Tire load monitoring

Abstract

A computer-implemented method (100) of monitoring a current load (201) on a tire (3) mounted on a vehicle (2), the method (100) comprising: obtaining (e.g., by a server device (7)) sensor readings (23) from one or more tire monitoring system (TMS) sensors (5) mounted on the tire (5); accessing (for example, by the server device (7)) characteristic information (25a) relating to the tire (5); selecting (e.g., by the server device (7)) an appropriate computer model of a plurality of computer models (15) based on the characteristic information (25a); and (e.g., by the server device (7)) using the selected computer model (15) to estimate a current tire load value (201) based on the sensor readings (23).

Description

Technical Field

[0001] The present invention relates to a method for monitoring the current load on a tire mounted on a vehicle. The present invention also relates to a system for monitoring the current load on a tire. Background Art

[0002] Overloading of tires can lead to potential failures that pose a risk of accidents, and loads at incorrect inflation pressures can increase tire strain, thereby reducing carcass durability and causing uneven wear. Overloading of a vehicle can also lead to unstable driving and result in violations of legal regulations.

[0003] Sensors installed inside a tire are commonly referred to as Tire Monitoring System (TMS) sensors. TMS sensors are used to monitor some parameters of the tire itself (such as inflation pressure, internal air temperature, tire rotation time, etc.), and to extract information about the interaction of the tire with its surrounding environment (such as the road or the vehicle).

[0004] Current methods for monitoring tire load use telematics information such as vehicle speed, acceleration, engine RPM, engine load, and shock absorber data. Such methods may be inaccurate and require the collection of a large amount of data, which means that accurate load estimation calculations may take a long time.

[0005] It is known to use acceleration sensors arranged in the tire to measure the amount of deformation (the so-called "contact patch") when the tire contacts the ground.

[0006] There is still a need for a fast and reliable load assessment that can be used to monitor tire usage. Summary of the Invention

[0007] According to a first aspect of the present invention, there is provided a computer-implemented method for monitoring the current load on a tire mounted on a vehicle, the method comprising:

[0008] obtaining sensor readings from one or more Tire Monitoring System (TMS) sensors mounted on the tire (e.g., by a server device);

[0009] accessing characteristic information related to the tire (e.g., by the server device);

[0010] selecting a suitable computer model from a plurality of computer models based on the characteristic information (e.g., by the server device); and

[0011]

[0012]

[0013] (e.g., by the server device) uses the selected computer model to estimate the current tire load value based on the sensor readings.

[0014] It should be understood that the term "current" as used herein means real-time or near real-time, such that monitoring the current load means estimating the load in real-time or with a slight delay. Similarly, the current sensor readings are sensor readings that have been obtained at or near the time of performing the load estimation.

[0015] Those skilled in the art should understand that by selecting a suitable (e.g., customized) model based on the characteristic information, the current sensor readings can be used more effectively to estimate the current tire load. Since there are multiple different models provided and a suitable model is selected based on the tire characteristic information, the model itself does not have to consider the tire characteristic information as a variable. Thus, the selected model can be simpler and therefore have lower computational requirements. This has the additional advantage that the model can run on a device with lower processing power and / or the model can run faster. Clearly, quickly estimating the current tire load is important, especially in the case of overloaded tires, as this can lead to dangerous tire failures. In addition, the reduction of variables within each model makes the estimation of the current tire load more accurate.

[0016] In some embodiments, the characteristic information related to the tire includes one or more of the following: tire manufacturer, tread pattern, tire specification, tire compound, tire stiffness, tire size, tire mounting location, and retread information.

[0017] In some preferred embodiments, the multiple models include separate models that are specifically optimized for known tire products from a given manufacturer. By providing separate models for specific tire products, the complexity of each model is significantly reduced, and thus the model can be used to calculate the current tire load more quickly and accurately while having lower computational requirements.

[0018] In some embodiments, the method includes accessing characteristic information related to the vehicle. In the case of accessing characteristic information related to the vehicle, a suitable model from the multiple models can be selected based on both the characteristic information related to the tire and the characteristic information related to the vehicle.

[0019] In some embodiments, the characteristic information related to the vehicle includes one or more of the following: vehicle manufacturer, chassis type of the vehicle, vehicle usage, number of axles, product type, number of tires, number of tires mounted per axle.

[0020] Such vehicle characteristic information can help improve the accuracy of load estimation. Vehicle usage can be defined as a driving profile for each road type, which can include any information derivable from the amount of driving performed on each road type. For example, the driving profile for each road type can include a breakdown of each road type and the distance driven on each road type. It can also optionally include the average time driven on each road type for a particular vehicle or vehicle type. Additionally, it can optionally include the percentage of driving on each road type based on distance and / or time. For example, it may be known that 60% of the total vehicle distance is driven on highways, 20% is driven on suburban roads, and 10% is performed on city roads.

[0021] Product type can be defined as a specific vehicle product from a given manufacturer.

[0022] In some embodiments, the plurality of models includes individual models specifically optimized for known tire products from a given manufacturer that are assembled on known vehicle products from the given manufacturer.

