DESC:FORM 2
THE PATENTS ACT, 1970
(39 OF 1970)
&
THE PATENT RULES, 2003

COMPLETE SPECIFICATION
(See section 10, rule 13)

Title of the invention:
METHODS AND SYSTEMS FOR DETECTING TIRE PRESSURE CONDITIONS IN VEHICLES

APPLICANT:
Varroc Engineering Limited
An Indian entity
having address as:
L-4, MIDC Waluj, Aurangabad-431136, Maharashtra, India

The following specification particularly describes the invention and the manner in which it is to be performed.
CROSS-REFERENCE TO RELATED APPLICATIONS AND PRIORITY
The present application claims priority from an Indian patent Application No. 202221023705, filed on 22 April 2022, incorporated herein by a reference.
TECHNICAL FIELD
Present disclosure generally relates to automobiles. Particularly, but not exclusively, the present disclosure relates to indirect tire pressure measurement in vehicles.
BACKGROUND
Tire-pressure monitoring system (TPMS) are widely used in vehicles for monitoring the air pressure inside the pneumatic tires on vehicles. A TPMS reports real-time tire-pressure information to the driver, using either a gauge, a pictogram display, or a simple low-pressure warning light.
The TPMS in vehicle warns the driver if at least one or more tires are significantly under-inflated, possibly creating unsafe driving conditions. Inadequate tire inflation can shorten the life of the tires, negatively affect your vehicle's performance, and maybe even cause a tire to fail.
Presently, the tire pressure in vehicle is monitored using direct TPMS and indirect TPMS. Direct TPMS uses a sensor mounted in the wheel to measure air pressure in each tire. When air pressure drops fall below a recommended level, the sensor transmits that information to vehicle ECU for providing an appropriate indication to the driver. However, direct TPMS is an expensive solution as it involves replacement of battery of tire pressure sensor after certain time period and the pressure sensors get easily damaged at the time of mounting or dismounting, thereby making the maintenance of the TPMS troublesome.
Indirect TPMS do not use physical pressure sensors for monitoring tire pressure. Instead, the tire pressure is measured by evaluating and combining existing onboard sensor signals to estimate and monitor the tire pressure without physical pressure sensors in the wheels. However, indirect tire pressure measurement involves efficient processing of large chunk of sensor data for accurate and reliable prediction.
Therefore, there exists a need in the art to provide a solution which overcomes the above-mentioned problem and to provide a technique that efficiently processes the large chunk of sensor data to accurately predict the tire pressure condition in vehicles.
SUMMARY
The present disclosure overcomes one or more shortcomings of the prior art and provides additional advantages discussed throughout the present disclosure. Additional features and advantages are realized through the techniques of the present disclosure. Other embodiments and aspects of the disclosure are described in detail herein and are considered a part of the claimed disclosure.
In one non-limiting embodiment of the present disclosure, a method of predicting tire pressure condition in vehicles is disclosed. The method comprises obtaining a plurality of GPS location points at a predetermined interval of time along with a corresponding timestamp value, monitoring a revolution count of each wheel between two consecutive GPS location points, determining a plurality of GPS speed between two consecutive GPS location points, processing the GPS speed to obtain a filtered GPS speed, determining a plurality of parameters for the at least one wheel based on the filtered GPS speeds and a corresponding linear velocity, creating a plurality of packets comprising a plurality of samples for each wheel, determining mean and median values of the plurality of parameters for each packet, predicting a tire pressure status for each packet of each wheel using the AI/ML module, and generating an alert based on the prediction. Thus, the method facilitates accurate indirect tire pressure estimation and alert generation to the driver of the vehicle.
In another non-limiting embodiment of the present disclosure, a system for predicting tire pressure condition in vehicles is disclosed. The system comprises a GPS sensor configured to obtain a plurality of GPS location points at a predetermined interval of time along with a corresponding timestamp value, at least one speed sensor configured to detect a plurality of pulses of each wheel between two consecutive GPS points, and a processing unit is configured to monitor a revolution count of each wheel between two consecutive GPS location points. The processing unit may be then configured to determine a plurality of GPS speed between two consecutive GPS location points. The system further comprises a filtering unit configured to filter the plurality of GPS speeds to obtain filtered GPS speeds. The processing unit is then configured to determine a plurality of parameters for the at least one wheel based on the filtered GPS speeds and a corresponding linear velocity, create a plurality of packets comprising a plurality of samples for each wheel, determine mean and median values of the plurality of parameters for each packet. The system further comprises an AI/ML module configured to predict a tire pressure status for each packet of each wheel, and the alert generation unit is configured to generate an alert based on the prediction. Thus, the system facilitates accurate indirect tire pressure estimation and alert generation to the driver of the vehicle.
The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.
BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS
The features, nature, and advantages of the present disclosure will become more apparent from the detailed description set forth below when taken in conjunction with the drawings in which, like reference characters identify correspondingly throughout. Some embodiments of system and/or methods in accordance with embodiments of the present subject matter are now described, by way of example only, and with reference to the accompanying figures, in which:
Fig. 1 illustrates an environment for detecting tire pressure conditions in vehicle, in accordance with an embodiment of the present disclosure;
Fig. 2 illustrates an exemplary environment for determining GPS speed and linear velocity using speed sensor between two consecutive points, in accordance with an embodiment of the present disclosure;
Fig. 3(a) illustrates a block diagram of a system for detecting tire pressure conditions in vehicle, in accordance with an embodiment of the present disclosure;
Fig. 3(b) illustrates a block diagram of an AI/ML module, in accordance with an embodiment of the present disclosure;
Fig. 4(a) illustrates a flow diagram for training of the AI/ML module for predicting tire pressure condition, in accordance with an embodiment of the present disclosure;
Fig. 4(b) illustrates a flow diagram for predicting tire pressure condition of each wheel, in accordance with an embodiment of the present disclosure;
Fig. 5 illustrates a flowchart of a method of training the AI/ML module for predicting tire pressure condition, in accordance with an embodiment of the present disclosure;
Fig. 6 illustrates a flowchart of a method for filtering the invalid GPS speed values, in accordance with an embodiment of the present disclosure; and
Fig. 7 illustrates a flowchart of a method of detecting tire pressure conditions in vehicle, in accordance with another embodiment of the present disclosure.
It should be appreciated by those skilled in the art that any block diagram herein represents conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams and the like represent various processes which may be substantially represented in computer readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown.
DETAILED DESCRIPTION
The terms “comprise”, “comprising”, “include(s)”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, system or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or system or method. In other words, one or more elements in a system or apparatus proceeded by “comprises… a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or apparatus.
In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.
Fig. 1 illustrates an environment 100 for detecting tire pressure conditions in vehicle, in accordance with an embodiment of the present disclosure. In an embodiment, the environment 100 may comprises a vehicle 101 travelling on a road. The vehicle 101 is not limited to two-wheeler vehicle and may comprise any other vehicle. The vehicle 101 may comprise at least one speed sensor attached to each wheel of the vehicle 101 for counting the pulses between two consecutive GPS points and the vehicle 101 further comprises an electronic control unit (ECU) 107 for determining the revolution count based on pulses received between two GPS points and determine the linear velocity of the vehicle 101 based on the revolution count.
The vehicle 101 may further comprise GPS sensor 105 configured to obtain a plurality of GPS coordinates or GPS points at a predetermined time interval when the vehicle 101 is travelling on the road. The ECU 107 may be then configured to calculate the GPS speed between two consecutive GPS points. In one non-limiting embodiment, the ECU 107 may receive the GPS speed at a particular GPS point from a GPS module having the GPS sensor 105.
The ECU 107 may be then configured to discard the invalid GPS speed values based on a predetermined threshold value and to predict a tire pressure condition of the vehicle 101 using an Artificial Intelligence/Machine Learning module (AI/ML) module present in the ECU 107. In one non-limiting embodiment of the present disclosure, the AI/ML module may be present outside the ECU 107 in the vehicle 101.
The vehicle 101 includes a tire pressure indicator 109 configured to indicate the tire pressure status of the wheel of the vehicle 101 based on the predicted tire pressure condition of the wheel. The indication may include under-inflated condition and over-inflated condition of the tire.
This facilitates accurately estimating the tire pressure condition of each wheel of the vehicle using the onboard sensors of the vehicle and alerting the driver of the vehicle based on the estimated tire pressure condition of wheel of the vehicle.
Fig. 2 illustrates an exemplary environment 200 for determining GPS speed and linear velocity using speed sensor between two consecutive points, in accordance with an embodiment of the present disclosure.
In an embodiment of the present disclosure, the vehicle as shown in fig. 1 may travel on the road. The GPS sensor may be configured to share a plurality of GPS coordinates or GPS points (A, B, C, …, J) along with respective timestamp value. The GPS sensor may share the plurality of GPS coordinates or GPS points at regular interval of time.
The ECU of the vehicle may be configured to calculate GPS speed between two consecutive GPS point based on the GPS points and the timestamp value. In one non-limiting embodiment, the ECU may receive the GPS speed at a particular GPS point from a GPS module having the GPS sensor. The ECU may also be configured to determine and monitor revolution count of front and rear wheels corresponding to each interval from a plurality of intervals. Further, each interval corresponds to a distance between two consecutive GPS location points from the plurality of GPS location points based on an obtained pulses from the speed sensors that are installed on the front and rear wheels.
