FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENTS RULES, 2003
COMPLETE SPECIFICATION (See section 10, rule 13)
“A METHOD, APPARATUS AND SYSTEM FOR MONITORING BRAKE PAD LIFE OF A VEHICLE”
TATA MOTORS PASSENGER VEHICLES LIMITED, of Floor 3, 4, Plot-18, Nanavati Mahalaya, Mudhana Shetty Marg, BSE, Fort, Mumbai, Mumbai City, Maharashtra, 400001, India
The following specification particularly describes the invention and the manner in which it is to be performed.

TECHNICAL FIELD
[001] The present invention relates to vehicle systems. In particular, it relates to monitoring
the wear state of a brake-pad of a vehicle and determining its remaining useful life
(RUL).
BACKGROUND
[002] The following description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.
[003] Brake pads hold a paramount role in the automotive world, serving as the linchpin of safety and performance within a vehicle's braking system. These components play a pivotal role in the critical task of slowing down and stopping the vehicle when necessary. As and when the driver applies pressure to the brake pads, brake pads engage with the brake rotors, generating the friction needed to transform the vehicle's kinetic energy into heat. Now over a period of time, this heat causes the brake pads to gradually wear down. Additionally, the events such as constant press and release during braking, frequency of pressing the brake pads, and intensity of braking along with exposure to dust, debris, and moisture, contribute to wear down of the brake pads. Eventually, brake pads reach a point where their thickness becomes insufficient, reducing their ability to generate the necessary friction, compromising braking performance as well as the safety of both the occupants as well as the pedestrians. Therefore, regular inspections and maintenance are essential to monitor brake pad wear and accordingly, based on such inspection, one can think of replacing the brake pads timely before they become dangerously thin.
[005] In the existing scenario, there exists multiple brake pad monitoring systems which monitor the wear and tear state of the brake pad and suggest replacement as and when required. However, almost all of these existing systems deploy various kinds of sophisticated sensors and wear monitoring devices to determine the damaged state. But these additional components not only add to the product cost but also enhances the complexity associated with manufacturing of the vehicle.

[006] There is therefore a need for a method and system that utilizes the existing vehicle machinery to determine the wear and tear state of the brake pad of a vehicle and predict its RUL thus, indicating the driver in real-time about the wear state of the brake pads and the remaining effective life of the brake pads. The utilization of existing vehicle machinery not only significantly reduces the financial implications of encashing upon the existing technologies but also negates the need of retrofitting in the existing vehicles.
SUMMARY
[007] The present disclosure overcomes one or more shortcomings of the prior art and
provides additional advantages. Embodiments and aspects of the disclosure described
in detail herein are considered a part of the claimed disclosure.
[008] In one non-limiting embodiment of the present disclosure, a method for predicting Remaining Useful Life (RUL) of a brake pad of a vehicle is disclosed. The method includes monitoring perpetually a plurality of vehicle parameters while the vehicle is in motion. The method also includes calculating derived parameters from the plurality of vehicle parameters. The method also includes storing the plurality of vehicle parameters and the derived parameters temporarily at a cloud platform till the vehicle covers a predefined distance. The method also includes analyzing, by a pretrained learning model, wear state of brake pad of the vehicle once the vehicle has covered the predefined distance, where analyzing the wear state of brake pad includes calculating weight of the vehicle based on the plurality of monitored vehicle parameters and at least one of the derived parameters, determining temperature of the brake pad of the vehicle before pressing the brake pad of the vehicle and post releasing the brake pad of the vehicle, and analyzing wear state of the brake pad of the vehicle based on the weight of the vehicle and the determined temperature of the brake pad of the vehicle. The method also includes predicting the Remaining Useful Life (RUL) of the brake pad based on the analyzed wear state of the brake pad of the vehicle.
[009] In yet another embodiment of the present disclosure, the plurality of vehicle parameters comprises at least one of: initial vehicle speed at a moment when brake is applied, final vehicle speed when brake is released, gear state of the vehicle when brake is applied, brake press state, ambient temperature, engine RPM and acceleration and wherein the

