New energy automobile motor efficiency control method and system

Abstract

The invention discloses a new energy automobile motor efficiency control method and system, and relates to the technical field of efficiency control, and the method comprises the steps: carrying out the data collection of the operation state of a new energy automobile motor, and constructing a motor digital twin efficiency model; performing dynamic coupling analysis based on the motor digital twin efficiency model to extract a multi-field coupling influence factor, predicting the degradation trend of the motor efficiency parameter of the new energy vehicle based on the multi-field coupling influence factor, and determining a degradation trend prediction result; the method comprises the steps of establishing an environment disturbance factor library, obtaining real-time road condition topological data and driving behavior characteristic data, constructing a dynamic disturbance scene set based on the environment disturbance factor library, the real-time road condition topological data and the driving behavior characteristic data, and confirming an optimization strategy based on the dynamic disturbance scene set; and generating a dynamic efficiency regulation and control instruction set based on a degradation trend prediction result and an optimization strategy, and realizing energy efficiency closed-loop optimization control of the driving motor. The method has the effect of improving the motor control efficiency of the new energy automobile.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of efficiency control, in particular to a new energy automobile motor efficiency control method and system. BACKGROUND

[0002] New energy vehicles refer to vehicles that use on-board power sources as power and drive wheels with electric motors. It meets the requirements of road traffic and safety regulations. Its prospects are widely optimistic because it has relatively less impact on the environment than traditional cars, but the current technology is not mature. The power source provides power for the drive motor of the new energy vehicle, and the new energy vehicle motor converts the power of the power source into mechanical energy through a transmission device or directly drives the wheels and working devices. The most widely used power source on new energy vehicles is lead-acid batteries, but with the development of new energy vehicle technology, lead-acid batteries are gradually being replaced by other batteries due to their low specific energy, slow charging speed, and short service life.

[0003] In related technologies, the traditional new energy vehicle motor control method generally uses a parameter optimization strategy based on fixed working conditions, which is difficult to cope with complex and variable actual operating environments, thereby reducing the effect of new energy vehicle motor efficiency control, and there is room for improvement. SUMMARY

[0004] To overcome the deficiencies of the prior art, the present application provides a new energy automobile motor efficiency control method and system.

[0005] In a first aspect, the present application provides a new energy automobile motor efficiency control method, comprising the following steps: Step S1: Collecting the running state data of the new energy automobile motor through the on-board multi-source sensor array, obtaining the motor coupling data, and constructing a motor digital twin efficiency model based on the motor coupling data; Step S2: Based on the motor digital twin efficiency model, the multi-field coupling influence factors are extracted by dynamic coupling analysis, and the degradation trend of the new energy automobile motor efficiency parameters is predicted based on the multi-field coupling influence factors, and the degradation trend prediction result is confirmed; Step S3: Establishing an environmental disturbance factor library, obtaining real-time road topology data and driving behavior characteristic data, and then constructing a dynamic disturbance scene set based on the environmental disturbance factor library, real-time road topology data and driving behavior characteristic data, and confirming the optimization strategy based on the dynamic disturbance scene set; Step S4: Based on the degradation trend prediction result and the optimization strategy, a dynamic efficiency control instruction set is generated, and then the drive motor energy efficiency closed-loop optimization control is realized.

[0006] Preferably, the step S1 specifically comprises: Step S11: Collecting original sensing data through a vehicle-mounted multi-source sensor array deployed at a new energy vehicle motor stator winding, a rotor assembly, and a power module, the original sensing data including three-phase current harmonic component data, permanent magnet temperature field distribution characteristic data, radial air gap magnetic flux waveform data, and bearing vibration acceleration data; Step S12: Performing multi-channel signal preprocessing on the original sensing data, inputting the preprocessed original sensing data into a preset feature fusion network, and then generating motor coupling data; Step S13: Driving a digital twin engine based on the motor coupling data to construct a motor digital twin efficiency model.

[0007] Preferably, the step S2 specifically includes: Step S21: Setting a virtual working condition excitation source in the motor digital twin efficiency model, and collecting electromagnetic loss density distribution data, thermal strain gradient data, and mechanical stress tensor data under different virtual working conditions to construct a multi-field coupling feature matrix; Step S22: Performing dimensionality reduction processing on the multi-field coupling feature matrix to extract multi-field coupling influence factors, the multi-field coupling influence factors including a permanent magnet demagnetization sensitive factor, a winding thermal resistance change factor, and a bearing clearance expansion factor, and then constructing a multi-field coupling influence factor set according to the multi-field coupling influence factors; Step S23: Constructing a degradation prediction model based on a nonlinear autoregressive neural network, inputting the multi-field coupling influence factor set into the degradation prediction model for time series deduction, and outputting degradation trend prediction results, the degradation trend prediction results including an efficiency decay curve, a peak torque drop rate, and a winding insulation aging coefficient.