[0023] In some embodiments, each model in the plurality of models is a fitting algorithm developed by studying the correlation between each parameter from the sensor readings and the tire load of a tire (and optionally also the vehicle) with certain characteristic information.

[0024] In some embodiments, the method includes obtaining current telematics information from the vehicle. In such embodiments, the telematics information can include one or more of the following: GPS location, vehicle speed, vehicle lateral / longitudinal acceleration, type of road, engine load, gear shift, engine RPM, wheel speed, throttle / brake pedal position, tire temperature, external temperature, and / or steering wheel angle.

[0025] In some embodiments, the method includes using the current telematics information to detect favorable load measurement conditions and obtaining the TMS sensor readings when favorable load measurement conditions are detected. One or more of engine load information, throttle input, brake input, steering input, lateral vehicle acceleration, and longitudinal vehicle acceleration can be used to detect favorable load measurement conditions. The load on the tire will change due to the dynamic movement of the vehicle. For example, the front tire load will increase during braking. By detecting favorable load measurement conditions, the likelihood of an abnormal load estimate can be reduced.

[0026] In some embodiments, the sensor readings include one or more of the following: radial acceleration values, inflation pressure, and internal air temperature. For example, the one or more tire monitoring system (TMS) sensors mounted on the tire may include an acceleration sensor and / or a pressure sensor and / or a temperature sensor.

[0027] It is now understood that radial acceleration values can be particularly useful for load estimation because they provide an accurate measurement of tire rolling dynamics. The method can be used in conjunction with more traditional pressure and / or temperature sensor readings, or alone. Thus, in some embodiments, the method further includes: obtaining sensor readings that include radial acceleration values; analyzing the radial acceleration values to calculate one or more tire parameters selected from the following: tire contact patch length, tire wear estimation, tire rotation time (t_rev), automatic mounting position location, and tire mileage estimation; and using the selected model to estimate the current tire load value based on the sensor readings and one or more of the tire parameters. The tire contact patch length can be defined as the total amount of time (t_patch) that a single portion of the tire remains in the contact patch, or can be defined as a contact patch ratio, which is the ratio between the total amount of time (t_patch) that a single portion of the tire remains in the contact patch and the total tire rotation time (t_rev). The automatic mounting position location can be defined as locating the position of the tire on the axle / chassis (e.g., left side, front axle).

[0028] In some embodiments, the method includes providing feedback to the user related to the current tire load value. In some embodiments, the feedback is provided in real time.

[0029] In some embodiments, the feedback includes one or more of the following: a notification of exceeding the tire load index, a notification that the tire is operating at an incorrect inflation pressure for the current load, a notification that the vehicle has exceeded its maximum load capacity, and a notification that the vehicle has an unbalanced weight distribution on its tires. Advance notification of load problems can allow the user (who can be a driver or a fleet manager) to take action to correct the problem, thereby reducing the likelihood of failures such as tire blowouts.

[0030] In some embodiments, the model is used to detect the current tire load based on the sensor readings and the telematics information. Utilizing both TMS sensor readings and telematics information increases the amount of data input into the model, which can result in more accurate load estimation.

[0031] In some preferred embodiments, the sensor readings include inflation pressure and radial acceleration values, wherein the radial acceleration values are analyzed (e.g., by the TMS sensor) to provide information related to the tire contact patch length and the tire rotation time (t_rev), and wherein the characteristic information related to the tire includes tire compound or tire stiffness and tire size. Although the radial acceleration and the inflation pressure are raw sensor readings, the raw values measured for the radial acceleration can be used to calculate the footprint length and the tire rotation time (t_rev). In an embodiment, the rotation time can be measured directly. In an embodiment, the rotation time (t_rev) (whether measured directly or calculated using the radial acceleration value) can be used to calculate the tangential speed of the tire using the tire radius. The inflation pressure can be a non-normalized pressure reading or a normalized pressure reading, where the normalized pressure reading is the internal air pressure divided by the internal temperature.

[0032] In an embodiment, the method includes estimating the tire contact patch length and the tire rotation time (t_rev) by evaluating peaks that occur in a waveform that is obtained by differentiating a time series waveform of the tire radial acceleration detected by an acceleration sensor mounted on the tire. Such techniques are known from WO2020071249A1, which is hereby incorporated by reference.

[0033] In some embodiments, according to the radial acceleration value is used to calculate the tangential tire speed v, where a is the radial acceleration and r is the tire radius.

[0034] In other embodiments, according to the tire rotation time (t_rev) is used to calculate the tangential tire speed v, where r is the tire radius and t_rev is the tire rotation time. In other embodiments, the sensor readings can include readings from a wheel speed sensor. This means that the wheel speed (and thus the tangential tire speed) can be measured directly.

[0035] In some embodiments, the characteristic information related to the tire includes tire compound or tire stiffness and tire size.

[0036] In some embodiments, the method includes suggesting an action to the user, optionally where the action is load rebalancing and / or pressure regulation.

[0037] In some embodiments, the current load tire value is calculated only once during a trip made by the vehicle. Since it is unlikely that the vehicle will be loaded or unloaded while in motion, the load on the tires is unlikely to change significantly during the trip. By reducing the load estimation to once per trip, energy can be saved, which is particularly beneficial when using battery-powered TMS sensors.

