DESC:FIELD OF THE INVENTION
[0001] This present disclosure generally relates to electrical motors, and more specifically to systems and methods for adaptive real-time flux control and predictive performance optimization in electric motors.

BACKGROUND OF THE INVENTION
[0002] Conventional motor control systems in electric vehicles (EVs) primarily rely on fixed magnetic configurations and reactive electrical control mechanisms. These systems typically employ vector control, permanent magnet designs, or variable frequency drives to manage motor performance. While functional, these conventional approaches have significant limitations. They lack real-time adaptability to varying driving conditions due to their fixed magnetic properties, leading to suboptimal energy utilization, especially under fluctuating loads. Performance trade-offs are common, as motors are often designed for specific operational ranges, resulting in compromised efficiency outside these parameters. Moreover, the absence of predictive optimization means these systems react to current conditions rather than anticipating future demands, leading to less efficient overall performance. The reliance on purely electrical adjustments often results in slower response times to rapid changes in driving conditions. Additionally, conventional systems struggle to simultaneously optimize for both efficiency and power output in real-time, typically favoring one over the other. These limitations collectively result in reduced energy efficiency, constrained performance adaptability, and an inability to fully optimize motor operation across diverse driving scenarios encountered by modern EVs.

[0003] Existing electric vehicle motor control systems have the following limitations: lack of adaptive flux control in response to immediate driving conditions, incapable of predictive performance optimization, and inability to adapt to changing driving conditions and demands.

[0004] Limitations and disadvantages of conventional and traditional approaches will become apparent to one of ordinary skill in the art, through comparison of described systems with some aspects of the present invention, as set forth in the remainder of the present application and with reference to the drawings.

SUMMARY OF THE INVENTION
[0005] Aspects of the present disclosure relate to systems and methods for adaptive real-time flux control and predictive optimization in electric vehicle (EV) motors. A dynamic approach to motor control, is introduced which utilizes algorithms for real-time flux density adjustment based on instantaneous driving conditions. Unlike conventional EV motor systems that rely on fixed magnetic properties or purely electrical control mechanisms, the system of the present disclosure enables physical modification of the motor's magnetic circuit, providing a new dimension of control. The system incorporates a predictive control mechanism that anticipates power demands based on driving conditions, offering proactive performance optimization. This unified approach allows for dynamic optimization of either efficiency or power output in real-time. Further, the system’s ability to adapt to varying load conditions in real-time significantly enhances motor responsiveness and overall energy efficiency across diverse driving scenarios, including, but not limited to, city, highway, and uphill driving.

[0006] Aspects of the present disclosure relate to the system's capacity to dynamically adjust motor characteristics for simplifying EV transmission systems. By enabling rapid adjustments to the motor's magnetic properties, the system achieves a level of adaptability and efficiency not realized in conventional designs that rely on fixed magnetic circuits or slower-responding control systems. The integration of real-time adaptive control with predictive algorithms offers improved motor performance without the need for complex mechanical transmission systems.

[0007] Aspects of the present disclosure relate to an advanced system and method for adaptive real-time flux control coupled with predictive performance optimization in electric vehicle motors. This system enables dynamic adjustment of magnetic flux within the motor in real-time, responding to immediate driving conditions and operational demands. Simultaneously, the system incorporates predictive algorithms that anticipates future driving scenarios and energy requirements, allowing for proactive optimization of motor performance. Thus, the system of the present disclosure enhances overall energy efficiency across diverse driving conditions while maintaining the flexibility to balance power output and efficiency as needed. By combining adaptive flux control with predictive optimization, the system aims to significantly improve motor responsiveness, efficiency, and overall performance.

