FORM 2
THE PATENTS ACT 1970
[39 OF 1970]
&
THE PATENTS RULES, 2003
COMPLETE SPECIFICATION
[See section 10; Rule 13]
TITLE: “METHOD AND SYSTEM FOR PREDICTING POWERTRAIN NOISE OF A
VEHICLE”
Name and Address of the Applicant: TATA MOTORS LIMITED
Bombay House, 24 Homi Mody Street, Hutatma Chowk, Mumbai 400 001, Maharashtra, India. Nationality: Indian
The following specification particularly describes the invention and the manner in which it is to be performed.

TECHNICAL FIELD
The present subject matter is related in general to an automobile, more particularly, but not exclusively the present subject matter relates to a method and a system for predicting powertrain noise of a vehicle.
BACKGROUND
With the development of the automobile industry and the improvement of automobile quality, vehicle noise, vibration, and harshness (noise vibration harshness, NVH) have become one of the key indicators of automobile performance. For new vehicles, the noise generated by the powertrain is the main source that affects the NVH performance of the vehicle. Currently, in automobiles, to test/check the powertrain noise of the vehicle, an operator performs a physical test or purchases data from one or more consultants. The powertrain of the vehicle may include components such as engine, clutch and gear box of the vehicle. In physical testing of the powertrain noise, the operator is required to remove the powertrain from the vehicle along with its entire wiring harness and simulating the vehicle on test bench environment. The problem with the physical test involves emulating all functional interlocks, as if the vehicle is running on test bench-all Engine Control Unit (ECUs), neutral gear signal, clutch pressed, doors lock, wheels Anti-locking Braking System (ABS), etc. Further, procuring data from the consultants involves increased cost, along with non¬availability of necessary benchmark data. Thus, there is a requirement/need for efficiently testing powertrain noise of the vehicle.
The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
SUMMARY

In an embodiment, the present disclosure relates to a method for training a model for predicting powertrain noise of a vehicle. The method comprises receiving one or more vehicle specification parameters and one or more noise parameters associated with the vehicle. The method comprises training a model based on the one or more vehicle specification parameters and the one or more noise parameters.
In an embodiment, the present disclosure relates to a method for predicting powertrain noise of a vehicle. The method comprises receiving one or more vehicle specification parameters and one or more noise parameters associated with the vehicle. The method comprises predicting level of powertrain noise of the vehicle using a trained model based on the one or more vehicle specification parameters and the one or more noise parameters.
In an embodiment, the present disclosure relates to a prediction system for predicting powertrain noise of a vehicle. The prediction system includes a processor and a memory communicatively coupled to the processor. The memory stores processor-executable instructions, which on execution cause the processor to predict powertrain noise of the vehicle. The prediction system receives one or more vehicle specification parameters and one or more noise parameters associated with the vehicle. The prediction system predicts level of powertrain noise of the vehicle using a trained model based on the one or more vehicle specification parameters and the one or more noise parameters.
In an embodiment, the present disclosure relates to a model training system for training a model for predicting powertrain noise of a vehicle. The model training system includes a processor and a memory communicatively coupled to the processor. The memory stores processor-executable instructions, which on execution cause the processor to train a model for predicting powertrain noise of a vehicle. The model training system receives one or more vehicle specification parameters and one or more noise parameters associated with the vehicle. The model training system trains a model based on the one or more vehicle specification parameters and the one or more noise parameters.
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 accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components. 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 regarding the accompanying figures, in which:
Figure 1a shows an exemplary environment of a model training system for training a model for predicting powertrain noise of a vehicle, in accordance with some embodiments of the present disclosure;
Figure 1b shows an exemplary embodiment of a prediction system for predicting powertrain noise of a vehicle, in accordance with some embodiments of present disclosure;
Figure 2a shows a detailed block diagram of a model training system for training a model for predicting powertrain noise of a vehicle, in accordance with some embodiments of the present disclosure;
Figure 2b shows a detailed block diagram of a prediction system for predicting powertrain noise of a vehicle, in accordance with some embodiments of the present disclosure;
Figure 3 shows a trained model system for predicting powertrain noise of a vehicle, in accordance with some embodiments of present disclosure;
Figure 4a illustrates a flowchart showing an exemplary method for training a model for predicting powertrain noise of a vehicle, in accordance with some embodiments of present disclosure;

Figure 4b illustrates a flowchart showing an exemplary method for predicting powertrain noise of a vehicle, in accordance with some embodiments of present disclosure; and
Figure 5 shows a histogram diagram and a graph for successful validation of a trained system in accordance with the present disclosure.
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 substantially represented in computer readable medium and executed by a computer or processor, whether such computer or processor is explicitly shown.
DETAILED DESCRIPTION
In the present document, the word "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.
While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the spirit and the scope of the disclosure.
The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device, 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 device 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 method.

