Battery physical examination and vehicle-network interaction control method based on SSA and Autoformer

Abstract

The application discloses a battery physical examination and vehicle-network interaction control method based on SSA and Autoformer, and relates to the technical field of power system regulation and control. The method collects charging data of electric vehicles in real time through a high-precision battery charging information acquisition device and transmits the data to an upper computer for analysis. The SSA is used to optimize the BHI to accurately evaluate the battery health status and generate health warning information. A correlation model of the battery health status and vehicle-network interaction behavior is constructed based on the BHI to optimize the interaction strategy between electric vehicles and the power grid. The Autoformer model is used to process historical charging data to predict the charging and discharging depth adjustment coefficient and the interaction time shortening coefficient in the vehicle-network interaction process. The battery maintenance strategy is generated according to the BHI to dynamically adjust the charging and discharging power and the interaction time interval. The application significantly improves the accuracy of battery health evaluation and the intelligent level of vehicle-network interaction.

Description

Technical Field

[0001] This invention relates to the field of power system control technology, and in particular to a battery health check and vehicle-to-grid interaction control method based on SSA and Autoformer. Background Technology

[0002] With the increasing popularity of electric vehicles, battery health monitoring and vehicle-to-grid (V2G) control technologies are playing an increasingly important role in the coordinated development of electric vehicles and smart grids. Effective monitoring of battery state of health (SOH) can not only extend battery life and improve safety, but also reduce grid risks and promote the reuse of batteries by optimizing V2G scheduling, ultimately maximizing the economic, reliability, and environmental benefits of battery technology and energy systems.

[0003] However, existing technologies have significant shortcomings in areas such as charging information collection, battery health assessment, and vehicle-to-grid (V2G) interaction control. First, the frequency of charging information collection is low, lacking sufficient granularity to capture instantaneous changes in current and voltage during battery charging. Furthermore, data incompleteness and standardization issues lead to incomplete monitoring of charging behavior and battery status. Second, existing battery health assessment methods primarily rely on battery capacity degradation curves, ignoring the influence of environmental factors and usage habits, resulting in insufficient accuracy and a lack of intelligent optimization algorithms. Finally, existing V2G interaction control strategies fail to adequately consider battery health status, potentially leading to over-discharge of unhealthy batteries, shortening battery life, and increasing safety hazards to the power grid. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention proposes a battery health assessment and vehicle-to-grid (V2G) interaction control method based on SSA and Autoformer. This method improves the accuracy and frequency of data collection by enhancing the precision and completeness of electric vehicle charging information; optimizes the Battery Health Index (BHI) assessment index using SSA to accurately evaluate battery health; constructs a BHI-based V2G safety interaction model to optimize V2G power scheduling and ensure a balance between battery health and grid scheduling; and proposes a BHI-based battery maintenance and V2G control strategy to extend battery life and improve V2G efficiency.

[0005] To achieve the above objectives, the present invention employs the following technical solution:

[0006] A battery health check and vehicle-to-grid interaction control method based on SSA and Autoformer includes the following steps:

[0007] Step 1: Collect battery charging information through the electric vehicle charging information collection device, and transmit the battery charging information to the host computer via the WIFI module;

[0008] Step 2: Construct the Battery Health Status Index (BHI) and use the tunic group algorithm to optimize the weights of the indicators to assess the battery health status. Calculate the battery health status index based on the predetermined health assessment indicators and generate health warning information.

[0009] Step 3: Based on the Battery Health Index (BHI), establish a correlation model between battery health status and vehicle-grid interaction behavior, analyze the relationship between battery charge / discharge depth, interaction time interval, and interaction depth, and determine the interaction strategy between electric vehicles and the power grid.

[0010] Step 4: Use the Autoformer model to process historical charging data and predict the charging and discharging depth adjustment coefficient and the interaction time reduction coefficient during the vehicle-to-grid interaction process;

[0011] Step 5: Generate a battery maintenance strategy based on the Battery Health Index (BHI) and control the electric vehicle's interaction with the power grid, including adjusting charging and discharging power and setting interaction time intervals.

