Tire wear condition estimation system

Abstract

To provide a comprehensive tire wear state estimation system for providing a more accurate and reliable estimation value of tire wear state.SOLUTION: A tire wear state estimation system includes at least one tire that supports a vehicle. A sensor is mounted on the tire, and measures tire parameters. At least one sensor is mounted on the vehicle, and measures vehicle parameters. Each one of a plurality of sub-models receives tire parameters selected from the tire mounted sensor and vehicle parameters selected from the vehicle mounted sensor. Each one of the plurality of sub-models generates a sub-model wear state estimation value. A model reliability is determined for each one of the plurality of sub-models. A supervisory model receives the wear state estimation value and the model reliability for each one of the sub-models as inputs. The supervisory model generates a combined wear state estimation value for the tire.SELECTED DRAWING: None

Description

[Technical Field]

[0001] The present invention relates generally to tire monitoring systems. More particularly, the present invention relates to systems for predicting tire wear. Specifically, the present invention is directed to a system that estimates the wear state of a tire by employing sub-models and determining an overall wear state from estimates produced by each sub-model. [Background technology]

[0002] Tire wear plays an important role in vehicle factors such as safety, reliability, and performance. Treadwear, which refers to the loss of material from the tread of a tire, directly affects such vehicle factors. As a result, it is desirable to monitor and / or measure the amount of treadwear a tire undergoes. For convenience, the term "treadwear" may be used interchangeably herein with the term "tire wear."

[0003] One approach to monitoring and / or measuring tread wear is through the use of wear sensors placed in the tire tread, referred to as the direct method or approach. The direct approach of measuring tire wear from sensors attached to the tire presents several challenges. Placing sensors in an uncured or "green" tire and curing them at high temperatures can result in damage to the wear sensors. Additionally, sensor durability can prove an issue in meeting the multi-million cycle demands on tires. Furthermore, wear sensors in a direct measurement approach must be small enough to not cause uniformity issues due to the high speed at which the tire rotates. Finally, wear sensors are expensive and can significantly increase the cost of the tire.

[0004] Due to these challenges, alternative approaches have been developed, including predicting tread wear over the life of a tire, which involves indirect estimation of tire wear state. These alternative approaches face certain drawbacks in the prior art due to a lack of optimal prediction techniques, which in turn reduces the accuracy and / or reliability of tread wear predictions.

[0005] Prior art indirect tire wear estimation involves statistical models based on determining specific tire behavior and / or characteristics. For example, indirect wear estimates are based on analyzing a combination of parameters such as tire rolling radius, tire slip, tire frictional energy, tire vibration, tire cornering stiffness, tire braking stiffness, tire contact patch length, as well as tire mileage, weather, and tire construction.

[0006] Each of these techniques provides a particular estimate of tire wear state. However, the reliability of each technique may be affected by changes in external parameters such as weather, vehicle position, road surface and road roughness, as well as changes in tire physical parameters such as tire temperature, vehicle load conditions, etc. Furthermore, any one of these techniques may outperform the others by providing a more accurate and / or reliable estimate of tire wear based on the tire's operating environment and the accompanying changes in external and physical parameters. In the prior art, there was no way to combine or evaluate the results of each separate technique in real time to arrive at an optimal wear state estimate.

[0007] As a result, there is a need in the art for a comprehensive tire wear condition estimation system that provides more accurate and reliable tire wear condition estimates than prior art systems. Summary of the Invention [Means for solving the problem]

[0008] According to one aspect of an exemplary embodiment of the present invention, there is provided a tire wear state estimation system. The system includes at least one tire supporting a vehicle. A sensor is attached to the tire, the sensor attached to the tire measuring a tire parameter. At least one sensor is attached to the vehicle, the sensor attached to the vehicle measuring a vehicle parameter. Each of a plurality of sub-models receives a selected tire parameter from a sensor attached to the tire and a selected vehicle parameter from a sensor attached to the vehicle. Each of the plurality of sub-models generates a respective sub-model wear state estimate. A confidence is determined for each of the plurality of sub-models. A supervisory model receives the sub-model wear state estimate and the confidence for each of the sub-models as inputs. The supervisory model generates a combined wear state estimate for the tire. [Brief explanation of the drawings]