[0008] In an example implementation, a system for adaptive real-time flux control in one or more electric motors is disclosed, wherein each electric motor of the one or more electric motors comprising a main winding and one or more auxiliary windings in a stator of the one or more electric motors. The system includes a real-time data integration platform (RDIP) configured to collect and process real-time data from a plurality of sources, wherein the RDIP is configured to generate fused data based on the real-time data; a predictive performance optimization engine (PPOE) configured to receive the fused data from the RDIP and process the fused data to generate prediction data pertaining to at least one metric associated with the one or more electric motors for a set period; and an adaptive flux control module (AFCM) configured to adjust a magnetic flux in the one or more electric motors based on the real-time data received from the RDIP and the prediction data received from the PPOE.
[0009] In an aspect combinable with the example implementation, the RDIP is configured to collect the real-time data from the plurality of sources comprising at least one of internal sensors of a vehicle, global positioning system (GPS) for location and route information, external Application Programming Interfaces (APIs) for real-time weather conditions and traffic updates, and historical performance data stored in the vehicle's onboard computer.

[0010] In another aspect combinable with any of the previous aspects, the RDIP is configured to perform data fusion using a Multi-Source Adaptive Filtering (MSAF) algorithm.

[0011] In another aspect combinable with any of the previous aspects, the at least one operating metric of the one or more electric motors is a power requirement of the one or more electric motors, wherein the PPOE is configured to generate the prediction data for the power requirement of the one or more electric motors for the set period, based on at least one of a current power consumption, a predicted change due to terrain, a predicted change due to speed, a predicted change due to environmental factors, and weighting factors.

[0012] In another aspect combinable with any of the previous aspects, the AFCM is configured to estimate a current magnetic flux in the one or more electric motors and determine an optimal flux level in the one or more electric motors based on current conditions derived from the real-time data received from the RDIP and prediction conditions derived from the prediction data received from the PPOE.

[0013] In another aspect combinable with any of the previous aspects, the system is adapted to operate in a multi-motor configuration comprising a plurality of electric motors.

[0014] In another aspect combinable with any of the previous aspects, the system further includes a multi-motor coordination system (MMCS), wherein the MMCS is configured to: receive, from the RDIP, the real-time data corresponding to a performance of each electric motor of the plurality of electric motors; receive, from the PPOE, the prediction data pertaining to power requirements of each electric motor; and calculate at least one of an efficiency and a power demand of each electric motor based on operating conditions of each electric motor derived from the real-time data received from the RDIP and the prediction data received from the PPOE.

[0015] In an example implementation, a method for adaptive real-time flux control in one or more electric motors is disclosed, wherein each electric motor of the one or more electric motors comprising a main winding and one or more auxiliary windings in a stator of the one or more electric motors. The method includes collecting and processing, by a real-time data integration platform (RDIP), real-time data from a plurality of sources, the collecting and processing further comprising generating fused data based on the real-time data; receiving, by a predictive performance optimization engine (PPOE), the fused data from the RDIP and processing the fused data to generate prediction data pertaining to at least one metric associated with the one or more electric motors for a set period; and adjusting, by an adaptive flux control module (AFCM), a magnetic flux in the one or more electric motors based on the real-time data received from the RDIP and the prediction data received from the PPOE.

[0016] In an aspect combinable with the example implementation, collecting the real-time data comprises collecting the real-time data from the plurality of sources comprising at least one of internal sensors of a vehicle, global positioning system (GPS) for location and route information, external Application Programming Interfaces (APIs) for real-time weather conditions and traffic updates, and historical performance data stored in the vehicle's onboard computer.

[0017] In another aspect combinable with any of the previous aspects, generating the fused data comprises performing, by the RDIP, data fusion using a Multi-Source Adaptive Filtering (MSAF) algorithm.

[0018] In another aspect combinable with any of the previous aspects, the at least one operating metric of the electric motor is a power requirement of the one or more electric motors, wherein generating the prediction data comprises generating, by the PPOE, the prediction data for the power requirement of the one or more electric motors for the set period, based on at least one of a current power consumption, a predicted change due to terrain, a predicted change due to speed, a predicted change due to environmental factors, and weighting factors.

[0019] In another aspect combinable with any of the previous aspects, adjusting the magnetic flux comprises, estimating, by the AFCM, a current magnetic flux in the one or more electric motors and determine an optimal flux level in the one or more electric motors based on current conditions derived from the real-time data received from the RDIP and prediction conditions derived from the prediction data received from the PPOE.