The ECU may be configured to determine a linear velocity of the vehicle corresponding to the GPS speed calculated between two consecutive GPS point. The linear velocity of the vehicle may be determined at least based on revolution count of front and rear wheels at each interval from the plurality of intervals. Further, each interval corresponds to the distance between the two consecutive GPS location points from the plurality of GPS location points.
In an embodiment of the present disclosure, the ECU may predict the tire pressure condition of each wheel of the vehicle at least based on GPS speeds and corresponding linear velocity along with a ratio of revolution count of the front and rear wheel. The prediction of tire pressure condition is discussed in detail in below embodiments.
Fig. 3(a) illustrates a block diagram of a system 300 for detecting tire pressure conditions in vehicle and fig. 3(b) illustrates a block diagram of an AI/ML module, in accordance with an embodiment of the present disclosure.
In an embodiment of the present disclosure, the system 300 may comprise a memory 301, speed sensors 303, GPS sensor 305, a processing unit 307, a filtering unit 309, an AI/ML module 311, and an alert generation unit 313 in communication with each other. The system 300 may be installed on the vehicle for detecting tire pressure conditions of the vehicle.
In an embodiment, the GPS sensor 305 may be configured to obtain a plurality of GPS coordinates or GPS points at regular interval of time from the GPS satellite and provide the plurality of GPS locations to the processing unit 307 along with their respective timestamp value. The processing unit 307 may be configured to determine a GPS speed of vehicle between each of the two consecutive GPS points based on the respective timestamp value.
In the same embodiment, the speed sensors 303 may be configured to count the pulses between two consecutive GPS points and the processing unit 307 may be configured to calculate the revolution count of each wheel based on the counted pulses. The speed sensors 303 may be installed on the front and rear side wheels of the vehicle. The speed sensors 303 may be a hall effect speed sensor. However, the speed sensor is not limited to above example and any other type of speed sensor is well within the scope of present disclosure.
The processing unit 307 may be then configured to determine the linear velocity of each of the front and rear wheels based on the respective revolution count of the front and rear wheels. In one non-limiting embodiment, the determined plurality of GPS speeds are mapped against the corresponding linear velocity of the front and rear wheels in the memory 301.
The filtering unit 309 may be configured to compare each of the plurality of GPS speed with a predetermined threshold value and discard at least one GPS speed of the plurality of GPS speed if the at least one speed is below the predetermined threshold value. In one non-limiting embodiment, the predetermined threshold value may be between 10km/hr to 30km/hr. However, the predetermined threshold value is not limited to above example and any other predetermined threshold value of speed used for comparison is well within the scope of present disclosure.
The filtering unit 309 along with the processing unit 307 may be then configured to apply band filtering to the remaining of the plurality of GPS speed. To apply the band filtering, the filtering unit 309 may be configured to calculate normalized difference using the remaining plurality of GPS speed and the corresponding mapped linear velocity.
In one non-limiting embodiment, the normalized difference may be calculated based on the following equations:
A=(GPS speed -Linear velocity of wheel) (1)
B=Linear velocity of the wheel=(No.of revolutions)/s*2*p*r (2)
Normalized Difference=A/B (3)
where the GPS speed and linear velocity of the wheel are in m/s and ‘r’ is radius of tire at 100 % inflation condition.
The filtering unit 309 along with the processing unit 307 may be then configured to compare the normalized difference of the each of the remaining of the plurality of GPS speed with a predetermined range and neglect one or more GPS speeds for which the normalized difference is outside the predetermined range to provide filtered GPS speeds. In one non-limiting embodiment, the predetermined range for the normalized difference may be calculated by conducting a number of experiments on the vehicle and the range for the normalized difference may be fixed for a particular type of vehicle.
The processing unit 307 may be then configured to determine a plurality of parameters based on the GPS speeds and the respective mapped linear velocity of each wheel of the vehicle. In one non-limiting embodiment, the plurality of parameters may comprise radius of each wheel and ratio of revolution count of the front and rear wheels. In one non-limiting embodiment, the plurality of parameters may also comprise the circumference of the wheel. However, the plurality of parameters are not restricted to above examples and any other parameter required for estimating/predicting tire pressure condition is well within the scope of present disclosure.
In one non-limiting embodiment, the radius of the front wheel, the rear wheel, and ratio of revolution count may be calculated using the below equations:
radius_f=(GPS speed)/(rotational speed_f ) (4)
radius_r=(GPS speed)/(rotational speed_r ) (5)
ratio=(revolution count_f)/(revolution count_r ) (6)
where radius_f is radius of front wheel, radius_(r ) is radius of rear wheel, rotational speed_f is rotational speed of front wheel, rotational speed_r is rotational speed of rear wheel, revolution count_f is revolution count of front wheel, and revolution count_r is revolution count of rear wheel. In another non-limiting embodiment, the circumference of the front and rear wheel may be calculated based on the radius of front wheel and the radius of the rear wheel.