derived parameters comprises at least kinetic energy, engine torque and deceleration of the vehicle.
[0010] In yet another embodiment of the present disclosure, training of the learning
model comprises receiving the plurality of vehicle parameters and the derived parameters. calculating temperature of brake pad before pressing, by a heat generation learning model, wherein the heat generation learning model calculates the temperature of brake pad before pressing as a function of average speed of the vehicle, break press state, time stamp, ambient temperature of the vehicle and the temperature of the brake pad post latest brake release. Further, calculating temperature of brake pad post release, by a cooling model, wherein the cooling model calculates the temperature of brake pad post release as a function of kinetic energy of the vehicle, time duration for which brake pad is actuated, brake press state and the temperature of the brake pad just before the brake pad is pressed. The method further comprises analysing the derived parameters and temperature of brake pad before pressing and post release of the brake pad to determine wear state of the brake pad of the vehicle. Also, the method comprises mapping the determined wear state of the brake pad of the vehicle with a prestored data available in a lookup table and predicting the RUL of the brake pad of the vehicle based on the mapping.
0011] In yet another embodiment of the present disclosure, the stored plurality of vehicle parameters and the derived parameters are deleted every time when the wear state of the brake pad is analyzed by the pretrained learning model.
[0012] In yet another embodiment of the present disclosure, A device for predicting
Remaining Useful Life (RUL) of a brake pad of a vehicle, the device comprising a memory and a processing unit. The memory is configured to receive plurality of vehicle parameters and derived parameters and store the plurality of vehicle parameters and the derived parameters temporarily till the vehicle covers a predefined distance. The processing unit in conjunction with the memory is configured to analyze, via a pretrained learning model, wear state of the brake pad of the vehicle once the vehicle has covered the predefined distance by calculating weight of the vehicle based on the plurality of monitored vehicle parameters and at least one of the derived parameters. The processing unit further configured to determine temperature of the brake pad of the

vehicle before pressing the brake pad of the vehicle and post releasing the brake pad of the vehicle. Further, the processing unit is configured to analyze wear state of the brake pad of the vehicle based on the weight of the vehicle and the determined temperature of the brake pad of the vehicle and predict the Remaining Useful Life (RUL) of the brake pad based on the analyzed wear state of the brake pad of the vehicle.
[0013] In yet another embodiment of the present disclosure, the plurality of vehicle parameters comprises at least one of: initial vehicle speed at a moment when brake is applied, final vehicle speed when brake is released, gear state of the vehicle when brake is applied, brake press state, ambient temperature, engine RPM and acceleration and wherein the derived parameters comprises at least kinetic energy, engine torque and deceleration of the vehicle.
[0014] In yet another embodiment of the present disclosure, to train the learning model,
the processing unit is configured to receive the plurality of vehicle parameters and the derived parameters. Processing unit is further configured to calculate temperature of brake pad before pressing, by a heat generation learning model, wherein the heat generation learning model calculates the temperature of brake pad before pressing as a function of average speed of the vehicle, break press state, time stamp, ambient temperature of the vehicle and the temperature of the brake pad post latest brake release. The processing unit is further configured to calculate temperature of brake pad post release, by a cooling model, wherein the cooling model calculates the temperature of brake pad post release as a function of kinetic energy of the vehicle, time duration for which brake pad is actuated, brake press state and the temperature of the brake pad just before the brake pad is pressed. Furthermore, the processing unit is configured to analyze the derived parameters and temperature of brake pad before pressing and post release of the brake pad to determine wear state of the brake pad of the vehicle and map the determined wear state of the brake pad of the vehicle with a prestored data available in a lookup table. The processing unit is also configured to predict the RUL of the brake pad of the vehicle based on the mapped wear state.
[0015] In yet another embodiment of the present disclosure, the cloud platform is configured to delete the stored plurality of vehicle parameters and the derived parameters every time when the wear state of the brake pad is analyzed by the pretrained learning model.

