Description:FIELD OF THE INVENTION:

[0001] The present disclosure relates to electric vehicles (EVs), and more particularly to a method and system for determining an optimal torque for an electric motor of the EV.
BACKGROUND:

[0002] Electric vehicles (EVs) have become a key focus of sustainable transportation due to their reduced carbon footprint and high energy efficiency. On the other hand, a major challenge faced by EVs is optimizing energy consumption to maximize battery life and driving range. Unlike internal combustion engine (ICE) vehicles that may quickly refuel, EVs rely on battery packs that require significant charging time, making energy management a critical concern. Inefficient energy utilization can lead to reduced range, increased charging frequency, and overall diminished vehicle performance, limiting the practicality of EVs.
[0003] One of the main challenges in EV technology is determining the optimal torque required for the electric motor while considering multiple dynamic factors such as speed, state of charge (SoC), road conditions, and environmental influences. Conventional torque control strategies often rely on generalized torque limiting techniques that do not adapt to changing driving conditions, leading to suboptimal perfor mance. Additionally, the trade-off between vehicle weight and battery capacity remains a significant concern, as increasing battery size improves range but also adds weight, negatively affecting efficiency.
[0004] Existing solutions for torque control and energy management include Proportional-Integral-Derivative (PID) controllers, Linear Quadratic Regulation (LQR), and Model Predictive Control (MPC). While these methods offer some level of control, they have inherent limitations. PID controllers, widely used in industrial and mobility applications, work well in single-input, single-output (SISO) systems but become complex and difficult to tune in multi-input, multi-output (MIMO) systems such as EVs operating in dynamic environments. LQR controllers, on the other hand, require precise system modeling, making them less adaptable to real-world variations. MPC offers better predictive capabilities but is computationally intensive, limiting its feasibility for real-time torque adjustments
SUMMARY

[0005] This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention. This summary is neither intended to identify key or essential inventive concepts of the invention nor is it intended for determining the scope of the invention.
[0006] To overcome, or at least mitigate, one of the problems mentioned above in the state of the art, there is a requirement for a system and method for determining an optimal torque for an electric motor of an electric vehicle (EV).
[0007] In an aspect of the present invention, a method for determining an optimal torque for an electric motor of an electric vehicle (EV) is disclosed. The method includes determining at least one of a power (kW) of the EV, a state of charge (SoC) of a battery of the EV, a remaining SoC, a distance between a first location and a second location, one or more path characteristics, and one or more environment parameters. The method further includes computing an efficient path based on at least one of the one or more path characteristics and the one or more environment parameters. The efficient path indicates a route that minimizes battery consumption. The method further includes determining an optimal torque value for the electric motor of the EV based on at least one of the speed of the EV, the SoC of the battery of the EV, the remaining SoC, the distance, and the computed efficient path using a physics-based artificial intelligence module. The optimal torque value indicates a torque value that minimizes the rate of battery power discharge .
[0008] In another aspect of the present invention, a system for determining an optimal torque for an electric motor of an EV is disclosed. The system includes a memory and at least one processor in communication with the memory. Theat least one processor is configured to determine at least one of a speed of the EV, a state of charge (SoC) of a battery of the EV, a remaining SoC, a distance between a first location and a second location, one or more path characteristics, and one or more environment parameters. The at least one processor is configured to compute an efficient path based on at least one of the one or more path characteristics and the one or more environment parameters using a dynamic programming module. The efficient path indicates a route that minimizes the rate of battery consumption. The at least one processor is configured to determine an optimal torque value for the electric motor of the EV based one at least one of the speed of the EV, the SoC of the battery of the EV, the rate of battery discharge, the distance, and the computed efficient path using physics based artificial intelligence module. The optimal torque value indicates a torque value that minimizes battery power discharge.
[0009] To further clarify the advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which are illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
BRIEF DESCRIPTION OF THE DRAWINGS
[00010] These and other features, aspects, and advantages of the present invention will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:
[00011] FIG. 1 illustrates an environment for an implementation of a system for determining an optimal torque for an electric motor of an electric vehicle (EV)/ electric outboard, according to an embodiment of the present disclosure;
[00012] FIG. 2 illustrates the system for determining an optimal torque for an electric motor of the EV, according to an embodiment of the present disclosure;
[00013] FIG. 3 illustrates a process flow of training a physics-based artificial intelligence module of the system, according to an embodiment of the present disclosure; and
[00014] FIG. 4 illustrates a method for determining an optimal torque for an electric motor of the EV, according to an embodiment of the present disclosure.
