Description:Complete Specification:
The following specification describes and ascertains the nature of this invention and the manner in which it is to be performed:


Field of the invention:
[0001] The present disclosure relates a controller and method for fatigue lifetime estimation of engine components in a vehicle.

Background of the invention:
[0002] According to a prior art US2020334922 discloses determining vehicle service timeframes based on vehicle data. A device may receive vehicle data from a vehicle telematics device or a client device. The vehicle data may include information relating to a vehicle, a vehicle component, and a sensor associated with the vehicle. The device may determine a vehicle profile, and one or more of a driving behavior and a driving location based on the vehicle data. The vehicle profile may include information relating to a condition of the vehicle component. The device may determine a wear rate for the vehicle component based on the vehicle profile, and one or more of the driving behavior or the driving location. The device may determine a service timeframes for the vehicle component based on the wear rate, the condition of the vehicle component, and a wear threshold. The device may generate a recommendation based on the service timeframe, and transmit the recommendation to the client device.

Brief description of the accompanying drawings:
[0003] An embodiment of the disclosure is described with reference to the following accompanying drawings,
[0004] Fig. 1 illustrates a block diagram of a controller for fatigue lifetime estimation of engine components in a vehicle, according to an embodiment of the present invention, and
[0005] Fig. 2 illustrates a flow diagram of a method for estimating fatigue lifetime of engine components in a vehicle, according to the present invention.

Detailed description of the embodiments:
[0006] Fig. 1 illustrates a block diagram of a controller for fatigue lifetime estimation of engine components in a vehicle, according to an embodiment of the present invention. The controller 110 is shown to be part of a system 100 which comprises at least one vehicle 130. The controller 110 configured to receive and collect data comprising parameters 128 related to vehicle 130 through a communication network 120, process the collected data through an estimation module 118 to evaluate a fatigue damage of the engine component. The estimation module 118 is pre-trained using an Artificial Intelligence (AI) and/ or Machine Learning (ML) models. The controller 110 determines a lifetime of the engine component and which is as an output 114 of the estimation module 118, characterized in that, the estimation module 118 is configured to take driving profile 116 of the vehicle 130 as input for lifetime calculation of the engine components. The driving profile 116 is derived using the vehicle parameter 128. The lifetime may also be referred to as remaining useful life (RUL) or fatigue lifetime etc.

[0007] According to an embodiment of the present invention, the communication network 120 is at least one selected from a group comprising a Controller Area Network (CAN), a Local Interconnect Network (LIN), other vehicular network, Wi-Fi, Bluetooth, or Subscriber Identity Module (SIM) or e-SIM based network through a Telematics Control Unit (TCU) or Connectivity Control Unit (CCU).

[0008] According to an embodiment of the present invention, the engine components is at least one selected from a group comprising a fuel pump, a fuel rail, a fuel injector, a fuel rail pressure sensor, a fuel injector nozzle, a high pressure connector, an engine block, valves, crankshaft, and the like.

[0009] According to an embodiment of the present invention, the parameters 128 related to vehicle 130 are selected from a group comprising a global distance, an engine speed 102, a vehicle velocity 104, an acceleration pedal position 106, a fuel injection quantity 108, a fuel rail pressure, an engine torque, a gear position, and the like.

[0010] According to an embodiment of the present invention, the controller 110 is part of a device which at least one of internal to the vehicle 130 and external to the vehicle 130. The device is at least one selectable from a group comprising an Engine Control Unit, a smartphone, a cloud computer, and the like.

[0011] According to an embodiment of the present invention, the driving profile 116 is considered for a specific duty class of the vehicle 130 for estimation/prediction of failure of engine component.

[0012] According to an embodiment of the present invention, an operation of the controller 110 is explained. The controller 110 receives or collects raw or real-time data containing the parameter 128 from the vehicle 130 either through the TCU which is connected with the CAN or directly collected from the CAN or through On-Board Diagnostics (OBD) port or other known communications. The collected data containing the parameters 128 undergoes data preparation through automated statistical data cleaning. The statistical data cleaning comprises outlier detection using Interquartile Range (IQR) method, missing value treatment (dropping Not Application (NA) values), terrain classification or route detection through classification based on route labels and extrapolation. The terrain classification or route detection is performed by identification module (not shown) which is again pre-trained using AI and/or ML techniques or concepts known in the art. The identification module takes the vehicle parameters 128 as input and classifies the current/present route or terrain into different types such as rural, city, hilly, iced, etc. Further, the controller 110 is also configured to extrapolate the data if less data is collected for the estimation module 118.