[0020] In another aspect combinable with any of the previous aspects, the method is performed in a multi-motor configuration comprising a plurality of electric motors.

[0021] In another aspect combinable with any of the previous aspects, the method further includes: receiving, by a multi-motor coordination system (MMCS), the real-time data corresponding to a performance of each electric motor of the plurality of electric motors from the RDIP; receiving, by the MMCS, the prediction data pertaining to power requirements of each electric motor from the PPOE; and calculating, by the MMCS, at least one of an efficiency and a power demand of each electric motor based on operating conditions of each electric motor derived from the real-time data received from the RDIP and the prediction data received from the PPOE.

[0022] These and other features and advantages of the present invention may be appreciated from a review of the following detailed description of the present invention, along with the accompanying figures in which like reference numerals refer to like parts throughout.

BRIEF DESCRIPTION OF THE DRAWINGS
[0023] FIG. 1 is a schematic representation of a system for adaptive real-time flux control and predictive performance optimization in electric motor(s) according to an aspect of the present disclosure.

[0024] FIG. 2A is a schematic representation of a stator of an induction motor according to an aspect of the present disclosure.

[0025] FIG. 2B is a diagrammatic representation of a connection configuration between a main winding and an additional auxiliary winding of the stator to achieve high power factor according to an aspect of the present disclosure.

[0026] FIG. 3 is a schematic representation of a rotor of an induction motor according to an aspect of the present disclosure.

[0027] FIG. 4 is flowchart illustrating a method for adaptive real-time flux control and predictive performance optimization in electric motor(s) according to an aspect of the present disclosure.

DETAILED DESCRIPTION OF THE INVENTION
[0028] The following described implementations may be found in the disclosed system for adaptive real-time flux control and predictive performance optimization in electric motors.

[0029] FIG. 1 is a schematic representation of a system for adaptive real-time flux control and predictive performance optimization in electric motor(s) according to an aspect of the present disclosure. Referring to FIG. 1, there is shown a system 100 integrated with one or more electric motors 102. Each electric motor of the one or more electric motors 102 includes a main winding 102M and one or more auxiliary windings 102A in a stator of the one or more electric motors 102. The system includes a real-time data integration platform (RDIP) 106, a predictive performance optimization engine (PPOE) 108, an adaptive flux control module (AFCM) 110, and a multi- motor coordination system (MMCS) 112. These components are interconnected in a closed-loop system. The RDIP 106 continuously feeds data to the other three components, the PPOE 108, the AFCM 110 and the MMCS 112. The AFCM 110 and the MMCS 112 work together to optimize current motor performance based on immediate conditions. The PPOE 108 anticipates future needs and informs both the AFCM 110 and the MMCS 112 to prepare for upcoming changes. This integrated approach ensures that the electric vehicle is always operating at peak efficiency and performance.

[0030] The system 100 is designed to significantly enhance the efficiency and performance of electric vehicles. At its core, this system 100 aims to dynamically adjust motor performance based on current driving conditions while also anticipating future needs.

[0031] The RDIP 106 may comprise suitable logic, circuitry, interfaces and/or code that may be configured to collect and process real-time data from a plurality of sources 104. The RDIP 106 is further configured to generate fused data based on the real-time data. The RDIP 106 serves as the central data hub of the system 100, collecting and processing information from various sources 104. The RDIP 106 gathers data from multiple sources 104 that may include, but are not limited to, internal vehicle sensors (e.g., speed, acceleration, battery status, motor temperatures), GPS for location and route information, external APIs for real-time weather conditions and traffic updates, and historical performance data stored in the vehicle's onboard computer. In an implementation, the RDIP 106 uses a data fusion technique called Multi-Source Adaptive Filtering (MSAF), which integrates data from the multiple sources 104 with varying levels of accuracy and reliability. The weighted average formula for data fusion using the MSAF algorithm is given by,

X_fused = S(w_i * X_i) / S(w_i)

where,
X_fused is the final, fused data point;
X_i is the data from source I;
w_i is the reliability weight of source i.

