Tire change estimation system and method

Abstract

A tire replacement estimation system includes a tire supporting a vehicle. A sensor unit is mounted on the tire and includes a footprint centerline length measurement sensor and a pressure sensor. A processor is in electronic communication with the sensor unit and receives the measured centerline length and the measured pressure. An electronic vehicle network transmits selected vehicle parameters to the processor. A wear state predictor is stored on the processor and receives the measured centerline length, the measured pressure, and the selected vehicle parameters to generate an estimated wear state of the tire. An estimation model is stored on the processor and receives a plurality of estimated wear states of the tire and predicts a future wear state of the tire. The estimation model generates an estimated tire replacement date when the predicted future wear state of the tire exceeds a predetermined wear threshold.

Description

TECHNICAL FIELD

[0001] The present invention relates generally to tire monitoring systems. More specifically, the present invention relates to systems that predict tire wear. In particular, the present invention is directed to a system and method for estimating an optimal tire replacement based on a predicted wear state of a tire. BACKGROUND

[0002] Tire wear plays an important role in vehicle factors such as safety, reliability, and performance. Tread wear, which refers to the loss of material from the tire tread, directly impacts such vehicle factors. Therefore, it is desirable to monitor and / or measure the amount of tread wear experienced by a tire, which is referred to as the tire wear state. It should be understood that the terms "tread wear" and "tire wear" can be used interchangeably for convenience.

[0003] One way to monitor and / or measure tread wear is by using a wear sensor disposed in the tire tread, which is referred to as a direct method or approach. The direct approach of measuring tire wear from a sensor mounted on the tire has multiple challenges. Placing a sensor in an unvulcanized or "green" tire so that it is then vulcanized at high temperatures can result in damage to the wear sensor. Additionally, sensor durability can prove problematic in meeting the millions of cycles requirement of the tire. Furthermore, in the direct measurement approach, the wear sensor must be small enough so as not to cause any uniformity issues when the tire is rotating at high speeds. Finally, the wear sensor can be expensive and significantly increase the cost of the tire.

[0004] Due to these challenges, several alternative approaches have been developed that involve predicting the tread wear over the life of a tire, including indirect estimation of the tire wear state. Due to the lack of optimal prediction techniques, these alternative approaches have experienced some drawbacks in the prior art that reduce the accuracy and / or reliability of the tread wear prediction. For example, many such techniques involve data or information that is not readily available, such as non-standard vehicle system signals, or data that is not accurate under all driving conditions.

[0005] Additionally, while some indirect estimation techniques have been developed that show improved accuracy and / or reliability, such techniques often only indicate the wear state of the tire. While such information is helpful, it can have limited value to some users. For example, some users can not fully understand the indication of the tire wear state. Additionally, many systems compare the estimated tire wear state to a threshold to inform the user that the tire should be replaced after the tire has reached a minimum wear state or threshold. However, it is often desirable to inform or notify the user before the wear threshold at which the tire can need to be replaced. Such advance notification enables the user to proactively schedule a tire replacement as desired and before reaching the minimum wear state or threshold.

[0006] Accordingly, there is a need in the art for a system and method that accurately and reliably estimates the wear state of a tire, predicts the future wear state of the tire, and estimates an optimal tire replacement based on the wear state. SUMMARY

[0007] According to an aspect of the exemplary embodiments of this application, a tire replacement estimation system is provided. The system includes a vehicle and a tire supporting the vehicle. A sensor unit is mounted on the tire and includes a footprint centerline length measurement sensor to measure a centerline length of a footprint of the tire, and a pressure sensor to measure a pressure of the tire. A processor is in electronic communication with the sensor unit and receives the measured centerline length and the measured pressure. An electronic vehicle network transmits selected vehicle parameters to the processor. A wear state predictor is stored on the processor and receives as inputs the measured centerline length, the measured pressure, and the selected vehicle parameters, and generates an estimated wear state of the tire from the inputs. An estimation model is stored on the processor and receives as inputs a plurality of estimated wear states of the tire generated by the wear state predictor, the estimation model predicting a future wear state of the tire. The estimation model generates an estimated tire replacement date when the predicted future wear state of the tire exceeds a predetermined wear threshold.

