Determining tire pressure value of a tire of a vehicle

Abstract

Approaches for generating tire pressure status for a tire of a vehicle are described. In an example, a current value corresponding to a plurality of input vehicle parameters is obtained from a plurality of vehicle integrated sensors. Thereafter, the current values corresponding to the plurality of vehicle parameters are fed into a trained pressure monitoring model for processing. Based on the analysis, the pressure monitoring model outputs the current tire pressure value indicating current pressure of the tire of the vehicle. Once determined, the current tire pressure value is compared with a threshold pressure range of values. Based on this comparison, a notification is generated that includes the tire pressure status, such as "optimal," "low," or "high", which is then transmitted to the vehicle's user interface for display.

Description

TECHNICAL FIELD

[0001] The present subject matter relates, in general, to vehicle safety systems. More specifically, the present subject matter relates to a machine learning-based tire pressure monitoring system (TPMS) that determines tire pressure status using vehicle parameter data without requiring physical pressure sensors.BACKGROUND

[0002] Monitoring tire pressure is an important aspect of vehicle safety and maintenance to alert the drivers about underinflated tires. Maintaining proper tire inflation ensures optimal handling, shorter braking distance, improved fuel efficiency, and extended tire life. As may be understood, underinflated tires may compromise vehicle control, increase the risk of blowouts, especially at high speeds or during long trips, and lead to premature tire wear. Systems designed to alert drivers about low tire pressure play a significant role in enhancing overall driving safety and performance.BRIEF DESCRIPTION OF FIGURES

[0003] Systems and / or methods, in accordance with examples of the present subject matter are now described and with reference to the accompanying figures, in which:

[0004] FIG. 1 illustrates a training system for training a pressure monitoring model, as per an example;

[0005] FIG. 2 illustrates a tire pressure monitoring system for generating a tire pressure status corresponding to a tire of a vehicle, as per one example;

[0006] FIG. 3 illustrates a method for training a pressure monitoring model, as per an example; and

[0007] FIG. 4 illustrates a method for generating a tire pressure status corresponding to a tire of a vehicle based on a trained pressure monitoring model, as per an example.

[0008] Throughout the drawings, identical reference numbers designate similar, but not necessarily identical, elements. The figures are not necessarily to scale, and the size of some parts may be exaggerated to more clearly illustrate the example shown. Moreover, the drawings provide examples and / or implementations consistent with the description; however, the description is not limited to the examples and / or implementations provided in the drawings.DETAILED DESCRIPTION

[0009] Tire Pressure Monitoring Systems (TPMS) are critical safety features in modem vehicles, designed to alert drivers about underinflated tires. As may be understood, proper tire inflation is essential for vehicle safety, fuel efficiency, and tire longevity. On the other hand, underinflated tires may lead to reduced handling, increased stopping distances, and even tire blowouts, especially at high speeds or during long journeys. TPMS helps drivers maintain optimal tire pressure, thereby enhancing overall vehicle performance and safety.

[0010] In general, conventional TPMS solutions fall into two main categories, namely, Direct TPMS and Indirect TPMS. In an example, the direct TPMS uses physical sensors inside each tire to measure pressure directly. While accurate, these solutions are expensive, require regular maintenance, and have complex installation. Indirect TPMS, on the other hand, infers tire pressure using Anti-lock braking system (ABS) and ESC wheel speed sensors to detect differences in rotational speed. Indirection TPMS is more cost-effective but is limited to vehicles equipped with ABS and ESC systems and may be less accurate in certain driving conditions.

[0011] Approaches for generating tire pressure status for a tire of a vehicle are described. In an example, proper tire inflation is essential forvehicle safety, fuel efficiency, and tire longevity. Therefore, providing an indication to the driver regarding underinflated status of tires ensures vehicle safety, fuel efficiency, and tire longevity. In operation, while the vehicle is travelling on a road, a current value corresponding to a plurality of input vehicle parameters is obtained from a plurality of vehicle integrated sensors. In an example, the plurality of input vehicle parameters are indicative of a tire pressure of the vehicle. Examples of such plurality of input vehicle parameters include, but are not limited to, a battery current, a motor speed, a motor torque, a vehicle mode, an acceleration, an angular velocity, Motor Control Unit (MCU) temperature, a bus voltage, a battery State of Charge (SoC), and a vehicle speed. The obtained current values corresponding to the plurality of input vehicle parameters are subsequently processed to determine the tire pressure status of the tire of the vehicle.

[0012] To do so, a machine learning based pressure monitoring model is used. In an example, the pressure monitoring model is trained based on a training data comprising training parameter values pertaining to a plurality of vehicle parameters and corresponding reference tire pressure values. For training, the training data is initially pre-processed to reduce inconsistency from the training data. In an example, the inconsistency in the training data may be related to missing values, mismatch in values, or any type of inconsistency. In an example, the training data is obtained from a repository storing vehicle parameters corresponding to a plurality of vehicles which have run over the road in past in variety of conditions providing an exhaustive data for training the pressure monitoring model.

[0013] Once the inconsistency is removed / reduced, the training values corresponding to the vehicle parameters which are relevant for training the model are retrieved from the training data. In an example, the initial set of vehicle parameters comprised in the training data may include some parameters that are not useful for predicting tire pressure. So, these irrelevant parameters are identified through statistical analysis and domain expertise and subsequently removed from the training data. It may be notedthat, this helps to reduce noise in the training data and improve model’s efficiency and accuracy.