[0032] In an implementation, the MSAF algorithm may apply filters such as, but not limited to, Kalman filters to each individual data stream to reduce noise and improve accuracy. The algorithm then assigns a reliability score to each data source based on its historical accuracy and current performance. The filtered data from all the sources 104 are then combined using the weighted average formula. After each fusion operation, the reliability scores are updated based on how well each source matched the fused result.

[0033] For example, consider that the vehicle is approaching a curve on a rainy day. The RDIP 106 receives one or more of the following data: GPS data indicating a curve ahead, weather API reporting rain, wheel sensors detecting slightly reduced traction, and historical data showing that this curve is often taken too fast.

[0034] The MSAF algorithm combines this data, giving higher weight to the real-time sensor data and GPS information. The fused data point thus obtained, may indicate a potentially hazardous curve ahead, which is then fed to other components for action.

[0035] The PPOE 108 may comprise suitable logic, circuitry, interfaces and/or code that may be configured to receive the fused data from the RDIP 106 and process the fused data to generate prediction data pertaining to at least one metric associated with the one or more electric motors 102 for a set period.

[0036] In an implementation, the PPOE 108 employs a neural network system configured to recognize patterns and make predictions based on a variety of inputs. This approach allows the system 100 to learn from past experiences and apply that knowledge to future situations.

[0037] The PPOE 108 takes in the fused data from the RDIP 106 and processes the fused data through its neural network, which has been trained on vast amounts of driving data. The neural network analyses the relationships between various factors and how they typically affect vehicle performance.

[0038] Based on this analysis, the PPOE 108 may generate predictions for the next 30 seconds of driving, for example, updating these predictions every second. This 30-second predictive window allows the system 100 to prepare for upcoming changes in terrain, traffic, or driving style well in advance. Predictive Power Requirement (PPR) is given by:

PPR(t+?t) = a * C(t) + ß * T(t) + ? * S(t) + d * E(t)

where,
PPR(t+?t) is the predicted power requirement ?t seconds in the future;
C(t) is the current power consumption;
T(t) is the predicted change due to terrain;
S(t) is the predicted change due to speed;
E(t) is the predicted change due to environmental factors;
a, ß, ?, and d are weighting factors determined by machine learning.

[0039] For instance, the PPOE 108 may receive data from the RDIP 106 indicating an uphill section 500 meters ahead, with a 5% grade. Consider that the current speed is 60 km/h, and the driver's habit is to maintain speed on hills. The PPOE 108 then calculates as follows: PPR(t+15) = 1.1 * 50kW + 0.8 * 15kW + 0.2 * 0kW + 0.1 * 2kW = 69kW. This predicts a need for 69kW of power in 15 seconds, over the current 50kW, primarily due to the upcoming hill.

[0040] The AFCM 110 may comprise suitable logic, circuitry, interfaces and/or code that may be configured to adjust a magnetic flux in the one or more electric motors 102 based on the real-time data received from the RDIP 106 and the prediction data received from the PPOE 108.

[0041] The AFCM 110 dynamically adjusts the magnetic flux in the one or more electric motors 102 to ensure optimal performance across varying speed and load conditions.

[0042] In an implementation, the AFCM 110 operates on a continuous cycle of measurement, calculation, and adjustment. The operation of the AFCM 110 begins by gathering real-time data from sensors placed throughout the motor system from the RDIP 106. The AFCM 110 also receives predictive data from the PPOE 108 (updated every second).

[0043] Using the real-time data, the AFCM 110 estimates the current magnetic flux in the one or more electric motors 102. The AFCM 110 then determines the optimal flux level based on current conditions based on the data received from the RDIP 106 and anticipated conditions based on the predicted data (predictions) from the PPOE 108. If there is a discrepancy between the actual flux and optimal flux, the AFCM 110 sends signals to the power electronics system. The optimal flux calculation (OFC) is given by:

F_opt = k * (T_req / I) * v(?_target)

where,
F_opt is the optimal flux;
K is a motor-specific constant;
T_req is the required torque (from prediction data from the PPOE 108);
I is the current;
?_target is the target efficiency.

