RISC-V architecture-based new energy electric vehicle energy storage real-time control method and device

Abstract

The invention relates to the technical field of new energy vehicles, and provides a new energy electric vehicle energy storage real-time control method and device based on an RISC-V framework. The method comprises the following steps: acquiring driving parameter information of the new energy electric vehicle in real time; the driving parameter information comprises speed and acceleration; judging whether the new energy electric vehicle is in a deceleration state or not based on the acceleration; if yes, acquiring battery parameter information and environment temperature, and inputting the battery parameter information and the environment temperature into a preset charging current threshold prediction model to obtain a charging current threshold of the battery; wherein the battery is used for supplying power to the new energy electric vehicle; determining a target reverse rotation speed of the motor based on the charging current threshold; the motor is arranged on the new energy electric vehicle; and controlling the motor to rotate reversely based on the target reverse rotation speed. According to the method, the safety of the battery can be ensured while maximum energy recovery is realized in the kinetic energy recovery process.

Description

Technical Field

[0001] The present application relates to the field of new energy vehicle technology, and in particular to a method and device for real-time control of energy storage in new energy electric vehicles based on a RISC-V architecture. Background Art

[0002] As the global energy crisis and environmental pollution become increasingly serious, new energy vehicles have received widespread attention and developed rapidly due to their environmental protection and high efficiency. In new energy vehicles, batteries are the main energy storage device, and their performance directly affects the vehicle's endurance and safety. In order to improve the energy efficiency of vehicles, kinetic energy recovery technology is widely used in new energy vehicles.

[0003] Kinetic energy recovery technology converts the vehicle's kinetic energy into electrical energy and stores it in the battery when the vehicle decelerates, which can not only extend the vehicle's range but also reduce energy waste. However, in practical applications, the kinetic energy recovery process faces the problem of how to maximize energy recovery while ensuring battery safety. Summary of the invention

[0004] The present application provides a method and device for real-time control of energy storage of new energy electric vehicles based on RISC-V architecture to solve the problems raised by the above background technology.

[0005] In a first aspect, the present application provides a real-time control method for energy storage of a new energy electric vehicle based on a RISC-V architecture, which is used for a RISC-V processor on a new energy electric vehicle, and the method comprises:

[0006] Acquire driving parameter information of the new energy electric vehicle in real time; the driving parameter information includes speed and acceleration;

[0007] Determining whether the new energy electric vehicle is in a deceleration state based on the acceleration;

[0008] If yes, obtain battery parameter information and ambient temperature, and input the battery parameter information and the ambient temperature into a preset charging current threshold prediction model to obtain the charging current threshold of the battery; wherein the battery is used to power the new energy electric vehicle;

[0009] Determining a target reverse speed of the motor based on the charging current threshold; the motor is provided in the new energy electric vehicle;

[0010] The reverse rotation of the electric motor is controlled based on the target reverse rotation speed.

[0011] In a possible implementation, judging whether the new energy electric vehicle is in a deceleration state based on the acceleration includes:

[0012] Determine whether the acceleration is less than 0;

[0013] If the acceleration is less than 0, it is determined that the new energy electric vehicle is in a deceleration state.

[0014] In a possible implementation, determining the target reverse rotation speed of the motor based on the charging current threshold includes:

[0015] pass Obtaining the initial reverse speed of the motor; wherein, is the initial reversal speed of the motor, For the speed, The new energy electric vehicle The gear ratio corresponding to each wheel is The new energy electric vehicle The radius of the wheel is Representatives of the new energy electric vehicles include wheels;

[0016] pass Obtaining the charging current value corresponding to the battery at the initial reversal speed; wherein, is the charging current, is the voltage conversion coefficient corresponding to the motor, is the current voltage of the battery, is the internal resistance of the battery;

[0017] comparing the charging current value with the charging current threshold;

[0018] If the charging current value is not greater than the charging current threshold, determining the initial reversal speed as the target reversal speed;

[0019] If the charging current value is greater than the charging current threshold, Determine the target reversal speed, wherein, is the target reversal speed, is the charging current threshold.