[0008] Preferably, the step S23 specifically further includes: Integrating an online learning unit in the degradation prediction model, performing difference analysis on actual degradation data and degradation trend prediction results collected in real time, confirming a difference evaluation coefficient based on a result of the difference analysis, dynamically adjusting an activation function parameter of a hidden layer node of the nonlinear autoregressive neural network, and establishing a state evaluation unit to perform probability distribution modeling on a confidence interval of the degradation trend prediction results; When it is detected that the difference evaluation coefficient of the actual degradation data and the degradation trend prediction results exceeds a preset threshold value, triggering a corresponding reconstruction mechanism of the motor digital twin model.

[0009] Preferably, the step S3 specifically includes: Step S31: constructing an environmental disturbance factor library containing environmental temperature and humidity gradient data, altitude and air pressure fluctuation feature data, and peripheral power equipment interference distribution data, and obtaining real-time road condition topology data through a vehicle-mounted CAN bus, the real-time road condition topology data containing road slope coefficient, curve radius of curvature, and traffic flow density feature data; Step S32: collecting driving behavior feature data through a new energy vehicle cockpit sensor, the driving behavior feature data including acceleration pedal opening degree change rate, brake pedal force value, and steering wheel steering angular velocity, and constructing a driving behavior feature vector based on the driving behavior feature data; Step S33: performing association rule mining on the environmental disturbance factor library, real-time road condition topology data, and driving behavior feature vector, and constructing a dynamic disturbance scene set based on knowledge graph technology; Step S34: performing strategy optimization on the dynamic disturbance scene set, and outputting an optimized strategy, the optimized strategy containing work mode switching strategy, energy distribution weight matrix, and heat management priority.

[0010] Preferably, the step S4 specifically includes: establishing an efficiency optimization objective function, and generating a constraint condition set based on the degradation trend prediction result, the constraint condition set including a maximum allowed temperature rise threshold, a minimum efficiency retention rate, and a torque fluctuation tolerance interval; solving the efficiency optimization objective function by using a multi-objective particle swarm optimization algorithm, and generating a dynamic efficiency regulation instruction set, the dynamic efficiency regulation instruction set containing current harmonic suppression parameters, magnetic field weakening coefficients, and cooling liquid flow regulation instructions; distributing the dynamic efficiency regulation instruction set to a motor controller, a heat management system, and an energy management unit, to realize drive motor energy efficiency closed-loop optimization control.

[0011] Preferably, after the dynamic efficiency regulation instruction set is distributed to the motor controller, the heat management system, and the energy management unit, the method further includes: establishing an energy efficiency optimization effect evaluation function, and confirming an energy efficiency optimization effect score based on the energy efficiency optimization effect evaluation function; comparing the energy efficiency optimization effect score with a preset score threshold; if the energy efficiency optimization effect score exceeds the preset score threshold, the dynamic efficiency regulation instruction set does not need to be adjusted; if the energy efficiency optimization effect score is lower than the preset score threshold, the dynamic efficiency regulation instruction set needs to be adjusted.

[0012] In a second aspect, the application provides a new energy vehicle motor efficiency control system, including: The data acquisition module is configured to acquire data of an operating state of the motor of the new energy vehicle through a vehicle-mounted multi-source sensor array, acquire motor coupling data, and construct a motor digital twin efficiency model based on the motor coupling data; The prediction module is configured to extract multi-field coupling influence factors based on dynamic coupling analysis of the motor digital twin efficiency model, predict a degradation trend of an efficiency parameter of the motor of the new energy vehicle based on the multi-field coupling influence factors, and confirm a degradation trend prediction result. The strategy generation module is configured to establish an environmental disturbance factor library, acquire real-time road topology data and driving behavior characteristic data, construct a dynamic disturbance scenario set based on the environmental disturbance factor library, the real-time road topology data, and the driving behavior characteristic data, and confirm an optimization strategy based on the dynamic disturbance scenario set. The optimization module is configured to generate a dynamic efficiency regulation instruction set based on the degradation trend prediction result and the optimization strategy, and thus realize closed-loop optimization control of the driving motor efficiency.