The terms “includes”, “including”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device, or method that includes 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 device or method. In other words, one or more elements in a system or apparatus proceeded by “includes… a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or method.
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.
The present disclosure relates to a prediction system and a method for predicting powertrain noise of a vehicle. The proposed method is configured to receive one or more vehicle specification parameters and one or more noise parameters of the vehicle during idling state of the vehicle. Upon receiving, the proposed method predicts the level of the powertrain noise of the vehicle using a trained machine learning model based on the one or more noise parameters and the one or more vehicle specification parameters. Thus, the present disclosure is able to predict the powertrain noise by eliminating the physical testing and purchasing of data from other consultants. Hence, resulting in reduced cost and time for testing powertrain noise of the vehicle.
Figure 1a shows an exemplary environment 100a of a model training system 101 for training a model for predicting powertrain noise of a vehicle. The exemplary environment 100a may include the model training system 101, and a vehicle 102. The environment 100a may be exterior of the vehicle 102. The model training system 101 may be implemented in any vehicle. The model training system 101 may be used to train a machine learning model for predicting the powertrain noise of the vehicle 102 by communicating with the vehicle 102. Further, the model training system 101 may include a processor 103, an I/O interface 104, and a memory 105. In some

embodiments, the memory 105 may be communicatively coupled to the processor 103. The memory 105 stores instructions, executable by the processor 103, which, on execution, may cause the model training system 101 for training the model for predicting powertrain noise of the vehicle 102, as disclosed in the present disclosure. In an embodiment, the memory 105 may include one or more modules 200 and data module 204 (as shown in Figure 2a). The one or more modules 200 may be configured to perform the steps of the present disclosure using the data module 204, for training the model for predicting powertrain noise of the vehicle 102. In an embodiment, each of the one or more modules 200 may be a hardware unit which may be outside the memory 105 and coupled with the model training system 101. In an embodiment, the model training system 101 may be associated with multiple vehicles for training the model for predicting powertrain noise of the vehicles.
In an embodiment, initially, the model training system 101 is configured to receive one or more parameters related to a vehicle specification and one or more noise parameters associated with the vehicle 102. In an embodiment, the one or more noise parameters may include, but is not limited to, measured exterior noise of the vehicle on Left hand side, Right hand side and front side. In an embodiment, the one or more vehicle specification parameters comprise engine type, number of cylinders, fuel type, engine capacity, Revolutions Per Minute (RPM) during the idling state. Further, the model training system 106 is configured to train a model based on the one or more vehicle specification parameters and the one or more noise parameters. In an embodiment, the model may be a Random Forest Regressor model.
Figure 1b shows an exemplary environment 100b of a prediction system 106 for predicting powertrain noise of a vehicle. The exemplary environment 100b may include the prediction system 106, and the vehicle 102. The environment 100a may be exterior of the vehicle 102. The vehicle 102 may be a four-wheeler vehicle, a three-wheeler vehicle, electric vehicle, a car and the like. Further, the prediction system 106 may include a processor 107, an I/O interface 108, and a memory 109. In some embodiments, the memory 109 may be communicatively coupled to the processor 107. The memory 109 stores instructions, executable by the processor 107, which, on execution, may cause the prediction system 106 for predicting powertrain noise of the vehicle 102, as disclosed in the present disclosure. In an embodiment, the memory 109 may include one or more modules 210 and data module 204 (as shown in Figure 2b). The one or more modules 210