[0008] According to another aspect of the exemplary embodiments of this application, a method of estimating replacement of a tire supporting a vehicle is provided. The method includes the steps of mounting a sensor unit on the tire, measuring a footprint centerline length of the tire with the sensor unit, and measuring a pressure of the tire with the sensor unit. The measured centerline length and the measured pressure are received in a processor. Selected vehicle parameters are transmitted from an electronic vehicle network to the processor. A wear state predictor is stored on the processor and receives as inputs the measured centerline length, the measured pressure, and the selected vehicle parameters. The wear state predictor generates an estimated wear state of the tire. An estimation model is stored on the processor and receives as inputs a plurality of estimated wear states of the tire from the wear state predictor. A future wear state of the tire is predicted with the estimation model. An estimated tire replacement date is generated with the estimation model when the predicted future wear state of the tire exceeds a predetermined wear threshold.

[0009] According to the present application, it further comprises the following technical solutions:

[0010] 1. A tire replacement estimation system, comprising:

[0011] a vehicle;

[0012] a tire supporting the vehicle;

[0013] a sensor unit mounted on the tire, the sensor unit comprising:

[0014] a footprint centerline length measurement sensor to measure a centerline length of a footprint of the tire; and

[0015] a pressure sensor to measure a pressure of the tire;

[0016] a processor in electronic communication with the sensor unit, the processor receiving the measured centerline length and the measured pressure;

[0017] an electronic vehicle network to transmit selected vehicle parameters to the processor;

[0018] a wear state predictor stored on the processor and receiving as inputs the measured centerline length, the measured pressure, and the selected vehicle parameters, the wear state predictor generating an estimated wear state of the tire from the inputs;

[0019] a prognosis model stored on the processor and receiving as inputs a plurality of estimated wear states of the tire from the wear state predictor, the prognosis model predicting a future wear state of the tire; and

[0020] a predicted tire replacement date generated by the prognosis model when the predicted future wear state of the tire exceeds a predetermined wear threshold.

[0021] 2. The tire replacement prognosis system of claim 1, wherein the selected vehicle parameters include a vehicle speed, a lateral acceleration, and a longitudinal acceleration.

[0022] 3. The tire replacement prognosis system of claim 2, wherein the wear state predictor includes a screening module that compares the vehicle speed, the lateral acceleration, and the longitudinal acceleration to determine whether the vehicle is cruising.

[0023] 4. The tire replacement prognosis system of claim 1, wherein the wear state predictor includes a counter module that counts a plurality of centerline length measurements until a predetermined sample size of centerline length measurements is obtained.

[0024] 5. The tire replacement prognosis system of claim 1, wherein the wear state predictor includes a normalization module that applies a pressure scaling factor to the centerline length measurements to generate a normalized footprint centerline length.

[0025] 6. The tire replacement estimation system of clause 5, wherein the wear state predictor comprises a median estimator that receives a plurality of normalized footprint centerline lengths and calculates a median of the normalized footprint centerline lengths.

[0026] 7. The tire replacement estimation system of clause 6, wherein the wear state predictor comprises a scaling module that rescales an initial value of the normalized footprint centerline lengths to a standard value and generates scaled footprint centerline lengths.

[0027] 8. The tire replacement estimation system of clause 7, wherein the wear state predictor comprises an exponentially moving average calculator that generates exponentially weighted footprint centerline lengths from the scaled footprint centerline lengths.

[0028] 9. The tire replacement estimation system of clause 8, wherein the wear state predictor comprises a wear state model that receives the exponentially weighted footprint centerline lengths and generates the estimated wear state of the tire.

[0029] 10. The tire replacement estimation system of clause 9, wherein the wear state model comprises at least one of a classification model and a regression model.