[0009] The invention will now be described, by way of example only, with reference to the accompanying drawings, in which: [Figure 1] 1 is a perspective view of a vehicle used in connection with the tire wear state estimation system of the present invention and a partial cross-sectional view of a tire equipped with a sensor; [Figure 2] FIG. 2 is a schematic plan view of the vehicle shown in FIG. [Figure 3] FIG. 2 is a flow chart showing an embodiment of a sub-model of the tire wear state estimation system of the present invention. [Figure 4] 1 is a schematic diagram of a monitoring model of a first exemplary embodiment of a tire wear state estimation system of the present invention; [Figure 5] FIG. 4 is a schematic diagram of a monitoring model of a second exemplary embodiment of the tire wear state estimation system of the present invention. [Figure 6] FIG. 2 is a schematic perspective view of the vehicle shown in FIG. 1 with an illustration of data transmission to a cloud-based server and a display device.

[0010] Like numbers refer to like parts throughout the drawings.

[0011] (definition) "Axial" and "axially" mean lines or directions parallel to the axis of rotation of the tire.

[0012] "CAN" is an abbreviation for Controller Area Network.

[0013] "Circumferential" means lines or directions extending along the perimeter of the surface of the annular tread perpendicular to the axial direction.

[0014] "Equatorial Center Plane (CP)" means the plane perpendicular to the tire's axis of rotation and passing through the center of its tread.

[0015] "Footprint" means the contact patch or area of ​​contact made by the tire tread on a flat surface as the tire rolls or rotates.

[0016] "GPS" is an abbreviation for Global Positioning System.

[0017] "Inboard side" means the side of the tire nearest the vehicle when the tire is mounted on a wheel and the wheel is mounted on a vehicle.

[0018] "Lateral" means in an axial direction.

[0019] "Net contact area" means the total area of ​​the ground-contacting tread elements between the side edges along the entire circumference of the tread divided by the total area of ​​the entire tread between the side edges.

[0020] "Outboard side" means the side of the tire farthest away from the vehicle when the tire is mounted on a wheel and the wheel is mounted on the vehicle.

[0021] "Radial" and "radially" means directions radially toward or away from the axis of rotation of the tire.

[0022] "Rib" means a circumferentially extending strip of rubber on a tread defined by at least one circumferential groove and either a second such groove or a lateral edge, the strip not being separated laterally by sufficiently deep grooves.

[0023] "TPMS" is an abbreviation for Tire Pressure Monitoring System.

[0024] "Tread element" or "traction element" means a rib or block element defined by a shape having adjacent grooves. DETAILED DESCRIPTION OF THE INVENTION

[0025] The present invention provides a system that provides an indirect estimate of tire wear state using a supervisory model that determines a comprehensive tire wear state from tire wear state estimates produced by different sub-models.

[0026] A first exemplary embodiment of a tire wear condition estimation system of the present invention is designated 10 and is shown in FIGS. 1-4 and 6. With particular reference to FIG. 1, the system 10 estimates tire wear condition for each tire 12 supporting a vehicle 14. Although the vehicle 14 is depicted as a passenger car, the present invention is not so limited. The principles of the present invention apply to other vehicle categories, such as commercial trucks, off-road vehicles, etc., where the vehicle may be supported by more or fewer tires. Furthermore, the present invention applies to a single vehicle 14 or to a fleet of vehicles.

[0027] Each tire 12 includes a pair of bead areas 16 (only one shown) and a bead core (not shown) embedded in each bead area. A pair of sidewalls 18 (only one shown) extend radially outward from the respective bead area 16 to a ground-contacting tread 20. The tire 12 is reinforced by a carcass 22 that extends annularly from one bead area 16 to the other, as known to those skilled in the art. An inner liner 24 is formed on the inside 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 when mounted, forms an interior cavity 28 filled with a pressurized fluid, such as air.