[0044] For example, following the prediction of the PPOE 108 of a 69-kW power requirement for the upcoming hill, current conditions may include:
• Flux (F) = 0.5 Wb
• Current (I) = 200 A
• Efficiency (?) = 0.85

[0045] For example, the AFCM 110 calculates: F_opt = 0.002 * (330 Nm / 200 A) * v(0.9) = 0.63 Wb. The AFCM 110 then gradually increases the flux from 0.5 Wb to 0.63 Wb over the next 15 seconds, preparing the motor for the uphill climb while maintaining current efficiency.

[0046] In an implementation, the system 100 is adapted to operate in a multi-motor configuration comprising a plurality of electric motors 102.

[0047] The MMCS 112 may comprise suitable logic, circuitry, interfaces and/or code that may be configured to receive, from the RDIP 106, the real-time data corresponding to a performance of each electric motor of the plurality of electric motors 102. The MMCS 112 further receives, from the PPOE 108, the prediction data pertaining to power requirements of each electric motor. The MMCS 112 then calculates an efficiency and/or a power demand of each electric motor based on operating conditions of each electric motor derived from the real-time data received from the RDIP 106 and the prediction data received from the PPOE 108.

[0048] Thus, the MMCS 112 optimizes energy distribution across multiple motors in real-time, for vehicles with complex drivetrains.

[0049] In an implementation, the MMCS 112 receives real-time data about each motor's performance from the RDIP 106 and predictive data about upcoming power needs from the PPOE 108. The MMCS 112 calculates the current efficiency of each motor based on its operating conditions and determines the power demand for each motor based on current conditions and predictions of the PPOE 108.

[0050] In some implementations, the system 100 uses an advanced optimization algorithm to solve the power distribution problem, aiming to minimize total power consumption while meeting the vehicle's power demands. This optimization considers both current efficiency and anticipated future needs based on predictions of the PPOE 108.

[0051] Based on the optimization results, the MMCS 112 sends control signals to adjust the operating parameters of each motor. This process repeats continuously, allowing for real-time adaptation to changing conditions.

[0052] For example, consider a dual-motor EV approaching a hill. The MMCS 112 may receive a 69-kW power requirement prediction from the PPOE 108.

[0053] The current state includes:
• Front Motor: Operating at 30 kW with 88% efficiency.
• Rear Motor: Operating at 20 kW with 90% efficiency.

[0054] The MMCS 112 solves the optimization problem and determines the optimal power distribution:
• Front Motor: 36 kW
• Rear Motor: 33 kW

[0055] This system 100 optimizes overall efficiency while meeting the predicted power requirement. The MMCS 112 then adjusts the power allocation to each motor, accordingly, ensuring optimal performance as the vehicle performs an uphill climb. This solution optimizes overall efficiency while meeting the predicted power requirements.

[0056] All four components of the system 100 operate simultaneously in a continuous loop:
• The RDIP 106 constantly feeds real-time data to all the other components.
• The PPOE 108 continuously generates, and updates predictions based on this data.
• The AFCM 110 and the MMCS 112 use both the real-time data and predictions to optimize motor performance and power distribution.

[0057] The results of these optimizations are fed back into the system, informing the system 100 of the predictions and the required adjustments.

[0058] FIG. 2A is a diagrammatic representation of a stator of an induction motor in accordance with an exemplary implementation of the disclosure. Referring to FIG. 2A, there is shown a stator 200 of the induction motor, which includes a frame or yoke 202, a stator core 204, stator slots 206 and stator windings 208.

[0059] The frame or yoke 202 is made of close-grained alloy cast iron or aluminum alloy and forms an integral part of the stator 200. The main function of the frame or yoke 202 is to provide a protective cover for other sophisticated components or parts of the induction motor. The stator core 204 is made up of laminations which include the stator slots 206 that are punched from sheets of electrical grade steel. The space provided in the stator slots 206 is sufficient to accommodate the stator windings 208 that include one or more sets of winding wires. In related aspects, the space provided in the stator slots 206 may be more than in conventional slots. The winding wires are insulated wires. The size of the stator slots 206 may be adjusted and maintained for uniform distribution of the stator windings 208.