[0020] In one possible implementation, the training method of the charging current threshold prediction model includes:

[0021] Acquire a training data set; the training data set includes a matching relationship between multiple input parameter information and output parameter information, the input parameter information is battery parameter information and ambient temperature, and the output parameter information is a charging current threshold;

[0022] Dividing the training data set into a training set, a validation set and a calibration set;

[0023] For each matching relationship in the training set, the input parameter information of the matching relationship is used as the input of the preset neural network, and the output parameter information of the matching relationship is used as the output of the preset neural network to train the preset neural network to obtain an initial charging current threshold prediction model;

[0024] Determining a prediction accuracy of the initial charging current threshold prediction model based on the validation set, and judging whether the prediction accuracy is greater than a preset prediction accuracy;

[0025] If not, the model parameters of the initial charging current threshold prediction model are optimized based on the preset gradient descent algorithm and the correction set until the prediction accuracy of the initial charging current threshold prediction model is greater than the preset prediction accuracy, thereby obtaining the charging current threshold prediction model.

[0026] In a possible implementation, determining the prediction accuracy of the initial charging current threshold prediction model based on the validation set includes:

[0027] For each matching relationship in the verification set, inputting the input parameter information corresponding to the matching relationship into the initial charging current threshold prediction model to obtain a charging current threshold prediction value, and obtaining an absolute value of a difference between the charging current threshold prediction value and the charging current threshold corresponding to the matching relationship, and determining that the matching relationship is a target matching relationship when the absolute value is less than a preset absolute value;

[0028] The ratio between the number of the target matching relationships and the total number of matching relationships in the validation set is taken as the prediction accuracy.

[0029] In a possible implementation, the optimizing the model parameters of the initial charging current threshold prediction model based on the preset gradient descent algorithm and the correction set includes:

[0030] For each matching relationship in the correction set, the input parameter information corresponding to the matching relationship is input into the initial charging current threshold prediction model to obtain a charging current threshold prediction value, and a predicted loss value is determined based on the charging current threshold prediction value and the charging current threshold corresponding to the matching relationship, and the predicted loss value is back-propagated in the initial charging current threshold prediction model to update the model parameters of the initial charging current threshold prediction model.

[0031] In one possible implementation, the method further includes:

[0032] Binding the driving parameter information, the battery parameter information, the ambient temperature and the target reverse speed to obtain a binding result;

[0033] Generate an encrypted password based on the identification image of the new energy electric vehicle;

[0034] Encrypting the binding result based on the encryption password to obtain an encrypted binding result;

[0035] The encrypted binding result is stored in a database.

[0036] In a possible implementation, the step of generating an encrypted password based on the identification image of the new energy electric vehicle includes:

[0037] For each pixel of the identification image, obtaining RGB space information corresponding to the pixel; the RGB space information includes a red value, a blue value and a green value;

[0038] Sequentially extract the maximum red value, the maximum blue value, the maximum green value, the minimum red value, the minimum blue value and the minimum green value from all the RGB space information to obtain a color value sequence;

[0039] Subtracting the minimum red value from the maximum red value to obtain a first color difference, and subtracting the minimum blue value from the maximum blue value to obtain a second color difference;

[0040] Obtaining a coding algorithm matrix; the coding algorithm matrix includes multiple rows and columns, and each position of the coding algorithm matrix is ​​provided with a coding algorithm;

[0041] Determine a target coding algorithm in the coding algorithm matrix; the number corresponding to the row where the target coding algorithm is located is consistent with the number corresponding to the first color difference value, and the number corresponding to the column where the target coding algorithm is located is consistent with the number corresponding to the second color difference value;

[0042] The color value sequence is encoded based on the target encoding algorithm to obtain the encrypted password.