[0028] The sensor unit 30 may be attached to the inner liner 24 of each tire 12 by adhesive or other means to measure a particular parameter of the tire or a particular condition of the tire, as described in more detail below. It should be understood that the sensor unit 30 may be attached in such manner or to other components of the tire 12, i.e., between multiple layers of the carcass 22, on or in one of the sidewalls 18, on or in the tread 20, and / or combinations thereof, etc. For convenience, reference will be made herein to the attachment of the sensor unit 30 to the tire 12, but it should be understood that attachment includes all such attachments.

[0029] A sensor unit 30 is attached to each tire 12 for the purpose of detecting certain real-time tire parameters within the tire, such as tire pressure and temperature. Preferably, the sensor unit 30 is a commercially available type tire pressure monitoring system (TPMS) module or sensor and may be of any known configuration. For convenience, the sensor unit 30 will be referred to as a TPMS sensor. Each TPMS sensor 30 also preferably includes electronic memory capacity for storing identification (ID) information, known as tire ID information, for each tire 12. Alternatively, the tire ID information may be contained in another sensor unit or in a separate tire ID storage medium, such as a tire ID tag 34.

[0030] The tire ID information may include manufacturing information for the tire 12, such as tire type, tire model, rim size, width, and outer diameter, size information, such as location of manufacture, date of manufacture, tread cap code including or correlating to compound identification, and mold code including or correlating to tread structure identification. The tire ID information may also include service history or other information for identifying specific characteristics and parameters of each tire 12, as well as tire mechanical properties such as cornering parameters, spring constant, load-inflation relationship, etc. Such tire identification allows correlation of measured tire parameters with a particular tire 12, providing local or primary tracking of the tire, its current condition, and / or its condition over time. Additionally, global positioning system (GPS) functionality may be included in the TPMS sensor 30 and / or tire ID tag 34 to provide location tracking of the tire 12 during transportation and / or location tracking of the vehicle 14 on which the tire is mounted.

[0031] 2, the TMPS sensor 30 and tire ID tag 34 each include an antenna for wireless transmission 36 of the measured tire temperature as well as tire ID data to a processor 38. The processor 38 may be mounted on the vehicle 14 as shown, or may be integrated into the TPMS sensor 30. For convenience, the processor 38 is described as being mounted on the vehicle 14, but it should be understood that the processor may instead be integrated into the TPMS sensor 30. Preferably, the processor 38 is in electronic communication with or is integrated into an electronic system of the vehicle 14, such as a vehicle CAN bus system 42, also known as a CAN bus.

[0032] An embodiment of the tire wear condition estimation system 10 preferably executes on a processor 38 or other processor accessible via a vehicle CAN bus 42, which allows for input of data from the TMPS sensors 30 and tire ID tags 34, as well as input of data from other sensors in electronic communication with the CAN bus. In this manner, the tire wear condition estimation system 10 preferably allows for measurements of tire temperature and tire pressure using the TPMS sensors 30, which are transmitted to the processor 38. Tire ID information is preferably transmitted from the tire ID tags 34 to the processor 38. The processor 38 preferably correlates the measured tire temperature, measured tire pressure, measurement time, and ID information for each tire 12.

[0033] 4, a first exemplary embodiment of the tire wear state estimation system 10 includes a supervisory model 60. The supervisory model 60 estimates the reliability of multiple submodels or estimators using a reliability score function that calculates a reliability score for each submodel based on external or physical parameters. The estimated reliability of each submodel is combined with the individual tire wear state estimates from each submodel to generate a single combined wear state estimate 62. The preferred supervisory model 60 is a Bayesian network, which is a probabilistic graphical model that represents a set of variables and the conditional dependencies of sets of variables via a directed acyclic graph. Of course, other types of predictive models may be used for the supervisory model 60.