[0014] On the other hand, it may be the case that, there are some potentially valuable parameters for tire pressure prediction which may not be directly measured by the vehicle's sensors. In such a case, these additional parameters may often be derived or calculated from existing parameter values. For example, wheel angular acceleration may be calculated from changes in motor speed overtime, vehicle acceleration may be derived from changes in vehicle speed, and power consumption may be calculated from battery current and bus voltage. Values of these additional parameters are added to the training dataset to provide additional relevant information for the machine learning model.

[0015] Returning to the present example, once the final training data is obtained, the pressure monitoring model is trained using the training data. In an example, the pressure monitoring model, when trained, is to generate a tire pressure value corresponding to a tire of a vehicle based on a current value of a plurality of input vehicle parameters. During the training process, the pressure monitoring model correlates the training values corresponding to the plurality of vehicle parameters with the reference tire pressures.

[0016] Once trained, the pressure monitoring model is used for determining a current tire pressure value in real-time corresponding to the tire of the vehicle which is running on a road to indicate whether the tire pressure is low or optimal. To this end, the current values corresponding to the plurality of vehicle parameters are fed into the trained pressure monitoring model for processing. In an example, the pressure monitoring model analyses the relationships and patterns within the current values of the vehicle parameters that correlate with reference tire pressure values. Based on the analysis, the model outputs the current tire pressure value indicating current pressure of the tire of the vehicle.

[0017] Once determined, the current tire pressure value is compared with a threshold pressure range of values. In an example, the thresholdpressure range of values indicates the acceptable limits of tire pressure for safe and optimal vehicle performance, which may vary depending on factors such as vehicle type, load conditions, and ambient temperature. Based on this comparison, a notification is generated that includes the tire pressure status, such as "optimal," "low," or "high", which is then transmitted to the vehicle’s user interface for display. Such status indication on display interface enables the driver to take timely corrective actions, if necessary, thereby enhancing safety and vehicle efficiency.

[0018] As will be explained further, the present approaches enable realtime determination of tire pressure value without the need for physical pressure sensors, based on the processing of values of various vehicle parameters using the trained pressure monitoring model. The pressure monitoring model is trained based on training values of the plurality of vehicle parameters collected from vehicles operating under various conditions and tire pressure states. Therefore, based on the observations and learnings which the model had from the vast variety of training data, the pressure monitoring model provides accurate predictions regarding the current tire pressure status. Using such machine learning model eliminates the need for expensive and maintenance-intensive physical tire pressure sensors while ensuring timely alerts for low tire pressure conditions. The accuracy of tire pressure monitoring is enhanced through the use of multiple relevant vehicle parameters and advanced machine learning techniques, providing a cost-effective and reliable solution for improving vehicle safety and efficiency.

[0019] FIG. 1 illustrates a training system 102 comprising a processor and memory (not shown), for training a pressure monitoring model. In an example, the training system 102 (referred to as system 102) may be communicatively coupled to a repository 104 through a network 106. The repository 104 may further include training data 108. The training data 108 may include training values corresponding to a plurality of vehicle parameters corresponding to various tire pressure states.

[0020] In one example, along with the training values corresponding to the plurality of vehicle parameters, the training data 108 may further include reference tire pressure values corresponding to the training values of the plurality of vehicle parameters. Examples of plurality of vehicle parameters include, but are not limited to, battery current, motor speed, motor torque, vehicle mode, acceleration, angular velocity, MCU temperature, bus voltage, battery pack SoC, and vehicle speed. It may be noted that the training values corresponding to the plurality of vehicle parameters may include values corresponding to normal tire pressure as well as low tire pressure conditions. For example, energy consumption data when tire pressure is at the recommended level would be considered a normal or optimal value, while energy consumption data when tire pressure is below the recommended level would be considered a low-pressure value. In an example, the values of these parameters are collected at a frequency of 100ms to provide real-time data for tire pressure monitoring.

[0021] It may be noted that, the training data 108, although depicted as being obtained from a single repository, such as repository 104, may also be obtained from multiple other sources without deviating from the scope of the present subject matter. In such cases, each of such multiple repositories may be interconnected through a network, such as the network 106.

[0022] The network 106 may be a private network or a public network and may be implemented as a wired network, a wireless network, or a combination of a wired and wireless network. The network 106 may also include a collection of individual networks, interconnected with each other and functioning as a single large network, such as the Internet. Examples of such individual networks include, but are not limited to, Global System for Mobile Communication (GSM) network, Universal Mobile Telecommunications System (UMTS) network, Personal Communications Service (PCS) network, Time Division Multiple Access (TDMA) network, Code Division Multiple Access (CDMA) network, Next Generation Network(NGN), Public Switched Telephone Network (PSTN), Long Term Evolution (LTE), and Integrated Services Digital Network (ISDN).