[0043] In a second aspect, the present application provides a new energy electric vehicle energy storage real-time control device based on the RISC-V architecture, which is used for a RISC-V processor on a new energy electric vehicle, and the device includes:

[0044] An acquisition module is used to acquire the driving parameter information of the new energy electric vehicle in real time; the driving parameter information includes speed and acceleration;

[0045] A judgment module, used for judging whether the new energy electric vehicle is in a deceleration state based on the acceleration;

[0046] An input module, used for obtaining battery parameter information and ambient temperature when the new energy electric vehicle is in a deceleration state, and inputting the battery parameter information and the ambient temperature into a preset charging current threshold prediction model to obtain the charging current threshold of the battery; wherein the battery is used to power the new energy electric vehicle;

[0047] A determination module, configured to determine a target reverse rotation speed of the motor based on the charging current threshold; the motor is provided in the new energy electric vehicle;

[0048] A control module is used to control the reverse rotation of the motor based on the target reverse rotation speed.

[0049] The present application provides a real-time control method and device for energy storage of a new energy electric vehicle based on a RISC-V architecture, which is used for a RISC-V processor on a new energy electric vehicle. The method includes: obtaining driving parameter information of the new energy electric vehicle in real time; the driving parameter information includes speed and acceleration; judging whether the new energy electric vehicle is in a deceleration state based on the acceleration; if so, obtaining battery parameter information and ambient temperature, and inputting the battery parameter information and the ambient temperature into a preset charging current threshold prediction model to obtain a charging current threshold of the battery; wherein the battery is used to power the new energy electric vehicle; determining a target reversal speed of the motor based on the charging current threshold; the motor is provided in the new energy electric vehicle; and controlling the reversal of the motor based on the target reversal speed. This method, on the one hand, uses a RISC-V processor as the core control unit, which has efficient instruction execution capabilities and low-latency response characteristics. It can obtain and process the driving parameters of new energy electric vehicles, battery parameter information and ambient temperature in real time, ensuring that the system can quickly judge and start the kinetic energy recovery process at the moment of vehicle deceleration, thereby improving the response speed and real-time performance of the control system. On the other hand, based on the predicted charging current threshold, the target reverse speed of the motor is accurately determined, and the motor is reversed through the RISC-V processor to achieve efficient conversion of kinetic energy into electrical energy. This method maximizes the amount of kinetic energy recovery while ensuring safe charging of the battery, significantly improves the overall energy utilization efficiency, and helps to extend the vehicle's range. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0051] Figure 1 A flow chart of a real-time control method for energy storage of a new energy electric vehicle based on the RISC-V architecture provided in an embodiment of the present application;

[0052] Figure 2 A schematic block diagram of the structure of a new energy electric vehicle energy storage real-time control device based on the RISC-V architecture provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0055] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0056] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0057] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0058] See also Figure 1 , Figure 1 A flow chart of a real-time control method for energy storage of a new energy electric vehicle based on the RISC-V architecture provided in an embodiment of the present application, wherein the method is used for a RISC-V processor on a new energy electric vehicle, such as Figure 1 As shown, the real-time control method for energy storage of new energy electric vehicles based on RISC-V architecture provided in an embodiment of the present application includes steps S1 to S5.

[0059] Step S1, obtaining driving parameter information of the new energy electric vehicle in real time; the driving parameter information includes speed and acceleration.

[0060] Specifically, the speed is obtained by a speed sensor provided in the new energy electric vehicle, and the acceleration is obtained by an acceleration sensor provided in the new energy electric vehicle.

[0061] Step S2: determining whether the new energy electric vehicle is in a deceleration state based on the acceleration.

[0062] Specifically, step S2 includes the following steps:

[0063] Determine whether the acceleration is less than 0;

[0064] If the acceleration is less than 0, it is determined that the new energy electric vehicle is in a deceleration state.

[0065] Step S3: If yes, obtain battery parameter information and ambient temperature, and input the battery parameter information and the ambient temperature into a preset charging current threshold prediction model to obtain the charging current threshold of the battery; wherein the battery is used to power the new energy electric vehicle.