may be configured to perform the steps of the present disclosure using the data module 204, for predicting powertrain noise of the vehicle 102. In an embodiment, each of the one or more modules 210 may be a hardware unit which may be outside the memory 109 and coupled with the prediction system 106. In an embodiment, the prediction system 106 may be associated with multiple vehicles for predicting powertrain noise of the vehicles.
In an embodiment, during testing of powertrain of the vehicle 102, the prediction system 106 is configured to receive one or more parameters related to a vehicle specification and one or more noise parameters associated with the vehicle 102. In an embodiment, the one or more noise parameters may include, but is not limited to, measured exterior noise of the vehicle on Left hand side, Right hand side and front side. In an embodiment, one or more noise parameters are obtained during an idling state of the vehicle 102. Accordingly, the noise predicted may be the idling noise of the vehicle. In other embodiments, noise may be predicted for a running state of the vehicle. I an embodiment, the one or more noise parameters are obtained from microphones placed at appropriate locations around the vehicle.
In an embodiment, the one or more vehicle specification parameters comprise engine type, number of cylinders, fuel type, engine capacity, Revolutions Per Minute (RPM) during idling state. Further, the prediction system 106 is configured to predict level of powertrain noise of the vehicle 102 using a trained model based on the one or more vehicle specification parameters and the one or more noise parameters.
Figure 2a shows a detailed block diagram of a model training system for training a model for predicting powertrain noise of a vehicle, in accordance with some embodiments of the present disclosure.
The data module 204 and the one or more modules 200 in the memory 105 of the model training system 101 is described herein in detail.
In one implementation, the one or more modules 200 may include, but are not limited to, a receiving module 201, a training module 202 and one or more other modules 203, associated with the model training system 101.

In an embodiment, the data module 204 in the memory 105 may include the noise parameters 205, the vehicle specification parameters 206 and other data 207 associated with the model training system 101.
In an embodiment, the data module 204 in the memory 105 may be processed by the one or more modules 200 of the model training system 101. In an embodiment, the one or more modules 200 may be implemented as dedicated units and when implemented in such a manner, said modules may be configured with the functionality defined in the present disclosure to result in a novel hardware. As used herein, the term module may refer to an Application Specific Integrated Circuit (ASIC), an electronic circuit, a Field-Programmable Gate Arrays (FPGA), Programmable System-on-Chip (PSoC), a combinational logic circuit, and/or other suitable components that provide the described functionality.
One or more modules 200 of the present disclosure function to train the model for predicting the powertrain noise of the vehicle 102. The one or more modules 200 may also include other modules 203 to perform various other functionalities of the model training system 101. It will be appreciated that such modules may be represented as a single module or a combination of different modules. The one or more modules 200 along with the data module 204, may be implemented in any system, for training model for predicting the powertrain noise of the vehicle 102.
The noise parameters 205 may include information regarding the one or more noise parameters of the vehicle 102. The one or more noise parameters may include, but is not limited to, measured exterior noise of the vehicle on Left hand side, Right hand side and front side.
The vehicle specification parameters 206 may include information regarding the specifications of the vehicle 102. The vehicle specification parameters 206 comprise engine type, number of cylinders, fuel type, engine capacity, Revolutions Per Minute (RPM) during idling state.
The other data 207 may store data, including temporary data and temporary files, generated by modules for performing the various functions of the model training system 101.

In an embodiment, prior to predicting the powertrain noise of the vehicle 102, the operator may train the model training system 101 to predict the powertrain noise. Initially, the receiving module 201 of the model training system 101 is configured to receive the one or more noise parameters and the one or more vehicle specification parameters. The training module 202 is configured to train the model based on the one or more noise parameters and the one or more vehicle specification parameters.
Figure 2b shows a detailed block diagram of a prediction system for predicting powertrain noise of a vehicle, in accordance with some embodiments of the present disclosure.
The data module 204 and the one or more modules 210 in the memory 109 of the prediction system 106 is described herein in detail.
In one implementation, the one or more modules 210 may include, but are not limited to, a receiving module 211, a predicting module 212 and one or more other modules 213, associated with the prediction system 106.
In an embodiment, the data module 204 in the memory 109 may include noise parameters 205, vehicle specification parameters 206 and other data 207 associated with the prediction system 106.
In an embodiment, the data module 204 in the memory 109 may be processed by the one or more modules 210 of the prediction system 106. In an embodiment, the one or more modules 210 may be implemented as dedicated units and when implemented in such a manner, said modules may be configured with the functionality defined in the present disclosure to result in a novel hardware. As used herein, the term module may refer to an Application Specific Integrated Circuit (ASIC), an electronic circuit, a Field-Programmable Gate Arrays (FPGA), Programmable System-on-Chip (PSoC), a combinational logic circuit, and/or other suitable components that provide the described functionality.
One or more modules 210 of the present disclosure function to predict the powertrain noise of the vehicle 102. The one or more modules 210 may also include other modules 213 to perform various other functionalities of the prediction system 106. It will be appreciated that such modules may be represented as a single module or a combination of different modules. The one or more modules