[0023] The system 102 may further include instructions 110 and a training engine 112. In an example, the instructions 110 are fetched from the memory and executed by the processor included within the system 102. The training engine 112 may be implemented as a combination of hardware and programming, for example, programmable instructions to implement a variety of functionalities. In examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the training engine 112 may be executable instructions, such as instructions 110. Such instructions may be stored on a non-transitory machine-readable storage medium which may be coupled either directly with the system 102 or indirectly (for example, through networked means). In an example, the training engine 112 may include a processing resource, for example, either a single processor or a combination of multiple processors, to execute such instructions. In the present examples, the non-transitory machine-readable storage medium may store instructions, such as instructions 110, that when executed by the processing resource, implement training engine 112. In other examples, the training engine 112 may be implemented as an electronic circuitry.

[0024] The instructions 110 when executed by the processing resource, cause the training engine 112 to train a pressure monitoring model 114. The instructions 110 may be executed by the processing resource for training the pressure monitoring model 114 based on the training data 108. The system 102 may further include training vehicle parameter values(s) 116 and reference tire pressure value(s) 118. In an example, the system 102 may obtain training data 108 corresponding to a single vehicle from the repository 104, and the information pertaining to that is stored as training vehicle parameter value(s) 116 and reference tire pressure value(s) 118 in the system 102.

[0025] For training, the vehicle parameters values, such as training vehicle parameter value(s) 116, and corresponding reference tire pressure value(s) 118 may be used to train the pressure monitoring model 114. The pressure monitoring model 114 may then be used to determine real-time current tire pressure value based on current values corresponding to the plurality of input vehicle parameters for a vehicle in operation.

[0026] In operation, the training engine 112 obtains the training data 108 from the repository 104 and stores the training data 108 as training vehicle parameter value(s) 116 and reference tire pressure value(s) 118 in the system 102. In an example, the training data 108 may include a plurality of sets comprising training value corresponding the plurality of vehicle parameters with each set annotated with corresponding reference tire pressure value.

[0027] In another example, the system 102 obtains the training data 108 from the repository 104 which may include training vehicle parameter value(s) 116 corresponding to a limited number of vehicle parameters. In such a case, once the training data 108 is obtained, the existing training vehicle parameter value(s) 116 are used to determine parameter values corresponding to some additional vehicle parameters. It may be noted that the vehicle parameter values may include data corresponding to both normal and low tire pressure conditions.

[0028] Examples of vehicle parameters, whose parameter values are comprised within the training vehicle parameter value(s) 116, include, but are not limited to, battery current, motor speed, motor torque, vehicle mode, acceleration, angular velocity, MCU temperature, bus voltage, battery pack SoC, and vehicle speed. It may be noted, although the training data 108 is described as having a plurality of vehicle parameter sets, however, it may include various sets of training data with each set corresponding to a single vehicle or driving condition.

[0029] Prior to training the pressure monitoring model, the training engine 112 performs preprocessing on the training data 108 to eliminateinconsistencies that could impact model accuracy. This preprocessing step addresses issues such as missing values, outliers, mismatched data formats, and erroneous sensor readings. Techniques such as data cleaning, normalization, and imputation are applied to ensure the training data is consistent, reliable, and suitable for effective model learning.

[0030] Following the preprocessing, the training engine 112 proceeds to identify and construct relevant vehicle parameters for model training. This involves two key steps, selecting the most informative vehicle parameters from the pre-processed data and determining values for additional derived parameters which may be relevant. In an example, selection of most informative vehicle parameters is performed to isolate parameters that have the highest predictive value for tire pressure status. In parallel, feature engineering is applied to enhance model performance by deriving new or additional parameters from existing ones. For example, wheel angular acceleration may be calculated from variations in motor speed over time, vehicle acceleration may be derived from changes in vehicle speed, and power consumption may be computed using battery current and bus voltage. These derived features are calculated through transformations or combinations of existing vehicle parameter values and are incorporated into the training dataset to enrich the input space and improve the accuracy of the pressure monitoring model.

[0031] Thereafter, the training engine 112 processes the training vehicle parameter value(s) 116 and reference tire pressure value(s) 118 which comes out to be relevant vehicle parameters based on above processing to make an interrelation between these vehicle parameters and trains the pressure monitoring model 114 based on this interrelation. During the training process, the pressure monitoring model 114 is to associate the vehicle parameter values with the corresponding reference tire pressure values. In an example, the pressure monitoring model 114 may identify patterns and relationships between these elements, learning to recognize what constitutes low tire pressure for different combination and values ofvehicle parameters. When trained, the pressure monitoring model 114 develops an understanding of the relationship between vehicle parameters and tire pressure, distinguishing between normal, low tire pressure, and high tire pressure conditions across various operating scenarios.

[0032] Once trained, the pressure monitoring model 114 may be used for determining current tire pressure value in real-time based on current value corresponding to a plurality of input vehicle parameters from a vehicle in operation. For example, vehicle parameter data including current values corresponding to the plurality of input vehicle parameters from an operating vehicle may be processed using the pressure monitoring model 114. In such a case, based on pressure monitoring model 114, the current tire pressure value is determined which is subsequently compared with a threshold range of values of tire pressure to determine a tire pressure status to alert the driver about the current tire pressure status. The manner in which the vehicle parameter values of an operating vehicle is processed to generate tire pressure status predictions based on the trained pressure monitoring model 114 is further described in conjunction with FIG. 2.