[0016] In yet another embodiment of the present disclosure, the processing unit is
further configured to transmit information related to wear state of the brake pad and the predicted RUL of the brake pad of the vehicle to a User Interface (UI) and to a master dashboard. The processing unit is configured to generate an alert signal on the User Interface of the vehicle if the predicted RUL of the brake pad reaches a pre-defined threshold level and provide option for resetting the RUL, on the User Interface, if a new brake pad is installed.
[0017] In yet another embodiment of the present disclosure, a centralized system is
disclosed. The centralized system comprising a connected vehicle platform, a database, a control unit. The centralized system configured to receive one or more data points associated with a plurality of vehicles, wherein the one or more datapoints comprises information related to a plurality of vehicle parameters and corresponding derived parameters. The database configured to store the plurality of data points corresponding to the each of the plurality of the vehicles. The control unit coupled to the connected vehicle platform and the database and configured to analyze wear state of the brake pad of each of the plurality of the vehicle and predict Remaining useful Life (RUL) of each of the plurality of the vehicles based on the process. Thereafter , it transmits information related to the wear state of the brake pad and the predicted RUL of the brake pad of the each of the plurality of vehicles to a master dashboard and analyze driving pattern and environmental variables corresponding to each of the plurality of vehicles based on the datapoints and information transmitted to the master dashboard.
[0018] 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 DRAWINGS
[0019] 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 Figs., in which:
[0020] Fig.1 depicts an exemplary block diagram 100 illustrating a system to monitor wear state of a brake pad of a vehicle and determining its remaining useful life (RUL), in accordance with an embodiment of the present disclosure;
[0021] Fig.2 depicts an exemplary block diagram 200 illustrating the brake pad life monitoring system being hosted at a connected vehicle platform, in accordance with another embodiment of the present disclosure;
[0022] Fig.3 depicts an exemplary block diagram 300 illustrating a system to determine the weight of the vehicle, in accordance with still another embodiment of the present disclosure;
[0023] Fig.4 depicts an exemplary block diagram 400 illustrating a system to determine the temperature of the brake pads of the vehicle corresponding to their pressing state, in accordance with the embodiments of the present disclosure;
[0024] Fig.5 depicts an exemplary block diagram 500 illustrating a system to collect data related to the wear state of brake pads of multiple vehicles and their respective RULs on a master dashboard, in accordance with the embodiments of the present disclosure;
[0025] Figure 6 represents a flowchart 600 of an exemplary method for monitoring the wear state of a brake-pad of a vehicle and determining its remaining useful life (RUL), in accordance with the embodiments of the present disclosure;
[0026] Figure 6A represents a flowchart illustrating a part of an exemplary method for analysing the wear state of the brake-pads of the vehicle, in accordance with the embodiments of the present disclosure;
[0027] It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various

processes which may be represented in a computer readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown.
DETAILED DESCRIPTION
[0028] The foregoing has broadly outlined the features and technical advantages of the present disclosure in order that the detailed description of the disclosure that follows may be better understood. It should be appreciated by those skilled in the art that the conception and specific embodiment disclosed may be readily utilized as a basis for modifying or designing other structures for carrying out the same purposes of the present disclosure.
[0029] The novel features which are believed to be characteristic of the disclosure, both as to its organization and method of operation, together with further objects and advantages will be better understood from the following description when considered in connection with the accompanying figures. It is to be expressly understood, however, that each of the figures is provided for the purpose of illustration and description only and is not intended as a definition of the limits of the present disclosure.
[0030] In the present disclosure, the term “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any embodiment or implementation of the present subject matter described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.
[0031] The terms “comprise”, “comprising”, “include”, “including”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a device that comprises a list of components does not include only those components but may include other components not expressly listed or inherent to such setup or device. 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.
[0032] The terms like “at least one” and “one or more” may be used interchangeably or in combination throughout the description.
[0033] The terms like “user”, “driver”, “vehicle owner” may be used interchangeably or in combination throughout the description.

[0034] The terms like “brake-pads”, “brakes” may be used interchangeably or in combination throughout the description.
[0035] Brake pads are critical components that provide friction, enabling vehicles to slow down and stop safely as and when required. Their proper function ensures driver control, enhances road safety thus preventing accidents. However, depending on the intensity and frequency of their application, brake pads tend to wear out which may lead to reduced braking efficiency, longer stopping distances, increased risk of accidents, and potential damage to other brake components. Neglecting their timely replacement may further escalate repair costs, compromise driver safety, and cause severe accidents due to inadequate braking capabilities. The existing technologies in the market to regularly monitor the brake pad wear and tear state come with sophisticated sensors or other related equipments which may further add to the cost as well as the complexity of the vehicle systems.
[0036] In order to overcome the above-mentioned challenges, the present disclosure aims to provide timely indication and alerts about the RUL of the brake pads. In order to provide these alerts, the present disclosure aims to develop a low-cost, machine learning based system to monitor/forecast the brake-pad wear state and display the predicted brake pad RUL using real-time as well as calculated/derived parameters collected from the vehicle without any need for deploying dedicated brake pad sensors or any other additional components. After estimating the RUL of the brake pads, display unit of the vehicle displays the remaining distance which may be effectively covered with the existing brake pads (RUL) and issues an alert or warning accordingly for the vehicle owner to replace the brake pads to ensure their effective functioning.
[0037] Fig.1 depicts an exemplary block diagram 100 illustrating a system to monitor wear state of a brake pad of a vehicle and determining its remaining useful life (RUL). In this, various vehicle sensors 102 are configured to monitor the real-time parameters of the vehicle. In one non-limiting embodiment, these parameters may include vehicle speed, gear information, odometer reading, brake press state, engine RPM, time stamp for which brakes are pressed, among others. These monitored parameters are then sent to the vehicle electronic control unit (ECU) 104 which in turn may comprise of a vehicle Controller area network (CAN) 106 and a vehicle telematics unit (VTU) 108. The