210 along with the data module 204, may be implemented in any prediction system, for predicting
the powertrain noise of the vehicle 102.
The noise parameters 205 may include information regarding the one or more noise parameters of the vehicle 102. The one or more noise parameters may include, but is not limited to, measured exterior noise of the vehicle on Left hand side, Right hand side and front side.
The vehicle specification parameters 206 may include information regarding the specifications of the vehicle 102. The vehicle specification parameters 206 comprise engine type, number of cylinders, fuel type, engine capacity, Revolutions Per Minute (RPM) during idling state.
The other data 207 may store data, including temporary data and temporary files, generated by modules for performing the various functions of the prediction system 106.
Initially, consider a scenario where an operator is required to perform testing of the vehicle 102 for noise. In an embodiment, the vehicle 102 may be a car. In an embodiment, the powertrain of the car may include, but not limited to, engine, clutch and gear box of the car. The receiving module
211 of the prediction system 106 is configured to receive the one or more noise parameters
associated with the car. The one or more noise parameters may be obtained using a microphone.
In an embodiment, the microphone may obtain the one or more noise parameters during the idling
state of the car. In an embodiment, the microphone may be placed on the right-hand side, left hand
side and front side of a driving compartment of the car at predefined distance from the car. In an
embodiment, the one or more noise parameters may include, but is not limited to, measured
exterior noise of the car on left hand side, right hand side and front side of the driving compartment.
In an embodiment, the measured exterior noise of the car is one-third octave of a predefined decibel
range. In an embodiment, the predefined decibel range may be 20 to 20,000 hertz.
In an embodiment, the receiving module 211 is configured to receive the one or more parameters related to the car specification. The one or more parameters related to the car specification may include, but is not limited to, engine type, number of cylinders, fuel type, engine capacity, Revolutions Per Minute (RPM) during idling state. The engine type may include normally aspirated engine, turbocharged engine, common rail direct injection engine, multi-point fuel injection engine, etc. In an embodiment, the one or more vehicle specification parameters may also

include, whether the vehicle is a passenger vehicle or a commercial vehicle. In an embodiment, the one or more noise parameters and the one or more parameters related to vehicle specification may be collectively referred to as input 304 (as shown in Figure 3). Thereafter, the predicting module 212 of the prediction system 106 is configured to predict the level of powertrain noise of the car using a trained model based on the on the one or more vehicle specification parameters and the one or more noise parameters. In an embodiment, the level of powertrain noise predicted may be referred to as output 305 (as shown in Figure 3)..
Figure 3 shows a trained model system for predicting powertrain noise of a vehicle, in accordance with some embodiments of present disclosure. In an embodiment, one or more parameters related to a vehicle specification and one or more noise parameters associated with the vehicle may be provided as training input 301 to a machine learning model 302. The machine learning model 302 may be trained using input parameters 301. The machine learning model 302 may use a suitable algorithm while training.. A trained model 303 is configured to predict the level of powertrain noise of the vehicle based on the on the one or more vehicle specification parameters and the one or more noise parameters 304. In an embodiment, the trained model (303) may be referred to as trained/prediction system. In an embodiment, the level of powertrain noise predicted may be referred to as output 305. To select suitable input parameters 304 and the model 302, one or more experiments (as explained below) were conducted, as will be explained in the below section.
Figure 4a illustrates a flowchart showing an exemplary method for training a model for predicting powertrain noise of a vehicle, in accordance with some embodiments of present disclosure.
As illustrated in Figure 4a, the method 400a may include one or more blocks for executing processes in the model training system 101. The method 400a may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform particular functions or implement particular abstract data types.
The order in which the method 400a are described may not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the