[0034] Sub-models or estimators analyzed by the supervisory model 60 include a rolling radius-based wear state estimator 54, a slippage-based wear state estimator 56, and a friction energy-based wear state estimator 58. Referring to FIG. 3, the exemplary rolling radius-based wear state estimator 54 includes a rolling radius calculator 66 that calculates the change in radius of the tire 12 to generate a rolling radius wear estimate 64. Other sub-models analyzed by the supervisory model 60 include a vibration-based wear state estimator, a cornering stiffness-based wear state estimator, a braking stiffness-based wear state estimator, a contact patch length-based wear state estimator, and a tire wear state estimator based on an analysis of a combination of parameters such as tire mileage, weather, and tire construction.

[0035] In the rolling radius-based wear state estimator 54, tire parameters 68 obtained from the TPMS sensors 30, such as pressure, temperature, and ID, are input to a rolling radius calculator 66. Additionally, vehicle parameters 70 are measured by sensors attached to the vehicle 14 and in electronic communication with the vehicle CAN bus system 42 (FIG. 2). Specifically, the vehicle parameters 70, such as wheel speed, vehicle speed, acceleration, and / or position, are obtained, and the vehicle parameters 70 are input to the rolling radius calculator 66.

[0036] A rolling radius calculator 66 calculates the change in radius of the tire 12 based on tire parameters 68 and vehicle parameters 70, and the change in radius is used by the rolling radius-based wear condition estimator 54 to generate a rolling radius wear estimate 64. Exemplary techniques for determining the rolling radius wear estimate 64 are described in U.S. Patent Nos. 9,663,115, 9,878,721, and 9,719,886, owned by The Goodyear Tire & Rubber Company, the same assignee as the present invention, and incorporated herein by reference.

[0037] The exemplary slippage-based wear state estimator 56 includes a tire slippage calculator 72 that calculates the slippage of the tire 12 to generate a slippage-based wear state estimate 74. In the slippage-based wear state estimator 56, tire parameters 68 obtained from the TPMS sensors 30, such as pressure, temperature, and ID, are input to the tire slippage calculator 72. Additionally, vehicle parameters 70, such as wheel speed, vehicle speed, and / or acceleration, are obtained and input to the tire slippage calculator 72.

[0038] The slippage calculator 72 calculates the slippage of the tire 12 based on the tire parameters 68 and the vehicle parameters 70, and the slippage of the tire 12 is used by the slippage-based wear state estimator 56 to generate a slippage-based wear state estimate 74. Exemplary techniques for determining the slippage-based wear state estimate 74 are described in U.S. Patent Nos. 9,610,810, 9,821,611, and 10,603,962, owned by The Goodyear Tire & Rubber Company, the same assignee as the present invention, and incorporated herein by reference.

[0039] The exemplary friction energy-based wear state estimator 58 includes a tire friction energy calculator 76 that calculates the friction energy of the tire 12 to generate a friction energy-based wear estimate 78. In the friction energy-based wear state estimator 58, tire parameters 68 obtained from the TPMS sensors 30, such as pressure, temperature, and ID, are input to the friction energy calculator 76. Additionally, vehicle parameters 70, such as vehicle inertia and / or position, are obtained and input to the friction energy calculator 76.

[0040] Friction energy calculator 76 calculates the friction energy of tire 12 based on tire parameters 68 and vehicle parameters 70, and the friction energy of tire 12 is used by friction energy-based wear state estimator 58 to generate a friction energy-based wear estimate 78. An exemplary technique for determining friction energy-based wear estimate 78 is described in U.S. Pat. No. 9,873,293, owned by The Goodyear Tire & Rubber Company, the same assignee as the present invention, and incorporated herein by reference.

[0041] As mentioned above, other sub-models may be analyzed by the monitoring model 60. Exemplary techniques for determining a vibration-based wear state estimate are described in U.S. Pat. Nos. 9,259,976 and 9,050,864, owned by The Goodyear Tire & Rubber Company, commonly assigned to the present invention, and U.S. Patent Application Publication Nos. 2018 / 0154707 and 2020 / 0182746, which are incorporated herein by reference. Exemplary techniques for determining a cornering stiffness-based wear state estimate are described in U.S. Pat. No. 9,428,013, owned by The Goodyear Tire & Rubber Company, commonly assigned to the present invention, and which are incorporated herein by reference.