[0060] The space provided in the stator slots 206 is configured to accommodate the one or more sets of winding wires which include the main winding (M) which carries the supply power/energy (RMF) required for rotating the rotor and the one or more additional windings (A) which is used for transmission of the power (alternating EMF) induced in the one or more additional windings (A) while the rotor is rotating. The energy produced during the rotation of the rotor meets part of the energy requirement of the induction motor, as the induction motor partly functions as a generator.

[0061] Further, the stator 200 may include rabbets and bore that are punched carefully to ensure uniformity of air gap. The shaft and bearings used in the rotor of the induction motor are like any other conventional induction motor. The heat produced in the induction motor is comparatively less because of less current and low losses.

[0062] A number of poles and a number of windings that will be required for the stator 200 is decided based on the speed of the induction motor as the speed of the induction motor is directly proportional to frequency and inversely proportional to the number of poles according to the equation, N = 120f/P, wherein ‘N’ is the speed, ‘f’ is the frequency and ‘P’ is the number of poles.

[0063] FIG. 2B is a diagrammatic representation of a connection configuration between a main winding and an additional auxiliary winding of the stator to achieve high power factor in accordance with an exemplary implementation of the disclosure. Referring to FIG. 2B, there is shown a main coil 202 of the stator with a start terminal (Ms) and an end terminal (Me) and an auxiliary coil 204 with a start terminal (As) and an end terminal (Ae).

[0064] As depicted in FIG. 2B, the start terminal (As) of the auxiliary coil 204 is connected to the end terminal (Me) of the main coil 202.

[0065] An electronic control unit (ECU) of the induction motor receives the back EMF from the stator coils and provides the same to the auxiliary windings. Thus, the main winding and the multiple auxiliary windings are enabled with more than one power component being feed to each winding. Each winding has more than one power component enabling an efficiency component as:

• Power Component generated from the back EMF induced from the previous coil due to flux cutting.
• Power component generated by the back EMF at the coil due to flux cutting while the rotor is rotating the magnetic field (RMF).

[0066] The above-described connection configuration of the windings reduces the input current component.

[0067] FIG. 3 is a diagrammatic representation of a rotor of an induction motor in accordance with an exemplary implementation of the disclosure. Referring to FIG. 3, there is shown a rotor 300 which includes steel laminations 302, aluminum bars 304, a rotor shaft 306 and end rings 308.

[0068] The rotor 300 includes a cylinder of the steel laminations 302, with the aluminum bars 304. In some implementations, the rotor 300 may include highly conductive metal (typically aluminum or copper) embedded into its surface. At both ends of the rotor 300, rotor conductors are short-circuited by the continuous end rings 308 of similar materials to that of the rotor conductors. The rotor conductors and their end rings 308 by themselves form a closed circuit.

[0069] When an alternating current is run through the stator windings 208, the RMF is produced. This induces a current in the rotor windings, which produces its own magnetic field. The interaction of the magnetic fields produced by the stator and rotor windings produces a torque on the rotor 300.

[0070] FIG. 4 is flowchart illustrating a method for adaptive real-time flux control in electric motor(s) according to an aspect of the present disclosure. Referring to FIG. 4, there is shown a flowchart of a method 400 for adaptive real-time flux control in electric motor(s) 102.

[0071] Referring to FIG. 4, at 402, the method 400 includes collecting and processing, by a real-time data integration platform (RDIP) (e.g., RDIP 106), real-time data from a plurality of sources (e.g., sources 104), the collecting and processing further comprising generating fused data based on the real-time data.

[0072] At 404, the method 400 includes receiving, by a predictive performance optimization engine (PPOE) (e.g., the PPOE 108) the fused data from the RDIP and processing the fused data to generate prediction data pertaining to at least one metric associated with the one or more electric motors for a set period.