[0030] 11. The tire replacement estimation system of clause 1, wherein the estimation model comprises a time series estimation model.

[0031] 12. The tire replacement estimation system of clause 11, wherein the time series estimation model comprises an exponential smoothing model.

[0032] 13. The tire replacement estimation system of clause 1, further comprising a display device in electronic communication with the processor to receive the estimated tire replacement date.

[0033] 14. The tire replacement estimation system of clause 1, wherein the sensor unit comprises an electronic memory capacity to store identification information of the tire.

[0034] 15. The tire replacement estimation system of clause 1, wherein the sensor unit comprises an antenna to wirelessly transmit measured parameters of tire pressure and centerline length to the processor.

[0035] 16. The tire replacement estimation system of clause 1, wherein the processor is integrated into the sensor unit.

[0036] 17. The tire change estimation system of clause 1, wherein the processor is a remote processor, the remote processor being at least one of a vehicle-based processor and a cloud-based processor.

[0037] 18. A method of estimating a change of a tire supporting a vehicle, the method comprising the steps of:

[0038] installing a sensor unit on the tire;

[0039] measuring a contact patch centerline length of the tire with the sensor unit;

[0040] measuring a pressure of the tire with the sensor unit;

[0041] receiving the measured centerline length and the measured pressure in a processor;

[0042] transmitting selected vehicle parameters from an electronic vehicle network to the processor;

[0043] storing a wear state predictor on the processor;

[0044] receiving the measured centerline length, the measured pressure, and the selected vehicle parameters as inputs into the wear state predictor;

[0045] generating an estimated wear state of the tire from the inputs with the wear state predictor;

[0046] storing an estimation model on the processor;

[0047] receiving a plurality of estimated wear states of the tire as inputs from the wear state predictor into the estimation model;

[0048] predicting a future wear state of the tire with the estimation model; and

[0049] generating an estimated tire change date with the estimation model when the predicted future wear state of the tire exceeds a predetermined wear threshold.

[0050] 19. The method of estimating a change of a tire supporting a vehicle of clause 18, wherein the selected vehicle parameters include a vehicle speed, a lateral acceleration, and a longitudinal acceleration, and the method further comprises the step of comparing the vehicle speed, the lateral acceleration, and the longitudinal acceleration to determine whether the vehicle is cruising with a screening module.

[0051] 20. The method for predicting tire replacement of a supporting vehicle according to technical solution 18, wherein the wear state predictor includes a wear state model, and the wear state model includes at least one of a classification model and a regression model. Attached Figure Description

[0052] The invention will be described by way of example and with reference to the accompanying drawings, wherein:

[0053] Figure 1 This is a schematic perspective view of a vehicle including tires employing an exemplary embodiment of the tire replacement prediction system of the present invention;

[0054] Figure 2 yes Figure 1 The image shows a plan view of the tire tracks in brand new condition;

[0055] Figure 3 yes Figure 1 The image shows a plan view of the tire tracks under wear conditions.

[0056] Figure 4 This is a first schematic diagram of an exemplary embodiment of the tire replacement prediction system of the present invention;

[0057] Figure 5 This is a first graphical representation of an aspect of the tire replacement prediction system of the present invention;

[0058] Figure 6 This is a second graphical representation of an aspect of the tire replacement prediction system of the present invention;

[0059] Figure 7 This is a third graphical representation of an aspect of the tire replacement prediction system of the present invention;

[0060] Figure 8 This is a second schematic diagram of an aspect of the tire replacement prediction system of the present invention;

[0061] Figure 9 This is a fourth graphical representation of an aspect of the tire replacement prediction system of the present invention; and

[0062] Figure 10 It is a representation of data transmission to cloud-based servers and to user devices. Figure 1 A schematic diagram of the vehicle shown.

[0063] In all views, similar numbers refer to similar parts.

[0064] definition

[0065] 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.

[0066] "Axial" and "axially" refer to a line or direction parallel to the axis of rotation of the tire.