[0013] In a third aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, cause the computer to perform the new energy vehicle motor efficiency control method of any one of the preceding aspects.

[0014] In summary, the present application has the following beneficial technical effects: The present application provides a new energy vehicle motor efficiency control method, which constructs a motor digital twin efficiency model by acquiring motor coupling data, extracts multi-field coupling influence factors based on dynamic coupling analysis of the motor digital twin efficiency model, predicts a degradation trend of an efficiency parameter of the motor of the new energy vehicle based on the multi-field coupling influence factors, confirms a degradation trend prediction result, establishes an environmental disturbance factor library, acquires real-time road topology data and driving behavior characteristic data, and then confirms an optimization strategy based on the environmental disturbance factor library, the real-time road topology data, and the driving behavior characteristic data, generates a dynamic efficiency regulation instruction set based on the degradation trend prediction result and the optimization strategy, and thus effectively controls the motor efficiency based on multiple parameters, effectively reduces the situation that it is difficult to cope with the actual operating environment due to a parameter optimization strategy based on a fixed operating condition, and thus effectively improves the effect of new energy vehicle motor efficiency control. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0016] Figure 1 is a flow chart of a new energy vehicle motor efficiency control method according to an embodiment of the present application.

[0017] Figure 2 is a system schematic diagram of a new energy vehicle motor efficiency control according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] The following will be described in detail below with reference to the accompanying drawings. Figures 1-2 The present application will be further described in detail.

[0019] Embodiment 1 The embodiment of the present application discloses a new energy vehicle motor efficiency control method.

[0020] With reference to Figure 1 A new energy vehicle motor efficiency control method, comprising the following steps: Step S1: collecting data of the running state of the new energy vehicle motor through a vehicle-mounted multi-source sensor array, acquiring motor coupling data, and constructing a motor digital twin efficiency model based on the motor coupling data; Step S2: performing dynamic coupling analysis based on the motor digital twin efficiency model to extract multi-field coupling influence factors, predicting the degradation trend of the new energy vehicle motor efficiency parameters based on the multi-field coupling influence factors, and confirming the degradation trend prediction result; Step S3: establishing an environmental disturbance factor library, acquiring real-time road topology data and driving behavior characteristic data, and then constructing a dynamic disturbance scene set based on the environmental disturbance factor library, real-time road topology data and driving behavior characteristic data, and confirming the optimization strategy based on the dynamic disturbance scene set; Step S4: generating a dynamic efficiency regulation instruction set based on the degradation trend prediction result and the optimization strategy, and then realizing drive motor energy efficiency closed-loop optimization control.

[0021] According to the technical scheme, the motor coupling data during motor operation is collected in real time through the vehicle-mounted multi-source sensor array, and a motor digital twin efficiency model is constructed based on the motor coupling data by using a digital twin technology. The motor digital twin efficiency model can accurately map the efficiency characteristics of the motor under different working conditions. For example, the energy loss of the motor under high speed or high torque can be simulated, thereby laying a foundation for subsequent analysis. According to the motor digital twin efficiency model, the multi-field coupling relationship during motor operation is dynamically analyzed, and multi-field coupling influence factors such as the influence of temperature change on winding resistance, the correlation between electromagnetic loss and speed, and the change of mechanical friction with the degree of wear are extracted. In the embodiment of the application, taking temperature as an example, when the motor temperature rises, the winding resistance increases, resulting in increased copper loss and decreased efficiency. By analyzing the influence of the above factors on efficiency, the degradation trend of the motor efficiency parameter with time or mileage can be predicted. For example, it is predicted that the efficiency of a certain type of motor may decrease by 3%-5% after driving 100,000 kilometers due to bearing wear and winding aging, thereby obtaining the degradation trend prediction result, which provides a basis for early intervention. An environmental disturbance factor library is established, real-time road condition topology data and driving behavior characteristic data are obtained, a dynamic disturbance scene set is constructed based on the above data, and a complex scene of "high temperature + climbing + frequent rapid acceleration" is exemplified. For each complex scene, the influence of the scene on the motor efficiency is analyzed, and a corresponding optimization strategy is developed, such as adjusting the motor control strategy when climbing to preferentially ensure torque output to avoid a sharp decrease in efficiency. According to the degradation trend prediction result and the optimization strategy under the dynamic disturbance scene, a dynamic efficiency control instruction set is generated. In the embodiment of the application, the dynamic efficiency control instruction set includes but is not limited to real-time adjustment of motor voltage and current control parameters, optimization of energy distribution strategy, etc. The dynamic efficiency control instruction set is used to realize dynamic optimization of motor energy efficiency through closed-loop control. For example, when it is predicted that the motor temperature will rise and the efficiency will decrease due to long-time high-load operation, the dynamic efficiency control instruction set will automatically reduce the upper limit of motor power output in combination with the current congested road condition, and start the cooling system to maintain the efficiency at a high level on the premise of ensuring power demand. Through the above steps, the effect of new energy vehicle motor efficiency control is effectively improved.