[0066] Specifically, the battery parameter information is acquired through various sensors provided in the battery, wherein the battery parameter information includes the remaining charge of the battery, the battery temperature, and the remaining life of the battery, and the charging current threshold is the maximum current value to ensure the safety of the battery.

[0067] Step S4, determining a target reverse speed of the motor based on the charging current threshold; the motor is provided in the new energy electric vehicle.

[0068] Specifically, step S4 includes the following steps:

[0069] pass Obtaining the initial reverse speed of the motor; wherein, is the initial reversal speed of the motor, For the speed, The new energy electric vehicle The gear ratio corresponding to each wheel is The new energy electric vehicle The radius of the wheel is Representatives of the new energy electric vehicles include wheels; The transmission ratio can be obtained by consulting the technical specifications of the new energy electric vehicle, and in the process of designing the new energy electric vehicle, the transmission ratio corresponding to each wheel of the new energy electric vehicle can be obtained through experimental testing;

[0070] pass Obtaining the charging current value corresponding to the battery at the initial reversal speed; wherein, is the charging current, is the voltage conversion coefficient corresponding to the motor, is the current voltage of the battery, is the internal resistance of the battery; in this embodiment, a voltage conversion coefficient is designed to be The electric motor is provided in the new energy electric vehicle, and the technical specifications of the electric motor are obtained by referring to the technical specifications of the electric motor. ;

[0071] comparing the charging current value with the charging current threshold;

[0072] If the charging current value is not greater than the charging current threshold, determining the initial reversal speed as the target reversal speed;

[0073] If the charging current value is greater than the charging current threshold, Determine the target reversal speed, wherein, is the target reversal speed, is the charging current threshold.

[0074] It can be understood that the method of step S4 can achieve maximum energy recovery during the kinetic energy recovery process while ensuring the safety of the battery.

[0075] Step S5: Control the motor to reverse based on the target reverse rotation speed.

[0076] The method provided in this embodiment, on the one hand, adopts a RISC-V processor as a core control unit, has efficient instruction execution capability and low-latency response characteristics, can obtain and process the driving parameters of the new energy electric vehicle as well as battery parameter information and ambient temperature in real time, ensures that at the moment of vehicle deceleration, the system can quickly judge and start the kinetic energy recovery process, and improves the response speed and real-time performance of the control system. On the other hand, based on the predicted charging current threshold, the target reverse speed of the motor is accurately determined, and the motor is reversed through the RISC-V processor to achieve efficient conversion of kinetic energy into electrical energy. This method maximizes the amount of kinetic energy recovery while ensuring safe charging of the battery, significantly improves the overall energy utilization efficiency, and helps to extend the vehicle's cruising range.

[0077] In some embodiments, the training method of the charging current threshold prediction model comprises the following steps:

[0078] Acquire a training data set; the training data set includes a plurality of matching relationships between input parameter information and output parameter information, the input parameter information is battery parameter information and ambient temperature, and the output parameter information is a charging current threshold; it should be noted that, for each matching relationship, the charging current threshold corresponding to the matching relationship is a maximum safe current obtained by an experimental method so that the battery is in a charging environment corresponding to the input parameter information corresponding to the matching relationship;

[0079] Dividing the training data set into a training set, a validation set and a calibration set;

[0080] For each matching relationship in the training set, the input parameter information of the matching relationship is used as the input of the preset neural network, and the output parameter information of the matching relationship is used as the output of the preset neural network to train the preset neural network to obtain an initial charging current threshold prediction model;

[0081] Determining a prediction accuracy of the initial charging current threshold prediction model based on the validation set, and judging whether the prediction accuracy is greater than a preset prediction accuracy;

[0082] If not, the model parameters of the initial charging current threshold prediction model are optimized based on the preset gradient descent algorithm and the correction set until the prediction accuracy of the initial charging current threshold prediction model is greater than the preset prediction accuracy, thereby obtaining the charging current threshold prediction model.