[0067] "CAN bus" is an abbreviation for Controller Area Network.

[0068] "Circumferential" refers to a line or direction extending along the perimeter of the surface of the annular tread that is perpendicular to the axial direction.

[0069] "Central Equatorial Plane (CP)" refers to the plane perpendicular to the tire's axis of rotation and passing through the center of the tread.

[0070] "Imprint" refers to the contact mark or contact area formed between the tire tread and the flat surface when the tire rotates or rolls.

[0071] "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.

[0072] "Horizontal" indicates the axial direction.

[0073] "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.

[0074] "Radial" and "radially" refer to directions that are radially toward or away from the axis of rotation of the tire.

[0075] "Tread strip" refers to a circumferentially extending rubber strip on the tire tread that is defined by at least one circumferential tread groove or a second such tread groove or a lateral edge, the strip being not laterally separated by full-depth tread grooves.

[0076] "Tread element" or "traction element" refers to a tread strip or tread block element defined by the shape of adjacent tread grooves. Detailed Implementation

[0077] refer to Figures 1 to 10 An exemplary embodiment of the tire replacement prediction system of the present invention is designated as 10. (See also: Special Reference) Figure 1 System 10 estimates the replacement of each tire 12 supporting vehicle 14. Although vehicle 14 is depicted as a passenger car, the invention is not limited thereto. The principles of the invention are applied to other vehicle categories such as commercial trucks, where the vehicle can be constructed by a combination of components... Figure 1 The tires shown are supported by more or fewer tires.

[0078] The tires 12 have a conventional construction and, as is known to those skilled in the art, each tire is mounted on a respective wheel 16. Each tire 12 includes a pair of sidewalls 18 extending to a circumferential tread 20 that wears over time due to road abrasion. An inner liner 22 is disposed on an inner surface of the tire 12 and, when the tire is mounted on the wheel 16, forms an inner cavity 24 that is filled with a pressurized fluid, such as air.

[0079] The sensor unit 26 is attached to the inner liner 22 of each tire 12 by means such as an adhesive and measures certain parameters or conditions of the tire as will be described in greater detail below. It is understood that the sensor unit 26 can be attached to other components of the tire 12 in this manner, such as on or in one of the sidewalls 18, on or in the tread 20, on the wheel 16, and / or combinations thereof. For convenience, reference will be made herein to the mounting of the sensor unit 26 on the tire 12, it being understood that such mounting includes all such attachments.

[0080] The sensor unit 26 is mounted on each tire 12 for detecting certain real-time tire parameters, such as tire pressure 38 (P) Figure 4 ) and / or tire temperature. To this end, the sensor unit 26 preferably includes a pressure sensor and / or a temperature sensor and can have any known configuration.

[0081] The sensor unit 26 preferably also includes electronic memory capacity for storing identification (ID) information for each tire 12, referred to as tire ID information. Alternatively, the tire ID information can be included in another sensor unit or in a separate tire ID storage medium, such as a tire ID tag, which is preferably in electronic communication with the sensor unit 26. The tire ID information can include tire parameters and / or manufacturing information for each tire 12, such as: tire type; tire model; size information, such as rim size, width, and overall diameter; manufacturing location; manufacturing date; tread face code including or related to compound identification; mold code including or related to tread design identification; tire footprint shape factor (FSF), mold design drop; tire belt / breaker angle; and cap material.

[0082] Turning Figure 2 , the sensor unit 26 (P Figure 1The length 28 of the centerline 30 of the footprint 32 of the tire 12 is also preferably measured. More specifically, when the tire 12 contacts the ground, the area of contact formed by the tread 20 with the ground is referred to as the footprint 32. The centerline 30 of the footprint 32 corresponds to the equatorial center plane of the tire 12, which is a plane perpendicular to the axis of rotation of the tire and passing through the center of the tread 20. Thus, the sensor unit 26 measures the length 28 of the centerline 30 of the tire footprint 32, which is referred to herein as the footprint centerline length 28. The sensor unit 26 can employ any suitable technique for measuring the footprint centerline length 28. For example, the sensor unit 26 can include a strain sensor or a piezoelectric sensor that measures the deformation of the tread 20 and thus indicates the centerline length 28.