Once the plurality of parameters are calculated, the processing unit 307 may be then configured to create a plurality of packets and each packet may comprise a plurality of samples. In one non-limiting embodiment, the number of packets may always be odd in number and the number of samples in a packet may be decided based on experiment. The number of samples may be fixed for a particular type of vehicle.
In one non-limiting embodiment, the plurality of samples of each packet created by the processing unit 307 may correspond to a plurality of parameters. The plurality of parameters may be calculated based on the filtered GPS speed and related linear velocity corresponding to each interval from the plurality of intervals. Further each interval corresponds to a distance between two consecutive GPS location points from the plurality of GPS location points.
After creating the plurality of packets, the processing unit 307 may be then configured to calculate a central tendency statistic of the plurality of parameters for each packet based on the values of samples present in the packet. In one non-limiting embodiment, to calculate the central tendency statistics the processing unit 307 may be then configured to calculate a mean and a median of the plurality of parameters for each packet.
The AI/ML module 311 as shown in fig. 3(b) may comprise at least one processor 321, database 323, a classification unit 325, a prediction unit 327 in communication with each other. The at least one processor 321 may be configured to receive a plurality of training data sets. Each training data set may include values of the plurality of parameters associated with each wheel at different pressure level values. The at least one processor 321 may be configured to train the classification unit 325 with the plurality of training data sets to generate at least one classifier function. The at least one classifier function may be stored in the database 323.
In accordance with the embodiment, for example each training data set may comprise plurality of parameters such as radius of the wheel, circumference of the wheel, ratio of the revolution of both the wheels, diameter of the tire for both the wheels. Further, a set of plurality of parameters may be assigned to the plurality of pressure levels. Thus, each training data set may comprise a set of plurality of parameters. The Set of parameters may comprise pressure levels corresponding to the front and rear tire.
In an embodiment, the different pressure levels include, but not limited to, 100% inflation, 90% inflation, 85% inflation, 80% inflation, 75% inflation, 70% inflation, 50% inflation of both front and rear wheels along with their respective parameters value are considered for training the AI/ML module and generating the classifier function. In one embodiment, different permutations and combinations of pressure levels of the front and rear tires may be considered such F100R90(Front 100, Rear 90), F85R70 (front 85 rear 70), and the like. The different pressure levels may act as a predetermined pressure threshold value.
The prediction unit 327 in communication with the at least one processor 321 may be configured to predict a tire pressure status for each packet of each wheel using the classifier function. The processing unit 307 may be then configured to predict the tire pressure status as under-inflated if the predicted tire pressure status of maximum number of packets is below a predetermined pressure threshold. In one non-limiting embodiment, the predetermined pressure threshold value may be 75% inflation and if the predicted tire inflation value is below 75% of tire inflation value, the tire pressure status is predicted as under inflated. The value of predetermined pressure threshold is not limited to above example and may vary based on road, type of a vehicle, type of tire used in the vehicle, and environmental conditions in which the vehicle is driven.
Further for example, consider the plurality of parameters of each training data set for both the wheels at above mentioned predetermined threshold pressure value i.e., for e.g., F85R70 (front 85 rear 70). The plurality of parameters of each training data set for both the wheels may be of 12-inch tire diameter, 5-inch wheel radius, and a ratio of revolution for both the wheels may be 100/100 to cover a distance between two consecutive GPS points. However, if the tire pressure in one of the wheels (front wheel for example) is reduced due to puncture, the pressure may change to F60R70 (front 60 rear 70). As a result, the plurality of parameters of each data packet obtained in real time for both the wheels may change and a ratio of revolution for both the wheels (F:R) may be 120/100 to cover a distance between two consecutive GPS points.
Thus, the number of revolutions of the front tire received in real time may be more as compared to the number of revolutions stored in the training dataset. Thus, based on this change in number of revolutions, the prediction unit 327 of the AI/ML module 311 may predict that the tire pressure of the front tire has reduced and needs attention. This change in the number of revolutions of the wheel is due to the reduction in tire pressure. As the tire pressure drops, the radius of the tire also reduces. This reduction results into increase in the number of revolutions to cover the same distance. In the above example, since the tire pressure of the front tire has reduced from F85 to F60, the number of revolutions required to cover the distance between the same two GPS points for the front wheel is increased from 100 to 120, whereas the rear wheel takes the same number of revolutions (i.e. 100). This change in the number of revolutions and/or the ratio of revolutions between the front and the rear wheels may be monitored by the alert generation unit 313. The alert generation unit 313 may be configured to generate an alert to the driver indicating the under-inflation tire pressure condition. The alert may be generated through an audio buzzer or indicator light, or both.