[0033] FIG. 2 illustrates an environment 200 depicting a vehicle 202 running on a road 204, as per an example. The vehicle 202 includes a tire pressure monitoring system 206 (referred to as system 206), for performing tire pressure monitoring and generating alerts indicating tire pressure status of the vehicle 202. To do so, current values corresponding to input vehicle parameters are required to be processed based on a pressure monitoring model, such as pressure monitoring model 114. In an example, the current value corresponding to the plurality of input vehicle parameters are obtained in real-time from various sensors which are integrated on the vehicle, without requiring any additional sensors.

[0034] Similar to the system 102, system 206 may further include instructions 208 and an analysis engine 210. In an example, the instructions 208 are fetched from a memory and executed by a processor included within the system 206. The analysis engine 210 may be implemented as acombination of hardware and programming, for example, programmable instructions to implement a variety of functionalities. In examples described herein, such combinations of hardware and programming may be implemented in several different ways.

[0035] For example, the programming for the analysis engine 210 may be executable instructions, such as instructions 208. Such instructions 208 may be stored on a non-transitory machine-readable storage medium which may be coupled either directly with the system 206 or indirectly (for example, through networked means). In an example, the analysis engine 210 may include a processing resource, for example, either a single processor or a combination of multiple processors, to execute such instructions. In the present examples, the non-transitory machine-readable storage medium may store instructions, such as instructions 208, that when executed by the processing resource, implement analysis engine 210. In other examples, the analysis engine 210 may be implemented as electronic circuitry.

[0036] The system 206 may include a pressure monitoring model, such as the pressure monitoring model 114. The system 206 may further include an input vehicle parameter value(s) 212, a current tire pressure value 214, a threshold pressure range 216 and a tire pressure status 218. In an example, the pressure monitoring model 114 is a trained model based on thousands of training data points and corresponding tire pressure values with respect to various vehicle operating conditions.

[0037] In operation, during the driving of vehicle 202, the driver may wish to check the current tire pressure status to ensure safe and efficient travel. To check this without aborting driving, the driver interacts with a Human Machine Interface (HMI) 220 of the vehicle 202 by engaging the notification enable / disable switch 222. In an example, the notification enable / disable switch 222 (referred to as switch 222) serves as a user- friendly control mechanism and may be implemented in various forms depending on the vehicle’s design, such as a physical button located on theHMI, a soft key integrated into the HMI 220, or even a voice-activated command system.

[0038] Once the switch 222 is enabled, the analysis engine 210 may obtain or retrieve current values of a plurality of input vehicle parameters and may stores them as the input vehicle parameter value(s) 212 in the system 206. In an example, the input vehicle parameters are indicative of a tire pressure of the vehicle 202. Examples of plurality of vehicle parameters include, but are not limited to, battery current, motor speed, motor torque, vehicle mode, acceleration, angular velocity, MCU temperature, bus voltage, battery pack SoC, and vehicle speed. In an example, the current values corresponding to the plurality of input vehicle parameters are obtained from a plurality of sensors (not shown in FIG. 2) which are already integrated within the vehicle 202 at a predefined frequency, such as 100ms. Examples of such vehicle integrated sensors include, but are not limited to, a battery current sensor, a motor speed sensor, a torque sensor, an inertial measurement unit (IMU) comprising accelerometer and gyroscope, a temperature sensor for monitoring microcontroller unit (MCU) temperature, a voltage sensor for measuring bus voltage, a state-of-charge (SoC) sensor for battery pack monitoring, and a vehicle speed sensor.

[0039] In addition to the obtained input vehicle parameter value(s) 212, the analysis engine 210 may process the input vehicle parameter value(s) 212 to derive a current value corresponding to a plurality of additional vehicle parameters. These additional parameters are not directly measured but are inferred or computed based on the input data using predefined algorithms, models, or lookup tables.

[0040] In an example, the current values of the additional vehicle parameters are indicative of the tire pressure of the vehicle. For instance, variations in motor torque, vehicle acceleration, and angular velocity may be analyzed in conjunction with battery current and vehicle speed to estimate tire pressure behavior under different driving conditions. This indirect estimation allows the system to enhance tire pressure monitoringeven in scenarios where direct pressure sensors may be unavailable, malfunctioning, or supplemented by predictive diagnostics.

[0041] By processing both direct and derived data, the analysis engine 210 ensures a comprehensive and intelligent assessment of tire pressure, contributing to improved vehicle safety, performance, and maintenance planning.

[0042] Returning to the present example, once obtained, the analysis engine 210 may process the input vehicle parameter value(s) 212 using the trained pressure monitoring model 114 to determine the current tire pressure value 214. The model analyzes the complex relationships and patterns within the input vehicle parameter value(s) 212 that correlate with a reference tire pressure value as learned within the pressure monitoring model 114 and reference it as current tire pressure value 214. In an example, since the data is collected at 100ms interval, the analysis engine 210 may analyze trends over time using the model. For example, the analysis engine 210 may look for specific patterns in the IMU data, i.e., acceleration and angular velocity, that indicate the characteristics vibration profile of a low-pressure tire. Further, the analysis engine 210 considers how multiple parameters interact. For example, it might analyze how the combination of motor speed, torque, and energy consumption changes under different tire pressure conditions.