[00015] Further, skilled artisans will appreciate that elements in the drawings are illustrated for simplicity and may not have necessarily been drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help improve understanding of aspects of the present invention. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present invention so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.
DETAILED DESCRIPTION OF FIGURES
[00016] For the purpose of promoting an understanding of the principles of the present disclosure, reference will now be made to the various embodiments and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the present disclosure is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the present disclosure as illustrated therein being contemplated as would normally occur to one skilled in the art to which the present disclosure relates.
[00017] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are explanatory of the present disclosure and are not intended to be restrictive thereof.
[00018] Whether or not a certain feature or element was limited to being used only once, it may still be referred to as “one or more features” or “one or more elements” or “at least one feature” or “at least one element.” Furthermore, the use of the terms “one or more” or “at least one” feature or element do not preclude there being none of that feature or element, unless otherwise specified by limiting language including, but not limited to, “there needs to be one or more…” or “one or more elements is required.”
[00019] Reference is made herein to some “embodiments.” It should be understood that an embodiment is an example of a possible implementation of any features and/or elements of the present disclosure. Some embodiments have been described for the purpose of explaining one or more of the potential ways in which the specific features and/or elements of the proposed disclosure fulfil the requirements of uniqueness, utility, and non-obviousness.
[00020] Use of the phrases and/or terms including, but not limited to, “a first embodiment,” “a further embodiment,” “an alternate embodiment,” “one embodiment,” “an embodiment,” “multiple embodiments,” “some embodiments,” “other embodiments,” “further embodiment”, “furthermore embodiment”, “additional embodiment” or other variants thereof do not necessarily refer to the same embodiments. Unless otherwise specified, one or more particular features and/or elements described in connection with one or more embodiments may be found in one embodiment, or may be found in more than one embodiment, or may be found in all embodiments, or may be found in no embodiments. Although one or more features and/or elements may be described herein in the context of only a single embodiment, or in the context of more than one embodiment, or in the context of all embodiments, the features and/or elements may instead be provided separately or in any appropriate combination or not at all. Conversely, any features and/or elements described in the context of separate embodiments may alternatively be realized as existing together in the context of a single embodiment.
[00021] Any particular and all details set forth herein are used in the context of some embodiments and therefore should not necessarily be taken as limiting factors to the proposed disclosure.
[00022] The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such process or method. Similarly, one or more devices or sub-systems or elements or structures or components proceeded by “comprises... a” does not, without more constraints, preclude the existence of other devices or other sub-systems or other elements or other structures or other components or additional devices or additional sub-systems or additional elements or additional structures or additional components.
[00023] Embodiments of the present disclosure will be described below in detail with reference to the accompanying drawings.
[00024] For the sake of clarity, the first digit of a reference numeral of each component of the present disclosure is indicative of the Figure number, in which the corresponding component is shown. For example, reference numerals starting with digit “1” are shown at least in Figure 1. Similarly, reference numerals starting with digit “2” are shown at least in Figure 2.
[00025] Embodiments of the present disclosure disclose a system for determining an optimal torque for an electric vehicle (EV). The components of the disclosed system are configured to determine the optimal torque for the EV.
[00026] FIG. 1 illustrates an environment 100 for an implementation of a system 114 for determining an optimal torque for the electric motor 112 of the EV 101, according to an embodiment of the present disclosure.
[00027] In a non-limiting example, the system 114 may be implemented in the vehicle, for instance, any mechanical means of transportation such as automobiles (car), motorcycles, trucks, buses, scooters, motorcycles, and bicycles. In another example, the EV 101 may include water vehicles such as boats, ships, submarines, and hovercrafts. In one such embodiment, the present disclosure is explained by implementing the system 114 in the vehicle 101 alternatively referred to as an electric vehicle (EV) 101 within the scope of the present disclosure. The Electric Vehicle (EV) 101 or a battery-powered vehicle including, and not limited to two-wheelers such as scooters, mopeds, motorbikes/motorcycles; three-wheelers such as auto-rickshaws, four-wheelers such as cars and other Light Commercial Vehicles (LCVs) and Heavy Commercial Vehicles (HCVs) primarily work on the principle of driving an electric motor using the power from the batteries provided in the EV 101. The types of EVs include Battery Electric Vehicle (BEV), Hybrid Electric Vehicle (HEV) and Range Extended Electric Vehicle. However, the subsequent paragraphs pertain to the different elements of a Battery Electric Vehicle (BEV).