In another embodiment, the different pressure levels including, but not limited to, 100% inflation, 105% inflation, 110% inflation, etc., of both front and rear wheels along with their respective parameters value may be considered for training the AI/ML module and generating the classifier function for detecting over-inflated tire condition.
In the same embodiment, the prediction unit 327 in communication with the at least one processor 321 may be configured to predict a tire pressure status for each packet of each wheel using the above-mentioned classifier function. The processing unit 307 may be then configured to predict the tire pressure status as over inflated if the predicted tire pressure status of maximum number of packets is above a predetermined pressure threshold. In one non-limiting embodiment, the predetermined pressure threshold value may be 105 % inflation and if the predicted tire inflation value is above 105% of tire inflation value, the tire pressure status is predicted as over inflated. The value of predetermined pressure threshold is not limited to above example and may vary based on road, type of vehicle, type of tire used in the vehicle, and environmental conditions in which the vehicle is driven.
Further for example, consider the plurality of parameters of each training data set for both the wheels at above mentioned predetermined threshold pressure value i.e., for e.g., F85R70 (front 85 rear 70). The plurality of parameters of each training data set for both the wheels may be of 12-inch tire diameter, 5-inch wheel radius, and a ratio of revolution for both the wheels may be 100/100 to cover a distance between two consecutive GPS points as stated above. However, if the tire pressure in one of the wheels (front wheel for example) is increased due to overfilling, the pressure may change to F100R70 (front 100 rear 70). As a result, the plurality of parameters of each data packet obtained in real time for both the wheels may change and a ratio of revolution for both the wheels (F:R) may be 90/100 to cover a distance between two consecutive GPS points. This change in the number of revolutions and/or the ratio of revolutions between the front and the rear wheels may be monitored by the alert generation unit 313. The alert generation unit 313 may be configured to generate an alert to the driver indicating the over-inflation tire pressure condition. The alert may be generated through an audio buzzer, or indicator light, or both. The units 309, 325, and 327 may comprise a respective hardware unit or dedicated hardware circuitry required for carrying out the functionality as discussed in above embodiments.
Thus, the system 300 facilitates accurate estimation of the tire pressure condition of each wheel of the vehicle using the onboard sensors of the vehicle and generate an alert for the driver of the vehicle based on the estimated tire pressure condition of each wheel of the vehicle.
Fig. 4(a) illustrates a flow diagram 400a for training of the AI/ML module for predicting tire pressure condition, in accordance with an embodiment of the present disclosure.
In an embodiment of the present disclosure, a plurality of training data sets i.e., training data set-1, training data set-2, …, training data set-N are retrieved from the memory or the databases. Each training data set may include values of the plurality of parameters associated with each wheel at different pressure level values. The AI/ML module is trained based on the training data sets 1, 2, 3…, N to generate a classifier function, as discussed in above embodiments. The classifier function may vary from vehicle to vehicle. The at least one classifier function may be stored in the database.
In an embodiment, the different pressure levels for both the tires may be represented in the form of different permutations and combinations of pressure levels of the front and rear tires may be considered such F100R90(Front 100, Rear 90), F85R70 (front 85 rear 70), and the like. Alternatively, different pressure levels for both the tires may be represented in the form of Percentage (%) inflation including, but not limited to, 100% inflation, 90% inflation, 85% inflation, 80% inflation, 75% inflation, 70% inflation, 50% inflation. In another embodiment, the of both front and rear wheels along with their respective parameters value are considered for training the AI/ML module and generating the classifier function for under-inflated tire condition.
In another embodiment, the different pressure levels includes, but not limited to, 100% inflation, 105% inflation, 110% inflation, etc., of both front and rear wheels along with their respective parameters value are considered for training the AI/ML module and generating the classifier function for detecting over-inflated tire condition.
The classifier function may further include a lower and higher predetermined pressure threshold percentage value for categorizing the tire pressure condition as under-inflated or over-inflated tire pressure condition. The AI/ML module trained based on the above procedure may be used to predict the tire-pressure condition of the vehicle.
Fig. 4(b) illustrates a flow diagram 400b for predicting tire pressure condition of each wheel, in accordance with an embodiment of the present disclosure.
In an embodiment, a number of data packets 1, 2, …, N are provided to AI/ML module for predicting a tire-pressure status. Each data packet may comprise the mean and median of the plurality of parameters calculated from the values of samples present in the data packet.
Each data packet may be processed using the classifier function generated during the training of the AI/ML module to generate prediction results 1, 2, 3, …, N for the data packets 1, 2, …, N. The prediction result may be then used to generate an alert if under inflation or over inflation condition is detected.
Fig. 5 illustrates a flowchart of a method 500 of training the AI/ML module for predicting tire pressure condition, in accordance with an embodiment of the present disclosure.