[0012] In one embodiment, the electric vehicle charging information collection device is integrated inside the charging pile, comprising:

[0013] The CAN transceiver terminal is used to obtain electric vehicle charging information in CAN message form through the CAN communication interface S+ and S- of the charging gun;

[0014] The main control chip receives and parses the messages via a CAN transceiver, generates formatted data packets, and communicates with the WIFI module via an SCI serial port.

[0015] The power supply motherboard is used to power the CAN transceiver, main control chip and WIFI module;

[0016] The expression for the battery charging information is:

[0017] X C =[X1,X2,X3,X4,X5,X6,X7,X8,X9,X 10 ]

[0018] In the formula: X c The collected battery charging information includes: X1 (battery type), X2 (battery capacity), X3 (battery rated voltage), X4 (measured charging voltage), X5 (measured charging current), X6 (highest single-cell voltage), X7 (current state of charge, SOC), X8 (estimated remaining charging time), and X9 (cumulative charging time). 10 This is the highest temperature of the battery.

[0019] In one embodiment, the Battery Health Index (BHI) is calculated using the following formula:

[0020] BHI=ω1×SOC diff +ω2×V diff +ω3×T norm +ω4×C eff +ω5×R int ;

[0021] In the formula, ω1, ω2, ω3, ω4, and ω5 are the index weights; SOC diff V is the rate of change of SOC; diff For the voltage difference of individual cells; T norm C is a normalized temperature index. eff R is the capacity decay coefficient; int The rate of change of the battery's internal resistance;

[0022] in:

[0023]

[0024]

[0025] In the formula, X7(t) is the current state of charge (SOC) at time t, and X7(t-1) is the current state of charge (SOC) at time t-1; T ref The reference temperature under normal operating conditions is T. max Maximum permissible temperature; C est The estimated current maximum available capacity is calculated using cumulative charge and discharge data;

[0026] The remaining battery life (RUL) is calculated based on the Battery Health Index (BHI), using the following expression:

[0027]

[0028] In the formula, SOH = BHI·100%, and the average daily discharge is calculated from historical data.

[0029] In one embodiment, the method for optimizing the index weights using the tunic swarm algorithm includes:

[0030] Initialize population parameters: Set population size N and number of iterations T. max Randomly initialize N sets of weights, expression:

[0031] W i =(ω i1 ,ω i2 ,ω i3 ,ω i4 ,ω i5 ), i = 1, 2, 3, 4, 5;

[0032] Define the fitness function F(W) expression:

[0033]

[0034] Update the leader weight expression:

[0035] W new =W best +c1×r1×(W best -W);

[0036] Update follower weight expression:

[0037]

[0038] After weight normalization, the expression is satisfied:

[0039] Repeat the steps until T is reached. max Or convergence condition;

[0040] Where: ω i1 ,ω i2 ,ω i3 ,ω i4 ,ω i5 The weighting coefficients are used to balance the importance of each indicator; F(W) is the fitness function; and BHI is the weighting coefficient. actual,t The true BHI value calculated from historical data, BHI pred,t Let W be the BHI value calculated based on the current weights, and W be the set of weight combinations in the current population. new W represents the latest weight combination in the current population. best W represents the optimal weight combination in the current population. i For the i-th weight combination, r1 is a random number between [0,1], c1 is the exploration step size coefficient, controlling the convergence speed, c2 is the adjustment factor, controlling the follower step size, r2 is a random number between [0,1], and ω k This is the k-th weight coefficient.

[0041] In one embodiment, the steps for establishing the correlation model between battery health status and vehicle-to-grid interaction behavior are as follows:

[0042] Remaining charge / discharge cycles T s The expression is:

[0043] T s =T init ×BHI-T used ;

[0044] Wherein: T initT represents the initial rated number of cycles for the battery. used This refers to the number of charge / discharge cycles already used.