[0042] An exemplary technique for determining a braking stiffness-based wear state estimate is described in U.S. Patent No. 9,442,045, owned by The Goodyear Tire & Rubber Company, the assignee of the present invention, and incorporated herein by reference. An exemplary technique for determining a contact patch length-based wear state estimate is described in U.S. Patent Application Nos. 62 / 893,862, 62 / 893,852, and 62 / 893,860, owned by The Goodyear Tire & Rubber Company, the assignee of the present invention, and incorporated herein by reference. An exemplary technique for determining a tire wear state estimate based on an analysis of a combination of parameters such as tire mileage, weather, and tire construction is described in U.S. Patent Application Publication No. 2018 / 0272813, owned by The Goodyear Tire & Rubber Company, the assignee of the present invention, and incorporated herein by reference.

[0043] Returning to Figure 4, the tire wear state estimation system 10 calculates the reliability of the sub-models or estimators and inputs them into a supervisory model 60 to generate a combined wear state estimate 62. Reference is made here to, by way of example, the rolling radius-based wear state estimator 54, the slippage-based wear state estimator 56, and the friction energy-based wear state estimator 58. In particular, respective model reliability scores 82, 84, and 86 are determined for each of the rolling radius-based wear state estimator 54, the slippage-based wear state estimator 56, and the friction energy-based wear state estimator 58, with each estimator being determined with high precision based on external and physical parameters, referred to as sensitivity parameters.

[0044] For example, the rolling radius model reliability score 82 is determined using a rolling radius reliability score function 88. The rolling radius sensitivity parameters 94 are factors not accounted for in the rolling radius-based wear condition estimator 54 that are known to affect the reliability of the rolling radius wear estimate 64. The sensitivity parameters 94 include the load condition of the vehicle 14, i.e., deviation of the current vehicle load from the nominal vehicle load condition; extremely high or low tire inflation pressure conditions, i.e., deviation of the tire inflation pressure from the nominal inflation pressure range; road grade conditions, i.e., deviation of the slope of the road the vehicle is traveling on from a flat road condition; and GPS conditions, i.e., deviation of the vehicle speed indicated by the vehicle GPS from the undriven wheel speed. These sensitivity parameters 94 are input into the rolling radius reliability score function 88, which scores the parameters using regression techniques, machine learning models, and / or statistical modeling techniques, such as fuzzy logic techniques or functions, to generate the rolling radius model reliability score 82.

[0045] The slippage-based model reliability score 84 is determined using a slippage-based reliability score function 90. Slippage-based sensitivity parameters 96 are factors not accounted for in the slippage-based slip wear state estimator 56 that are known to affect the reliability of the slippage-based wear state estimate 74. The sensitivity parameters 96 include the load condition of the vehicle 14, i.e., deviation of the current vehicle load from the nominal vehicle load condition; extremely high or low tire inflation pressure conditions, i.e., deviation of the tire inflation pressure from the nominal inflation pressure range; GPS conditions, i.e., deviation of the vehicle speed indicated by the vehicle GPS from the undriven wheel speed; ambient temperature of the tire 12; and road surface conditions, i.e., the surface characteristics of the road on which the vehicle is traveling as indicated by the coefficient of friction. These sensitivity parameters 96 are input into the slippage-based reliability score function 90, which scores the parameters using regression techniques, machine learning models, and / or statistical modeling techniques, such as fuzzy logic techniques or functions, to generate the slippage-based model reliability score 84.