[0022] It should be noted that the step S1 specifically includes: Step S11: collecting original sensing data through a vehicle-mounted multi-source sensor array deployed at a new energy vehicle motor stator winding, a rotor assembly and a power module. The original sensing data includes three-phase current harmonic component data, permanent magnet temperature field distribution characteristic data, radial air gap magnetic density waveform data and bearing vibration acceleration data. Step S12: multi-channel signal preprocessing is performed on the original sensing data, and the preprocessed original sensing data is input into a preset feature fusion network, and motor coupling data is generated; Step S13: driving a digital twin engine based on the motor coupling data, a motor digital twin efficiency model is constructed.

[0023] Specifically, precise data acquisition is performed through a vehicle-mounted multi-source sensor array. For example, a current sensor is deployed at the motor stator winding to capture harmonic component data in three-phase current in real time. These harmonic components can reflect potential faults such as inter-turn short circuit of the winding. A temperature sensor array is embedded near the rotor permanent magnet assembly to obtain temperature field distribution characteristic data. For example, the edge temperature of the permanent magnet may be 15-20℃ higher than the center temperature when running at high speed. A Hall sensor or a fluxgate sensor is used to collect radial air gap magnetic flux density waveform data for analyzing electromagnetic coupling state. An acceleration sensor is arranged at the bearing seat to capture bearing vibration acceleration data. For example, when the rolling element is worn, the 100Hz component in the vibration spectrum will be significantly enhanced. The above-mentioned sensor array covers multiple physical fields of the motor, such as electric, magnetic, thermal and mechanical fields, providing original data support for subsequent analysis. The original sensing data is subjected to multi-channel signal preprocessing. For example, wavelet transform is used to remove high-frequency noise for current harmonic component data. Interpolation processing is performed on temperature field distribution data to make up for the problem of insufficient sensor arrangement density. Filtering is performed on magnetic flux density waveform data to eliminate power ripple interference. The preprocessed original sensing data is input into a preset feature fusion network. The feature fusion network can automatically extract coupling features across multiple physical fields. For example, joint analysis of current harmonic components and magnetic flux density waveform data can identify the coupling relationship between air gap magnetic flux density distortion caused by rotor eccentricity and current harmonic increase. Fusion of temperature field distribution and vibration data can find the correlation between bearing overheating and abnormal vibration. The feature fusion network outputs motor coupling data. Based on the motor coupling data, a digital twin engine is driven to construct a motor digital twin efficiency model. The digital twin engine maps multiple field coupling features into motor efficiency characteristics through a combination of physical modeling and data-driven modeling, thereby constructing a motor digital twin efficiency model. Through precise layout of the sensor array and multi-channel signal processing, high-precision acquisition and feature fusion of motor multi-physical field data are realized, avoiding the one-sidedness of single parameter monitoring. The motor digital twin efficiency model converts abstract coupling data into quantifiable efficiency loss prediction, providing a precise virtual mapping basis for subsequent dynamic optimization. It should be noted that the step S2 specifically includes: Step S21: setting a virtual working condition excitation source in the motor digital twin efficiency model, and collecting electromagnetic loss density distribution data, thermal strain gradient data and mechanical stress tensor data under different virtual working conditions to construct a multi-field coupling feature matrix. Step S22: Dimensionality reduction processing is performed on the multi-field coupling feature matrix to extract multi-field coupling influence factors, the multi-field coupling influence factors include a permanent magnet demagnetization sensitive factor, a winding thermal resistance change factor, and a bearing gap expansion factor, and a multi-field coupling influence factor set is constructed according to the multi-field coupling influence factors; Step S23: A degradation prediction model is constructed based on a nonlinear autoregressive neural network, the multi-field coupling influence factor set is input into the degradation prediction model for time series deduction, and a degradation trend prediction result is output, the degradation trend prediction result includes an efficiency decay curve, a peak torque drop rate, and a winding insulation aging coefficient.