[0013] Once the statistical data cleaning is completed, the controller 110 performs statistical evaluation. The statistical evaluation comprises processing of the statistically cleaned data as input by the estimation module 118. The estimation module 118 performs the fatigue damage evaluation using preset threshold. The estimation module 118 is configured to determine driving profile or driving behavior or driving score for the vehicle 130 using the same statistically cleaned data. A correlation model between the parameters 128 resulting in fatigue damage is used to determine the driving profile. The estimation module 118 is continuously updated with real time data. The estimation module 118 processing depends upon the duty class of the vehicle 130 identified and the driving profile 116, which then gives the output 114 as the lifetime of the engine component. The estimation module 118 in general is modeled considering worst case driving profile and probability of maximum damage associated with worst case driving. However, based on the current driving profile 116, the lifetime of the engine component is adjusted.

[0014] According to an embodiment of the present invention, the controller 110 is part of the cloud 124 based solution. The cloud 124 receives the data which is transmitted by the TCU of the vehicle 130 through mobile/cellular network 122. Alternatively, the parameter 128 is collected by a smartphone or portable electronic device 126 which is in communication with the vehicle 130 through wireless or wired means known in the art, and the smartphone in-turn transmits the collected data to the cloud 124 through the mobile network 122. The cloud 124 then performs the necessary operation as already defined and determines the fatigue lifetime of the engine component. An example of the estimation module 118 comprises use of linear regression and/or other known algorithms known in the art.

[0015] According to the present invention, a working of the controller 110 is explained. Consider a vehicle service provider contains fleet of vehicles 130 for taxis, transport, etc. Each of the vehicle 130 is fit with the TCU or other connectivity means. The data from all the vehicles 130, whenever driven, are collected, and stored in the cloud 124. The cloud 124 then derives the driving profile 116 and feeds as input to the estimation module 118 which is pre-trained for the evaluation of fatigue analysis of the engine components of the vehicle 130. The real-time parameter 128 of the vehicle 130 is taken as input and the lifetime calculation of the engine component of the vehicle 130 is provided as output 114. Thus, if the driving of the vehicle 130 is normal or not in a critical way and optimal, the lifetime of the engine component is increased and if the driving of the vehicle 130 is in critical way, then the lifetime of the engine component is decreased. The critical way signifies aggressive/rash driving behavior. Further, the same vehicle 130 if driven by two or more different drivers over a period of time, then the same is also considered as the lifetime gets adjusted as per the type of driving profile by different drivers.

[0016] In accordance to an embodiment of the present invention, the controller 110 is provided with necessary signal detection, acquisition, and processing circuits. The controller 110 is the control unit which comprises input/output interfaces having pins or ports, the memory element 112 such as Random Access Memory (RAM) and/or Read Only Memory (ROM), Analog-to-Digital Converter (ADC) and a Digital-to-Analog Convertor (DAC), clocks, timers, counters and at least one processor (capable of implementing machine learning) connected with each other and to other components through communication bus channels. The memory element 112 is pre-stored with logics or instructions or programs or applications or modules/models and/or threshold values/ranges, system threshold, predefined/predetermined criteria/conditions, engine maps/table which is/are accessed by at least one processor as per the defined routines. The internal components of the controller 110 are not explained for being state of the art, and the same must not be understood in a limiting manner. The controller 110 may also comprise communication units to or may be connected to other control units to communicate through wireless or wired means such as Global System for Mobile Communications (GSM), 3G, 4G, 5G, Wi-Fi, Bluetooth, Ethernet, serial networks, and the like. The controller 110 is implementable in the form of System-in-Package (SiP) or System-on-Chip (SOC) or any other known types. Examples of controller 110 comprises but not limited to, microcontroller, microprocessor, microcomputer, etc.

[0017] According to the present invention, the vehicle 130 comprises but not limited to two-wheeler, three wheeler vehicles, four wheeler vehicles, Off-Highway (OHW) vehicle, multi-wheel vehicles and the like including the stationary application like gensets and construction equipment vehicles (CEV).

[0018] According to an embodiment of the present invention, the driver profile 116 is regularly updated whenever a new driver drives the same vehicle 130. Thus, the drawback of static modeling of fatigue calculation is avoided. Instead, a real time driving profile 116 based fatigue calculation is done for the vehicle 130.

[0019] Fig. 2 illustrates a flow diagram of a method for estimating fatigue lifetime of engine components in a vehicle, according to the present invention. The method comprises plurality of steps, of which a step 202 comprises receiving and collecting data comprising parameters 128 related to vehicle 130 through the communication network 120. A step 204 comprises processing the collected data through the estimation module 118 to evaluate the fatigue damage of the engine component. The estimation module 118 is pre-trained using an Artificial Intelligence (AI) and/or Machine Learning (ML) models for example, a linear regression model. A step 206 comprises determining lifetime of the engine component through the estimation module 118 and providing as the output 114. The method is characterized by a step 208 which comprises processing, by the estimation module 118, driving profile 116 of the vehicle 130 as input for lifetime calculation of the engine components. The driving profile 116 is derived using the vehicle parameter 128.