[0083] Wherein, determining the prediction accuracy of the initial charging current threshold prediction model based on the verification set comprises the following steps:

[0084] For each matching relationship in the verification set, inputting the input parameter information corresponding to the matching relationship into the initial charging current threshold prediction model to obtain a charging current threshold prediction value, and obtaining an absolute value of a difference between the charging current threshold prediction value and the charging current threshold corresponding to the matching relationship, and determining that the matching relationship is a target matching relationship when the absolute value is less than a preset absolute value;

[0085] The ratio between the number of the target matching relationships and the total number of matching relationships in the validation set is taken as the prediction accuracy.

[0086] The optimization of the model parameters of the initial charging current threshold prediction model based on the preset gradient descent algorithm and the correction set comprises the following steps:

[0087] For each matching relationship in the correction set, the input parameter information corresponding to the matching relationship is input into the initial charging current threshold prediction model to obtain a charging current threshold prediction value, and a predicted loss value is determined based on the charging current threshold prediction value and the charging current threshold corresponding to the matching relationship, and the predicted loss value is back-propagated in the initial charging current threshold prediction model to update the model parameters of the initial charging current threshold prediction model.

[0088] In some embodiments, the method further comprises the following steps:

[0089] Binding the driving parameter information, the battery parameter information, the ambient temperature and the target reverse speed to obtain a binding result;

[0090] Generate an encrypted password based on the identification image of the new energy electric vehicle;

[0091] Encrypting the binding result based on the encryption password to obtain an encrypted binding result;

[0092] The encrypted binding result is stored in a database.

[0093] The step of generating an encrypted password based on the identification image of the new energy electric vehicle comprises the following steps:

[0094] For each pixel of the identification image, obtaining RGB space information corresponding to the pixel; the RGB space information includes a red value, a blue value and a green value;

[0095] Sequentially extract the maximum red value, the maximum blue value, the maximum green value, the minimum red value, the minimum blue value and the minimum green value from all the RGB space information to obtain a color value sequence;

[0096] Subtracting the minimum red value from the maximum red value to obtain a first color difference, and subtracting the minimum blue value from the maximum blue value to obtain a second color difference;

[0097] Obtaining a coding algorithm matrix; the coding algorithm matrix includes multiple rows and columns, and each position of the coding algorithm matrix is ​​provided with a coding algorithm;

[0098] Determine a target coding algorithm in the coding algorithm matrix; the number corresponding to the row where the target coding algorithm is located is consistent with the number corresponding to the first color difference value, and the number corresponding to the column where the target coding algorithm is located is consistent with the number corresponding to the second color difference value;

[0099] The color value sequence is encoded based on the target encoding algorithm to obtain the encrypted password.

[0100] The method provided in this embodiment, on the one hand, realizes the structured storage of the driving parameter information, the battery parameter information, the ambient temperature and the target reverse speed, providing a reliable data basis for further improving the intelligence of the real-time control method of energy storage of new energy electric vehicles in the future; on the other hand, by encrypting the binding result, it can prevent unauthorized personnel from tampering with the binding result, thereby ensuring the security of the binding result; on the other hand, by generating an encrypted password through the identification image of the new energy electric vehicle, the difficulty of cracking the encrypted password is increased, thereby further improving the security of the binding result.

[0101] See also Figure 2 , Figure 2 The schematic block diagram of the structure of the real-time control device 100 for energy storage of a new energy electric vehicle based on the RISC-V architecture provided in the embodiment of the present application, the real-time control device 100 for energy storage of a new energy electric vehicle based on the RISC-V architecture is used for the RISC-V processor on the new energy electric vehicle, such as Figure 2 As shown, the new energy electric vehicle energy storage real-time control device 100 based on the RISC-V architecture provided in the embodiment of the present application includes:

[0102] The acquisition module 110 is used to acquire the driving parameter information of the new energy electric vehicle in real time; the driving parameter information includes speed and acceleration.