[0073] At 406, the method 400 includes adjusting, by an adaptive flux control module (AFCM) (e.g., the AFCM 110), a magnetic flux in the one or more electric motors based on the real-time data received from the RDIP and the prediction data received from the PPOE.

[0074] This invention represents a significant advancement in electric vehicle motor control technology. By integrating real-time data processing, predictive algorithms, adaptive flux control, and multi-motor coordination, the system offers unprecedented levels of efficiency and performance optimization. The system includes:
• Dynamic adjustment of magnetic flux in real-time.
• Predictive optimization based on anticipated driving conditions.
• Seamless integration of multiple data sources for comprehensive decision-making.
• Adaptive power distribution in multi-motor configurations.

[0075] The above-mentioned features collectively address the limitations of conventional EV motor control systems, offering improved energy efficiency, enhanced performance across diverse driving conditions, and may facilitate simplified drivetrain designs.

[0076] The adaptability and efficiency gains provided by this system may extend vehicle range and improve driving experiences.

[0077] The advantages of the system of the present disclosure include:

• Adaptive Real-Time Flux Control: Enables dynamic adjustment of motor magnetic flux in response to immediate driving conditions.

• Predictive Performance Optimization: Utilizes advanced algorithms to anticipate and prepare for future driving scenarios and energy needs.

• Enhanced Efficiency and Power Management: Optimizes the balance between energy efficiency and power output in real-time.

• Improved Responsiveness: Allows for rapid adaptation to changing driving conditions and demands.

• Potential for Enhanced Range and Performance: By optimizing motor operation continuously, the system aims to improve overall vehicle efficiency and performance.

[0078] Aspects of the present disclosure further relate to the integration of advanced predictive algorithms with adaptive flux control. Unlike reactive conventional systems, this invention incorporates predictive modelling to anticipate future energy requirements and driving conditions.

[0079] The present invention may be realized in hardware, or a combination of hardware and software. The present invention may be realized in a centralized fashion, in at least one computer system, or in a distributed fashion, where different elements may be spread across several interconnected computer systems. A computer system or other apparatus/devices adapted to carry out the methods described herein may be suited. A combination of hardware and software may be a general-purpose computer system with a computer program that, when loaded and executed on the computer system, may control the computer system such that it carries out the methods described herein. The present invention may be realized in hardware that comprises a portion of an integrated circuit that also performs other functions. The present invention may also be realized as a firmware which form part of the media rendering device.

[0080] The present invention may also be embedded in a computer program product, which includes all the features that enable the implementation of the methods described herein, and which when loaded and/or executed on a computer system may be configured to carry out these methods. Computer program, in the present context, means any expression, in any language, code or notation, of a set of instructions intended to cause a system with information processing capability to perform a particular function either directly, or after either or both of the following: a) conversion to another language, code or notation; b) reproduction in a different material form.

[0081] While the present disclosure is described with reference to certain embodiments, it will be understood by those skilled in the art that various changes may be made, and equivalents may be substituted without departure from the scope of the present disclosure. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the present disclosure without departure from its scope. Therefore, it is intended that the present disclosure is not limited to the particular embodiment disclosed, but that the present disclosure will include all embodiments that fall within the scope of the appended claims. ,CLAIMS:I/WE CLAIM:

1. A system for adaptive real-time flux control in one or more electric motors, each electric motor of the one or more electric motors comprising a main winding and one or more auxiliary windings in a stator of the one or more electric motors, the system comprising:
a real-time data integration platform (RDIP) configured to collect and process real-time data from a plurality of sources, wherein the RDIP is configured to generate fused data based on the real-time data;
a predictive performance optimization engine (PPOE) configured to receive the fused data from the RDIP and process the fused data to generate prediction data pertaining to at least one metric associated with the one or more electric motors for a set period; and
an adaptive flux control module (AFCM) configured to adjust a magnetic flux in the one or more electric motors based on the real-time data received from the RDIP and the prediction data received from the PPOE.