[00028] In construction, the EV/ Electrical outboard 101 may include a plurality of components such as a battery or battery pack 102, a speed sensor 103, a voltage sensor 104, a current sensor 106, a temperature sensor 108, a dashboard 110, and an electric motor 112 (alternatively referred to as motor 112). The battery or battery pack 102, the speed sensor 103, the voltage sensor 104, the current sensor 106, the temperature sensor 108, the dashboard 110, and the electric motor 112 may be in communication with a system 114. Further, the system 114 may include an electronic control unit 116. The electronic control unit may be configured to control the plurality of components.
[00029] The speed sensor 103 may be configured to determine rotations per minute (RPM) of the electric motor 112 associated with the EV or in case if Electric outboard it may be configured to determine the speed based on the GPS101.
[00030] In an embodiment, the voltage sensor 104, a current sensor 106, and a temperature sensor 108 may be configured to determine a voltage, a current, and a temperature of the battery 102 of the EV 101. The primary function of the above-mentioned elements is detailed in the subsequent paragraphs: The battery 102 of the EV 101 (also known as Electric Vehicle Battery (EVB) or traction battery) is re-chargeable in nature and is the primary source of energy required for the operation of the EV 101.
[00031] The ECU 116 primarily controls/regulates the operation of the electric motor based on the signal transmitted from the vehicle battery, wherein the primary functions of the ECU 116 include starting the electric motor 112, stopping the electric motor 112, controlling the speed of the electric motor 112, enabling the EV 101 to move in the reverse direction and protect the electric motor 112 from premature wear and tear. The primary function of the electric motor 112 is to convert electrical energy into mechanical energy, wherein the converted mechanical energy is subsequently transferred to the transmission system of the EV 101 to facilitate movement of the EV 101. Additionally, the electric motor 112 also acts as a generator during regenerative braking (i.e., kinetic energy generated during vehicle braking/deceleration is converted into potential energy and stored in the battery of the EV 101). The types of motors generally employed in EVs include, but are not limited to DC series motor, Brushless DC motor (also known as BLDC motors), Permanent Magnet Synchronous Motor (PMSM), Three Phase AC Induction Motors and Switched Reluctance Motors (SRM).
[00032] In one embodiment, all data pertaining to the EV 101 and/or charging infrastructure may be collected and processed using a remote server 118 (known as cloud 118), wherein the processed data is indicated to the rider/driver of the EV 101 through a display unit present in the dashboard 110 of th e EV 101. In an embodiment, the display unit may be an interactive display unit. In another embodiment, the display unit may be a non-interactive display unit.
[00033] In addition to the hardware components/elements, the EV 101 may be supported with software modules comprising intelligent features including and not limited to navigation assistance, hill assistance, cloud connectivity, Over-The-Air (OTA) updates, adaptive display techniques and so on. The firmware of the EV 101 may also comprise Artificial Intelligence (AI) and Machine Learning (ML) driven modules which enable the prediction of a plurality of parameters such as and not limited to driver/rider behaviour, road condition, charging infrastructures or charging grids in the vicinity and so on. The data pertaining to the intelligent features may be displayed through the display unit present in the dashboard 110 of the EV 101. In one embodiment, the display unit may contain a Liquid Crystal Display (LCD) screen of a predefined dimension. In another embodiment, the display unit may contain a Light-Emitting Diode (LED) screen of a predefined dimension. The display unit may be a water-resistant display supporting one or more User-Interface (UI) designs. The EV 101 may support multiple frequency bands such as 2G, 3G, 4G, 5G, and so on. Additionally, the EV 101 may also be equipped with wireless infrastructure such as, and not limited to Bluetooth, Wi-Fi and so on to facilitate wireless communication with other EVs or the cloud.
[00034] Further, the EV 101 may include a system 114 configured to determine at least one of a speed of the EV 101, a state of charge (SoC) of a battery 102 of the EV 101, a remaining SoC, a distance between a first location and a second location, one or more path characteristics, and one or more environment parameters. The system 114 may be further configured compute an efficient path based on at least one of the one or more path characteristics and the one or more environment parameters using a dynamic programming module. The efficient path indicates a route that minimizes battery consumption. The system 114 may be further configured to determine an optimal torque value for the electric motor 112 of the EV 101 based one at least one of the speed of the EV 101, the SoC of the battery 102 of the EV 101, the remaining SoC, the distance between the first location and the second location, and the computed efficient path using physics based artificial intelligence (AI) module.