[0046] The friction energy-based model reliability score 86 is determined using a friction energy-based reliability score function 92. Friction energy-based sensitivity parameters 98 are factors not accounted for in the friction energy-based wear state estimator 58 that are known to affect the reliability of the friction energy-based wear estimate 78. The sensitivity parameters 98 include the ambient temperature of the tire 12, the road surface condition, i.e., the surface characteristics of the road on which the vehicle 14 is traveling as indicated by the coefficient of friction, and the road roughness condition, i.e., the roughness of the road on which the vehicle is traveling as indicated by the International Roughness Index (IRI). These sensitivity parameters 98 are input into the friction energy-based reliability score function 92, which scores the parameters using regression techniques, machine learning models, and / or statistical modeling techniques, such as fuzzy logic techniques or functions, to generate the friction energy-based model reliability score 86.

[0047] The rolling radius wear estimate 64 generated by the rolling radius based wear state estimator 54 and the rolling radius model reliability score 82 are input into the monitoring model 60. The slippage based wear estimate 74 generated by the slippage based wear state estimator 56 and the slippage based model reliability score 84 are also input into the monitoring model 60. Additionally, the friction energy based wear estimate 78 generated by the friction energy based wear state estimator 58 and the friction energy based model reliability score 86 are input into the monitoring model 60.

[0048] The tire wear state estimation system 10 preferably also includes an estimate of the tire wear state at a past time step 80, which may be referred to as the tire wear state at T-1. As time progresses, the tire 12 continues to wear, so the estimate of the tire wear state at the past time step 80 improves the current estimate of the tire wear state 62. Therefore, the estimate of the tire wear state at the past time step 80 is preferably also input into the monitoring model 60. If an estimate of the tire wear state at the past time step 80 is not available, the mileage 120 of the vehicle 14 can be input into the monitoring model 120 to obtain an estimate of the tire wear state at the past time step.

[0049] Thus, the supervisory model 60 receives as input the rolling radius model wear estimate 64, the rolling radius model confidence score 82, the slippage-based model wear estimate 74, the slippage-based model confidence score 84, the friction energy-based model wear estimate 78, the friction energy-based model confidence score 86, and the estimate of the tire wear state at the past time step 80. The supervisory model 60 then performs statistical inference to determine a probability distribution over the tire wear states and indicates a single most likely combined wear estimate 62. When a Bayesian network is used as the supervisory model 60, the wear estimate 62 is generated by performing Bayesian inference.

[0050] In this manner, the first embodiment of the tire wear state estimation system 10 of the present invention uses a supervisory model 60 to provide an accurate and reliable estimate of tire wear state estimate 62. The supervisory model determines the overall wear state 62 from the estimates produced by the multiple sub-models 54, 56, and 58.

[0051] 1-3 and 5-6, a second exemplary embodiment of a tire wear state estimation system of the present invention is shown at 100. The second embodiment of the tire wear state estimation system 100 is similar in structure and operation to the first embodiment of the tire wear state estimation system 10, except that the rolling radius model reliability score 82 and the slippage-based model reliability score 84 are determined differently in the second embodiment of the tire wear state estimation system. Therefore, only the differences between the second embodiment of the tire wear state estimation system 100 and the first embodiment of the tire wear state estimation system 10 will be described.

[0052] In a second embodiment of the tire wear estimation system 100, the reliability 82 of the rolling radius model is inferred using multiple correlations. For example, the first rolling radius correlation 102 includes correlating the rolling radius of the tire 12 to the distance traveled by the vehicle 14. The second rolling radius correlation 104 includes correlating the Global Positioning System (GPS) speed to the wheel speed of the vehicle 14. The third rolling radius correlation 106 includes correlating the rolling radius of the tire 12 to the vehicle load. The fourth rolling radius correlation 108 is related to the slope of the road on which the vehicle 14 is traveling. These correlations 102, 104, 106, and 108 are used by the supervisory model to infer the reliability 82 of the rolling radius model. When a Bayesian network is used as the supervisory model 60, the reliability 82 is inferred by performing Bayesian inference.