[0083] It has been observed that the centerline length 28 decreases as the tire 12 wears. For example, Figure 2 The footprint 32 shown in FIG. 1 A corresponds to a tire 12 in a brand new condition with no tire wear. Figure 3 The footprint of the same tire 12 is shown after traveling about 21,000 kilometers (km) in a worn state or condition. After such travel, the tire 12 has experienced a decrease in the tread depth of about 30 percent (%) as indicated by the worn footprint at 32W, and a decrease in the centerline length of about 6% as indicated by 28W, as compared to the brand new condition shown in FIG. 1 A. Figure 2 The footprint 32 shown in FIG. 1 A corresponds to a tire 12 in a brand new condition with no tire wear.

[0084] Further testing has confirmed this observation, showing that a decrease in the centerline length 28 corresponds to wear of the tire 12, including up to a 20% decrease in the centerline length when the tread depth is reduced 100% or completely to the legal limit. It should be understood that the sensor unit 26 measures the centerline length 28, 28W of the tire 12 at a point in time, and for convenience, any such measurement should be referred to as the centerline length 28.

[0085] It should be understood that the pressure sensor, the temperature sensor, the tire ID capacity, and / or the centerline length sensor can be incorporated into a single sensor unit 26, or can be incorporated into multiple units. For convenience, reference will be made herein to a single sensor unit 26.

[0086] Reference is made to Figure 4The sensor unit 26 includes a transmission device 34 for transmitting the measured parameters of tire pressure 38 and centerline length 28, as well as tire ID information, to a processor 36. The sensor unit transmission device 34 preferably includes an antenna for wireless radio frequency transmission. The processor 36 can be integrated into the sensor unit 26 or can be a remote processor, which can be installed on the vehicle 14 or can be cloud-based. For convenience, the processor 36 will be described as a remote processor installed on the vehicle 14, with the understanding that the processor can alternatively be cloud-based or integrated into the sensor unit 26.

[0087] The vehicle 14 includes an electronic network, referred to in the art as a CAN bus 40. The CAN bus 40 transmits selected vehicle parameters including vehicle speed 42, lateral acceleration 44, and longitudinal acceleration 46 to the processor 36 through a vehicle transmission device 48. The vehicle transmission device 48 preferably includes an antenna for wireless radio frequency transmission. Alternatively, one or more of the vehicle speed 42, lateral acceleration 44, and longitudinal acceleration 46 can be measured by the sensor unit 26 and transmitted to the processor 36 by the sensor unit transmission device 34.

[0088] Aspects of the tire replacement estimation system 10 are preferably executed on the processor 36, which implements the input of data from the sensor unit 26 and / or the CAN bus 40 to execute specific analysis techniques and algorithms, described below, which are stored in a suitable storage medium also in electronic communication with the processor.

[0089] In this manner, the sensor unit 26 measures the tire pressure 38 and centerline length 28 and transmits these measured tire parameters to the processor 36 along with the tire ID information. The vehicle parameters of vehicle speed 42, lateral acceleration 44, and longitudinal acceleration 46 are also transmitted to the processor 36. The wear state predictor 112 is also stored on or in electronic communication with the processor 36. Upon receipt by the processor 36, the activation trigger 50 of the wear state predictor 112 initiates the analysis techniques of the tire replacement estimation system 10.

[0090] The activation trigger 50 initiates a screening module 52, which reviews the vehicle speed 42, lateral acceleration 44, and longitudinal acceleration 46 to determine whether the vehicle 14 is traveling at a constant speed along a generally straight path, referred to as coasting. More specifically, the optimal measured centerline length 28 for the tire replacement estimation system 10 is preferably obtained when the vehicle 14 is coasting. If the vehicle speed 42 varies beyond predetermined minimum and maximum values, if the lateral acceleration 44 exceeds a predetermined threshold, and / or if the longitudinal acceleration 46 exceeds a predetermined threshold, the vehicle 14 is not coasting, and the screening module 52 stops the execution of the tire replacement estimation 54.