vehicle ECU 104 calculates the other derived vehicle parameters. In another non-limiting embodiment, these calculated/derived parameters by the vehicle ECU 104 may include acceleration, deceleration, engine torque, among others. These parameters, both real-time as well as derived, are transmitted to a connected vehicle platform (CVP) 110 by the VTU 108 in conjunction with the vehicle CAN 106. In one non-limiting embodiment, the CVP 110 may be a cloud platform. The CVP 110 hosts a memory 112 which may be used for storing the parameters sent to it by the VTU 108. These parameters sent by the VTU 108 are temporarily stored in the memory unit 112 at the CVP 110 till the time the vehicle covers a pre-defined distance. Once the pre-defined distance is covered by the vehicle, then the memory unit 112 sends all the received data for the pre-defined distance to a processing unit 114 hosted by the CVP 110. This processing unit 114 in turn hosts a break-pad life monitoring system 116 which is configured to invoke a pre-trained learning model to calculate the brake pad wear state and determine its RUL. The memory unit 112 deletes the stored parameters as and when the learning model is invoked for a pre-defined distance travelled by the vehicle and the RUL is calculated based on the stored parameters. For instance, in an non-limiting exemplary scenario, the memory unit 112 at the CVP 110 may be configured to store the received parameters for every 100 kms distance covered by the vehicle i.e., the memory unit 112 stores the received parameters data for 100kms and transmits them to the break-pad life monitoring system 116 after every 100kms covered where the learning model is invoked to calculate the brake-pad wear state and determine its RUL, whereas the memory unit 112 deletes the whole database consisting of the received parameters for those 100kms covered by the vehicle and start the process of storing the received parameters for next 100kms and so on. In this way, only small amount of memory may be utilized for providing the necessary data for calculating the RUL. The distance 100km is considered only as an exemplary scenario and this should not be considered in limiting sense. CVP may be configured for storing the data related to different value of distance by the owner or manufacturer or user, based on their requirement.
[0038] The processing unit 114 then transmits the calculated brake-pad wear state as well as the predicted RUL of the brake-pad of the vehicle to a User interface (UI) 118. The processing unit 114 may also be configured to generate an alert signal if the predicted RUL of the brake-pad of the vehicle falls below a pre-defined threshold to warn the

user to change the brake-pads to maintain effective and safe functioning of the vehicle. Further based on the derived results from the pre-trained learning model, the processing unit 114 may also indicate to the user the need to replace the existing brake-pad with new ones. Also, a feature may be provided at the UI 118 to reset the whole mechanism if the existing brake pads are replaced. Now, in one non-limiting embodiment of the present disclosure, the learning model being invoked by the brake-pad life monitoring system 116 may be trained by the historic data collected by the Master Dashboard and certain thresholds may be derived based on that data which may indicate the safety percentage of continuing with the existing brake pads or may also indicate the need for their replacement if the predicted RUL of the brake-pad of the vehicle falls below a certain pre-determined threshold derived from that historically collected data. In another non-limiting embodiment, the UI 118 may include the vehicle’s dashboard, the vehicle owner’s mobile device or any other such device which is capable of displaying the transmitted information and resetting the mechanism if brake-pads are replaced.
[0039] Now, to elaborate further on the functioning of the CVP, Fig. 2 of the present disclosure needs to be referred which depicts an exemplary block diagram 200 illustrating the components of a system being hosted at the CVP 202 to calculate the brake-pad wear state of the vehicle and further predict its RUL. In this, the CVP 202 hosts a memory unit 204 which may be configured to receive both monitored as well as derived parameters from the VTU and store them temporarily till a pre-defined distance is travelled by the vehicle. After covering the pre-defined distance, the memory unit 204 feeds the monitored and derived parameters to the processing unit 206 being hosted at the CVP 202. This processing unit 206 may be configured to analyze wear state of the brake pad of the vehicle once the vehicle has covered the predefined distance. For this analysis, the processing unit 206 in turn comprises a brake-pad life monitoring system 208 which hosts plurality of pre-trained learning models to determine different parameters in order to estimate the RUL of the brake-pad of the associated vehicle. The plurality of pre-trained learning models may comprise a weight determination model 210, a temperature determination model 212 and a brake-pad wear estimation model 214. The weight determination model 210 may be deployed to determine the real-time weight of the vehicle whereas the temperature determination model 212 may be deployed to determine the real-time temperature of the brake-pad of the vehicle. And the output from these two learning models is fed to the brake-pad wear model 214 which