At block 501, a plurality of the data sets are collected from the memory. The plurality of data sets comprise values of plurality of parameters associated with each wheel at plurality of pressure levels. The pressure levels may be percentage of tire pressure inflation as discussed in above embodiments.
At block 503, a machine learning (ML) module or artificial intelligence (AI) module may be trained based on the plurality of data sets. At block 505, at least one classifier function may be generated based on the training. In one non-limiting embodiment, the classifier function may be different for under-inflated and over-inflated tire pressure conditions. The classifier function may vary from vehicle to vehicle. The at least one classifier function may be stored in the database for predicting tire pressure condition in vehicles.
In another embodiment of the present disclosure, the steps of method 500 may be performed in an order different from the order described above.
Fig. 6 illustrates a flowchart of a method 600 for filtering the invalid GPS speed values, in accordance with an embodiment of the present disclosure.
At block 601, the plurality of calculated GPS speeds are compared with a predetermined threshold. In one non-limiting embodiment of the present disclosure, the predetermined threshold may be between 10km/hr to 30km/hr.
At block 603, the at least one GPS speed is discarded from further calculation if the at least one GPS speed is below the predetermined threshold. The remaining of the plurality of GPS speed are then subjected to band filtering. At block 605, a normalized difference is calculated using the remaining of the plurality of GPS speed and the corresponding mapped linear velocity of each tire. The normalized difference may be calculated using the equations (1)-(3), as discussed in above embodiments.
At block 607, the normalized difference of remaining of the plurality of GPS speed may be compared with a predetermined range. The predetermined range may be obtained by conduction experiment and the predetermined range may be fixed for a particular type of vehicle.
At block 609, one or more GPS speed for which the normalized difference is outside the predetermined range are neglected to have filtered GPS speeds. The filtered GPS speed may be then used for predicting the tire pressure condition of the vehicle.
Fig. 7 illustrates a flowchart of a method of detecting tire pressure conditions in vehicle, in accordance with another embodiment of the present disclosure.
At block 701, a plurality of GPS coordinates or GPS points are obtained at regular interval of time along with their respective timestamp value using the GPS sensor. At block 703, a revolution count of the pulses between two consecutive GPS point are monitored using the speed sensor installed at each wheel of the vehicle. The monitoring may be carried out using the procedure as discussed in above embodiments. A linear velocity of each wheel may be calculated based on the monitoring.
At block 705, a GPS speed of vehicle between each of the two consecutive GPS points may be determined based on the respective timestamp value. In one non-limiting embodiment, the determined plurality of GPS speeds are mapped against the corresponding linear velocity of the front and rear wheels in the memory.
At block 707, each of the GPS speed is compared with a predetermined threshold value and at least one GPS speed of the plurality of GPS speed is discarded, if the at least one speed is below the predetermined threshold value. In one non-limiting embodiment, the predetermined threshold value may be between 10km/hr to 30km/hr. However, the predetermined threshold value is not limited to above example and any other predetermined threshold value of speed used for comparison is well within the scope of present disclosure.
At block 709, band filtering is applied to the remaining of the plurality of GPS speed. The application of the band filtering comprises calculating a normalized difference using the remaining of the plurality of GPS speed and the corresponding mapped linear velocity. The normalized difference may be calculated based on the equations (1)-(3) as discussed in above embodiments.
The application of the band filtering further comprises comparing the normalized difference of the each of the remaining of the plurality of GPS speed with a predetermined range and neglecting one or more GPS speeds for which the normalized difference is outside the predetermined range to provide filtered GPS speeds. In one non-limiting embodiment, the predetermined range for the normalized difference may be calculated by conducting a number of experiments on the vehicle and the range for the normalized difference may be fixed for a particular type of vehicle.
At block 711, a plurality of parameters for the at least one wheel may be determined based on the GPS speeds and the respective mapped linear velocity of each wheel of the vehicle. In one non-limiting embodiment, the plurality of parameters may comprise radius of each wheel and ratio of revolution count of the front and rear wheels. In one non-limiting embodiment, the plurality of parameters may also comprise the circumference of the wheel. In one non-limiting embodiment, the plurality of parameters may be calculated using the equations (4)-(6).
At block 713, a plurality of packets are created, and each packet may comprise a plurality of samples for each wheel. In one non-limiting embodiment, the number of packets may always be odd in number and the number of samples in a packet may be decided based on experiment. The number of samples may be fixed for a particular type of vehicle. After creating the plurality of packets, a central tendency statistics of the plurality of parameters for each packet are determined based on the values of samples present in the packet. In one non-limiting embodiment, calculating the central tendency statistics may comprise calculating a mean and a median of the plurality of parameters for each packet.
At block 715, a tire pressure status for each packet of each wheel is predicted by the AI/ML module using the classifier function. The prediction may be carried out as per procedure described in above embodiments. At block 717, an alert is generated to the driver based on the prediction results. The alert may be generated through an audio buzzer or indicator light, or both.