[00035] In an alternative embodiment, the system 114 may alternatively reside in the remote server 116, without departing from the scope of the present disclosure. Further, the system 114 may be configured to transmit computed efficient path based on at least one of the one or more path characteristics and the one or more environment parameters to the remote server 116 (alternatively referred to as cloud 116). On receipt of the computed efficient path, the remote server may be configured to determine the optimal torque for the EV 101. Additionally, an application installed on a user device (not shown) and in communication with the remote server 116 may display the determined optimal torque of the vehicle 101 and the subsequent operations performed for controlling the electric motor 112. Similarly, the dashboard 126 may also display an event indicating the determined optimal torque for the vehicle 101 and the subsequent operations performed for controlling the illumination device 112 and the vehicle motor 112. Further, the constructional and operational details of the system 114 are explained in subsequent paragraphs in conjunction with Figures 2 to 4, without departing from the scope of the present disclosure.
[00036] FIG. 2 illustrates the system 114 for determining an optimal torque for the electric motor 112 of the EV 101, according to an embodiment of the present disclosure. The system 114 may be deployed in the EV 101 to determine the optimal torque of the electric motor 112.
[00037] In an embodiment, torque may be defined as a rotational force applied to a mechanical system, such as a drive shaft or wheel assembly, to induce angular motion. In the context of the electric vehicle (EV) 101, torque represents the rotational output generated by the electric motor 112 and transferred to the wheels or propeller (in case of water vehicles) to produce forward or reverse motion. Torque may be measured in Newton-meters (Nm) and is mathematically represented as the product of a linear force and the perpendicular distance from the axis of rotation, i.e.,
τ = r × F, where τ denotes torque, r is the lever arm distance, and F is the applied force.
[00038] In an embodiment, the method and system 114 determines the optimal torque for the electric motor 112 of the EV 101 thereby reducing the battery consumption. The detailed explanation for determining the optimal torque for the electric motor 112 of the EV 101 is provided in the upcoming paragraphs.
[00039] The system 114 may include, but is not limited to, one or more processors 202 (referred to as processor), a memory 204, an input component 206, an output component 208, a communication interface 210, and one or more modules 212.
[00040] The one or more processor 202 may be a single processing unit or several units, all of which could include multiple computing units. The one or more processors 202 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the one or more processors 202 are adapted to fetch and execute computer-readable instructions and data stored in the memory 204.
[00041] The input component 206 may be configured to receive information, such as user input. For example, the input component 206 may include, but not be limited to, a touchscreen display, a keyboard, a keypad, a mouse, a button, a switch, and/or a microphone associated with the user device 201.
[00042] The output component 208 may be configured to display information from the system 114 to the user or other systems, utilizing a variety of devices and technologies tailored to specific application needs. The output component 208 may include visual output devices such as display screens (LCD, LED, OLED,TFT), projectors, and heads-up displays (HUDs) for presenting graphical or textual information. Additionally, auditory output through speakers and headphones provides audio feedback and alerts, while haptic output devices, like vibration motors in smartphones or game controllers, offer tactile feedback. Functionally, the output component 208 serves multiple roles, including displaying graphical user interface (GUI) elements for user interaction, delivering notifications and alerts through sound, visual indicators, or vibrations, and rendering complex data visualizations like charts and graphs for easier comprehension.
[00043] In an embodiment, the output component 208 may be configured to receive processed data from the processor 202, which determines the information to be communicated, and the output component 208 may access the memory 204 to retrieve and display stored information such as documents, media files, or application states.
[00044] Furthermore, the output component 208 may be configured to meet the specific requirements of different applications, such as high-resolution visual output and immersive audio for gaming systems or clear and precise data visualization and alert mechanisms for industrial control systems. Through these varied output methods, the output component 208 ensures effective communication of information, enhancing both system 114 functionality and user experience.
[00045] The communication interface 210 is a hardware and/or software component that may be configured to enable the EV 101 to exchange data with other vehicles or user devices or systems. The communication interface 210 may be configured to serve as the link for transmitting and receiving information, either within a local environment (e.g., between components of the same system) or across networks.
[00046] The one or more modules 212, amongst other things, include routines, programs, objects, components, data structures, etc., which perform particular tasks or implement data types. The modules 212 may also be implemented as, signal processor(s), state machine(s), logic circuitries, and/or any other device or component that manipulates signals based on operational instructions.
[00047] Further, the one or more modules 212 may be implemented in hardware, instructions executed by a processing unit, or by a combination thereof. The processing unit can comprise a computer, a processor, such as the one or more processor 202, a state machine, a logic array, or any other suitable devices capable of processing instructions. The processing unit can be a general-purpose processor which executes instructions to cause the general-purpose processor to perform the required tasks or, the processing unit can be dedicated to performing the required functions. In another embodiment of the present disclosure, the one or more modules 212 may be machine-readable instructions (software) which, when executed by a processor/processing unit 202, perform any of the described functionalities.