[0038] In some embodiments, the method includes using TMS data and / or telematics data from the one or more tire monitoring system (TMS) sensors to detect the start of a trip and estimating the current tire load value in response to detecting the start of the trip.

[0039] In some embodiments, the start of a trip is detected by determining the presence of a non-zero radial acceleration reading in the TMS data after an inactive period.

[0040] In an embodiment, the length of the inactive period is compared to a threshold, and if the time exceeds the threshold, a new trip start is determined.

[0041] By comparing the period with a threshold, for example, after the vehicle starts moving after a short stop at a traffic light, the possibility of false detection of the start of a trip is reduced.

[0042] In a preferred set of embodiments, a time history set of the GPS location of the vehicle is collected from the telematics data, and the start of a trip is determined based on a change in the GPS location after a stationary period. In an embodiment, the time the vehicle is stationary is compared to a threshold, and if the time exceeds the threshold, a new trip start is determined.

[0043] By comparing the time the vehicle is stationary with a threshold, for example, after the vehicle starts moving after a short stop at a traffic light, the possibility of false detection of the start of a trip is reduced.

[0044] In other embodiments, the start of a trip can be detected by identifying an "ignition on" signal from the telematics data.

[0045] In an embodiment, after detecting the start of a trip, the method includes periodically acquiring data of a predetermined number of tire rotations within a fixed period after the detection of the start of the trip. The data acquisition can start immediately upon detecting the start of the trip, or start shortly after detecting the start of the trip, for example, immediately when the best load estimation conditions are detected after the detection of the start of the trip.

[0046] In some embodiments, the current load tire value is calculated at fixed time intervals or at fixed travel distance intervals. This can reduce energy consumption by reducing the number of load estimations performed. Thus, the methods described herein can be repeated at fixed time intervals or at fixed travel distance intervals.

[0047] In some embodiments, the method includes storing the estimated current tire load value. The estimated current tire load value can be stored on a server, or on a user output device, or on another device.

[0048] In some embodiments, the method includes collecting the estimated current tire load values for a given tire over a period of time (e.g., the service life of the tire installed on a particular vehicle).

[0049] In some embodiments, the method includes outputting tire usage data that indicates the current load on the tire over time during the period. Such output can allow a user (such as a fleet manager or a tire manufacturer) to see if the tire is routinely overloaded and thus understand the impact on the life of the tire.

[0050] In some embodiments, each of the plurality of models is pre-trained based on historical data obtained for tires and / or vehicles having the characteristic information. This means that each model has been optimized to relate the characteristic information to the observed tire load measurements (e.g., linearly and / or non-linearly). Such modeling can be based on, for example, linear regression, random forests, support vector regressors, neural networks, or any combination thereof.

[0051] According to a second aspect of the invention, there is provided a computer-implemented method of monitoring the current load on a vehicle by:

[0052] applying the method described herein (according to any embodiment of the first aspect) to each tire installed on the vehicle;

[0053] accessing information related to the arrangement of the tires on each axle of the vehicle (e.g., vehicle characteristic information); and

[0054] calculating the total vehicle load or the load per axle.

[0055] It should be understood that, where applicable, this aspect may include (and preferably does include) one or more (e.g., all) of the preferred and optional features disclosed herein, e.g., the preferred and optional features related to other aspects and embodiments of the invention.

[0056] According to a third aspect of the present invention, there is provided a system for monitoring the current load on a tire, the system being configured to perform the method according to the first aspect, the system comprising:

[0057] One or more TMS sensors mounted on the tire and configured to obtain sensor readings;

[0058] A processor configured to process the sensor readings; and

[0059] A memory configured to store the sensor readings and / or parameters based on the sensor readings.

[0060] It should be understood that, where applicable, this aspect may include (and preferably does include) one or more (e.g., all) of the preferred and optional features disclosed herein, e.g., the preferred and optional features related to other aspects and embodiments of the present invention.

[0061] In some embodiments, the processor is embodied as a tire-mounted processor, e.g., in the same tire-mounted device as the one or more TMS sensors. In some embodiments, the processor is included in a receiver of the sensor readings, e.g., a receiver mounted in the vehicle, such as a suitable network communication device (e.g., a dongle). In some embodiments, the processor is embodied as a server remote from the vehicle, e.g., a cloud server. In some embodiments, the sensor readings are processed (e.g., analyzed) by one or more of these processors.

[0062] In some embodiments, the system includes one or more user output devices for displaying to the user an estimated tire load value and / or a notified and / or recommended action. The above description applies equally to such a system.

[0063] In some embodiments, at least one of the tire monitoring system (TMS) sensors mounted on the tire is an acceleration sensor, preferably a radial acceleration sensor. The sensor readings may include radial acceleration readings (e.g., waveforms) as radial acceleration values.

[0064] In some embodiments, at least one of the tire monitoring system (TMS) sensors mounted on the tire is an air pressure sensor, which is preferably mounted inside the tire to measure the internal air pressure.

[0065] In some embodiments, at least one tire monitoring system (TMS) sensor mounted on the tire is an air temperature sensor, which is preferably mounted inside the tire to measure the internal air temperature.