[0043] Continuing further, the analysis engine 210 may compare the current tire pressure value 214 with the threshold pressure range of values, i.e., threshold pressure range 216. In an example, the threshold pressure range 216 may indicate a predefined acceptable range of tire pressure values, including a lower limit and an upper limit, which are configured based on manufacturer specifications or user-defined preferences. Such range serves as a benchmark to assess whether the current tire pressure 214 is within safe and optimal operating conditions.

[0044] Based on the result of the comparison, the analysis engine 210 may generate a notification including the tire pressure status 218, which isto be transmitted to a user interface, such as HMI 220, of the vehicle 202. In an example, the tire pressure status 218 is one of a low tire pressure status, a high tire pressure status, or an optimal tire pressure status. Such notification is displayed on the HMI 220 via a notification interface 224, which is configured to visually and / or audibly alert the driver regarding the current tire pressure condition. The notification interface 224 may include graphical indicators, color-coded alerts (e.g., red for low, yellow for high, green for optimal), and textual messages to ensure clarity and prompt recognition by the driver.

[0045] In an example, based on the comparison, when it is determined that the current tire pressure value 214 is below a predefined lower limit of the threshold pressure range 216, the analysis engine 210 may generate the notification including the low tire pressure status. This status indicates that the tire pressure has dropped below the safe operating level, potentially affecting vehicle performance, fuel efficiency, and safety. The notification may include a warning symbol, a message such as “Low Tire Pressure Detected,” and a recommendation to check and inflate the tires.

[0046] In addition, based on the comparison, when it is determined that the current tire pressure value 214 is below the predefined lower limit of the threshold pressure range 216, the analysis engine 210 not only generates the low tire pressure status notification but also initiates a user assistance feature to support the driver in resolving the issue. Specifically, the analysis engine 210 displays a navigation interface via the HMI 220, which provides the driver with real-time information about nearby air filling stations. This interface includes, location of each air filling station, distance from the current vehicle position, and estimated travel time to reach each station. Such feature enhances driver convenience and safety by enabling quick access to corrective services, reducing the risk of tire-related incidents during travel.

[0047] Further, when it is determined that the current tire pressure value 214 is above a predefined upper limit of the threshold pressure range 216,the analysis engine 210 may generate the notification including the high tire pressure status. This status alerts the driver that the tire pressure exceeds the recommended maximum, which may lead to uneven tire wear or risk of tire damage. The notification may similarly include a warning symbol and a message such as “High Tire Pressure Detected,” along with a suggestion to release excess air.

[0048] On the other hand, when it is determined that the current tire pressure value 214 is within the threshold pressure range 216, the analysis engine 210 may generate the notification including the optimal tire pressure status. Such status confirms that the tire pressure is within the recommended limits, ensuring safe and efficient vehicle operation. The notification may be displayed as a green indicator or a message such as “Tire Pressure Optimal,” providing reassurance to the driver without requiring any immediate action.

[0049] This process of obtaining input vehicle parameters, processing them using the pressure monitoring model, determining tire pressure status, and displaying alerts, if necessary, continues throughout the vehicle's operation, providing real-time tire pressure monitoring without the need for physical pressure sensors within the vehicle 202.

[0050] FIG. 3 illustrates example method 300 for training a pressure monitoring model, in accordance with examples of the present subject matter. The order in which the above-mentioned method is described is not intended to be construed as a limitation, and some of the method blocks described may be combined in a different order to implement the method, or alternative method.

[0051] Furthermore, the above-mentioned method may be implemented in suitable hardware, computer-readable instructions, or combination thereof. The steps of such method may be performed by either a system under the instruction of machine executable instructions stored on a non- transitory computer readable medium or by dedicated hardware circuits, microcontrollers, or logic circuits. For example, the method may beperformed by a training system, such as system 102. In an implementation, the method may be performed under an “as a service” delivery model, where the system 102, operated by a provider, receives programmable code. Herein, some examples are also intended to cover non-transitory computer readable medium, for example, digital data storage media, which are computer readable and encode computer-executable instructions, where said instructions perform some or all the steps of the above- mentioned method.

[0052] In an example, the method 300 may be implemented by the system 102 for training the pressure monitoring model 114 based on training data, such as training data 108. At block 302, training data is obtained from a repository over a network. For example, the training engine 112 obtains the training data 108 from the repository 104 and stores the training data 108 as training vehicle parameter value(s) 116 and reference tire pressure value(s) 118 in the system 102. In an example, the training data 108 may include a plurality of sets comprising training value corresponding the plurality of vehicle parameters with each set annotated with corresponding reference tire pressure value.

[0053] In another example, the system 102 obtains the training data 108 from the repository 104 which may include training vehicle parameter value(s) 116 corresponding to a limited number of vehicle parameters. In such a case, once the training data 108 is obtained, the existed training vehicle parameter value(s) 116 are used to determine parameter values corresponding to some additional vehicle parameters. It may be noted that the vehicle parameter values may include data corresponding to both normal and low tire pressure conditions. Examples of vehicle parameters, whose parameter values are comprised within the training vehicle parameter value(s) 116, include, but are not limited to, battery current, motor speed, motor torque, vehicle mode, acceleration, angular velocity, MCU temperature, bus voltage, battery pack SoC, and vehicle speed. It may be noted, although the training data 108 is described as having a plurality ofvehicle parameter sets, however, it may include various sets of training data with each set corresponding to a single vehicle or driving condition.