[0045] The expression for depth of charge / discharge is:

[0046]

[0047] Where: P c For charging depth, P d For discharge depth, P c,min For the minimum depth of battery charge (e.g., 10%), P d,min For the lowest depth of discharge of the battery (e.g., 10%), α c ,α d This is the adjustment coefficient for the depth of charge and discharge, which is usually set based on experience or experimental data;

[0048] Interaction time interval T between vehicles and the internet c expression:

[0049] T c =T c,max -β×(1-BHI);

[0050] Wherein: T c,max β represents the maximum vehicle-to-network interaction time interval (minutes), and β is the vehicle-to-network interaction time reduction coefficient (empirical parameter).

[0051] Charging and discharging power expression:

[0052]

[0053] Where: P max This represents the maximum charging and discharging power.

[0054] In one embodiment, the step of processing historical charging data using the Autoformer model specifically includes:

[0055] Y t =F(X) t )+ε t ;

[0056] Where: Y t For the output variable of future vehicle-to-everything (V2X) interaction coefficients, ε t Let F represent the prediction error, and let X be the prediction function determined by the Autoformer model. t The input variable is the historical vehicle-to-vehicle interaction coefficient;

[0057] Y t =(α c,t+1 ,α d,t+1 ,β t+1 )

[0058] Where: α c,t+1 For the predicted depth of charge adjustment coefficient, α d,t+1 For the predicted depth of discharge adjustment coefficient, β t+1 The coefficient for reducing the predicted vehicle-to-network interaction time;

[0059] X t = (BHI) t ,P c,t ,P d,t ,T c,t ,T bat,t ,P EV,t ,α c,t ,α d,t ,β t );

[0060] Among them: BHI t Battery health status index, P c,t For the current charging depth, P d,t For the current discharge depth, T c,t For the current vehicle-to-network interaction time interval, T bat,t For the current battery temperature, P EV,t For current electric vehicle charging and discharging power, α c,t The current charging depth adjustment coefficient, α d,t The current discharge depth adjustment coefficient, β t This is a coefficient that shortens the current vehicle-to-network interaction time.

[0061] In one embodiment, the specific steps for predicting the charge / discharge depth adjustment coefficient and the interaction time reduction coefficient during the vehicle-to-grid interaction process include:

[0062] The long-term and short-term features of the input data are extracted through the autocorrelation mechanism and recursive decomposition module of the Autoformer model.

[0063] The generated prediction output expression is:

[0064] Y t =M Autoformer (X t );

[0065] Where: Y t For future vehicle-to-everything (V2X) interaction coefficient, X t For historical vehicle-to-everything (V2X) interaction coefficients;

[0066] The expression for the analytical prediction result is:

[0067]

[0068] Where: α c,t+1 For the predicted depth of charge adjustment coefficient, αd,t+1 For the predicted depth of discharge adjustment coefficient, β t+1 For the predicted vehicle-to-network interaction time reduction coefficient, M Autoformer Indicates the Autoformer prediction model, f Autoformer g Autoformer h Autoformer To be more specific about the Autoformer prediction model;

[0069] The predicted adjustment coefficient α c,t+1 α d,t+1 β t+1 Substituting into the following formula, the expression for dynamically adjusting the charge / discharge depth and interaction time interval for the next cycle is:

[0070]

[0071] Among them: BHI t Battery health status index, P c,t+1 For the predicted depth of charge, P d,t+1 For the predicted discharge depth, T c,t+1 For the predicted vehicle-to-network interaction time interval, P c,min P d,min It is the minimum depth of charge and discharge, T c,max It is the maximum vehicle-to-network interaction time interval.

[0072] In one embodiment, the battery health index (BHI) is used to generate a battery maintenance strategy, including the following steps:

[0073] Battery maintenance strategies are generated based on the Battery Health Index (BHI). The strategy is categorized according to the BHI value using the following expression:

[0074]

[0075] The corresponding maintenance strategy is as follows:

[0076] When BHI > 0.8, the charging and discharging strategy remains unchanged, allowing high-frequency vehicle-to-grid interaction;

[0077] When 0.5 ≤ BHI ≤ 0.8, limit the depth of charge / discharge to P. c,min and P d,min and reduce the frequency of interaction;

[0078] When BHI≤0.5, only shallow charging and discharging are allowed, and vehicle-to-grid interaction is limited to the lowest frequency.