[0053] The reliability 84 of the slippage-based model is also inferred using multiple correlations. A first slippage-based correlation 110 includes a correlation between tire 12 slippage and vehicle 14 mileage. A second slippage-based correlation 112 includes a correlation between Global Positioning System (GPS) speed and vehicle 14 wheel speed. A third slippage-based correlation 114 includes correlating tire 12 slippage to tire temperature. A fourth slippage-based correlation 116 relates to the surface characteristics of the road the vehicle 14 is traveling on. A fifth correlation 118 relates to the roughness of the road the vehicle 14 is traveling on. These correlations 110, 112, 114, 116, and 118 are used by the supervisory model to infer the reliability 84 of the slippage-based model. When a Bayesian network is used as the supervisory model 60, the reliability 84 is inferred by performing Bayesian inference.

[0054] Similar to the first embodiment of the tire wear state estimation system 10, in the second embodiment of the tire wear state estimation system 100, the supervisory model 60 receives as input the rolling radius model wear estimate 64, the rolling radius model reliability 82, the slippage-based model wear state estimate 74, the slippage-based model reliability 84, the friction energy-based model wear estimate 78, the friction energy-based model reliability score 86, and the tire wear state estimate at the past time step 80. The supervisory model 60 then performs statistical inference to determine a probability distribution over the tire wear states, which serves to indicate a single, most likely combined wear estimate 62. If a Bayesian network is used as the supervisory model 60, the wear estimate 62 is generated by performing Bayesian inference.

[0055] In this manner, the second embodiment of the tire wear state estimation system 100 of the present invention provides accurate and reliable estimates of tire wear state estimate 62 using supervisory model 60. Supervisory model 60 determines overall wear state 62 from estimates produced by multiple sub-models 54, 56, and 58.

[0056] 6 , tire parameters 68 for each tire 12 and vehicle parameters 70 for the vehicle 14 may be transmitted wirelessly 40 from a processor 38 on the vehicle and / or a CAN bus 42 to a remote processor 48, such as a processor in a cloud-based server 44. The cloud-based server 44 may implement aspects of the tire wear condition estimation system 10, 100. The tire wear condition estimates 62 are transmitted wirelessly 46 to a device 50, such as a fleet management server or a vehicle operator device, which includes a display 52 for presenting the estimated wear condition to the fleet manager or operator of the vehicle 14.

[0057] The present invention also includes a method for estimating the state of wear 62 of a tire 12. The method includes steps according to the description presented above and shown in Figures 1 to 6.

[0058] It should be understood that the structure and method of the tire wear condition estimation system 10, 100 described above may be modified or rearranged, or components or steps known to those skilled in the art may be omitted or added, without affecting the overall concept or operation of the present invention.

[0059] The present invention has been described with reference to preferred embodiments. Potential modifications and alterations will occur to others upon reading and understanding this description. It is to be understood that all such modifications and alterations are included within the scope of the present invention as defined in the appended claims or equivalents thereof.

Claims

1. A tire wear state estimation system, At least one tire supporting the vehicle; a sensor attached to the at least one tire for measuring a tire parameter; at least one sensor attached to the vehicle for measuring a vehicle parameter; a plurality of sub-models, each sub-model receiving selected tire parameters from a sensor mounted on the tire and selected vehicle parameters from at least one sensor mounted on the vehicle; a plurality of sub-model wear state estimates, each generated by a respective one of the plurality of sub-models; a model reliability determined for each of the plurality of sub-models; a supervisory model that receives as input the plurality of sub-model wear state estimates and the model confidence for each of the plurality of sub-models and generates a combined wear state estimate for the at least one tire; the plurality of sub-models includes a rolling radius based wear state estimator; the model confidence for the rolling radius based wear state estimator is generated by estimating the plurality of correlations; The tire wear state estimation system, wherein the plurality of correlations include at least one of a correlation between the rolling radius of the at least one tire and a distance traveled by the vehicle, a correlation between a global positioning system speed and a wheel speed of the vehicle, a correlation between the rolling radius of the at least one tire and a vehicle load, and a correlation between a gradient of a road on which the vehicle is traveling.

2. 2. The tire wear state estimation system of claim 1, wherein the supervisory model performs Bayesian inference to determine a probability distribution across the plurality of sub-models in generating the combined wear state estimate.

