicle according to claim 6, wherein, The prediction model generates decay curves for typical tire wear rate, slow tire wear rate, and fast tire wear rate.

8. The tire changing system for supporting a vehicle according to claim 6, wherein, The expected travel distance at which a tire reaches its replacement tread depth is identified from the at least one decay curve.

9. The tire changing system for supporting a vehicle according to claim 8, wherein, The remaining usable distance for a tire to reach its replacement tread depth is estimated by subtracting the distance traveled by the tire from the expected distance to reach the replacement tread depth.

10. The tire changing system for supporting a vehicle according to claim 6, wherein, The accuracy of the at least one decay curve is improved by estimating the remaining tread depth of the tire using the tire's physical parameters, which include at least one of tire travel distance, tire pressure, and tire temperature.

11. The tire changing system for supporting a vehicle according to claim 7, wherein, The accuracy of the at least one decay curve is improved by estimating the remaining tread depth of the tire using the tire's physical parameters, which include at least one of tire travel distance, tire pressure, and tire temperature.

12. The tire changing system for supporting a vehicle according to claim 7, wherein, The prediction model includes shape parameters to modify the slope of the at least one decay curve.

13. The tire changing system for supporting a vehicle according to claim 12, wherein, The remaining tread depth of the tire is estimated as a size or percentage.

14. The tire changing system for supporting a vehicle according to claim 1, wherein, The remaining available distance estimate is converted into an estimate of the remaining available time to reach the tire replacement depth by dividing the estimated remaining available distance by the average distance traveled by the vehicle over time.

15. The tire changing system for supporting a vehicle according to claim 1, wherein, The residual correction module includes a machine learning model.

16. The tire changing system for supporting a vehicle according to claim 15, wherein, The machine learning model includes a predetermined percentile of the absolute error.

17. The tire changing system for supporting a vehicle according to claim 16, wherein, The machine learning model identifies confidence intervals around the center value for each observation point.

18. The tire changing system for supporting a vehicle according to claim 17, wherein, The filter module employs a receiving region with respect to a slow wear curve and a fast wear curve, wherein the slow wear curve and the fast wear curve are functions of the remaining tread depth and the tire travel distance.

Images