[0091] If the vehicle speed 42 is within predetermined minimum and maximum values, if the lateral acceleration 44 is below a predetermined threshold and / or the longitudinal acceleration 46 is below a predetermined threshold, the screening module 52 determines that the vehicle 14 is cruising, and the counter module 56 begins. The counter module 56 ensures that a sufficient sample size of centerline length measurements 28 are collected for analysis by the system 10. The counter 58 counts the centerline length measurements 28 until a predetermined sample size 60 is obtained, such as at least one hundred (100) measurements. When the predetermined sample size 60 is reached, the counter 58 allows for the generation of a wear state estimate, which will be described in detail below.

[0092] If the screening module 52 determines that the vehicle 14 is cruising, the normalization module 62 also begins. With additional reference to Figure 5 , each measured footprint centerline length 28 is affected by changes in the inflation pressure 38 of the tire 12. The normalization module 62 reduces or eliminates the effect of inflation changes on the measured footprint centerline length 28. Preferably, the measured footprint centerline length 28 and the corresponding measured tire pressure 38 are input into the normalization module 62, and a pressure scaling factor 64 is applied. For example, the pressure scaling factor 64 can be the change in the measured footprint centerline length 28 divided by the change in the measured tire pressure 38. When the pressure scaling factor 64 is applied, the measured footprint centerline length 28 is centered around the same mean value across the entire pressure range, enabling the generation of a normalized footprint centerline length 66 and output from the normalization module 62.

[0093] Returning to Figure 4 , the median estimator 68 receives the normalized footprint centerline length 66 and saves it until a predetermined number or sample size 70 of normalized footprint centerline lengths are received. For example, the sample size 70 can be one hundred (100) normalized footprint centerline lengths 66. Once the predetermined sample size 70 is reached, the median estimator calculates a median 72 of the sample of footprint centerline lengths 66. In this way, the median estimator 68 scales the normalized footprint centerline length 66 so that the system 10 takes the relative changes in footprint length, rather than the absolute changes in footprint length. The median normalized footprint centerline length 72 is output from the median estimator 68.

[0094] With additional reference to Figure 6 and Figure 7 , the normalized footprint centerline length 66 and the median normalized footprint centerline length 72 are input into the scaling module 74. As Figure 6 indicated, each respective tire 12 ( Figure 1). The construction variations affect each normalized footprint centerline length 66 and the remaining depth 80 of the tread 20. The scaling module 74 rescales the initial value 76 of the normalized footprint centerline length 66 to a standard value 78, such as 100, as shown in Figure 7 . Thus, the rescaling implemented by the scaling module 74 generates a scaled footprint centerline length 82 that reduces or eliminates the effects of variations in the construction of each respective tire 12.

[0095] Returning to Figure 4 , the scaled footprint centerline length 82 is input into an exponential moving average calculator 84. The exponential moving average calculator 84 enables the wear state predictor 112 to place more weight on the most recently measured footprint centerline lengths 28, and thus the most recent scaled footprint centerline length 82, focusing on the most recent and most relevant data points. The exponential moving average calculator 84 generates an exponentially weighted footprint centerline length 86.

[0096] The exponentially weighted footprint centerline length 86 is input into a wear state model 88 that generates an estimated wear state prediction 90 for each tire 12. The wear state model 88 can be a classification model that represents the estimated wear state 90 as a particular state or class of the tire 12, such as new, semi-worn, or fully worn. Alternatively, the wear state model 88 can be a regression model that represents the estimated wear state 90 as a remaining tread depth of the tire 12 in millimeters or inches.