[0066] In some embodiments, each sensor (or set of sensors) is disposed on the inner surface of the tire, for example, attached to the surface of the liner facing the tread portion or disposed on the inner surface on the sidewall side of the tire. However, the sensor does not necessarily have to be attached to the inner surface of the tire, and for example, part or all of the sensor may be embedded inside the tire.

[0067] In at least some embodiments, the one or more tire monitoring system (TMS) sensors mounted on the tire include: a transmitter for transmitting the sensor readings; optionally a processor configured to preprocess the sensor readings; and a battery for powering the transmitter at regular detection intervals (e.g., 10 s, 30 s, 60 s, etc.).

[0068] Of course, it should be understood that the term "server" as used herein means a computer or machine (e.g., a server device) connected to a network such that the server transmits data to and / or receives data from other devices (e.g., computers or other machines) on the network. Additionally or alternatively, the server may provide resources and / or services to other devices on the network. The network may be the Internet or some other suitable network. The server may be embodied in any suitable server type or server device, e.g., a file server, an application server, a communication server, a computing server, a web server, a proxy server, etc. The server may be a single computing device or may be a distributed system, i.e., the server functionality may be divided across multiple computing devices. For example, the server may be a cloud-based server, i.e., its functionality may be split "on demand" across many computers. In such an arrangement, server resources may be obtained from one or more data centers, which may be located in different physical locations.

[0069] Accordingly, it should be understood that the processes described above performed by the server may be performed by a single computing device (i.e., a single server) or by multiple separate computing devices (i.e., multiple servers). For example, all of the processes in the process may be performed by a single server that has access to all of the relevant information required. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] One or more non-limiting examples will now be described by way of example only and with reference to the drawings, in which:

[0071] Figure 1 Shows a schematic diagram of a load monitoring system installed on a heavy truck;

[0072] Figure 2 Is a schematic diagram of the load monitoring system;

[0073] Figure 3 Is a flowchart illustrating a load monitoring method;

[0074] Figure 4 Is a 3D graph showing the correlation between pressure, load, and the ground contact surface;

[0075] Figure 5 Illustrates in more detail Figure 3 Part of the method flowchart;

[0076] Figure 6 Illustrates Figure 5 A flowchart of an alternative method of the method shown;

[0077] Figure 7 Shows a scatter plot of predicted load (using a model according to an embodiment of the present invention) versus actual load;

[0078] Figure 8 Is a histogram showing the distribution of variable "actual load - predicted load";

[0079] Figure 9 Shows the output provided to the user. Detailed Description

[0080] In the drawings, it should be understood that the features and method steps shown in dashed lines are optional and can be freely omitted in embodiments of the present invention.

[0081] Figure 1 Shows a system 1 for monitoring the load on a plurality of vehicle tires 3 installed on a vehicle 2. The system 1 includes: a plurality of tire monitoring system (TMS) sensors 5, each tire monitoring system (TMS) sensor being installed inside a tire 3; and a network communication device 6, which is disposed in the vehicle 2. In an embodiment, the network communication device 6 can be a dongle that is inserted into a port of the vehicle 2 (such as, an OBD port, an FMS port, or other ports). In an alternative embodiment, the network communication device 6 can be a permanently installed transceiver box. The TMS sensors 5 are configured to communicate with a remote server 7 via the network communication device 6 in the vehicle 2. The remote server 7 can include an online database / cloud / platform. In this example, the TMS sensors 5 communicate via Connects to communicate with the network communication device 6. However, it should be understood that any suitable form of short-range wireless communication or wired connection can be used. The network communication device 6 is networked and communicates with the remote server 7 via a wireless network connection (e.g., a cellular network). The remote server 7 is connected to the user output device 10 via a wireless network connection. In the illustrated embodiment, a plurality of user output devices 10 are provided: a user terminal 10a, which is disposed inside the passenger compartment of the vehicle 2; a user mobile device 10b, which can be carried by the user; and a computer 10c of the fleet manager.

[0082] Figure 2 is a schematic diagram showing the input of the model 15 implemented by the remote server 7. First, the characteristic information 25 is received from the memory 11, and the characteristic information includes the tire-related characteristic information 25a and optionally the vehicle-related characteristic information 25b. In an embodiment, the memory 11 can be implemented at the remote server 7 itself. Alternatively, the memory can be included in the TMS sensor 5, the network communication device 6, or another server (not shown) that is operatively connected to the remote server 7. Since the model is constructed and trained to be used with a specific tire product, the characteristic information 25a is used to select the model 15 from the plurality of models 14. This will be explained later in conjunction with Figure 3 which will be explained. Then, the selected model 15 receives the input data. The TMS information 23 is obtained from the plurality of TMS sensors 5 installed in the tires 3 of the vehicle 2 and input into the selected model 15. In this embodiment, the telematics information 21 is received from the vehicle 2 and optionally also input into the selected model 15, as shown by the dashed arrow in Figure 2 Inputting the telematics information 21 and the TMS information 23 into the selected model 15 can improve the accuracy of the model 15. The telematics information 21 can be obtained by the sensors on the vehicle 2 in any known manner.

[0083] Now, the operation of the system 1 will be explained with reference to the flowchart of Figure 3 showing the load monitoring method 100.