[0079] In one embodiment, adjusting the vehicle-to-grid interaction control parameters according to BHI includes:

[0080] Interaction time interval T c The expression is:

[0081] T c =T c,max -β×(1-BHI);

[0082] Where: BHI is the battery health status index, T c T represents the interaction time interval, β is the interaction time adjustment coefficient, and the default value range is 10-30 minutes. c,max The maximum interaction time interval is preset.

[0083] The formula for calculating the depth of charge / discharge is as follows:

[0084] P c =α c ×(1-BHI)+P c,min

[0085] P d =α d ×(1-BHI)+P d,min

[0086] Where: P c P d For depth of charge and discharge, α c α d For the charge / discharge depth adjustment coefficient, P c,min P d,min This is the minimum depth of charge / discharge (typically 10%-20%).

[0087] α c and α d According to the BHI classification expression:

[0088]

[0089] Interaction time interval T c The specific adjustments are calculated using the following formula:

[0090]

[0091] Wherein: T max This represents the actual maximum interaction time interval.

[0092] Compared with existing technologies, the beneficial effects of this invention are as follows: By integrating multiple innovative technologies, this invention significantly improves the overall performance of electric vehicle charging and vehicle-to-grid (V2G) interaction systems. First, a Battery Health Index (BHI) is constructed, and the weights of the index are optimized using the tunic swarm algorithm, thereby more accurately assessing battery health, identifying potential faults in advance, and effectively extending battery life. Second, a correlation model between battery health and V2G interaction behavior is established to achieve dynamic matching between battery status and interaction strategies, avoiding damage to the battery from overcharging and discharging, and improving grid stability and efficiency. Furthermore, the Autoformer model is used to process historical charging data, predicting the charge / discharge depth adjustment coefficient and the interaction time reduction coefficient, optimizing charging plans, and reducing waiting time and energy waste. In terms of user experience, accurate battery health assessment and V2G interaction control provide users with more reliable charging services, improving charging efficiency and convenience. Simultaneously, by optimizing V2G interaction strategies and charging prediction capabilities, electric vehicles are more effectively utilized as distributed energy storage resources, balancing grid load and improving energy utilization efficiency. Attached Figure Description

[0093] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0094] in:

[0095] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0096] Figure 2 This is a functional diagram of the electric vehicle charging information collection device in an embodiment of the present invention;

[0097] Figure 3 This is a schematic diagram of the connection of the data acquisition device in an embodiment of the present invention. Detailed Implementation

[0098] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0099] like Figures 1-3As shown, this is an embodiment of the present invention, which provides a battery health check and vehicle-to-grid interaction control method based on SSA and Autoformer, including the following steps:

[0100] I. Electric Vehicle Charging Information Collection

[0101] Step 1: Install the charging information collection device

[0102] A dedicated charging information collection device is installed inside the charging station. This device acts like a "smart box," collecting various information about the electric vehicle's battery in real time. It mainly consists of three parts:

[0103] CAN transceiver terminals: These are the device's "ears." Through the CAN communication interface on the charging gun (similar to a USB interface, but specifically designed for in-vehicle communication), it can "hear" the charging information sent by the electric vehicle. This information is transmitted in a format called CAN messages, similar to emails, but with a more standardized format.

[0104] Main control chip: This is the "brain" of the device. It is responsible for receiving and parsing the messages "heard" by the CAN transceiver terminals. The main control chip is like a smart translator, able to translate the "code-like" messages sent by the electric vehicle into formatted data packets that we can understand.

[0105] WIFI module: This is the device's "mouth." It transmits the data packets translated by the main control chip to our host computer (which can be understood as the computer controlling the entire system) via the wireless WIFI network. This allows us to monitor the charging status of the electric vehicle's battery in real time on our computer.