eventually determines the brake-pad wear state of the vehicle and then predicts their RUL. However, the detailed functioning of these plurality of learning models have been explained in the upcoming paragraphs in conjunction with Fig. 3-4 of the present disclosure.
[0040] Fig.3 depicts an exemplary block diagram 300 illustrating the components of a system to determine the real-time weight of the vehicle. In this, the weight model 308 which is hosted at the processing unit of the CVP, as explained in Fig. 2, has been explained in detail. It receives the monitored parameters 304 and derived parameters 306 from the memory unit 302 being hosted at the CVP. In one non-limiting embodiment, the monitored parameters 304 may include initial vehicle speed, brake press state, gear information, engine RPM as well as acceleration whereas the derived parameters 306 may include engine torque. These parameters are then fed to a weight determination model 310, which is a pre-trained learning model to determine the weight of the vehicle based on the received input parameters. In one non-limiting embodiment of the present disclosure, this weight determination model 310 may be trained from the historically collected vehicle data and is therefore deployed to determine the weight of the vehicle. The weight determination model 310 deploys the pre-trained learning model and outputs the weight of the vehicle 312.
[0041] Fig.4 in turn, depicts an exemplary block diagram 400 illustrating a system to determine the temperature of the brake pads of the vehicle corresponding to their pressing state. In this, the temperature model 402 hosts a heat generation model 412 and a cooling model 416 to determine the temperature of the brake-pad of the vehicle as and when its pressing state changes. These heat generation model 412 and the cooling model 416 are pre-trained learning models and in one non-limiting embodiment of the present disclosure, these learning models may be trained from the historically collected vehicle data by the operator. Now, the heat generation model 412 and the cooling model 416 require diverse set of inputs to determine their corresponding temperatures which are explained in detail in the upcoming paragraphs.
[0042] The heat generation model 412 uses monitored parameters 406 along with the derived parameters 408 and other inputs to determine the temperature of the brake-pads of the vehicle after the brake-pads are pressed and brakes are applied. In one non-limiting

embodiment, the monitored parameters 406 may include the initial vehicle speed before the brake pads are pressed as well as the final vehicle speed after brake-pads have been pressed. Whether the brake-pads are pressed or not may be determined by monitoring the brake-pad press state, which may also be one of the monitored parameters 404 fed to the heat generation model 412. It may further include a time stamp parameter for defining the duration for which brakes are pressed whereas the derived parameters 406 may include deceleration. In addition to this, the heat generation model 412 also requires the kinetic energy parameter of the associated vehicle to effectively determine the temperature of the brake-pads of the vehicle when brakes are pressed. For this, the temperature model 402 takes the output of the weight determination model i.e., weight of the vehicle 404 as explained in Fig. 3, as an input along with the monitored parameters 406 to determine kinetic energy 410 which is then fed to the heat generation model 412 along with both monitored parameters 406 and the derived parameters 408. It also takes the temperature of the brake-pads just before the brake press 418 into consideration. All these described parameters are deployed by the heat generation learning model 412 to estimate the final temperature of the brake-pads just after the brake-pads are released 414.
[0043] Now, for the cooling model 416, the monitored parameters 420, the derived parameters 422 and the temperature of the brake-pads just after brakes are released from pressed state 414 may be required as inputs. In one non-limiting embodiment, the monitored parameters 420 may include brake press state and the time stamp indicating time duration for which no brakes were applied whereas the derived parameters 422 may include the average vehicle speed for the duration during which no brakes were applied. These parameters are then fed to the cooling model 416 which is a pre-trained learning model to determine the temperature of the brake pads just before the brakes were applied to 418 by the driver.
[0044] Referring back to Fig. 2 and 3, in conjunction with Fig. 4, the output from the weight determination model 310 and the kinetic energy 410 derived from it are applied to the brake-pad wear model 214. The temperature of the brake-pads just after the brake-pads release 414 as well as the temperature of the brake-pads just before the brake-pad press 418 from the temperature model 402 are also fed to the brake-pad wear model 214. The brake-pad wear model 214, which may also be a pre-trained learning model as