[0084] Steps 101 to 107 outline a process for monitoring the load on a single tire 3 on a vehicle 2. At step 101, sensor readings are obtained from a TMS sensor 5 mounted on the tire. Each sensor 5 acquires data on n tire rotations every m seconds at the start of each trip for a number of minutes. In an embodiment, each sensor 5 may acquire data on 10 tire rotations every 15 seconds after the start of the trip for 5 minutes. The sensor readings 23 include radial acceleration, inflation pressure, estimated contact patch length, and tire rotation time (t_rev) / tangential tire speed. The radial acceleration readings are in two forms. First, the raw radial acceleration readings. These readings are used to generate a waveform (acceleration plotted over time) from which the contact patch length can be estimated. Second, the average radial acceleration is calculated, which only considers the acceleration readings taken outside the contact patch. This average radial acceleration can be used to estimate the tangential tire speed. Although these estimates are not direct measurements, as is known, the estimation calculations are performed by a processor in the TMS sensor 5 itself and are thus still considered sensor readings received from the TMS sensor. The contact patch length is estimated by evaluating the peaks that occur in the waveform, which is obtained by differentiating the time series waveform of the tire radial acceleration detected by an acceleration sensor mounted on the tire. Such techniques are known from WO2020071249A1, which is incorporated herein by reference. The tire contact patch length is then estimated as the ratio between the contact patch time and the rotation time. At the same time, the tangential tire speed can be calculated according to Equation 1:

[0085]

[0086] where v is the tangential tire speed, a is the average radial acceleration outside the contact patch, and r is the radius of the tire. In other embodiments, according to the tire rotation time is used to calculate the tangential tire speed v, where r is the tire radius and t_rev is the tire rotation time. The processing steps for estimating the contact patch length and the tangential tire speed can be performed at the TMS sensor 5, or in the vehicle 2, or at a network communication device 6, or at a remote server 7. As explained with respect to Figure 1 and Figure 2 the TMS information 23 is transmitted via a short-range wireless connection (such as, ) to a network communication device 6 in the vehicle 2 and then via the network to a remote server 7, where the TMS information 23 is input into a model 15. The TMS information 23 may additionally include one or more of internal air temperature, wear estimate, automatic mounting position location, and tire mileage estimate.

[0087] At step 103, characteristic information 25 is accessed from memory 11. The characteristic information includes one or both of vehicle characteristic information 25b and tire characteristic information 25a. The tire characteristic information 25a may include one or more of tire manufacturer, tread pattern, specification, size, mounting location, retread information, and additional remaining tread depth (RTD) measured during a tire inspection. In a preferred embodiment, the tire characteristic information 25a may correspond to a specific tire product from a specific manufacturer. The vehicle characteristic information 25b may include one or more of vehicle manufacturer, chassis (number of tires / axles), vehicle usage, and towing vehicle load.

[0088] At step 105, one of the plurality of pre-trained models 14 is selected based on the characteristic information 25. The model 15 includes an algorithm that has been pre-trained based on historical data. The historical data includes data from three sources:

[0089] ● Indoor test devices

[0090] ○ A drum or similar device capable of simulating tire behavior under different speed, pressure, and load conditions

[0091] ● Outdoor tests

[0092] ○ Testing a vehicle in a controlled environment (such as a test track) or on a public road, where the vehicle operates under specific tire and vehicle conditions.

[0093] ○ During outdoor testing, load variations can be applied by vehicle weighing or by using a dedicated vehicle capable of applying variable tire loads / forces.

[0094] ● Test fleets

[0095] ○ Vehicles on public roads under uncontrolled conditions, where the vehicle / tire conditions may be unknown or may be only partially known.

[0096] Since vehicle characteristic information 25b and tire characteristic information 25a may have a significant impact on the monitoring of tire loads, separate models are provided for different vehicle and / or tire characteristics. This is because a model that can handle all vehicle and tire characteristics may be limited by computational requirements. In a preferred embodiment, a separate model 15 is constructed for each tire product based on the characteristic information 25a associated with that tire. These models 15 are vehicle-independent and will thus be applicable to any vehicle on which the tire product can be installed. This improves model accuracy and reduces the complexity of model 15, such that although the construction of many separate models may be more demanding than constructing a single model, the simpler models are more suitable for implementation on devices with limited processing capabilities, such as the TMS sensor device 5 or the network communication device 6 within the vehicle 2. In a preferred embodiment, the tire rubber compound and stiffness, as well as the tire size (both of which vary between tire products), are used as the tire characteristic information 25a on which the model selection is based.

[0097] At step 107, the TMS information 23 is input into the selected model 15. The model 15 correlates the input TMS information with the characteristic information to determine the load on the tire 3. This correlation can be linear or non-linear. The algorithms used to create the model 15 are linear regression, random forest, support vector regressor, neural network, or an ensemble of all of the above or an ensemble of subsets of the above. During the training phase of the model 15, historical data is analyzed to study the correlation between each parameter from the TMS data 23 and the tire load for each specific tire product. Based on this correlation, a fitted model 15 can be created for that specific tire product.