[0024] Specifically, a virtual working condition excitation source is set in the motor digital twin efficiency model to simulate complex scenarios in actual motor operation. For example, a combination of “rapid acceleration-hill climbing-high temperature” working conditions is set, and the excitation source injects excitation such as speed mutation, load step, and environmental temperature rise into the motor digital twin efficiency model. When the motor digital twin efficiency model is running, electromagnetic loss density distribution data, thermal strain gradient data, and mechanical stress tensor data are synchronously collected, the above data are arranged according to spatial position and time sequence, and a multi-field coupling feature matrix is constructed. The multi-field coupling feature matrix is subjected to dimensionality reduction processing while retaining the factors that have the greatest impact on motor degradation. Through the combination of physical mechanisms and data-driven methods, multi-field coupling influence factors are extracted: Permanent magnet demagnetization sensitive factor: associated with the distortion degree of magnetic density waveform and temperature; winding thermal resistance change factor: based on the coupling of temperature field distribution and current harmonics; bearing gap expansion factor: fusion analysis of vibration spectrum and mechanical stress; the multi-field coupling influence factors constitute a multi-field coupling influence factor set, thereby effectively realizing the extraction of key degradation indicators from massive data; A nonlinear autoregressive neural network is used to construct a degradation prediction model. The nonlinear autoregressive neural network can capture the dynamic nonlinear relationship between multi-field factors and degradation indicators. For example, historical data including the permanent magnet demagnetization sensitive factor, the winding thermal resistance change factor, and the like are input as inputs, time series deduction is performed through the delay feedback connection inside the nonlinear autoregressive neural network, and a degradation trend prediction result is output.

[0025] It should be noted that the step S23 specifically further includes: An online learning unit is integrated in the degradation prediction model, difference analysis is performed on actual degradation data and the degradation trend prediction result collected in real time, a difference evaluation coefficient is confirmed based on the result of the difference analysis, the activation function parameters of the hidden layer nodes of the nonlinear autoregressive neural network are dynamically adjusted, and a state evaluation unit is established to model the probability distribution of the confidence interval of the degradation trend prediction result; When the difference evaluation coefficient of the actual degradation data and the degradation trend prediction result exceeds the preset threshold, the reconstruction mechanism of the motor digital twin model is triggered.

[0026] Specifically, the online learning unit integrated in the degradation prediction model collects real-time actual degradation data (such as current permanent magnet temperature, winding resistance change, bearing vibration amplitude, etc.) in the motor operation, and compares it with the degradation trend prediction result output by the degradation prediction model. For example, the permanent magnet temperature is predicted to be 78℃ at a certain time, while the actual sensor collection value is 85℃, and the difference between the two is 7℃, which is used as the original data for difference analysis. The difference evaluation coefficient is generated by calculating the absolute value of the difference, the relative error and the cumulative deviation in the time sequence. For example, if the temperature difference weight is set to 0.4, when the absolute temperature difference exceeds 5℃ and lasts for 3 consecutive sampling periods, the difference evaluation coefficient is calculated as 0.65 (threshold is 0.5); Based on the difference evaluation coefficient, the activation function parameters of the hidden layer nodes of the nonlinear autoregressive neural network are dynamically adjusted. For example, if the activation function is a Sigmoid function, the center point parameter is adjusted to make the function curve shift towards the difference data; The state evaluation unit models the probability distribution of the confidence interval of the degradation trend prediction result. For example, for the efficiency decay curve, a normal distribution model is established based on the historical difference data statistics, with the predicted value as the mean and the difference evaluation coefficient as the variance. When the difference evaluation coefficient is 0.3, the confidence interval of the efficiency prediction value 94.5% is [93.2%, 95.8%], and the peak value of the probability density function is 1.2. When the difference evaluation coefficient rises to 0.6, the confidence interval expands to [92.1%, 96.3%], and the peak value drops to 0.8, which intuitively reflects the increase of prediction uncertainty. When the difference evaluation coefficient exceeds the preset threshold (such as 0.5), the reconstruction mechanism of the motor digital twin model is triggered.