[00048] In an embodiment, the one or more modules 212 may include the dynamic programming module 214 and the physics-based artificial intelligence module 216.
[00049] The dynamic programming module 214 may be configured to compute the efficient path based on at least one of the one or more path characteristics and the one or more environment parameters. The efficient path indicates the route that minimizes battery consumption.
[00050] The physics-based AI module 216 may be configured to determine the optimal torque value for the electric motor 112 of the EV 101 based one at least one of the speed of the EV 101, the SoC of the battery of the EV 101, the remaining SoC, the distance between the first location and the second location, and the computed efficient path. The optimal torque value indicates the torque value that minimizes battery power discharge.
[00051] In an embodiment, the processor 202 may be configured to determine at least one of the speed of the EV 101, the state of charge (SoC) of the battery of the EV 101, the remaining SoC, the distance between the first location and the second location, the one or more path characteristics, and the one or more environment parameters. The one or more environment parameters may include a drift, a terrain, an upstream, and a downstream.
[00052] In an embodiment, the processor 202 may be configured to determine the speed of the EV 101 by identifying a rotations per minute (RPM) of the electric motor 112 (alternatively referred to as the motor 112) associated with the EV 101 based on a change in a magnetic field using the speed sensor 103. Upon identifying the RPM of the motor 112, the processor 202 may be configured to determine the speed of the EV 101 based on the identified RPM of the motor 112 associated with the EV 101.
[00053] In an embodiment, the processor 202 may be configured to determine the SoC of the battery 102 of the EV 101 based on identifying at least one of the voltage, the current, and the temperature associated with the battery 102 of the EV 101 using one or more sensors. The one or more sensors may include the voltage sensor 104, the current sensor 106, and the temperature sensor 108.
[00054] Upon identifying the at least one of the voltage, the current, and the temperature associated with the battery 102 of the EV 101, the processor 202 may be configured to determine the SoC of the battery 102 of the EV 101 based on identifying the at least one of the voltage, the current, and the temperature associated with the battery 102 of the EV 101.
[00055] In one example, the speed sensor 103 may detect a variation in the magnetic field strength in proximity to the rotating shaft of the electric motor 112, thereby allowing the RPM of the motor 112 to be identified. Based on the identified RPM, the processor 202 may be configured to compute the linear speed of the EV 101 as 68 km/h by applying a calibrated mapping function correlating motor RPM with vehicle velocity.
[00056] Furthermore, the SoC of the battery 102 may be determined by the processor 202 through the identification of electrical and thermal characteristics. Specifically, the voltage sensor 104 may record a terminal voltage of for example 347 V, the current sensor 106 may register a discharge current of 92 A, and the temperature sensor 108 may detect a battery temperature of 34°C. The readings of the one or more sensors may be processed by the processor 202 using a battery management algorithm, which applies a lookup table or state estimation model (e.g., Kalman filter or Coulomb counting method) to determine the current SoC as 57%.
[00057] Additionally, the remaining SoC may be estimated to support approximately 27.4 km/nautical miles of additional travel based on historical consumption data and real-time power demand. The distance between the first location (e.g., a navigation origin point) and the second location (e.g., a destination waypoint) may be determined as 22.8 km//nautical miles using a GPS data.
[00058] Further, the processor 202 may evaluate one or more path characteristics, which may include a curvature, speed limit zones, incline profiles, and known obstacle regions or obstacles. Concurrently, the processor 202 may be configured to determine one or more environment parameters such as a terrain classification of “moderate incline,” a drift magnitude of 0.4 m/s² due to lateral crosswind, an upstream segment with a grade of +3.2% extending over 4.1 km, and a downstream segment with a grade of –2.7% across the final 2.6 km of the route.
[00059] Furthermore, upon determining the at least one of the speed of the EV 101, the SoC of the battery of the EV 101, the remaining SoC, the distance between the first location and the second location, the one or more path characteristics, and the one or more environment parameters, the processor 202 may be configured to compute the efficient path based on at least one of the one or more path characteristics and the one or more environment parameters. The efficient path indicates the route that minimizes battery consumption.
[00060] The efficient path may be computed by a dynamic programming module 214 associated with the processor 202.
[00061] The dynamic programming module 214 refers to a software module or component that implements the dynamic programming algorithmic technique. The dynamic programming module 214 may comprise functions and classes configured to solve problems that may be broken down into overlapping subproblems. The dynamic programming module 214 core functionality may be configured to focus on storing and reusing solutions to subproblems to avoid redundant calculations, ultimately leading to an efficient solution for the overall problem.