[0098] Figure 4 A 3D scatter plot created using historical (training) data is shown. The plot shows the load plotted against pressure and contact area ratio. This specific training data includes measurements taken at three different pressures and thus includes three different lines in the data. However, it can clearly be seen that there is a correlation between these three variables, and thus, any known correlation algorithm can be used to generate a best-fit plane based on the plotted training data. This best-fit plane represents the model 15, which can then be used to estimate the load if the contact area and pressure are known.

[0099] A cross-validation procedure with multiple folds is used to optimize the model 15. The historical data is divided into multiple sub-datasets (folds), and different combinations of model variations and historical data are tested sequentially to determine which model variation is best for solving the problem. Thus, the model 15 is optimized around the best model variation.

[0100] Figure 3 Steps 101 to 107 relate to the load estimation itself, butFigure 3 It also includes other steps related to evaluating when to perform load estimation. At step 111, "start of a trip" is detected. Regarding Figure 5 and Figure 6 The method for detecting the start of a trip will be discussed in more detail. The purpose of the present invention is to monitor the current tire load and also provide feedback to the user regarding the current tire / vehicle load conditions. However, since most TMS sensors are battery-powered, it is beneficial to minimize the number of transmissions by the TMS in order to reduce data costs and maximize the battery life of the TMS sensors. One possible solution to achieve these two goals is to reduce the number of load detection calculations to at most once per vehicle trip in order to detect possible weight changes. This solution operates based on the following assumption: the load is unlikely to change during a trip because the most likely causes of load change are the addition, removal, or movement of cargo, for which the vehicle 2 needs to stop. By implementing a trip start detection procedure at step 111, the start of a new trip can be detected. Since a new trip has started, the load conditions may have changed between trips, and therefore, in response to the trip start detection, an updated tire load needs to be detected. As Figure 3 shown, once the start of a trip has been detected, method 100 can proceed directly to step 101 to start load estimation. However, alternatively, method 100 can proceed to step 113, as explained below.

[0101] In an embodiment, the number of TMS transmissions can be controlled by performing data measurements at fixed time / distance intervals during a trip. Such embodiments can be implemented alone or in combination with the detection of the start of a trip.

[0102] The load on the vehicle tires 3 is affected by changing dynamic conditions during a trip due to weight transfer. For example, when the vehicle 2 brakes, the tires 3 at the front of the vehicle 2 experience an increased load, while the tires 3 at the rear of the vehicle 2 experience a decreased load. Similarly, when the vehicle 2 accelerates, the tires 3 at the rear of the vehicle 2 experience an increased load, while the tires 3 at the front of the vehicle 2 experience a decreased load. The same is true for lateral acceleration. When the vehicle 2 turns, the tires 3 on the outside of the turn will experience a greater load than the tires 3 on the inside of the turn. Clearly, the load calculated based on the TMS sensor readings obtained during such load transfer events will not have high accuracy, and therefore, in order to improve the accuracy of the load monitoring method 100, it is beneficial to detect favorable conditions for load monitoring evaluation. This can be done by obtaining telematics data at step 113 and analyzing the telematics data at step 115 to determine whether the current dynamic conditions are favorable for load monitoring evaluation.

[0103] The telematics data 21 is obtained by sensors in the vehicle 2 and collected by a network communication device 6 connected to an OBD, FMS, or similar port of the vehicle 2. In the illustrated embodiment, a single network communication device 6 is provided that communicates with all of the TMS sensors 5, but it should be understood that there may be multiple network communication devices 6. For example, in a large vehicle where the range of the wireless signals from the TMS sensors 5 is not sufficient to bring all of the TMS sensors 5 within the range of a single network communication device 6, multiple network communication devices 6 may be required. The telematics information 21 may include one or more of the following: acceleration, speed, GPS coordinates, type of road, engine load, gear shift, engine RPM, wheel speed, throttle / brake, pedal position, tire temperature, external temperature, and steering wheel angle.

[0104] For example, the vehicle longitudinal and lateral accelerations may each be compared with a threshold value, and if the vehicle acceleration is below that value, it is determined that the condition is favorable for load monitoring evaluation. When the vehicle is stationary or traveling in a straight line at a constant speed (such as on a highway), there may be optimal dynamic conditions for load monitoring evaluation. At step 115, if it is determined that the condition is favorable for load monitoring estimation, method 100 proceeds to step 101. If the condition is unfavorable, method 100 returns to step 113 and updated telematics data 21 is obtained.

[0105] In the illustrated embodiment, the network communication device 6 streams the telematics data 21 to a remote server 7.

[0106] It should be understood that steps 111, 113, and 115 are not inextricably linked, and the method according to the present invention may detect the start of a trip without analyzing the dynamic conditions, and similarly may analyze the dynamic conditions without first detecting the start of a trip.

[0107] In an embodiment, the dynamic conditions may be evaluated in other ways that do not require the use of the telematics data 21. For example, in an embodiment, the TMS information 23 may be used to determine favorable conditions. In such an embodiment, a relatively constant value in the radial wheel acceleration readings may indicate a constant speed and thus a favorable condition. Alternatively, multiple load monitoring estimations may be performed and then analyzed. A large change in the estimated load over a short period of time may indicate unfavorable conditions, and such results should therefore be ignored.