explained above, analyzes these received parameters, and compares the calculated data with the dataset pre-stored in a look-up table to determine the wear state of the brake-pads and then predict their effective RUL.
[0045] Fig. 5, in yet another embodiment, depicts an exemplary block diagram 500 illustrating a system to collect data from multiple vehicles and transmitting their respective analysed brake-pad wear state as well as predicted RULs on a master dashboard. In this, monitored as well as derived parameters are collected from a plurality of VTUs (502a, 502b…502n) associated with corresponding plurality of vehicles and transmitted to their respective memory units (506a, 506b….506n), hosted at a CVP 504. They are configured to store the received monitored and derived parameters temporarily for a pre-defined distance travelled by these vehicles. After the pre-defined distance is travelled by the vehicles, the data stored at the memory units (506a, 506b…506n) are transmitted to the processing unit 508 hosted at the CVP 504 which in turn transmits the data to a break-pad life monitoring system 510, thereby invoking the brake-pad wear model as explained in the foregoing paragraphs. The calculated brake-pad wear state and the predicted RULs of the respective vehicles are then collectively stored in the memory unit 512 at the operator side which may be linked to the master dashboard 514 for displaying the analysis. This collected data at the memory unit 512 and their corresponding display at the master dashboard 514 may then be utilized to study the driving patterns of multiple users, various environmental conditions or to refine the learning models being deployed for calculating the RULs of brake-pads. In yet another non-limiting embodiment, this data may also be utilized by the engineering division to enhance the efficiency and working of newly manufactured brake-pads.
[0046] Fig. 6 illustrates a flowchart 600 of an exemplary method monitoring wear state of a brake pad of a vehicle and determining its remaining useful life (RUL), in accordance with an embodiment of the present disclosure. The method 600 may also be described in the general context of computer executable instructions. Generally, computer executable instructions may include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform specific functions or implement specific abstract data types.

[0047] The order in which the method 600 is described is not intended to be construed as a limitation, and any number of the described method blocks may be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the spirit and scope of the subject matter described.
[0048] At step 602, the method 600 may include monitoring perpetually a plurality of vehicle parameters while the vehicle is in motion. In one non-limiting embodiment, the plurality of the real-time vehicle parameters may be determined by a variety of sensors like odometer, gear information, among others. Further, in yet another non-limiting embodiment of the present disclosure, the plurality of vehicle parameters may include initial vehicle speed at a moment when brake is applied, final vehicle speed when brake is released, gear state of the vehicle when brake is applied, brake press state, ambient temperature, engine RPM and acceleration of the vehicle.
[0049] At step 604, the method 600 may include calculating derived parameters from the plurality of vehicle parameters. In one non-limiting embodiment, the derived parameters may be calculated by the vehicle ECU as illustrated in Fig. 1. Further, in yet another non-limiting embodiment of the present disclosure, derived parameters comprise at least engine torque and deceleration of the vehicle.
[0050] At step 606, the method 600 may include storing the plurality of vehicle parameters and the derived parameters temporarily at a cloud platform till the vehicle covers a predefined distance. In one non-limiting embodiment, these parameters may be stored in the memory unit being hosted by the CVP as illustrated in Fig. 1 of the present disclosure.
[0051] At step 608, the method 600 may include analysing, by a pretrained learning model, wear state of brake pad of the vehicle once the vehicle has covered the predefined distance. In one non-limiting embodiment, the pre-trained learning model may be configured within a processing unit hosted by the CVP. Further, in yet another non-limiting embodiment of the present disclosure, the pre-trained learning model may be trained by the historically collected vehicle data. Furthermore, the processing unit may host a plurality of pre-trained learning model for analysing different parameters which may be understood in reference to Fig. 6A of the present disclosure.