[00062] In an exemplary embodiment, the dynamic programming module 214 may be configured to compute the n-th Fibonacci number, wherein each number in the sequence is defined as the sum of its two immediate predecessors, i.e., F(n) = F(n–1) + F(n–2), with base cases F(0) = 0 and F(1) = 1. The dynamic programming module 214 may be configured to optimize computation and eliminate redundant recursive calls, using either a memorization method (top-down) or a tabulation method (bottom-up). In the memorization method, intermediate results are stored in a cache structure and reused whenever the corresponding subproblem is revisited. In the tabulation method, a table is iteratively populated starting from the base cases, thereby constructing the final result through successive accumulation. Both techniques serve to reduce the overall time complexity from exponential O(2ⁿ) to linear O(n), thereby demonstrating the computational efficiency achievable through dynamic programming.
[00063] Upon computing the efficient path, a physics-based AI module 216 may be configured to determine the optimal torque value for the electric motor 112 of the EV 101 based one at least one of the speed of the EV 101, the SoC of the battery of the EV 101, the remaining SoC, the distance between the first location and the second location, and the computed efficient path. The optimal torque value indicates the torque value that minimizes battery power discharge.
[00064] In a non-limiting example, consider a scenario in which the EV 101 is operating with a current speed of 60 km/h, a battery SoC of 48%, and a remaining distance of 18.5 km between a first location (e.g., a user-designated origin) and a second location (e.g., a destination waypoint). The efficient path has been previously computed by the dynamic programming module 318, indicating a route . Based on the above parameters, the physics-based AI module 216 evaluates multiple torque profiles and determines an optimal torque value ,which minimizes energy expenditure while maintaining required traction and velocity. Such an optimal torque value is computed by considering real-time estimates of power draw per torque increment, the effect of terrain-induced resistive forces, and the impact of speed-torque curves on overall battery discharge. The computed torque is then relayed to the motor controller 220 to be applied across a predicted duty cycle, thereby enabling efficient energy usage aligned with the remaining SoC and trip requirements.
[00065]
[00066] FIG. 3 illustrates a method 300 depicting a process flow of training a physics-based artificial intelligence module 216, according to an embodiment of the present disclosure.
[00067] In an embodiment of the present invention, the physics-based AI module 216 refers to a specialized subset of the AI system trained to model and predict the physical behavior of the EV 101 based on both historical and real-time operational data. The physics-based AI module 216 is configured to incorporate empirical correlations learned through data and domain-specific physical constraints and relationships such as Newtonian mechanics, energy consumption profiles, and motor control dynamics within the AI learning process.
[00068] The physics-based AI module 216 may be a computational entity configured to emulate cognitive functions such as learning, pattern recognition, decision making, and predictive modeling through the application of algorithms and data-driven methods. Such modules may be implemented using machine learning architectures, including supervised, unsupervised, or reinforcement learning models, and may include artificial neural networks (ANNs), decision trees, or probabilistic inference engines. The AI module may be trained on large datasets to recognize latent relationships among input variables and may be employed to generate context-sensitive outputs under dynamic operating conditions.
[00069] At step 302, the method 300 may include collecting a first dataset based on one or more of the speed of the EV 101, the SoC of the battery 102 of the EV 101, the remaining SoC, the distance between the first location and the second location, and the computed efficient path stored in a database.
[00070] At step 304, the method 300 may include collecting a second dataset based on one or more of the speed of the EV 101, the SoC of the battery 102) of the EV 101, the remaining SoC, the distance between the first location and the second location, and the computed efficient path in real time.
[00071] At step 306, the method 300 may include generating a training set based on the first dataset and the second dataset.
[00072] At step 308, the method 300 may include training the physics-based AI module 216 based on the generated training set.
[00073] Simultaneously, a second dataset may be generated in real time from a currently operating EV 101. The processor 202 may capture a current vehicle speed of 58 km/h, a starting SoC of 59%, a projected remaining SoC of 21% after covering a 26.3 km route, and live path characteristics such as terrain type (e.g., mixed grade with one 5% incline), upstream and downstream segments, and lateral drift due to crosswinds.
[00074] In an embodiment, the first dataset and the second dataset may be preprocessed to remove outliers, normalized, and fused to form a training set consisting of structured feature vectors. The generated training set may be used to train the physics-based AI module 216. During training, the physics-based AI module 216 may be configured to learn to map the input features to an output label such as "optimal torque value" required to complete the journey with minimal battery consumption while maintaining desired velocity thresholds.
[00075] FIG. 4 illustrates a method 400 for determining an optimal torque for an electric motor 112 of the EV 101, according to an embodiment of the present disclosure.