[0108] Method 100, as described with respect to steps 101 to 103, estimates the current load on a single tire. In an embodiment, it may be useful to calculate the load on the entire vehicle, as overloading the vehicle may cause unstable driving and / or result in a violation of legal regulations.

[0109] At step 117, steps 101 to 107 are repeated for each tire on vehicle 2 to obtain a current load estimate for each tire 3. Although Figure 3 presented as a flowchart, it should be understood that steps 101 to 107 will be performed simultaneously for each tire 3. Since the load values are intended to indicate the current load, the load value assessment for each tire 3 should be temporally consistent. Each tire 3 will be equipped with at least one TMS sensor 5. Each TMS sensor 5 will communicate with the same network communication device 6.

[0110] At step 119, the current total vehicle load can be calculated simply by summing the individual tire load values for each tire 3 on vehicle 2. To perform this summation, the vehicle configuration must be known, specifically the number of axles and the number of tires 3. If the number of tires 3 per axle is known, the axle load per axle can also be calculated in the same way according to formula 2.

[0111]

[0112] where w i is the individual tire load and N is the number of tires on the axle or on the vehicle, depending on whether calculating the total axle load or the total vehicle load.

[0113] The vehicle configuration is included in the vehicle characteristic information 25b, which is obtained from the memory 11, as explained with respect to Figure 2 as explained.

[0114] At step 109, the load values are transmitted to the output device 10 for display to the user. As discussed with respect to Figure 1 as discussed, the output device 10 can be the in-vehicle user terminal 10a, the user's mobile device 10b, and / or the fleet manager's computer 10c. Since the method 100 of the present invention is designed to monitor the current tire load, it is advantageous to provide feedback in real time. In a simpler embodiment, only the raw load values (tire load values or total vehicle load values or both) can be displayed to the user. However, in an embodiment, the load values can be analyzed and specific warnings can be provided to the user. For example, when the tire load index is exceeded, or the tire is operating at an incorrect inflation pressure for the current load, or the vehicle exceeds its maximum load capacity, or the vehicle has an unbalanced weight distribution (left / right and / or between axles), the user can be notified. This analysis can be performed in the TMS sensor 5, the vehicle 2, the network communication device 6, the remote server 7, or the output device 10. Specifically, this analysis can be performed by an application installed on the user's mobile device 10b.

[0115] Figure 5 illustrates an example in Figure 3Flowchart of a method for detecting the start of a journey in step 111 of method 100. At step 121, a set of time histories of the GPS positions of vehicle 2 is collected from telematics information 21. However, it should be understood that the GPS information can come from any suitable source. The GPS information can come from a GPS sensor integral with vehicle 2, or the network communication device 6 can include a GPS sensor, or a separate GPS sensor can be provided in vehicle 2. At step 123, the GPS coordinate numerical resolution is reduced to a certain spatial accuracy. This reduction can be performed by truncation, rounding, or similar methods. In an embodiment, the resolution can be 100 m.

[0116] At step 125, the moment of change of the GPS position is identified, and the time difference between this moment and the minimum time of the previous GPS coordinates is calculated. It should be understood that the minimum time of the previous GPS coordinates is the first time at which the GPS coordinates were recorded, and thus the time difference between the first moment at which the GPS coordinates were recorded and the moment of change of the GPS coordinates is equal to the amount of time that vehicle 2 has been stationary. At step 127, this time difference (i.e., the time that vehicle 2 has been stationary) is compared with a predetermined threshold, and if the time does exceed the threshold, a new journey event is triggered at step 139. If the time is below the threshold, the method is restarted.

[0117] The threshold is set as a trade-off between the need to reduce the likelihood of a new journey event being falsely triggered and the need to ensure that a new journey event is not missed. For example, a threshold set too low may cause a new journey event to be triggered after vehicle 2 has stopped at a traffic light or in traffic congestion. At the same time, the threshold cannot be set too high so as not to potentially miss a stop that is long enough that the vehicle load conditions have changed, e.g., a stop at a warehouse where goods have been added to vehicle 2. In an embodiment, the predefined threshold is set to 10 minutes.

[0118] At step 123, the accuracy of the spatial coordinates is reduced. This is to reduce the likelihood of a false alarm of the start of a journey. For example, if the vehicle is moving around a warehouse, the GPS coordinates will change, but a new journey has not yet started. By reducing the spatial accuracy of the GPS coordinates to, for example, 100 m, a new journey will only be triggered when the position of the vehicle has changed significantly, because this significant movement indicates that a potential new journey has started.

[0119] Figure 6A flowchart is shown that illustrates an alternative method for using TMS information 23 to detect the start of a new trip. At step 131, sensor readings are obtained from the TMS sensor 5 mounted on the tire 3. These readings may include radial acceleration values. At step 133, an inactive period is identified, which may be a period when the radial acceleration value is equal to zero. At step 135, the moment when the sensor readings change is identified, and the time difference from the start of the inactive period is calculated. In the same manner as discussed above with respect to Figure 4 's method, this allows determination of the length of time the vehicle has been stationary. At step 137, the time difference is compared with a predefined threshold, and if the time difference exceeds the threshold, a new trip event is triggered. If the difference is below the threshold, the method restarts. The threshold is set according to the same criteria as discussed with respect to Figure 5 's method.