2. The system of claim 1, wherein the RDIP is configured to collect the real-time data from the plurality of sources comprising at least one of internal sensors of a vehicle, global positioning system (GPS) for location and route information, external Application Programming Interfaces (APIs) for real-time weather conditions and traffic updates, and historical performance data stored in the vehicle's onboard computer.

3. The system of claim 1, wherein the RDIP is configured to perform data fusion using a Multi-Source Adaptive Filtering (MSAF) algorithm.

4. The system of claim 1, wherein the at least one operating metric of the one or more electric motors is a power requirement of the one or more electric motors, wherein the PPOE is configured to generate the prediction data for the power requirement of the one or more electric motors for the set period, based on at least one of a current power consumption, a predicted change due to terrain, a predicted change due to speed, a predicted change due to environmental factors, and weighting factors.

5. The system of claim 1, wherein the AFCM is configured to estimate a current magnetic flux in the one or more electric motors and determine an optimal flux level in the one or more electric motors based on current conditions derived from the real-time data received from the RDIP and prediction conditions derived from the prediction data received from the PPOE.

6. The system of claim 1, wherein the system is adapted to operate in a multi-motor configuration comprising a plurality of electric motors.

7. The system of claim 6 further comprising a multi-motor coordination system (MMCS), wherein the MMCS is configured to:
receive, from the RDIP, the real-time data corresponding to a performance of each electric motor of the plurality of electric motors;
receive, from the PPOE, the prediction data pertaining to power requirements of each electric motor; and
calculate at least one of an efficiency and a power demand of each electric motor based on operating conditions of each electric motor derived from the real-time data received from the RDIP and the prediction data received from the PPOE.

8. A method for adaptive real-time flux control in one or more electric motors, each electric motor of the one or more electric motors comprising a main winding and one or more auxiliary windings in a stator of the one or more electric motors, the method comprising:
collecting and processing, by a real-time data integration platform (RDIP), real-time data from a plurality of sources, the collecting and processing further comprising generating fused data based on the real-time data;
receiving, by a predictive performance optimization engine (PPOE), the fused data from the RDIP and processing the fused data to generate prediction data pertaining to at least one metric associated with the one or more electric motors for a set period; and
adjusting, by an adaptive flux control module (AFCM), a magnetic flux in the one or more electric motors based on the real-time data received from the RDIP and the prediction data received from the PPOE.

9. The method of claim 8, wherein collecting the real-time data comprises collecting the real-time data from the plurality of sources comprising at least one of internal sensors of a vehicle, global positioning system (GPS) for location and route information, external Application Programming Interfaces (APIs) for real-time weather conditions and traffic updates, and historical performance data stored in the vehicle's onboard computer.

10. The method of claim 8, wherein generating the fused data comprises performing, by the RDIP, data fusion using a Multi-Source Adaptive Filtering (MSAF) algorithm.

11. The method of claim 8, wherein the at least one operating metric of the electric motor is a power requirement of the one or more electric motors, wherein generating the prediction data comprises generating, by the PPOE, the prediction data for the power requirement of the one or more electric motors for the set period, based on at least one of a current power consumption, a predicted change due to terrain, a predicted change due to speed, a predicted change due to environmental factors, and weighting factors.

12. The method of claim 8, wherein adjusting the magnetic flux comprises, estimating, by the AFCM, a current magnetic flux in the one or more electric motors and determine an optimal flux level in the one or more electric motors based on current conditions derived from the real-time data received from the RDIP and prediction conditions derived from the prediction data received from the PPOE.

13. The method of claim 8, wherein the method is performed in a multi-motor configuration comprising a plurality of electric motors.

14. The method of claim 13 further comprising:
receiving, by a multi-motor coordination system (MMCS), the real-time data corresponding to a performance of each electric motor of the plurality of electric motors from the RDIP;
receiving, by the MMCS, the prediction data pertaining to power requirements of each electric motor from the PPOE; and
calculating, by the MMCS, at least one of an efficiency and a power demand of each electric motor based on operating conditions of each electric motor derived from the real-time data received from the RDIP and the prediction data received from the PPOE.