[0052] Figure 6A represents the method steps followed for analysing the wear state of brake pad.
[0053] At step 608A, the method includes calculating weight of the vehicle based on the plurality of monitored vehicle parameters and at least one of the derived parameters. In one non-limiting embodiment, the weight of the vehicle may be determined by a pre-trained weight determination model hosted by the processing unit at the CVP.
[0054] At step 608B, the method includes determining temperature of the brake pad of the vehicle before pressing the brake pad of the vehicle and post releasing the brake pad of the vehicle. In one non-limiting embodiment, the temperature of the brake pads before pressing the brake-pads as well as after release of the pressed brake-pads may be determined by a pre-trained temperature model hosted by the processing unit at the CVP.
[0055] At step 608C, the method includes analysing the wear state of the brake pad of the vehicle based on the weight of the vehicle and the determined temperature of the brake pad of the vehicle. In one non-limiting embodiment, the wear state of the brake-pads may be analysed by a pre-trained brake-pad wear model which receives the output of the weight determination model and temperature model as input and predict its RUL. In yet another non-limiting embodiment, the brake-pad wear model may determine the wear state of the brake-pads by referring to a pre-stored lookup table and consequently predict its RUL.
[0056] At step 610, the method 600 may include predicting the Remaining Useful Life (RUL) of the brake pad based on the analyzed wear state of the brake pad of the vehicle. In one non-limiting embodiment, the predicted RUL may be transmitted to the user interface and corresponding alert signals may be generated to warn the user about brake-pad wear state if the RUL of the brake-pads falls below a threshold level. In yet another non-limiting embodiment, the processing unit hosted at the CVP may be configured to transmit the predicted RUL to the user interface. Along with this, the processing may be further configured to provide an option to reset the whole mechanism at the user interface if the brake-pads are replaced by the user.

[0057] 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.
[0058] 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.
[0059] 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, non-volatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
[0060] Suitable processors include, by way of example, a general-purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a graphic processing unit (GPU), 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.
Advantages of the embodiment of the present disclosure are illustrated herein-

[0061] In an embodiment, the present disclosure provides techniques for determining brake-pad wear state of the vehicle and predict its RUL without need for deploying any additional sophisticated sensors thus reducing the complexity of manufacturing as well as enhancing the economic sustainability.
[0062] In an embodiment, the present disclosure provides techniques for utilizing minimum storage at the cloud platform as the monitored and derived parameters are stored temporarily at the CVP thus significantly reducing excessive memory/storage requirement, thus, manging small amount of data may reduce computation complexity and generate quick response.
[0063] In an embodiment, the present disclosure provides techniques of easy processing for analysing the brake-pad wear state and predicting its RUL as the pre-trained learning model may be invoked after every pre-determined distance is travelled by the vehicle. Further, since single learning model may be deployed for all the in-field vehicles (same type of vehicles), thus enhancing the efficiency of the proposed system.

We Claim:
1. A method for predicting Remaining Useful Life (RUL) of a brake pad of a vehicle, the method comprising:
monitoring perpetually a plurality of vehicle parameters while the vehicle is in motion;
calculating derived parameters from the plurality of vehicle parameters;
storing the plurality of vehicle parameters and the derived parameters temporarily at a cloud platform till the vehicle covers a predefined distance;
analyzing, by a pretrained learning model, wear state of brake pad of the vehicle once the vehicle has covered the predefined distance, wherein analyzing the wear state of brake pad comprises:
calculating weight of the vehicle based on the plurality of monitored vehicle parameters and at least one of the derived parameters;
determining temperature of the brake pad of the vehicle before pressing the brake pad of the vehicle and post releasing the brake pad of the vehicle; and
analyzing wear state of the brake pad of the vehicle based on the weight of the vehicle and the determined temperature of the brake pad of the vehicle; and
predicting the Remaining Useful Life (RUL) of the brake pad based on the analyzed wear state of the brake pad of the vehicle.
2. The method as claimed in claim 1, wherein the plurality of vehicle parameters comprises at least one of: initial vehicle speed at a moment when brake is applied, final vehicle speed when brake is released, gear state of the vehicle when brake is applied, brake press state, ambient temperature, engine RPM and acceleration and wherein the derived parameters comprises at least kinetic energy, engine torque and deceleration of the vehicle.
3. The method as claimed in claim 1, wherein training of the learning model comprises:
receiving the plurality of vehicle parameters and the derived parameters;
calculating temperature of brake pad before pressing, by a heat generation learning model, wherein the heat generation learning model calculates the temperature of brake pad before pressing as a function of average speed of the vehicle, break press state, time stamp,