[0106] Step 2: Collect battery charging information

[0107] When an electric vehicle begins charging, the charging information collection device starts working. It collects the following important battery charging information:

[0108] Battery type (e.g., lithium battery or lead-acid battery)

[0109] Battery capacity (how much electricity the battery can store)

[0110] Battery rated voltage (voltage when the battery is operating normally)

[0111] Charging voltage measurement (voltage during current charging)

[0112] Charging current measurement (current during current charging)

[0113] Highest single-cell voltage (the voltage of the cell with the highest voltage in the battery pack)

[0114] Current state of charge (SOC, representing the current percentage of battery charge remaining)

[0115] Estimate remaining charging time (how long it is estimated to take to fully charge).

[0116] Cumulative charging time (how long the battery has been charging)

[0117] Maximum battery temperature (the highest temperature the battery reaches during charging).

[0118] This information is like giving the battery a comprehensive "physical examination," allowing us to clearly understand the various states of the battery during the charging process.

[0119] Step 3: Optimize index weights using the tunic group algorithm.

[0120] To more accurately assess the health of a battery, we need to find an optimal set of indicator weights. This is where an optimization algorithm called the Slug Group Algorithm (SSA) comes in.

[0121] The SSA algorithm is a swarm intelligence-based optimization algorithm. Like a group of tunicates searching for food together, it finds the optimal solution through continuous trial and error. In this problem, the SSA algorithm helps us find a set of weighted indicators so that the BHI (Battery Health Index) can most accurately reflect the battery's health status.

[0122] Specifically, the SSA algorithm will:

[0123] Initialize population parameters: Just like a group of tunicates randomly distributed in the ocean, we randomly initialize a set of index weights as the initial population.

[0124] Defining a fitness function: Just as we set a goal for salps (such as finding the place with the most food), we define a fitness function to evaluate the quality of each set of metric weights. The fitness function compares the BHI calculation results with the actual health status of the battery and gives a score.

[0125] Updating Leader and Follower Weights: In a tunic colony, there are always some "leaders" guiding the group forward. In the SSA algorithm, we update the positions of the leader (with the optimal metric weight) and followers (with other metric weights) based on the fitness function results, causing the entire population to gradually move towards the optimal solution.

[0126] Through continuous iteration and optimization, the SSA algorithm will eventually find a set of optimal index weights, enabling BHI to most accurately assess the health status of the battery.

[0127] III. Establishment of a Vehicle-to-Network Interaction Behavior Association Model

[0128] Step 1: Analyzing the Relationship Between Battery Charge / Discharge Depth, Interaction Time Interval, and Interaction Depth. After establishing the Battery Health Index (BHI), we can begin building a correlation model between battery health and vehicle-grid interaction behavior. This model acts as a bridge, linking battery health and the interaction behavior between the electric vehicle and the power grid.

[0129] First, we need to analyze the relationship between the battery's depth of charge / discharge, interaction time interval, and interaction depth. Depth of charge / discharge refers to the degree of change in battery charge during charging and discharging; interaction time interval refers to the time interval between interactions between the electric vehicle and the power grid (such as charging or discharging); and interaction depth refers to the amount of electricity exchanged between the electric vehicle and the power grid.

[0130] By analyzing these relationships, we can understand what charging and discharging strategies and interactive behaviors should be adopted for batteries under different health conditions to ensure battery safety and lifespan.

[0131] Step 2: Determine the interaction strategy between electric vehicles and the power grid

[0132] Based on the above analysis, we can determine the interaction strategy between electric vehicles and the power grid. This strategy will consider multiple factors, such as:

[0133] Remaining charge / discharge cycles (how many more charge / discharge cycles the battery can complete)

[0134] Depth of charge / discharge (the amount of electricity charged or discharged in each cycle)

[0135] Vehicle-to-grid interaction time interval (the time interval between interactions between electric vehicles and the power grid)

[0136] Charging and discharging power (the amount of electrical power interacting between the electric vehicle and the power grid)

[0137] By taking these factors into account, we can develop an interactive strategy that can both ensure battery safety and lifespan and maximize the use of grid resources.

[0138] IV. Charge / Discharge and Interaction Prediction

[0139] Step 1: Process historical charging data using the Autoformer model

[0140] To more accurately predict future charge / discharge depths and interaction intervals, we need to employ an advanced prediction model—the Autoformer model. The Autoformer model is a deep learning model specifically designed for processing time series data. It can automatically extract long-term and short-term features from the data, thereby making more accurate predictions.