[0054] At block 304, the training data is pre-processed to reduce inconsistency present in the training data. For example, the training engine 112 performs preprocessing on the training data 108 to eliminate inconsistencies that could impact model accuracy. This preprocessing step addresses issues such as missing values, outliers, mismatched data formats, and erroneous sensor readings. Techniques such as data cleaning, normalization, and imputation are applied to ensure the training data is consistent, reliable, and suitable for effective model learning.

[0055] At block 306, relevant vehicle parameters are extracted from the training data. For example, the training engine 112 proceeds to identify and construct relevant vehicle parameters for model training. This involves two key steps, selecting the most informative vehicle parameters from the pre- processed data and determining values for additional derived parameters which may be relevant. In an example, selection of most informative vehicle parameters is performed to isolate parameters that have the highest predictive value for tire pressure status. In parallel, feature engineering is applied to enhance model performance by deriving new or additional parameters from existing ones. For example, wheel angular acceleration may be calculated from variations in motor speed over time, vehicle acceleration may be derived from changes in vehicle speed, and power consumption may be computed using battery current and bus voltage. These derived features are calculated through transformations or combinations of existing vehicle parameter values and are incorporated into the training dataset to enrich the input space and improve the accuracy of the pressure monitoring model.

[0056] At block 308, a pressure monitoring model is trained based on the relevant vehicle parameters and the corresponding reference tire pressure. For example, the training engine 112 processes the training vehicle parameter value(s) 116 and reference tire pressure value(s) 118which comes out to be relevant vehicle parameters based on above processing to make an interrelation between these vehicle parameters and trains the pressure monitoring model 114 based on this interrelation. During the training process, the pressure monitoring model 114 is to associate the vehicle parameter values with the corresponding reference tire pressure values. In an example, the pressure monitoring model 114 may identify patterns and relationships between these elements, learning to recognize what constitutes low tire pressure for different combination and values of vehicle parameters. When trained, the pressure monitoring model 114 develops an understanding of the relationship between vehicle parameters and tire pressure, distinguishing between normal, low tire pressure, and high tire pressure conditions across various operating scenarios.

[0057] Once trained, the pressure monitoring model 114 may be used for determining current tire pressure value in real-time based on current value corresponding to a plurality of input vehicle parameters from a vehicle in operation. For example, vehicle parameter data including current values corresponding to the plurality of input vehicle parameters from an operating vehicle may be processed using the pressure monitoring model 114. In such a case, based on pressure monitoring model 114, the current tire pressure value is determined which is subsequently compared with a threshold range of values of tire pressure to determine a tire pressure status to alert the driver about the current tire pressure status.

[0058] FIG. 4 illustrates another example method 400 for generating a tire pressure status corresponding to a tire of a vehicle running on a road. Based on the present approaches as described in the context of the example method 400, the values corresponding to the plurality of input vehicle parameters are analyzed based on the trained pressure monitoring model 114 to determine the current tire pressure value 214 and subsequently generate the tire pressure status indicating state of pressure as either low, high, or optimal.

[0059] Further, the above-mentioned method 400 may be implemented in suitable hardware, computer-readable instructions, or combination thereof. The steps of such method may be performed by either a system under the instruction of machine executable instructions stored on a non- transitory computer readable medium or by dedicated hardware circuits, microcontrollers, or logic circuits. For example, the method may be performed by a tire pressure monitoring system, such as system 206. In an implementation, the method may be performed under an “as a service” delivery model, where the system 206, operated by a provider, receives programmable code. Herein, some examples are also intended to cover non-transitory computer readable medium, for example, digital data storage media, which are computer readable and encode computer-executable instructions, where said instructions perform some or all the steps of the above-mentioned method.

[0060] At block 402, an input indicative of driver’s intention to either enable or disable a tire pressure monitoring function is received. For example, during the driving of vehicle 202, the driver may wish to check the current tire pressure status to ensure safe and efficient travel. To check this without aborting driving, the driver interacts with the HMI 220 of the vehicle 202 by engaging the switch 222. In an example, the switch 222 serves as a user-friendly control mechanism and may be implemented in various forms depending on the vehicle’s design, such as a physical button located on the HMI, a soft key integrated into the HMI 220, or even a voice-activated command system.

[0061] At block 404, a current value of a plurality of vehicle parameters are obtained from a plurality of vehicle integrated sensors. For example, the analysis engine 210 may obtain or retrieves current values of a plurality of input vehicle parameters and may store them as the input vehicle parameter value(s) 212 in the system 206. In an example, the input vehicle parameters are indicative of a tire pressure of the vehicle 202. Examples of plurality of vehicle parameters include, but are not limited to, battery current, motorspeed, motor torque, vehicle mode, acceleration, angular velocity, MCU temperature, bus voltage, battery pack SoC, and vehicle speed. In an example, the input vehicle parameter value(s) 212 are obtained from various sensors which are already integrated on the vehicle 202 at a frequency of 100ms.

[0062] At block 406, the current value of the plurality of input vehicle parameters are processed to determine current value corresponding to a plurality of additional vehicle parameters. For example, in addition to the obtained input vehicle parameter value(s) 212, the analysis engine 210 may process the input vehicle parameter value(s) 212 to derive a current value corresponding to a plurality of additional vehicle parameters. These additional parameters are not directly measured but are inferred or computed based on the input data using predefined algorithms, models, or lookup tables.