method. Additionally, individual blocks may be deleted from the methods without departing from the scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof.
At block 401, the method may receive, one or more vehicle specification parameters and one or more noise parameters associated with the vehicle.
At block 402, the method may train, a model based on the one or more vehicle specification parameters and the one or more noise parameters. In an embodiment, the one or more noise parameters may include, but is not limited to, measured exterior noise of the vehicle on Left hand side, Right hand side and front side. In an embodiment, the one or more vehicle specification parameters comprise engine type, number of cylinders, fuel type, engine capacity, Revolutions Per Minute (RPM) during the idling state.
Figure 4b illustrates a flowchart showing an exemplary method for predicting powertrain noise of a vehicle, in accordance with some embodiments of present disclosure.
As illustrated in Figure 4b, the method 400b may include one or more blocks for executing processes in the prediction system 106. The method 400b may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform particular functions or implement particular abstract data types.
The order in which the method 400b are described may not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof.
At block 403, the method may receive, one or more parameters related to a vehicle specification and one or more noise parameters associated with the vehicle.

At block 404, the method may predict, level of powertrain noise of the vehicle using a trained model based on the one or more vehicle specification parameters and the one or more noise parameters. In an embodiment, the one or more noise parameters may include, but is not limited to, measured exterior noise of the vehicle on Left hand side, Right hand side and front side. In an embodiment, one or more noise parameters are obtained during an idling state of vehicle 102. Accordingly, the noise predicted may be the idling noise of the vehicle. In an embodiment, the one or more noise parameters are obtained from microphones placed at appropriate locations around the vehicle. In an embodiment, the one or more vehicle specification parameters comprise engine type, number of cylinders, fuel type, engine capacity, Revolutions Per Minute (RPM) during idling state.
EXPERIMENTS
Experiments to select correct/appropriate input parameters
In order to select a correct/appropriate training input, one or more experiments were conducted. During the experiments, initially the parameters: fuel type, engine capacity, number of cylinders, Hot idle RPM, exterior noise in dBA from left hand side, right hand side, front side, cabin type of vehicle, engine center of gravity, engine surrounding acoustic shield were considered as input parameters for training a model. With these input parameters, the model predicted a noise level of 61.88dBA for the vehicle at idle. This predicted noise level was significantly above a measured noise level of 59.42dBA for the vehicle at idle. Various combination of input parameters were tried during the experiments to reduce the error between measured and predicted noise levels. During the experiments, while using the parameters: engine type, number of cylinders, fuel type, engine capacity, RPM during idling state, measured exterior noise of the vehicle on Left hand side, Right hand side and front side, the model predicted the noise level of 59.57dBA for the vehicle at idle which was close to the above measured noise level. In view of this result, the parameters cabin type of vehicle, engine center of gravity, engine surrounding acoustic shield were removed from the list of input parameters. The parameters engine type, number of cylinders, fuel type, engine capacity, RPM during idling state, measured exterior noise of the vehicle on Left hand side, Right hand side and front side were identified as the correct/appropriate input parameters for training the

model. The training module 202 of the system 101 was then configured to train the model based on the on the selected input parameters.
Experiments to select an appropriate model
To select a best suitable model for training the input parameters, one or more experiments using multiple machine learning algorithms were conducted. During the experiments, the linear regressor, random forest regressor, gradient boosting regressor, xGBoost, and Cat Boost algorithms were considered for accuracy prediction. The accuracy predication was calculated based on R2 score. An algorithm which offers higher R2 score was identified as higher accuracy prediction algorithm. During the experiments, the above algorithms offered the R2 score as mentioned in the below table.
AI/ML Algorithms and Prediction Accuracy table