[00076] At step 402, the method 400 may include determining the at least one of the speed of the EV 101, the state of charge (SoC) of the battery 102 of the EV 101, the remaining SoC, the distance between the first location and the second location, the one or more path characteristics, and the one or more environment parameters.
[00077] At step 404, the method 400 may include computing the efficient path based on at least one of the one or more path characteristics and the one or more environment parameters using the dynamic programming module 214. The efficient path indicates the route that minimizes battery consumption.
[00078] At step 406, the method 400 includes determining the optimal torque value for the electric motor 112 of the EV 101 based on the at least one of the speed of the EV 101, the SoC of the battery 102 of the EV 101, the remaining SoC, the distance between the first location and the second location, and the computed efficient path. The optimal torque value indicates a torque value that minimizes battery power discharge.
[00079] The present disclosure advantageously overcomes one or more technical problems associated with the existing systems, such as:
[00080] The present invention provides the method to determine the optimal torque to be applied to the electric motor 112 of the EV 101 by integrating real-time and historical operational parameters such as speed, state of charge (SoC), remaining distance, environmental factors, and route profile. This context-aware torque determination enables the system to minimize battery discharge during vehicle operation, thus enhancing driving range and energy efficiency.
[00081] The physics-based artificial intelligence (AI) module 216 in the system 114 is trained using both pre-collected datasets and live operational data. Such a training approach allows the physics-based AI module 216 to model nonlinear relationships between input parameters (e.g., terrain profile, SoC, vehicle speed) and output parameters (e.g., optimal torque) while incorporating physical laws and constraints such as Newtonian dynamics and motor control behaviors. As a result, the system 114 delivers high-accuracy torque predictions adaptable to varied driving scenarios.
[00082] The present disclosure incorporates the dynamic programming module 214 to determine the most energy-efficient route between two locations. The system 114 significantly reduces computational redundancy and accelerates decision-making by breaking down the route optimization problem into overlapping subproblems and caching intermediate results. This leads to real-time identification of low-consumption paths that directly influence optimal torque computation.
[00083] The present disclosure improves energy management by dynamically adjusting motor torque in response to driving conditions and road topology. The physics-based AI module 216 intelligently balances performance and energy conservation, thereby reducing unnecessary power consumption while maintaining adequate traction and acceleration performance.
[00084] It will be appreciated that the modules, processes, systems, and devices described above can be implemented in hardware, hardware programmed by software, software instruction stored on a non-transitory computer-readable medium or a combination of the above. Embodiments of the methods, processes, modules, devices, and systems (or their sub-components or modules), may be implemented on a general-purpose computer, a special-purpose computer, a programmed microprocessor or microcontroller and peripheral integrated circuit element, an ASIC or other integrated circuit, a digital signal processor, a hardwired electronic or logic circuit such as a discrete element circuit, a programmed logic circuit such as a programmable logic device (PLD), programmable logic array (PLA), field-programmable gate array (FPGA), programmable array logic (PAL) device, or the like. In general, any process capable of implementing the functions or steps described herein can be used to implement embodiments of the methods, systems, or computer program products (software program stored on a non-transitory computer readable medium).
[00085] Furthermore, embodiments of the disclosed methods, processes, modules, devices, systems, and computer program products may be readily implemented, fully or partially, in software using, for example, object or object-oriented software development environments that provide portable source code that can be used on a variety of computer platforms. Alternatively, embodiments of the disclosed methods, processes, modules, devices, systems, and computer program products can be implemented partially or fully in hardware using, for example, standard logic circuits or a very-large-scale integration (VLSI) design. Other hardware or software can be used to implement embodiments depending on the speed and/or efficiency requirements of the systems, the particular function, and/or particular software or hardware system, microprocessor, or microcomputer being utilized.
[00086] In this application, unless specifically stated otherwise, the use of the singular includes the plural and the use of “or” means “and/or.” Furthermore, use of the terms “including” or “having” is not limiting. Any range described herein will be understood to include the endpoints and all values between the endpoints. Features of the disclosed embodiments may be combined, rearranged, omitted, etc., within the scope of the invention to produce additional embodiments. Furthermore, certain features may sometimes be used to advantage without a corresponding use of other features.
, Claims:1. A method (400) for determining an optimal torque for an electric motor (112) of an electric vehicle (EV) (101), the method (400) comprising:
determining at least one of a speed of the EV (101), a state of charge (SoC) of a battery (102) of the EV (101), a remaining SoC, a distance between a first location and a second location, one or more path characteristics, and one or more environment parameters;
computing, by a dynamic programming module (214), an efficient path based on at least one of the one or more path characteristics and the one or more environment parameters, wherein the efficient path indicates a route that minimizes battery consumption; and
determining, by a physics based artificial intelligence (AI) module (216), an optimal torque value for the electric motor (112) of the EV (101) based one at least one of the speed of the EV (101), the SoC of the battery (102) of the EV (101), the remaining SoC, the distance between the first location and the second location, and the computed efficient path, wherein the optimal torque value indicates a torque value that minimizes battery power discharge.