[0097] Turning to Figure 8 , the estimated wear state 90 from the wear state predictor 112 is input into a forecast model 92. The forecast model 92 is preferably a time series forecasting model, such as an exponential smoothing model. Additionally, the estimated wear state 90 can be represented as an amount of anti-skid tread 20 remaining on each tire 12 in millimeters (mm). The anti-skid tread 20 is referred to in the art as a depth of the tread 20 extending radially inward from a radially outer surface of the tread to a base of the deepest sipe formed in the tread.

[0098] With additional reference to Figure 9 , the forecast model 92 analyzes the plurality of estimated wear states 90 with respect to time 100 and forecasts or predicts a future wear state 94 of the tire 12. When the estimated predicted future wear state 94 exceeds a predetermined wear threshold 96, a forecast tire replacement date 98 is generated.

[0099] With reference to Figure 10 , when the forecast tire replacement date 98 is generated for each tire 12 (i.e., the forecast tire replacement date 98 is generated for each tire 12), Figure 9When the data is transmitted 102, the estimated tire replacement date 98 can be wirelessly transmitted 106 to a display device 108 accessible to a user of the vehicle 14 for display, such as a smartphone, or to a fleet manager. Alternatively, the estimated tire replacement date 98 can be wirelessly transmitted 110 directly from the processor 36 to the display device 108.

[0100] According to the above described structure and method, the tire replacement estimation system 10 of the present application includes a wear state predictor 112 that generates an accurate and reliable estimate of the wear state 90 of each tire 12. The estimated wear state 90 is input into the estimation model 92, which predicts the future wear state 94 of each tire 12 and generates the optimal estimated tire replacement date 98.

[0101] The present application also includes a method of estimating replacement of the tires 12. The method includes the steps described above and illustrated in Figures 1 to 10 .

[0102] It should be understood that the structure and method of the tire replacement estimation system described above can be changed or rearranged, or components or steps omitted or added, without affecting the overall concept or operation of the present application, as would be known to one of ordinary skill in the art. For example, electronic communication can be through a wired connection or wireless communication, without affecting the overall concept or operation of the present application. Such wireless communication includes radio frequency (RF) and Bluetooth® communication.

[0103] The present application has been described with reference to the preferred embodiments. Persons of ordinary skill in the art will readily conceive of potential modifications and variations upon reading and understanding this specification. It is understood that all such modifications and variations are included within the scope of the present application as set forth in the appended claims or their equivalents.

Claims

1. A tire replacement estimation system comprising: a vehicle; a tire supporting the vehicle; a sensor unit mounted on the tire, the sensor unit comprising: a footprint centerline length measurement sensor to measure a centerline length of a footprint of the tire; and a pressure sensor to measure a pressure of the tire; a processor in electronic communication with the sensor unit, the processor receiving the measured centerline length and the measured pressure; an electronic vehicle network to transmit selected vehicle parameters to the processor; a wear state predictor stored on the processor and receiving as inputs the measured centerline length, the measured pressure, and the selected vehicle parameters, the wear state predictor generating an estimated wear state of the tire from the inputs; an estimation model stored on the processor and receiving as inputs a plurality of estimated wear states of the tire from the wear state predictor, the estimation model predicting a future wear state of the tire; and an estimated tire replacement date generated by the estimation model when the predicted future wear state of the tire exceeds a predetermined wear threshold; wherein the wear state predictor comprises a normalization module that applies a pressure scaling factor to the centerline length measurement to generate a normalized footprint centerline length; wherein the wear state predictor comprises a median estimator that receives a plurality of normalized footprint centerline lengths and calculates a median of the normalized footprint centerline lengths; wherein the wear state predictor comprises a scaling module that rescales an initial value of the normalized footprint centerline length to a standard value and generates a scaled footprint centerline length; wherein the wear state predictor comprises an exponential moving average calculator that generates an exponentially weighted footprint centerline length from the scaled footprint centerline length; wherein the wear state predictor comprises a wear state model that receives the exponentially weighted footprint centerline length and generates the estimated wear state of the tire.