[0120] Figure 7 A scatter plot of the actual load versus the predicted load using the TMS load prediction algorithm according to an embodiment of the present invention is shown. The model used was specifically optimized for the Duravis Drive tire product from . It can be clearly seen from the figure that for all three pressures tested, the data points lie on or close to the line Y = X, indicating that the predictions made by the model are accurate.

[0121] Additionally, Figure 8 a histogram is shown that indicates that the distribution of the actual load - predicted load values is concentrated around an interval corresponding to low values (meaning that the actual load and the predicted load are similar values).

[0122] Figure 9 An output screen 200 is shown that is displayed to the user on the output device 10. A separate current tire load 201 is shown for each tire 3. The output screen 200 also displays the axle load 203 per axle, the total vehicle load 205, and the payload 207, which is equal to the total vehicle load 205 minus the weight of the vehicle itself. In the illustrated embodiment, the output screen 200 also displays other information, such as the current vehicle speed 209 and the current vehicle coordinates 211.

[0123] In the embodiment discussed, processing steps such as the implementation of the model 15 are performed in the remote server 7. However, it is contemplated that some or all of the processing steps of the method 100 may be performed by the network communication device 6, by the vehicle 2 itself, or by the TMS sensor 5 at the edge. The trip start detection 111 may likewise be implemented directly at the edge, on the network communication device 6 or the vehicle 2, or in an embodiment where no telematics data is required, directly in the TMS sensor firmware.

[0124] In the embodiments discussed above, a single current load value was calculated. It is contemplated that the method could be configured to detect multiple load values during a stroke and combine these values into a moving average, a total measured average, or use other suitable aggregation functions to combine these values. Such embodiments could further improve load detection accuracy.

Claims

1. A computer-implemented method for monitoring the current load on a tire mounted on a vehicle, the method comprising: Obtain sensor readings from one or more tire monitoring system (TMS) sensors mounted on the tire; Access characteristic information related to the tire; Select a suitable model from a plurality of models based on the characteristic information; and Use the selected model to estimate the current tire load value based on the sensor readings.

2. The method according to claim 1, wherein the characteristic information related to the tire comprises one or more of the following: tire manufacturer, tread pattern, tire specification, tire compound, tire stiffness, tire size, tire mounting position, and retread information.

3. The method according to claim 1 or claim 2, wherein the plurality of models includes individual models specifically optimized for known tire products from a given manufacturer.

4. The method according to any one of the preceding claims, the method further comprising accessing characteristic information related to the vehicle.

5. The method according to claim 4, wherein the characteristic information related to the vehicle comprises one or more of the following: vehicle manufacturer, chassis type of the vehicle, vehicle usage, number of axles, product type, number of tires, and number of tires mounted per axle.

6. The method according to any one of the preceding claims, the method comprising: Obtain current telematics information from the vehicle, optionally where the telematics information includes one or more of the following: GPS position, vehicle speed, vehicle lateral / longitudinal acceleration, type of road, engine load, gear shift, engine RPM, wheel speed, throttle / brake pedal position, tire temperature, external temperature, and / or steering wheel angle.

7. The method according to claim 6, the method comprising: Use the current telematics information to detect favorable load measurement conditions and obtain the sensor readings when favorable load measurement conditions are detected.

8. The method according to any one of the preceding claims, wherein the sensor readings comprise one or more of the following: radial acceleration value, inflation pressure, and internal air temperature.

9. The method according to any one of the preceding claims, the method further comprising: Obtain sensor readings that include a radial acceleration value; Analyze the radial acceleration value to calculate one or more tire parameters selected from the following: tire contact patch length, tire wear estimate, tire rotation time, automatic mounting position location, and tire mileage estimate; and Use the selected model to estimate the current tire load value based on the sensor readings and one or more of the tire parameters.

10. The method according to any one of the preceding claims, the method comprising: Provide the user with real-time feedback related to the current tire load value, optionally where the feedback includes one or more of the following: notification of exceeding the tire load index, notification that the tire is operating at an incorrect inflation pressure for the current load, notification that the vehicle exceeds its maximum load capacity, and notification that the vehicle has an unbalanced weight distribution on its tires.

11. The method according to any one of the preceding claims, wherein the current load tire value is calculated only once during a journey made by the vehicle.

12. The method according to claim 11, the method comprising: Use data from the one or more tire monitoring system (TMS) sensors and / or telematics data to detect the start of a trip and estimate the current tire load value in response to detecting the start of the trip.

13. The method according to any one of claims 1 to 10, wherein the current load tire value is calculated at fixed time intervals or at fixed travel distance intervals.

14. The method according to any one of the preceding claims, wherein each of the plurality of models is pre-trained based on historical data obtained for tires having the same characteristic information.

15. A system for monitoring a current load on a tire and configured to perform the method according to any one of the preceding claims, the system comprising: One or more TMS sensors mounted on the tire and configured to obtain the sensor readings; A processor configured to process the sensor readings; and A memory configured to store the sensor readings and / or parameters based on the sensor readings.

Images