[0141] First, we collect a large amount of historical charging data, including battery charge / discharge depth, interaction time intervals, and Battery Health Index (BHI). Then, we input this data into the Autoformer model, allowing the model to automatically learn the patterns and regularities in the data.

[0142] Step 2: Predict the charge / discharge depth adjustment coefficient and the interaction time reduction coefficient

[0143] After the Autoformer model learns from historical data, we can use it to predict future charge / discharge depth adjustment coefficients and interaction time reduction coefficients. These coefficients are like "adjustment instructions" we give to future charge / discharge strategies and interaction behaviors; they will be dynamically adjusted based on the battery's health and the grid's needs.

[0144] Specifically, the Autoformer model extracts long-term and short-term features from the input data through autocorrelation mechanisms and recursive decomposition modules, and then generates predictive outputs. These predictive outputs tell us what charge / discharge depth and interaction intervals should be adopted at a certain point in the future to ensure battery safety and grid stability.

[0145] Step 3: Dynamically adjust the depth of charge / discharge and interaction time interval for the next cycle.

[0146] Based on the predictions from the Autoformer model, we can dynamically adjust the depth of charge / discharge and the interaction time interval for the next cycle. If a decline in battery health is predicted, we can appropriately reduce the depth of charge / discharge or extend the interaction time interval to protect battery safety and lifespan. Conversely, if an increase in grid demand is predicted, we can appropriately increase the depth of charge / discharge or shorten the interaction time interval to maximize the utilization of grid resources.

[0147] V. Battery Maintenance and Vehicle-to-Network Interaction Control

[0148] Step 1: Generate a battery maintenance strategy based on the Battery Health Index (BHI).

[0149] Finally, based on the Battery Health Index (BHI), we can generate corresponding battery maintenance strategies. These strategies are categorized according to the BHI value, and different maintenance measures are taken. For example:

[0150] If the BHI value is high (indicating good battery health), we can maintain the normal charge and discharge strategy.

[0151] If the BHI value is low (indicating a decline in battery health), we can limit the depth of charge and discharge and reduce the frequency of interaction to protect the battery's safety and lifespan.

[0152] If the BHI value is very low (indicating a severe decline in battery health), we may only be able to allow the battery to perform shallow charging and discharging, and limit vehicle-to-grid interaction to the lowest possible frequency, or even stop interaction altogether.

[0153] Step 2: Adjust the vehicle-to-everything (V2X) interaction control parameters according to the maintenance strategy.

[0154] Based on the generated maintenance strategy, we can adjust the control parameters for vehicle-to-grid interaction. These parameters include the interaction time interval and the depth of charge / discharge. By adjusting these parameters, we can implement the battery maintenance strategy to ensure battery safety and lifespan.

[0155] Step 3: Control the behavior of electric vehicles participating in grid interaction

[0156] Ultimately, based on the adjusted vehicle-to-grid (V2G) interaction control parameters, we can control the behavior of electric vehicles participating in grid interactions. This includes adjusting charging and discharging power and setting interaction time intervals. Through precise control, we can achieve safe and efficient interaction between electric vehicles and the grid, protecting battery safety and lifespan while maximizing the utilization of grid resources.

[0157] In summary, in the description of this invention, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. Furthermore, the described specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0158] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process. Furthermore, the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functionality involved.

[0159] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in this application, and these should all be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A battery health check and vehicle-to-grid interaction control method based on SSA and Autoformer, characterized in that, The method includes the following steps: Step 1: Collect battery charging information through the electric vehicle charging information collection device, and transmit the battery charging information to the host computer via the WIFI module; Step 2: Construct the Battery Health Status Index (BHI) and use the Saurus Entomophores Algorithm (SSA) to optimize the weights of the indexes in order to assess the battery health status. Calculate the battery health status index based on the predetermined health assessment indicators and generate health warning information. Step 3: Based on the Battery Health Index (BHI), establish a correlation model between battery health status and vehicle-grid interaction behavior, analyze the relationship between battery charge / discharge depth, interaction time interval, and interaction depth, and determine the interaction strategy between electric vehicles and the power grid. Step 4: Use the Autoformer model to process historical charging data and predict the charging and discharging depth adjustment coefficient and the interaction time reduction coefficient during the vehicle-to-grid interaction process; Step 5: Generate a battery maintenance strategy based on the Battery Health Index (BHI) and control the electric vehicle's interaction with the power grid, including adjusting charging and discharging power and setting interaction time intervals.