[0063] In an example, the current values of the additional vehicle parameters are indicative of the tire pressure of the vehicle. For instance, variations in motor torque, vehicle acceleration, and angular velocity may be analyzed in conjunction with battery current and vehicle speed to estimate tire pressure behavior under different driving conditions. This indirect estimation allows the system to enhance tire pressure monitoring even in scenarios where direct pressure sensors may be unavailable, malfunctioning, or supplemented by predictive diagnostics. By processing both direct and derived data, the analysis engine 210 ensures a comprehensive and intelligent assessment of tire pressure, contributing to improved vehicle safety, performance, and maintenance planning.

[0064] At block 408, the current value of the plurality of vehicle parameters are processed using a trained pressure monitoring model to determine a current tire pressure value. For example, the analysis engine 210 may process the input vehicle parameter value(s) 212 using the trained pressure monitoring model 114 to determine the current tire pressure value 214. The model analyzes the complex relationships and patterns within theinput vehicle parameter value(s) 212 that correlate with a reference tire pressure value as learned within the pressure monitoring model 114 and reference it as current tire pressure value 214. In an example, since the data is collected at 100ms interval, the analysis engine 210 may analyze trends over time using the model. For example, the analysis engine 210 in conjunction with the trained pressure monitoring model 114 may look for specific patterns in the IMU data, i.e. , acceleration and angular velocity, that indicate the characteristics vibration profile of a low-pressure tire. Further, the analysis engine 210 considers how multiple parameters interact. For example, it might analyze how the combination of motor speed, torque, and energy consumption changes under different tire pressure conditions.

[0065] At block 410, the current tire pressure value is compared with a threshold pressure range of values. For example, the analysis engine 210 may compare the current tire pressure value 214 with the threshold pressure range of values, i.e., threshold pressure range 216. In an example, the threshold pressure range 216 may indicate a predefined acceptable range of tire pressure values, including a lower limit and an upper limit, which are configured based on manufacturer specifications or user-defined preferences. Such range serves as a benchmark to assess whether the current tire pressure value 214 is within safe and optimal operating conditions.

[0066] At block 412, based on the comparison, a notification including a tire pressure status is generated. For example, the analysis engine 210 may generate a notification including the tire pressure status 218, which is to be transmitted to a user interface, such as HMI 220, of the vehicle 202. In an example, the tire pressure status 218 is one of a low tire pressure status, a high tire pressure status, or an optimal tire pressure status. Such notification is displayed on the HMI 220 via the notification interface 224, which is configured to visually and / or audibly alert the driver regarding the current tire pressure condition. The notification interface 224 may include graphical indicators, color-coded alerts (e.g., red for low, yellow for high,green for optimal), and textual messages to ensure clarity and prompt recognition by the driver.

[0067] In an example, based on the comparison, when it is determined that the current tire pressure value 214 is below a predefined lower limit of the threshold pressure range 216, the analysis engine 210 may generate the notification including the low tire pressure status. This status indicates that the tire pressure has dropped below the safe operating level, potentially affecting vehicle performance, fuel efficiency, and safety. The notification may include a warning symbol, a message such as “Low Tire Pressure Detected,” and a recommendation to check and inflate the tires.

[0068] In addition, based on the comparison, when it is determined that the current tire pressure value 214 is below the predefined lower limit of the threshold pressure range 216, the analysis engine 210 not only generates the low tire pressure status notification but may also initiates a user assistance feature to support the driver in resolving the issue. Specifically, the analysis engine 210 displays a navigation interface via the HMI 220, which provides the driver with real-time information about nearby air filling stations. This interface includes, location of each air filling station, distance from the current vehicle position, and estimated travel time to reach each station. Such feature enhances driver convenience and safety by enabling quick access to corrective services, reducing the risk of tire-related incidents during travel.

[0069] Further, when it is determined that the current tire pressure value 214 is above a predefined upper limit of the threshold pressure range 216, the analysis engine 210 may generate the notification including the high tire pressure status. This status alerts the driver that the tire pressure exceeds the recommended maximum, which may lead to uneven tire wear or risk of tire damage. The notification may similarly include a warning symbol and a message such as “High Tire Pressure Detected,” along with a suggestion to release excess air.

[0070] On the other hand, when it is determined that the current tire pressure value 214 is within the threshold pressure range 216, the analysis engine 210 may generate the notification including the optimal tire pressure status. Such status confirms that the tire pressure is within the recommended limits, ensuring safe and efficient vehicle operation. The notification may be displayed as a green indicator or a message such as “Tire Pressure Optimal,” providing reassurance to the driver without requiring any immediate action.

[0071] Although examples for the present disclosure have been described in language specific to structural features and / or methods, it is to be understood that the appended claims are not necessarily limited to the specific features or methods described. Rather, the specific features and methods are disclosed and explained as examples of the present disclosure.