Algorithm R2 Score (denotes prediction accuracy)
liner regressor 0.86
random forest regressor 0.93
gradient boosting regressor 0.89
xGBoost 0.91
Cat Boost 0.92
With the experiments, the random forest regressor which offered highest R2 score (i.e. highest accuracy for idle noise prediction was identified as the appropriate model for training the input parameters. The selected model was then utilised to train the input parameters for predicting the powertrain noise.
Experiments for validating a trained model system
To validate a trained model 303, experiments were conducted. Fig.5 shows a graph for successful validation of the trained system. During the experiments, the trained system was validated using various criteria. The criteria shown in Fig. 5 was used for validating the trained model 303 which is used for predicting the level of powertrain noise of the vehicle 102. The trained model 303 was

validated by comparing a measured noise value with a predicted noise value of the powertrain noise of the vehicle (as shown in Figure 5). During the experiments, a 1/3rd octave spectrum was used to calculate an overall noise value of the powertrain noise of the vehicle. The overall noise value was calculated by using an average value of the 1/3rd octave obtained from 20 Hz to 20 kHz spectrum band. During the experiments, after comparing the measured noise value with the predicted noise value, a differentiating value was obtained. For the successful validation, it was identified that the differentiating value should be within a predefined range value. As shown in Fig. 5, the measured value was 59.42 dBA and the predicted powertrain noise value obtained during the experiments was 59.57 dBA for the vehicle at idle. The differentiating value for the powertrain noise was calculated as 0.15 dB, which was obtained by subtracting the predicted powertrain value and the measured value. The differentiating value was also referred as error value. During the experiments, for successful powertrain noise prediction at idle, it was identified that the predicted powertrain value should be within +/- 1 dB with respect to the measured value. Also, the predicted powertrain value should be within +/- 2 dB with respect to the measured value throughout 1/3rd octave spectrum band. The trained model 303 which offers the predicted powertrain value within the said above predetermined value (as shown in Fig. 5) was considered as a qualified system and used for predicting powertrain noise of the vehicle.
Advantages
An embodiment of the present disclosure helps in automatically predicting powertrain noise using vehicle noise parameters and vehicle specification parameters.
An embodiment of the present disclosure results in reducing cost and time consumption in predicting the powertrain noise.
The described operations may be implemented as a method, system or article of manufacture using standard programming and/or engineering techniques to produce software, firmware, hardware, or any combination thereof. The described operations may be implemented as code maintained in a “non-transitory computer readable medium”, where a processor may read and execute the code from the computer readable medium. The processor is at least one of a microprocessor and a processor capable of processing and executing the queries. A non-transitory computer readable

medium may include media such as magnetic storage medium (e.g., hard disk drives, floppy disks, tape, etc.), optical storage (CD-ROMs, DVDs, optical disks, etc.), volatile and non-volatile memory devices (e.g., EEPROMs, ROMs, PROMs, RAMs, DRAMs, SRAMs, Flash Memory, firmware, programmable logic, etc.), etc. Further, non-transitory computer-readable media may include all computer-readable media except for a transitory. The code implementing the described operations may further be implemented in hardware logic (e.g., an integrated circuit chip, Programmable Gate Array (PGA), Application Specific Integrated Circuit (ASIC), etc.).
An “article of manufacture” includes non-transitory computer readable medium, and /or hardware logic, in which code may be implemented. A device in which the code implementing the described embodiments of operations is encoded may include a computer readable medium or hardware logic. Of course, those skilled in the art will recognize that many modifications may be made to this configuration without departing from the scope of the invention, and that the article of manufacture may include suitable information bearing medium known in the art.
The terms “an embodiment”, “embodiment”, “embodiments”, “the embodiment”, “the embodiments”, “one or more embodiments”, “some embodiments”, and “one embodiment” mean “one or more (but not all) embodiments of the invention(s)” unless expressly specified otherwise.
The terms “including”, “comprising”, “having” and variations thereof mean “including but not limited to”, unless expressly specified otherwise.
The enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise.
The terms “a”, “an” and “the” mean “one or more”, unless expressly specified otherwise.
A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary a variety of optional components are described to illustrate the wide variety of possible embodiments of the invention.
When a single device or article is described herein, it will be readily apparent that more than one device/article (whether or not they cooperate) may be used in place of a single device/article.