This the method 700 facilitates accurate estimation of the tire pressure condition of each wheel of the vehicle using the onboard sensors of the vehicle and generates an alert for the driver of the vehicle based on the estimated tire pressure condition of each wheel of the vehicle.
In another embodiment of the present disclosure, the steps of method 700 may be performed in an order different from the order described above.
The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments.
Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer- readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., are non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
Suitable processors include, by way of example, a processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) circuits, any other type of integrated circuit (IC), and/or a state machine.

,CLAIMS:WE CLAIM:
1. A method (700) for monitoring tire pressure of a vehicle, the method (700) comprising steps of:
obtaining a plurality of GPS location points at predetermined interval of time;
monitoring revolution count of at least one wheel corresponding to each interval from a plurality of intervals, wherein each interval corresponds to a distance between two consecutive GPS location points from the plurality of GPS location points; and
Characterized in that,
determining a plurality of GPS speeds of the at least one wheel, wherein each GPS speed corresponds to each interval from a plurality of intervals;
determining a plurality of linear velocities based on the monitored revolution count of the at least one wheel, wherein the plurality of linear velocities corresponds to each interval from a plurality of intervals;
mapping the plurality of GPS speeds corresponding to plurality of linear velocities;
processing the plurality of GPS speeds to obtain a plurality of filtered GPS speeds;
determining a plurality of parameters, corresponding to each interval from the plurality of intervals, based on the filtered GPS speed and the corresponding linear velocity of at least one wheel at each interval;
creating plurality of data packets each comprising plurality of samples corresponding to the plurality of parameters corresponding to each interval from the plurality of intervals, wherein determining a central tendency statistic for the plurality of parameters comprised by each data packets;
predicting a tire pressure status for each data packets of at the least one wheel through a trained AI/ML module (311); and
generating an alert based on the tire pressure status.
2. The method (700) for monitoring tire pressure of a vehicle as claimed in claim 1, wherein the linear velocity is determined based on the monitoring of revolution counts, wherein the monitoring of revolution counts is based on obtaining pulses of the at least one wheel corresponding to each interval from a plurality of intervals.
3. The method (700) for monitoring tire pressure of a vehicle as claimed in claim 1, wherein the GPS speed is determined based on each interval and a timestamp value.
4. The method (700) for monitoring tire pressure of a vehicle as claimed in claim 1, wherein the mapped plurality of GPS speeds, corresponding to plurality of linear velocities, are stored in the memory (301).
5. The method (700) for monitoring tire pressure of a vehicle as claimed in claim 1, wherein the plurality of GPS speeds are processed to obtain plurality of filtered GPS speeds for plurality of intervals by:
comparing the plurality of GPS speeds with a predetermined threshold value by a filtering unit (309);
discarding at least one GPS speed if the at least one GPS speed is less than predetermined threshold value;
calculating a normalized difference using remaining plurality of GPS speeds and the corresponding mapped linear velocity by the filtering unit (309) to apply band filter;
comparing the normalized difference of each of the remaining plurality of the GPS speeds with a predetermined range by the filtering unit (309) and a processing unit (307); and
neglecting one or more GPS speed having normalized difference more than the predetermined range to obtain filtered GPS speed and corresponding mapped linear velocity.
6. The method (700) for monitoring tire pressure of a vehicle as claimed in claim 1, wherein the AI/ML module (311) is trained by:
collecting the plurality of datasets comprising a plurality of parameters of at least one wheel corresponding to a plurality of pressure levels;
training the AI/ML module (311) by receiving the plurality of dataset by a processor unit (321); and
generating of classifier function based on the plurality of dataset by a classification unit (325).
7. The method (700) for monitoring tire pressure of a vehicle as claimed in claim 6, wherein the classifier function includes a lower and higher predetermined pressure threshold values, wherein the lower and higher predetermined pressure threshold values correspond to under inflated or over inflated tire pressure condition.
8. The method (700) for monitoring tire pressure of a vehicle as claimed in claim 1, wherein predicting (400) the tire pressure of at least one wheel comprising steps:
feeding the plurality of data packets corresponding to plurality of intervals to AI/ML module (311);
processing the plurality of data packets with classifier function generated in above step (505);
generating the plurality of prediction results for each of the plurality of data packets;
generating an alert as under inflated tire pressure when the maximum number of prediction result of data packets are below the predetermined pressure threshold value, wherein generating an alert as over inflated tire pressure when the maximum number of prediction result of data packets are above the predetermined pressure threshold values, and wherein generating an alert as normal inflated tire pressure when the maximum number of prediction result of data packets falls within the range of predetermined pressure threshold values.