ambient temperature of the vehicle and the temperature of the brake pad post latest brake release;
calculating temperature of brake pad post release, by a cooling model, wherein the cooling model calculates the temperature of brake pad post release as a function of kinetic energy of the vehicle, time duration for which brake pad is actuated, brake press state and the temperature of the brake pad just before the brake pad is pressed;
analysing the derived parameters and temperature of brake pad before pressing and post release of the brake pad to determine wear state of the brake pad of the vehicle;
mapping the determined wear state of the brake pad of the vehicle with a prestored data available in a lookup table; and
predicting the RUL of the brake pad of the vehicle based on the mapping.
4. The method as claimed in claim 1, wherein the stored plurality of vehicle parameters and the derived parameters are deleted every time when the wear state of the brake pad is analyzed by the pretrained learning model.
5. The method as claimed in claim 1, further comprising:
transmitting information related to wear state of the brake pad and the predicted RUL of the brake pad of the vehicle to a User Interface (UI) and to a master dashboard;
generating an alert signal on the User Interface of the vehicle if the predicted RUL of the brake pad reaches below a pre-defined threshold level; and
providing option for resetting the RUL, on the User Interface, if a new brake pad is installed.
6. A device for predicting Remaining Useful Life (RUL) of a brake pad of a vehicle, the device
comprising:
a memory, wherein the memory configured to:
receive plurality of vehicle parameters and derived parameters;
store the plurality of vehicle parameters and the derived parameters temporarily till the vehicle covers a predefined distance;
a processing unit, wherein the processing unit in conjunction with the memory configured to analyze, via a pretrained learning model, wear state of the brake pad of the vehicle once the vehicle has covered the predefined distance by:

calculating weight of the vehicle based on the plurality of monitored vehicle parameters and at least one of the derived parameters;
determining temperature of the brake pad of the vehicle before pressing the brake pad of the vehicle and post releasing the brake pad of the vehicle; and
analyzing wear state of the brake pad of the vehicle based on the weight of the vehicle and the determined temperature of the brake pad of the vehicle; and
predicting the Remaining Useful Life (RUL) of the brake pad based on the analyzed wear state of the brake pad of the vehicle.
7. The device as claimed in claim 6, wherein the plurality of vehicle parameters comprises at least one of: initial vehicle speed at a moment when brake is applied, final vehicle speed when brake is released, gear state of the vehicle when brake is applied, brake press state, ambient temperature, engine RPM and acceleration and wherein the derived parameters comprises at least kinetic energy, engine torque and deceleration of the vehicle.
8. The device as claimed in claim 6, wherein to train the learning model, the processing unit configured to:
receive the plurality of vehicle parameters and the derived parameters;
calculate temperature of brake pad before pressing, by a heat generation learning model, wherein the heat generation learning model calculates the temperature of brake pad before pressing as a function of average speed of the vehicle, break press state, time stamp, ambient temperature of the vehicle and the temperature of the brake pad post latest brake release;
calculate temperature of brake pad post release, by a cooling model, wherein the cooling model calculates the temperature of brake pad post release as a function of kinetic energy of the vehicle, time duration for which brake pad is actuated, brake press state and the temperature of the brake pad just before the brake pad is pressed;
analyze the derived parameters and temperature of brake pad before pressing and post release of the brake pad to determine wear state of the brake pad of the vehicle;
map the determined wear state of the brake pad of the vehicle with a prestored data available in a lookup table; and
predict the RUL of the brake pad of the vehicle based on the mapped wear state.

9. The device as claimed in claim 6, wherein the cloud platform configured to delete the stored
plurality of vehicle parameters and the derived parameters every time when the wear state of
the brake pad is analyzed by the pretrained learning model.
10. The device as claimed in claim 6, wherein the processing unit further configured to:
transmit information related to wear state of the brake pad and the predicted RUL of the brake pad of the vehicle to a User Interface (UI) and to a master dashboard;
generate an alert signal on the User Interface of the vehicle if the predicted RUL of the brake pad reaches a pre-defined threshold level; and
provide option for resetting the RUL, on the User Interface, if a new brake pad is installed.
11. A centralized system comprising:
a connected vehicle platform configured to receive one or more data points associated with a plurality of vehicles, wherein the one or more datapoints comprises information related to a plurality of vehicle parameters and corresponding derived parameters;
a database configured to store the plurality of data points corresponding to the each of the plurality of the vehicles;
a control unit coupled to the connected vehicle platform and the database and configured to:
analyze wear state of the brake pad of each of the plurality of the vehicle;
predict Remaining useful Life (RUL) of each of the plurality of the vehicles based on the process as claimed in claims 1-5;
transmit information related to the wear state of the brake pad and the predicted RUL of the brake pad of the each of the plurality of vehicles to a master dashboard; and
analyze driving pattern and environmental variables corresponding to each of the plurality of vehicles based on the datapoints and information transmitted to the master dashboard.