[0027] It should be noted that the step S3 specifically includes: Step S31: Construct an environmental disturbance factor library, which contains environmental temperature and humidity gradient data, altitude and pressure fluctuation characteristic data, and surrounding power equipment interference distribution data. Real-time road condition topology data is obtained through the vehicle CAN bus, which includes road slope coefficient, curve radius and traffic flow density characteristic data. Step S32: Collect driving behavior characteristic data through new energy vehicle cockpit sensors, including acceleration pedal opening rate of change, brake pedal force value and steering wheel steering angular velocity, and construct a driving behavior feature vector based on the driving behavior characteristic data. Step S33: Correlation rule mining is performed on the environmental disturbance factor library, real-time road condition topology data and driving behavior feature vector, and a dynamic disturbance scene set is constructed based on knowledge graph technology; Step S34: Strategy optimization is performed on the dynamic disturbance scene set, and an optimized strategy is output, the optimized strategy including a working mode switching strategy, an energy distribution weight matrix and a thermal management priority.

[0028] Specifically, the coupling relationship of the environmental disturbance factor library, real-time road condition topology data and driving behavior feature vector is analyzed through correlation rule mining. For example, it is found that when "environmental temperature > 35℃" and "slope > 5%" appear at the same time, there is a 85% probability of "rapid acceleration behavior"; when "altitude > 3000 meters" and "traffic flow density > 20 vehicles / km" are combined, the probability of the driver frequently braking reaches 72%. Based on the above rules, a dynamic disturbance scene set is constructed based on knowledge graph technology, and each scene is represented in the form of a triple, such as scene 1 {temperature 40℃, humidity 60%, slope 7%, acceleration change rate 75% / s}. The coupling strength of each factor is quantified through the connection weight between the nodes of the knowledge graph. Strategy optimization is performed on the dynamic disturbance scene set. In the embodiments of the present application, optimization methods such as reinforcement learning or genetic algorithm are used. For example, for scene 1 (high temperature + climbing + rapid acceleration), the optimization goal is to maximize the motor efficiency and control the temperature not to exceed the safety threshold: Working mode switching strategy: switch from high-efficiency mode to high-temperature-resistant mode to avoid high-temperature demagnetization; Energy distribution weight matrix: adjust the energy distribution ratio of the battery and the motor to reduce the motor heat; Thermal management priority: adjust the cooling system priority from the battery priority to the motor-battery parallel, and start the liquid cooling circuit of the motor winding; The fusion of the environmental disturbance factor library and real-time data in the above steps realizes comprehensive perception of complex external environment, and the construction of the driving behavior feature vector further enables the prediction of the driver's operation intention, such as adjusting the motor torque output curve in advance before rapid acceleration. The scene construction driven by the knowledge graph can capture the implicit association of man-car-environment, and effectively realize the multi-objective balance of environmental adaptability, energy efficiency optimization and driving experience.

[0029] It should be noted that the step S4 specifically includes: An efficiency optimization objective function is established, and a constraint condition set is generated based on the degradation trend prediction result, the constraint condition set including a maximum allowed temperature rise threshold, a minimum efficiency retention rate and a torque fluctuation tolerance interval; The multi-objective particle swarm optimization algorithm is used to solve the efficiency optimization objective function, and a dynamic efficiency regulation instruction set is generated, the dynamic efficiency regulation instruction set including current harmonic suppression parameters, magnetic field weakening coefficients and cooling liquid flow regulation instructions. The dynamic efficiency regulation instruction set is distributed to the motor controller, the thermal management system and the energy management unit to realize closed-loop optimization control of the driving motor energy efficiency.

[0030] Specifically, when the motor controller receives the current harmonic suppression parameters, the PWM modulation strategy is adjusted in real time; when the thermal management system executes the flow regulation instructions, the temperature feedback is monitored synchronously and fine-tuned; and the energy management unit adjusts the battery output power according to the field weakening coefficient to avoid overcurrent protection.

[0031] Further, after the dynamic efficiency regulation instruction set is distributed to the motor controller, the thermal management system and the energy management unit, the following steps are further included: An energy efficiency optimization effect evaluation function is established, and an energy efficiency optimization effect score is confirmed based on the energy efficiency optimization effect evaluation function; The energy efficiency optimization effect score is compared with a preset score threshold; If the energy efficiency optimization effect score exceeds the preset score threshold, the dynamic efficiency regulation instruction set does not need to be adjusted; If the energy efficiency optimization effect score is lower than the preset score threshold, the dynamic efficiency regulation instruction set needs to be adjusted.

[0032] Embodiment 2 The embodiment of the application further discloses a new energy automobile motor efficiency control system.