[0103] The judgment module 120 is used to judge whether the new energy electric vehicle is in a deceleration state based on the acceleration.

[0104] The input module 130 is used to obtain battery parameter information and ambient temperature if the new energy electric vehicle is in a deceleration state, and input the battery parameter information and the ambient temperature into a preset charging current threshold prediction model to obtain the charging current threshold of the battery; wherein the battery is used to power the new energy electric vehicle.

[0105] The determination module 140 is used to determine the target reverse speed of the motor based on the charging current threshold; the motor is provided in the new energy electric vehicle.

[0106] The control module 150 is configured to control the reverse rotation of the motor based on the target reverse rotation speed.

[0107] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and conciseness of description, the specific working process of the above-described device and each module can refer to the process in the aforementioned embodiment of the real-time control method for energy storage of new energy electric vehicles based on RISC-V architecture, and will not be repeated here.

[0108] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A real-time control method for energy storage of new energy electric vehicles based on RISC-V architecture, characterized in that: A RISC-V processor for a new energy electric vehicle, the method comprising: Acquire driving parameter information of the new energy electric vehicle in real time; the driving parameter information includes speed and acceleration; Determining whether the new energy electric vehicle is in a deceleration state based on the acceleration; If yes, obtain battery parameter information and ambient temperature, and input the battery parameter information and the ambient temperature into a preset charging current threshold prediction model to obtain the charging current threshold of the battery; wherein the battery is used to power the new energy electric vehicle; Determining a target reverse speed of the motor based on the charging current threshold; the motor is provided in the new energy electric vehicle; The reverse rotation of the electric motor is controlled based on the target reverse rotation speed.

2. The real-time control method for energy storage of new energy electric vehicles based on RISC-V architecture according to claim 1 is characterized in that: The determining whether the new energy electric vehicle is in a deceleration state based on the acceleration includes: Determine whether the acceleration is less than 0; If the acceleration is less than 0, it is determined that the new energy electric vehicle is in a deceleration state.

3. The real-time control method for energy storage of new energy electric vehicles based on RISC-V architecture according to claim 1 is characterized in that: The step of determining the target reverse rotation speed of the motor based on the charging current threshold comprises: Obtaining the initial reverse speed of the motor; wherein, is the initial reversal speed of the motor, For the speed, The new energy electric vehicle The gear ratio corresponding to each wheel is The new energy electric vehicle The radius of the wheel is Representatives of the new energy electric vehicles include wheels; pass Obtaining the charging current value corresponding to the battery at the initial reversal speed; wherein, is the charging current, is the voltage conversion coefficient corresponding to the motor, is the current voltage of the battery, is the internal resistance value of the battery; comparing the charging current value with the charging current threshold; If the charging current value is not greater than the charging current threshold, determining the initial reversal speed as the target reversal speed; If the charging current value is greater than the charging current threshold, Determine the target reversal speed, wherein, is the target reversal speed, is the charging current threshold.

4. The real-time control method for energy storage of new energy electric vehicles based on RISC-V architecture according to claim 1 is characterized in that: The training method of the charging current threshold prediction model comprises: Acquire a training data set; the training data set includes a matching relationship between multiple input parameter information and output parameter information, the input parameter information is battery parameter information and ambient temperature, and the output parameter information is a charging current threshold; Dividing the training data set into a training set, a validation set and a calibration set; For each matching relationship in the training set, the input parameter information of the matching relationship is used as the input of the preset neural network, and the output parameter information of the matching relationship is used as the output of the preset neural network to train the preset neural network to obtain an initial charging current threshold prediction model; Determining a prediction accuracy of the initial charging current threshold prediction model based on the validation set, and judging whether the prediction accuracy is greater than a preset prediction accuracy; If not, the model parameters of the initial charging current threshold prediction model are optimized based on the preset gradient descent algorithm and the correction set until the prediction accuracy of the initial charging current threshold prediction model is greater than the preset prediction accuracy, thereby obtaining the charging current threshold prediction model.