2. The tire replacement estimation system according to claim 1, wherein The selected vehicle parameters include a vehicle speed, a lateral acceleration, and a longitudinal acceleration.

3. The tire change estimation system according to claim 2, wherein, The wear state predictor comprises a screening module that compares the vehicle speed, the lateral acceleration, and the longitudinal acceleration to determine whether the vehicle is cruising.

4. The tire replacement estimation system according to claim 1, wherein The wear state predictor comprises a counter module that counts a plurality of centerline length measurements until a predetermined sample size of centerline length measurements is obtained.

5. The tire replacement estimation system according to claim 1, wherein The wear state model comprises at least one of a classification model and a regression model.

6. The tire replacement estimation system according to claim 1, wherein The estimation model comprises a time series estimation model.

7. The tire change estimation system according to claim 6, wherein The time series estimation model comprises an exponential smoothing model.

8. The tire replacement estimation system of claim 1, further comprising a display device in electronic communication with the processor to receive the estimated tire replacement date.

9. The tire change estimation system according to claim 1, wherein, The sensor unit comprises an electronic memory capacity to store identification information of the tire.

10. The tire replacement estimation system according to claim 1, wherein, The sensor unit includes an antenna for wirelessly transmitting measured parameters of tire pressure and centerline length to the processor.

11. The tire change estimation system according to claim 1, wherein, The processor is integrated into the sensor unit.

12. The tire change estimation system according to claim 1, wherein, The processor is a remote processor that is at least one of a vehicle-based processor and a cloud-based processor.

13. A method of estimating replacement of a tire supporting a vehicle, the method comprising the steps of: installing a sensor unit on the tire; measuring, with the sensor unit, a footprint centerline length of the tire; measuring, with the sensor unit, a pressure of the tire; receiving the measured centerline length and the measured pressure in a processor; transmitting selected vehicle parameters from an electronic vehicle network to the processor; storing a wear state predictor on the processor; receiving the measured centerline length, the measured pressure, and the selected vehicle parameters as inputs into the wear state predictor; generating, with the wear state predictor, an estimated wear state of the tire from the inputs; storing a prediction model on the processor; receiving a plurality of estimated wear states of the tire from the wear state predictor as inputs into the prediction model; predicting, with the prediction model, a future wear state of the tire; and generating, with the prediction model, an estimated tire replacement date when the predicted future wear state of the tire exceeds a predetermined wear threshold; wherein the wear state predictor includes a normalization module that applies a pressure scaling factor to the centerline length measurement to generate a normalized footprint centerline length; wherein the wear state predictor includes a median estimator that receives a plurality of normalized footprint centerline lengths and calculates a median of the normalized footprint centerline lengths; wherein the wear state predictor includes a scaling module that rescales an initial value of the normalized footprint centerline length to a standard value and generates a scaled footprint centerline length; wherein the wear state predictor includes an exponential moving average calculator that generates an exponentially weighted footprint centerline length from the scaled footprint centerline length; wherein the wear state predictor includes a wear state model that receives the exponentially weighted footprint centerline length and generates the estimated wear state of the tire.

14. The method of estimating replacement of a tire of a vehicle of claim 13, wherein, The selected vehicle parameters include vehicle speed, lateral acceleration, and longitudinal acceleration, and the method further comprises the step of comparing the vehicle speed, the lateral acceleration, and the longitudinal acceleration with a screening module to determine whether the vehicle is cruising.

15. The method of estimating replacement of a tire of a vehicle of claim 13, wherein, The wear state predictor includes a wear state model that includes at least one of a classification model and a regression model. The selected vehicle parameters include vehicle speed, lateral acceleration, and longitudinal acceleration, and the method further comprises the step of comparing the vehicle speed, the lateral acceleration, and the longitudinal acceleration with a screening module to determine whether the vehicle is cruising. The wear state predictor includes a wear state model that includes at least one of a classification model and a regression model.

Images