Claims

I / We Claim:1 . A system comprising: a processor; and an analysis engine coupled to the processor, wherein the analysis engine is to: obtain a current value of a plurality of input vehicle parameters from a plurality of vehicle integrated sensors, wherein the plurality of input vehicle parameters are indicative of a tire pressure of the vehicle; process the current value of the plurality of input vehicle parameters using a trained pressure monitoring model to determine a current tire pressure value, wherein the pressure monitoring model is trained based on a training parameter value corresponding to a plurality of vehicle parameters and corresponding reference tire pressure values; compare the current tire pressure value with a threshold pressure range of values; and based on the comparison, generate a notification comprising a tire pressure status to be transmitted to a user interface of the vehicle.

2. The system as claimed in claim 1 , wherein the plurality of input vehicle parameters comprises a battery current, a motor speed, a motor torque, an acceleration, an angular velocity, Motor Control Unit (MCU) temperature, a bus voltage, a battery State of Charge (SoC), and a vehicle speed.

3. The system as claimed in claim 1 , wherein the tire pressure status is one of a low tire pressure status, a high tire pressure status, and an optimal tire pressure status, wherein the analysis engine is to:based on the comparison, upon determining the current tire pressure value is below a predefined lower limit of the threshold pressure range of values, generate the notification comprising the low tire pressure status.

4. The system as claimed in claim 3, wherein the analysis engine is to: upon determining the current tire pressure value to be above a predefined upper limit of the threshold range of values, generate the notification comprising the high tire pressure status.

5. The system as claimed in claim 3, wherein the analysis engine is to: upon determining the current tire pressure value within the threshold pressure range of values, generate the notification comprising the optimal tire pressure status.

6. The system as claimed in claim 1 , wherein prior to obtaining the current value of the vehicle parameter, the analysis engine is to: receive, through a human machine interface (HMI), an input from a driver of the vehicle, wherein the input is indicative of a user preference to enable or disable a tire pressure monitoring function.

7. The system as claimed in claim 1 , wherein the analysis engine is to: upon determining the current tire pressure value is below a predefined lower limit of the threshold pressure range of values, display a navigation interface via a human machine interface (HMI), wherein the navigation interface provides information about nearby air filling stations, comprising location, distance, and estimated travel time.

8. The system as claimed in claim 1 , wherein the analysis engine is to: process the current value of the plurality of input vehicle parameters to determine current value corresponding to a plurality of additional vehicleparameters, wherein the current value of the additional vehicle parameters are indicative of tire pressure of the vehicle.

9. The system as claimed in claim 1 , wherein the vehicle integrated sensor comprises a battery current sensor, a motor speed sensor, a torque sensor, an inertial measurement unit (IMU) comprising accelerometer and gyroscope, a temperature sensor for monitoring microcontroller unit (MCU) temperature, a voltage sensor for measuring bus voltage, a state-of-charge (SoC) sensor for battery pack monitoring, and a vehicle speed sensor.

10. A method comprising: obtaining training data comprising a training parameter value corresponding to a plurality of vehicle parameters and a corresponding reference tire pressure value, wherein the plurality of vehicle parameters are indicative of a tire pressure of a vehicle; and training a pressure monitoring model based on the training parameter value, wherein the pressure monitoring model, when trained, is to determine a current tire pressure value of a tire of a vehicle based on a current value of a plurality of input vehicle parameters indicative of tire pressure of the vehicle.

11. The method as claimed in claim 10, wherein the plurality of vehicle parameters comprises a battery current, a motor speed, a motor torque, an acceleration, an angular velocity, Motor Control Unit (MCU) temperature, a bus voltage, a battery State of Charge (SoC), and a vehicle speed.

12. The method as claimed in claim 10, wherein the method comprises: preprocessing the training data to remove inconsistency, wherein the inconsistency indicates one or more missing values, outliers, mismatched formats, or erroneous sensor readings that may affect model accuracy; anddetermining values corresponding to additional parameters based on the training values of the vehicle parameters comprised within the training data, wherein the additional parameters are derived features such as wheel angular acceleration, vehicle acceleration, or power consumption, calculated using transformations or combinations of existing vehicle parameter values to enhance model performance.

13. A vehicle comprising: a plurality of vehicle integrated sensor configured to generate a current value of a plurality of vehicle parameters; a human machine-interface (HMI); a processor coupled to the vehicle integrated sensor and the HMI, wherein the processor is to: obtain a current value of a plurality of input vehicle parameters from a plurality of vehicle integrated sensors, wherein the plurality of input vehicle parameters are indicative of a tire pressure of the vehicle; process the current value of the plurality of input vehicle parameters using a trained pressure monitoring model to determine a current tire pressure value, wherein the pressure monitoring model is trained based on training parameter values corresponding to a plurality of vehicle parameter and corresponding reference tire pressure values; compare the current tire pressure value with a threshold pressure range of values; and based on the comparison, generate a notification comprising a tire pressure status to be transmitted to a user interface of the vehicle.

14. The vehicle as claimed in claim 13, wherein the plurality of input vehicle parameters comprises a battery current, a motor speed, a motor torque, an 1acceleration, an angular velocity, Motor Control Unit (MCU) temperature, a bus voltage, a battery State of Charge (SoC), and a vehicle speed.

15. The vehicle as claimed in claim 13, wherein the tire pressure status is one of a low tire pressure status, a high tire pressure status, and an optimal tire pressure status, wherein the processor is to: based on the comparison, upon determining the current tire pressure value is below a predefined lower limit of the threshold pressure range of values, generate the notification comprising the low tire pressure status.

Images