5. The real-time control method for energy storage of new energy electric vehicles based on RISC-V architecture according to claim 4 is characterized in that: The determining the prediction accuracy of the initial charging current threshold prediction model based on the verification set includes: For each matching relationship in the verification set, inputting the input parameter information corresponding to the matching relationship into the initial charging current threshold prediction model to obtain a charging current threshold prediction value, and obtaining an absolute value of a difference between the charging current threshold prediction value and the charging current threshold corresponding to the matching relationship, and determining that the matching relationship is a target matching relationship when the absolute value is less than a preset absolute value; The ratio between the number of the target matching relationships and the total number of matching relationships in the validation set is taken as the prediction accuracy.

6. The real-time control method for energy storage of new energy electric vehicles based on RISC-V architecture according to claim 4 is characterized in that: The optimizing the model parameters of the initial charging current threshold prediction model based on the preset gradient descent algorithm and the correction set includes: For each matching relationship in the correction set, the input parameter information corresponding to the matching relationship is input into the initial charging current threshold prediction model to obtain a charging current threshold prediction value, and a predicted loss value is determined based on the charging current threshold prediction value and the charging current threshold corresponding to the matching relationship, and the predicted loss value is back-propagated in the initial charging current threshold prediction model to update the model parameters of the initial charging current threshold prediction model.

7. The real-time control method for energy storage of new energy electric vehicles based on RISC-V architecture according to claim 1 is characterized in that: The method further comprises: Binding the driving parameter information, the battery parameter information, the ambient temperature and the target reverse speed to obtain a binding result; generating an encrypted password based on the identification image of the new energy electric vehicle; Encrypting the binding result based on the encryption password to obtain an encrypted binding result; The encrypted binding result is stored in a database.

8. The real-time control method for energy storage of new energy electric vehicles based on RISC-V architecture according to claim 1 is characterized in that: The step of generating an encrypted password based on the identification image of the new energy electric vehicle comprises: For each pixel of the identification image, obtaining RGB space information corresponding to the pixel; the RGB space information includes a red value, a blue value and a green value; Sequentially extract the maximum red value, the maximum blue value, the maximum green value, the minimum red value, the minimum blue value and the minimum green value from all the RGB space information to obtain a color value sequence; Subtracting the minimum red value from the maximum red value to obtain a first color difference, and subtracting the minimum blue value from the maximum blue value to obtain a second color difference; Obtaining a coding algorithm matrix; the coding algorithm matrix includes multiple rows and columns, and each position of the coding algorithm matrix is ​​provided with a coding algorithm; Determine a target coding algorithm in the coding algorithm matrix; the number corresponding to the row where the target coding algorithm is located is consistent with the number corresponding to the first color difference value, and the number corresponding to the column where the target coding algorithm is located is consistent with the number corresponding to the second color difference value; The color value sequence is encoded based on the target encoding algorithm to obtain the encrypted password.

9. A new energy electric vehicle energy storage real-time control device based on RISC-V architecture, characterized in that: A RISC-V processor for a new energy electric vehicle, the device comprising: An acquisition module is used to acquire the driving parameter information of the new energy electric vehicle in real time; the driving parameter information includes speed and acceleration; A judgment module, used for judging whether the new energy electric vehicle is in a deceleration state based on the acceleration; An input module, used for obtaining battery parameter information and ambient temperature when the new energy electric vehicle is in a deceleration state, and inputting the battery parameter information and the ambient temperature into a preset charging current threshold prediction model to obtain the charging current threshold of the battery; wherein the battery is used to power the new energy electric vehicle; A determination module, configured to determine a target reverse rotation speed of the motor based on the charging current threshold; the motor is provided in the new energy electric vehicle; A control module is used to control the reverse rotation of the motor based on the target reverse rotation speed.

Images