9. The method (700) for monitoring tire pressure of a vehicle as claimed in claim 8, wherein the plurality of the GPS speeds and plurality of the linear velocities are determined by the processing unit (307), wherein the pulse of the at least one wheel are obtained by the speed sensors (303).
10. A system (300) for monitoring tire pressure of a vehicle comprising:
a memory unit (301);
a processing unit (307) coupled to the memory unit (301), wherein the processing unit (307) is configured to execute programmed instructions stored in the memory for:
obtaining a plurality of GPS location points at predetermined interval of time;
monitoring revolution count of at least one wheel corresponding to each interval from a plurality of intervals, wherein each interval corresponds to a distance between two consecutive GPS location points from the plurality of GPS location points; and
Characterized in that,
determining a plurality of GPS speeds of the at least one wheel, wherein each GPS speed corresponds to each interval from a plurality of intervals;
determining a plurality of linear velocities based on the monitored revolution count of the at least one wheel, wherein the plurality of linear velocities corresponds to each interval from a plurality of intervals;
mapping the plurality of GPS speeds corresponding to plurality of linear velocities;
processing the plurality of GPS speeds to obtain a plurality of filtered GPS speeds;
determining a plurality of parameters, corresponding to each interval from the plurality of intervals, based on the filtered GPS speed and the corresponding linear velocity of at least one wheel at each interval;
creating plurality of data packets each comprising plurality of samples corresponding to the plurality of parameters corresponding to each interval from the plurality of intervals, wherein determining a central tendency statistic for the plurality of parameters comprised by each data packets;
predicting a tire pressure status for each data packets of at the least one wheel through a trained AI/ML module (311); and
generating an alert based on the tire pressure status.
11. The system (300) for monitoring tire pressure of a vehicle as claimed in claim 10, wherein the linear velocity is determined based on the monitoring of revolution counts, wherein the monitoring of revolution counts is based on obtaining pulses of the at least one wheel corresponding to each interval from a plurality of intervals.
12. The system (300) for monitoring tire pressure of a vehicle as claimed in claim 10, wherein the GPS speed is determined based on each interval and a timestamp value.
13. The system (300) for monitoring tire pressure of a vehicle as claimed in claim 10, wherein the mapped plurality of GPS speeds, corresponding to plurality of linear velocities, are stored in the memory (301).
14. The system (300) for monitoring tire pressure of a vehicle as claimed in claim 10, wherein the plurality of GPS speeds are processed to obtain plurality of filtered GPS speeds for plurality of intervals by:
comparing the plurality of GPS speeds with a predetermined threshold value by a filtering unit (309);
discarding at least one GPS speed if the at least one GPS speed is less than predetermined threshold value;
calculating a normalized difference using remaining plurality of GPS speeds and the corresponding mapped linear velocity by the filtering unit (309) to apply band filter;
comparing the normalized difference of each of the remaining plurality of the GPS speeds with a predetermined range by the filtering unit (309) and a processing unit (307); and
neglecting one or more GPS speed having normalized difference more than the predetermined range to obtain filtered GPS speed and corresponding mapped linear velocity.
15. The system (300) for monitoring tire pressure of a vehicle as claimed in claim 10, wherein the AI/ML module (311) is trained by:
collecting the plurality of datasets comprising a plurality of parameters of at least one wheel corresponding to a plurality of pressure levels;
training the AI/ML module (311) by receiving the plurality of dataset by a processor unit (321); and
generating of classifier function based on the plurality of dataset by a classification unit (325).
16. The system (300) for monitoring tire pressure of a vehicle as claimed in claim 15, wherein the classifier function includes a lower and higher predetermined pressure threshold values, wherein the lower and higher predetermined pressure threshold values correspond to under inflated or over inflated tire pressure condition.
17. The system (300) for monitoring tire pressure of a vehicle as claimed in claim 10, wherein predicting (400) the tire pressure of at least one wheel comprising steps:
feeding the plurality of data packets corresponding to plurality of intervals to AI/ML module (311);
processing the plurality of data packets with classifier function generated in above step (505);
generating the plurality of prediction results for each of the plurality of data packets;
generating an alert as under inflated tire pressure when the maximum number of prediction result of data packets are below the predetermined pressure threshold value, wherein generating an alert as over inflated tire pressure when the maximum number of prediction result of data packets are above the predetermined pressure threshold values, and wherein generating an alert as normal inflated tire pressure when the maximum number of prediction result of data packets falls within the range of predetermined pressure threshold values.
18. The system (300) for monitoring tire pressure of a vehicle as claimed in claim 17, wherein the plurality of the GPS speeds and plurality of the linear velocities are determined by the processing unit (307), wherein the pulse of the at least one wheel are obtained by the speed sensors (303).
Dated this 20th Day of April 2023

Priyank Gupta
Agent for the applicant
IN/PA-1454