[0020] According to the method, the engine components is at least one selected from a group comprising the fuel pump, the fuel rail, the fuel injector, the fuel rail pressure sensor, the fuel injector nozzle, the high pressure connector, the engine block, valve, and the like. Further, the parameters 128 related to the vehicle 130 are selected from the group comprising the global distance, engine speed 102, the vehicle velocity 104, the acceleration pedal position 106, the fuel injection quantity 108, the fuel rail pressure, the engine torque, the gear position, and the like.

[0021] According to the method is performed by the controller 110 which is part of the device which at least one of internal to the vehicle 130 and external to the vehicle 130. The device is at least one selectable from the group comprising the Engine Control Unit, the smartphone, the cloud computer, and the like.

[0022] According to the method, the driver profile 116 is considered for the specific duty class of the vehicle 130 for prediction of failure of engine component.

[0023] According to the present invention, the controller 110 enables driving behavior modelling using connectivity such as Internet-of-Things (IOT) for reliability evaluation of engine components. The present invention replaces existing physical load measurement and corresponding lifetime calculations with controller 110 and method using driving profile 116 based adjustment of lifetime calculations. Further, the controller 110 and method is based on Artificial Intelligence and/or Machine Learning technique. The present invention enables the usage of connectivity data for reliability validation of components overcoming elaborate physical measurements and evaluations. The controller 110 and method offers driving profiling 116 using supervised learning ML model, the driving profile 116 is continuously learned and updated using AI/ML techniques. Further, extrapolation factor to the connectivity data using AL/ML techniques is also provided. The output 114 is usable in many services such as calculation of insurance, predictive maintenance, prognostics, component availability in a location and the like.

[0024] It should be understood that embodiments explained in the description above are only illustrative and do not limit the scope of this invention. Many such embodiments and other modifications and changes in the embodiment explained in the description are envisaged. The scope of the invention is only limited by the scope of the claims.
, Claims:We claim:
1. A controller (110) for fatigue lifetime estimation of engine components in a vehicle (130), said controller (110) configured to,
receive and collect data comprising parameters (128) related to vehicle (130) through a communication network (120);
process said collected data through an estimation module (118) to evaluate a fatigue damage of said engine component, said estimation module (118) is pre-trained using an Artificial Intelligence (AI) and /or Machine Learning (ML) models, and
determine fatigue lifetime of said engine component through said estimation module (118) and provide as an output (114), characterized in that,
said estimation module (118) is configured to take driving profile (116) of said vehicle (130) as input for fatigue lifetime calculation of said engine components, said driving profile (116) is derived using said vehicle parameter (128).

2. The controller (110) as claimed in claim 1, wherein said engine components is at least one selected from a group comprising a fuel pump, a fuel rail, a fuel injector, a fuel rail pressure sensor, a fuel injector nozzle, a high pressure connector, an engine block, valves, and the like.

3. The controller (110) as claimed in claim 1, wherein said parameters (128) related to said vehicle (130) are selected from a group comprising a global distance, an engine speed (102), a vehicle velocity (104), an acceleration pedal position (106), a fuel injection quantity (108), a fuel rail pressure, an engine torque, a gear position, and the like.

4. The controller (110) as claimed in claim 1 is part of a device which at least one of internal to said vehicle (130) and external to said vehicle (130), wherein said device is at least one selectable from a group comprising an Engine Control Unit, a smartphone, a cloud computer, and the like.

5. The controller (110) as claimed in claim 1, wherein said driving profile (116) is considered for a specific duty class of said vehicle (130) for prediction of fatigue failure of engine component.

6. A method for estimating fatigue lifetime of engine components of a vehicle (130), said method comprising the steps of:
receiving and collecting data comprising parameters (128) related to vehicle (130) through a communication network (120);
processing said collected data through an estimation module (118) to evaluate a fatigue damage of said engine component, said estimation module (118) is pre-trained using an Artificial Intelligence (AI) and /or Machine Learning (ML) models, and
determining lifetime of said engine component through said estimation module (118) and provided as an output (114), characterized by,
processing, by said estimation module (118), driving profile (116) of said vehicle (130) as input for fatigue lifetime calculation of said engine components, said driving profile (116) is derived using said vehicle parameter (128).

7. The method as claimed in claim 6, wherein said engine components is at least one selected from a group comprising a fuel pump, a fuel rail, a fuel injector, a fuel rail pressure sensor, a fuel injector nozzle, a high pressure connector, an engine block, valves, and the like.

8. The method as claimed in claim 6, wherein said parameters (128) related to vehicle (130) are selected from a group comprising a global distance, an engine speed (102), a vehicle velocity (104), an acceleration pedal position (106), a fuel injection quantity (108), a fuel rail pressure, an engine torque, a gear position, and the like.

9. The method as claimed in claim 6 is performed by controller (110) which is part of a device which at least one of internal to said vehicle (130) and external to said vehicle (130), wherein said device is at least one selectable from a group comprising an Engine Control Unit, a smartphone, a cloud computer, and the like.

10. The method as claimed in claim 6, wherein said driver profile (116) is considered for a specific duty class of said vehicle (130) for prediction of fatigue failure of engine component.