3. 2. The tire wear state estimation system of claim 1, wherein the rolling radius based wear state estimator includes a rolling radius calculator, the rolling radius calculator receiving the selected tire parameters and the selected vehicle parameters to calculate a change in radius of the at least one tire.

4. 2. The tire wear state estimation system of claim 1, wherein the model reliability for the rolling radius-based wear state estimation device includes a rolling radius reliability score function, and the rolling radius reliability score function scores a rolling radius sensitivity parameter to generate the score of the model reliability for the rolling radius-based wear state estimation device.

5. 5. The tire wear state estimation system of claim 4, wherein the rolling radius sensitivity parameters include at least one of a load state, an inflation pressure state, a road gradient state, and a global positioning system state of the vehicle.

6. A tire wear state estimation system, comprising: At least one tire supporting the vehicle; a sensor attached to the at least one tire for measuring a tire parameter; at least one sensor attached to the vehicle for measuring a vehicle parameter; a plurality of sub-models, each sub-model receiving selected tire parameters from a sensor mounted on the tire and selected vehicle parameters from at least one sensor mounted on the vehicle; a plurality of sub-model wear state estimates, each generated by a respective one of the plurality of sub-models; a model reliability determined for each of the plurality of sub-models; a supervisory model that receives as input the plurality of sub-model wear state estimates and the model confidence for each of the plurality of sub-models and generates a combined wear state estimate for the at least one tire; the plurality of sub-models includes a slip-based wear state estimator; The model reliability for the slippage-based wear state estimator is inferred through multiple correlations; The tire wear state estimation system, wherein the plurality of correlations include at least one of a correlation between slippage of the at least one tire and a distance traveled by the vehicle, a correlation between a global positioning system speed and a wheel speed of the vehicle, a correlation between slippage of the at least one tire and a temperature of the at least one tire, a correlation of a surface characteristic of a road on which the vehicle is traveling, and a correlation of a roughness of a road on which the vehicle is traveling.

7. 7. The tire wear state estimation system of claim 6, wherein the slippage-based wear state estimator includes a tire slippage calculator, the tire slippage calculator receiving the selected tire parameters and the selected vehicle parameters to calculate the slippage of the at least one tire.

8. 7. The tire wear state estimation system of claim 6, wherein the model reliability for the slip-based wear state estimation device is calculated through a slip-based reliability score function that scores a slip-based sensitivity parameter.

9. 9. The tire wear state estimation system of claim 8, wherein the slippage-based sensitivity parameters include at least one of a load state of the vehicle, an inflation pressure state, a global positioning system state, an ambient temperature of the at least one tire, and a road surface state.

10. A tire wear state estimation system as described in claim 1 or 6, characterized in that the multiple sub-models include a friction energy-based wear state estimation device.

11. 11. The tire wear state estimation system of claim 10, wherein the friction energy based wear state estimation device includes a friction energy calculator, the friction energy calculator receiving the selected tire parameters and the selected vehicle parameters to calculate the friction energy of the at least one tire.

12. 12. The tire wear state estimation system of claim 11, wherein the model reliability for the friction energy based wear state estimator includes a friction energy based reliability score function, and the friction energy based reliability score function scores friction energy based sensitivity parameters to generate a score of the model reliability of the friction energy based wear state estimator.

13. 13. The tire wear state estimation system of claim 12, wherein the friction energy-based sensitivity parameters include at least one of an ambient temperature of the at least one tire, a road surface condition, and a road roughness condition.

14. A tire wear state estimation system as described in claim 1 or 6, characterized in that the multiple sub-models include at least one of a vibration-based wear state estimation device, a cornering stiffness-based wear state estimation device, a braking stiffness-based wear state estimation device, a contact patch length-based wear state estimation device, and a tire wear state estimation device based on analysis of a combination of parameters including at least one of tire mileage, weather, and tire structure.

15. 10. The tire wear state estimation system of claim 1 or 6, further comprising an estimate of the wear state of the at least one tire at a past time step received as an input to the monitoring model.

Images