[0033] Reference Figure 2 A new energy automobile motor efficiency control system includes: A data acquisition module is configured to acquire data of a running state of a new energy automobile motor through a vehicle-mounted multi-source sensor array, acquire motor coupling data, and construct a motor digital twin efficiency model based on the motor coupling data; A prediction module is configured to perform dynamic coupling analysis based on the motor digital twin efficiency model to extract multi-field coupling influence factors, predict a degradation trend of new energy automobile motor efficiency parameters based on the multi-field coupling influence factors, and confirm a degradation trend prediction result; A strategy generation module is configured to establish an environmental disturbance factor library, acquire real-time road topology data and driving behavior characteristic data, construct a dynamic disturbance scene set based on the environmental disturbance factor library, the real-time road topology data and the driving behavior characteristic data, and confirm an optimization strategy based on the dynamic disturbance scene set; An optimization module is configured to generate a dynamic efficiency regulation instruction set based on the degradation trend prediction result and the optimization strategy, so as to realize the closed-loop optimization control of the driving motor.

[0034] The above merely illustrates and describes the concept of the present application. Those skilled in the art can make various modifications or supplements to the described specific embodiments or use similar ways to replace, without departing from the concept of the present application. All of these shall fall within the protection scope of the present application.

[0035] In the description of the present application, the description of the terms "one embodiment", "an example", "a specific example" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present application, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the described specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0036] The preferred embodiments of the present application disclosed above are only used to help explain the present application. The preferred embodiments do not describe all the details and limit the present application to the specific embodiments. Obviously, many modifications and changes can be made according to the content of the present application. The present application selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can well understand and use the present application.

Claims

1. A method for controlling the efficiency of a new energy vehicle motor, characterized in that, Includes the following steps: Step S1: Collect data on the operating status of the electric motor of the new energy vehicle through the on-board multi-source sensor array, obtain motor coupling data, and construct a digital twin efficiency model of the motor based on the motor coupling data; Step S2: Based on the digital twin efficiency model of the motor, perform dynamic coupling analysis to extract multi-field coupling influencing factors, and predict the degradation trend of the efficiency parameters of the new energy vehicle motor based on the multi-field coupling influencing factors, and confirm the degradation trend prediction results. Step S3: Establish an environmental disturbance factor library, and acquire real-time road condition topology data and driving behavior feature data. Then, construct a dynamic disturbance scenario set based on the environmental disturbance factor library, real-time road condition topology data and driving behavior feature data, and determine the optimization strategy based on the dynamic disturbance scenario set. Step S4: Generate a dynamic efficiency control instruction set based on the degradation trend prediction results and the optimization strategy, thereby realizing closed-loop optimization control of the drive motor's energy efficiency.

2. The method for controlling the efficiency of a new energy vehicle motor according to claim 1, characterized in that, Step S1 specifically includes: Step S11: Collect raw sensing data by deploying an on-board multi-source sensor array at the stator winding, rotor assembly and power module of the new energy vehicle motor. The raw sensing data includes three-phase current harmonic component data, permanent magnet temperature field distribution characteristic data, radial air gap magnetic flux density waveform data and bearing vibration acceleration data. Step S12: Perform multi-channel signal preprocessing on the raw sensing data, and input the preprocessed raw sensing data into a preset feature fusion network to generate motor coupling data; Step S13: Based on the motor coupling data, drive the digital twin engine to construct a motor digital twin efficiency model.

3. The method for controlling the efficiency of a new energy vehicle motor according to claim 1, characterized in that, Step S2 specifically includes: Step S21: Set up a virtual operating condition excitation source in the digital twin efficiency model of the motor, and collect electromagnetic loss density distribution data, thermal strain gradient data and mechanical stress tensor data under different virtual operating conditions to construct a multi-field coupling feature matrix. Step S22: Dimensionality reduction is performed on the multi-field coupling feature matrix to extract the multi-field coupling influence factors. The multi-field coupling influence factors include permanent magnet demagnetization sensitivity factor, winding thermal resistance change factor and bearing clearance expansion factor. Then, a multi-field coupling influence factor set is constructed based on the multi-field coupling influence factors. Step S23: Construct a degradation prediction model based on a nonlinear autoregressive neural network, input the set of multi-field coupling influencing factors into the degradation prediction model for time series extrapolation, and output degradation trend prediction results. The degradation trend prediction results include efficiency decay curve, peak torque reduction rate and winding insulation aging coefficient.