Similarly, where more than one device or article is described herein (whether or not they cooperate), it will be readily apparent that a single device/article may be used in place of the more than one device or article, or a different number of devices/articles may be used instead of the shown number of devices or programs. The functionality and/or the features of a device may be alternatively embodied by one or more other devices which are not explicitly described as having such functionality/features. Thus, other embodiments of the invention need not include the device itself.
The illustrated operations of Figures 4a and 4b show certain events occurring in a certain order. In alternative embodiments, certain operations may be performed in a different order, modified, or removed. Moreover, steps may be added to the above-described logic and still conform to the described embodiments. Further, operations described herein may occur sequentially or certain operations may be processed in parallel. Yet further, operations may be performed by a single processing unit or by distributed processing units.
Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based here on. Accordingly, the disclosure of the embodiments of the invention is intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.
While various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope and spirit being indicated by the following claims.

Referral numerals:

Reference Number Description
100a and 100b Environment
101 Model training system
102 Vehicle
106 Prediction System
103, 107 Processor
104, 108 I/O interface
105, 109 Memory
200, 210 Modules
201 Receiving module
202 Training module
203, 213 Other modules
204 Data module
205 Noise parameters
206 Vehicle specification parameters
207 Other data
211 Receiving module
212 Predicting module
301 Training input
302 Machine learning
303 Trained model
304 Input
305 Output

WE CLAIM:
1. A method for predicting powertrain noise of a vehicle (102), the method comprising:
receiving, by a prediction system (106), one or more vehicle specification parameters and one or more noise parameters associated with the vehicle (102); and
predicting, by the prediction system (106), level of powertrain noise of the vehicle using a trained model based on the one or more vehicle specification parameters and the one or more noise parameters.
2. The method as claimed in claim 1, wherein the one or more noise parameters comprise measured exterior noise of the vehicle on Left hand side, Right hand side and front side.
3. The method as claimed in claim 1, wherein the one or more noise parameters are obtained during an idling state of the vehicle.
4. The method as claimed in claim 1, wherein the one or more vehicle specification parameters comprise engine type, number of cylinders, fuel type, engine capacity, Revolutions Per Minute (RPM) during idling state.
5. A method for training a model for predicting powertrain noise of a vehicle (102), the method comprising:
receiving, by a model training system (101), one or more vehicle specification parameters and one or more noise parameters associated with the vehicle (102); and
training, by the model training system (101), a model based on the one or more vehicle specification parameters and the one or more noise parameters.
6. The method as claimed in claim 5, wherein the one or more noise parameters comprise measured exterior noise of the vehicle on Left hand side, Right hand side and front side.
7. The method as claimed in claim 5, wherein the one or more vehicle specification parameters comprise engine type, number of cylinders, fuel type, engine capacity, Revolutions Per Minute (RPM) during idling state.

8. The method as claimed in claim 5, wherein the model is a Random Forest Regressor.
9. A prediction system (106) for predicting powertrain noise of a vehicle (102), comprising:
a processor (107); and
a memory (109) communicatively coupled to the processor (107), wherein the processor (107) is configured to:
receive one or more vehicle specification parameters and one or more noise parameters associated with the vehicle (102); and
predict level of powertrain noise of the vehicle (102) using a trained model based on the one or more vehicle specification parameters and the one or more noise parameters.
10. The prediction system (106) as claimed in claim 9, wherein the one or more noise parameters comprise measured exterior noise of the vehicle on Left hand side, Right hand side and front side.
11. The prediction system (106) as claimed in claim 9, wherein the one or more noise parameters are obtained during an idling state of the vehicle.
12. The prediction system (106) as claimed in claim 9, wherein the one or more vehicle specification parameters comprise engine type, number of cylinders, fuel type, engine capacity, Revolutions Per Minute (RPM) during idling state.
13. A model training system (101) for training a model for predicting powertrain noise of a vehicle, comprising:
a processor (103); and
a memory (105) communicatively coupled to the processor (103), wherein the processor (103) is configured to:
receive one or more vehicle specification parameters and one or more noise parameters associated with the vehicle (102); and

train a model based on the one or more vehicle specification parameters and the one or more noise parameters.
14. The model training system (101) as claimed in claim 13, wherein the one or more noise parameters comprise measured exterior noise of the vehicle on Left hand side, Right hand side and front side.
15. The model training system (101) as claimed in claim 13, wherein the one or more vehicle specification parameters comprise engine type, number of cylinders, fuel type, engine capacity, Revolutions Per Minute (RPM) during idling state.
16. The model training system (101) as claimed in claim 13, wherein the model is a Random Forest Regressor.