2. The method (400) as claimed in claim 1, wherein the one or more environment parameters include a drift magnitude, a terrain classification, an upstream, and a downstream.

3. The method (400) as claimed in claim 1, wherein determining the speed of the EV (101), the method (400) comprises:
identifying, by a speed sensor (103), a rotations per minute (RPM) of the electric motor (112) of the EV (101) based on a change in a magnetic field; and
determining, by the speed sensor (103), the speed of the EV (101) based on the identified RPM of the electric motor (112) of the EV (101).

4. The method (400) as claimed in claim 1, wherein determining the state of charge (SoC) of the battery (102) of the EV (101), the method (400) comprises:
identifying at least one of a voltage, a current, and a temperature associated with the battery (102) of the EV (101) using one or more sensors, wherein the one or more sensors include a voltage sensor (104), a current sensor (106), and a temperature sensor (108); and
determining the SoC of the battery (102) of the EV (101) based on identifying the at least one of the voltage, the current, and the temperature associated with the battery (102) of the EV (101).

5. The method (300) as claimed in claim 1, wherein training the physics-based AI module 216, the method (300) comprises:
collecting first dataset based on one or more of the speed of the EV (101), the SoC of the battery (102) of the EV (101), the remaining SoC, the distance between the first location and the second location, and the computed efficient path stored in a database;
collecting a second dataset based on one or more of the speed of the EV (101), the SoC of the battery (102) of the EV (101), the remaining SoC, the distance between the first location and the second location, and the computed efficient path in real time;
generating a training set based on the first dataset and the second dataset; and
training the physics-based AI module (216) based on the generated training set.

6. A system (114) for determining an optimal torque for an electric motor (112) of an electric vehicle (EV) (101), the system (114) comprising:
a memory (204);
at least one processor (202) in communication with the memory (204) is configured to:
determine at least one of a speed of the EV (101), a state of charge (SoC) of a battery (102) of the EV (101), a remaining SoC, a distance between a first location and a second location, one or more path characteristics, and one or more environment parameters;
compute an efficient path based on at least one of the one or more path characteristics and the one or more environment parameters using a dynamic programming module (214), wherein the efficient path indicates a route that minimizes battery consumption; and
determine an optimal torque value for the electric motor (112) of the EV (101) based one at least one of the speed of the EV (101), the SoC of the battery (102) of the EV (101), the remaining SoC, the distance between the first location and the second location, and the computed efficient path using a physics based artificial intelligence (AI) module (216), wherein the optimal torque value indicates a torque value that minimizes battery power discharge.

7. The system (114) as claimed in claim 6, wherein the one or more environment parameters include a drift magnitude, a terrain classification, an upstream, and a downstream.

8. The system (114) as claimed in claim 6, wherein determining the speed of the EV (101), the at least one processor (202) is configured to:
identify a rotations per minute (RPM) of the electric motor (112) of the EV (101) based on a change in a magnetic field using a speed sensor (103) ; and
determine the speed of the EV (101) based on the identified RPM of the electric motor (112) of the EV (101) using the speed sensor (103).

9. The system (114) as claimed in claim 6, wherein determining the state of charge (SoC) of the battery (102) of the EV (101), the at least one processor (202) is configured to:
identify at least one of a voltage, a current, and a temperature associated with the battery (102) of the EV (101) using one or more sensors, wherein the one or more sensors include a voltage sensor (104), a current sensor (106), and a temperature sensor (108); and
determine the SoC of the battery (102) of the EV (101) based on identifying the at least one of the voltage, the current, and the temperature associated with the battery (102) of the EV (101).

10. The system (114) as claimed in claim 6, wherein training the physics-based AI module (216), the at least one processor (202) is configured to:
collect a first dataset based on one or more of the speed of the EV (101), the SoC of the battery (102) of the EV (101), the remaining SoC, the distance between the first location and the second location, and the computed efficient path stored in a database;
collect a second dataset based on one or more of the speed of the EV (101), the SoC of the battery (102) of the EV (101), the remaining SoC, the distance between the first location and the second location, and the computed efficient path in real time;
generate a training set based on the first dataset and the second dataset; and
train the physics-based AI module (216) based on the generated training set.