4. The method for controlling the efficiency of a new energy vehicle motor according to claim 3, characterized in that, Step S23 specifically also includes: An online learning unit is integrated into the degradation prediction model. The difference analysis is performed between the actual degradation data collected in real time and the degradation trend prediction results. Based on the difference analysis results, the difference evaluation coefficient is confirmed, the activation function parameters of the hidden layer nodes of the nonlinear autoregressive neural network are dynamically adjusted, and a state evaluation unit is established to model the probability distribution of the confidence interval of the degradation trend prediction results. When the difference between the actual degradation data and the degradation trend prediction result exceeds the preset threshold, the reconstruction mechanism corresponding to the motor digital twin model is triggered.

5. The method for controlling the efficiency of a new energy vehicle motor according to claim 2, characterized in that, Step S3 specifically includes: Step S31: Construct an environmental disturbance factor library, which includes environmental temperature and humidity gradient data, altitude and air pressure fluctuation characteristic data, and surrounding power equipment interference distribution data. Real-time road condition topology data is obtained through the vehicle CAN bus, which includes road slope coefficient, curve curvature radius, and traffic flow density characteristic data. Step S32: Collect driving behavior feature data through the cockpit sensors of the new energy vehicle. The driving behavior feature data includes the accelerator pedal opening change rate, brake pedal force value and steering wheel steering angle velocity, and construct a driving behavior feature vector based on the driving behavior feature data. Step S33: Perform association rule mining on the environmental disturbance factor library, real-time road condition topology data and driving behavior feature vectors, and construct a dynamic disturbance scenario set based on knowledge graph technology; Step S34: Perform strategy optimization on the set of dynamic disturbance scenarios and output an optimization strategy. The optimization strategy includes a working mode switching strategy, an energy allocation weight matrix, and a thermal management priority.

6. The method for controlling the efficiency of a new energy vehicle motor according to claim 1, characterized in that, Step S4 specifically includes: An efficiency optimization objective function is established, and a set of constraints is generated based on the degradation trend prediction results. The set of constraints includes the maximum allowable temperature rise threshold, the minimum efficiency retention rate, and the torque fluctuation tolerance range. A multi-objective particle swarm optimization algorithm is used to solve the efficiency optimization objective function and generate a dynamic efficiency control instruction set, which includes current harmonic suppression parameters, magnetic field weakening coefficient and coolant flow control instructions. The dynamic efficiency control instruction set is distributed to the motor controller, thermal management system and energy management unit to realize closed-loop optimization control of drive motor energy efficiency.

7. The method for controlling the efficiency of a new energy vehicle motor according to claim 6, characterized in that, After the dynamic efficiency control instruction set is distributed to the motor controller, thermal management system, and energy management unit, it also includes: Establish an energy efficiency optimization effect evaluation function, and determine the energy efficiency optimization effect score based on the energy efficiency optimization effect evaluation function; The energy efficiency optimization score is compared with a preset score threshold. If the energy efficiency optimization effect score exceeds the preset score threshold, then there is no need to adjust the dynamic efficiency control instruction set. If the energy efficiency optimization score is lower than the preset score threshold, the dynamic efficiency control instruction set needs to be adjusted.

8. A new energy vehicle motor efficiency control system, applied to the new energy vehicle motor efficiency control method described in any one of claims 1-7, characterized in that, include: The data acquisition module is used to collect data on the operating status of the motor of the new energy vehicle through the on-board multi-source sensor array, obtain motor coupling data, and construct a digital twin efficiency model of the motor based on the motor coupling data. The prediction module is used to extract multi-field coupling influencing factors by performing dynamic coupling analysis based on the motor digital twin efficiency model, and to predict the degradation trend of the efficiency parameters of the new energy vehicle motor based on the multi-field coupling influencing factors, and to confirm the degradation trend prediction results. The strategy generation module is used to establish an environmental disturbance factor library, acquire real-time road condition topology data and driving behavior feature data, and then construct a dynamic disturbance scenario set based on the environmental disturbance factor library, real-time road condition topology data and driving behavior feature data, and determine the optimization strategy based on the dynamic disturbance scenario set. The optimization module is used to generate a dynamic efficiency control instruction set based on the degradation trend prediction results and the optimization strategy, thereby realizing closed-loop optimization control of the drive motor's energy efficiency.

9. A computer-readable storage medium, characterized in that: The device stores instructions that, when executed on a computer, cause the computer to perform a new energy vehicle motor efficiency control method as described in any one of claims 1 to 7.

Images