2. The battery health check and vehicle-to-grid interaction control method based on SSA and Autoformer according to claim 1, characterized in that, In step 1, the electric vehicle charging information collection device is integrated inside the charging pile, including: The CAN transceiver terminals are used to acquire electric vehicle charging information in CAN message form through the CAN communication interfaces S+ and S- of the charging gun; the main control chip receives and parses the messages through the CAN transceiver, generates formatted data packets, and communicates with the WIFI module through the SCI serial port; the power supply motherboard is used to supply power to the CAN transceiver, the main control chip, and the WIFI module. The expression for the battery charging information is: ； In the formula: For the collected battery charging information, For battery type, For battery capacity, For the battery's rated voltage, For charging voltage measurement value, For charging current measurement value, For the highest single cell voltage, For the current state of charge (SOC), To estimate the remaining charging time, For cumulative charging time, This is the highest temperature of the battery.

3. The battery health check and vehicle-to-grid interaction control method based on SSA and Autoformer according to claim 2, characterized in that, The Battery Health Index (BHI) is calculated using the following formula: ； In the formula, , , , , As the indicator weight; The rate of change of SOC; This is due to the voltage difference of individual cells; This is a normalized temperature index; This is the capacity decay coefficient; The rate of change of the battery's internal resistance; in: ； ； ； ； ； In the formula, Let SOC be the current state of charge at time t. Let SOC be the current state of charge at time t-1; This is the reference temperature under normal operating conditions. The maximum permissible temperature; The estimated current maximum available capacity is calculated using cumulative charge and discharge data; Calculate the remaining battery life based on the Battery Health Index (BHI). ,expression: ； In the formula, The average daily discharge was calculated from historical data.

4. The battery health check and vehicle-to-grid interaction control method based on SSA and Autoformer according to claim 3, characterized in that, The method for optimizing the index weights using the tunic swarm algorithm includes: Initialize population parameters: Set population size Number of iterations Randomly initialize N sets of weights, expression: ； Define fitness function expression: ； Update the leader weight expression: ； Update follower weight expression: ； After weight normalization, the expression is satisfied: ; Repeat the steps until the desired result is achieved. Or convergence condition; in: , , , , These are weighting coefficients used to balance the importance of various indicators. For the fitness function, The true BHI value calculated from historical data. The BHI value is calculated based on the current weights. This is the set of weight combinations in the current population. This represents the latest weight combination in the current population. This represents the optimal weight combination in the current population. For the i-th weight combination, A random number between [0,1]. To explore the step size coefficient and control the convergence speed, To adjust the factor and control the follower step size, A random number between [0,1] This is the k-th weight coefficient.

5. The battery health check and vehicle-to-grid interaction control method based on SSA and Autoformer according to claim 1, characterized in that, In step 3, the steps for establishing the correlation model between battery health status and vehicle-to-grid interaction behavior are as follows: Remaining charge / discharge cycles of the battery The expression is: ； in: This refers to the initial rated number of cycles for the battery. This refers to the number of charge / discharge cycles already used. The expression for depth of charge / discharge is: ； in: For charging depth, For discharge depth, Minimum depth of battery charge, For the minimum depth of discharge of the battery, , This is the adjustment coefficient for the depth of charge / discharge; Interaction time interval between vehicles and the internet expression: ； in: For the maximum vehicle-to-network interaction time interval, The coefficient for shortening vehicle-to-network interaction time; Charging and discharging power expression: ； in: This represents the maximum charging and discharging power.

6. The battery health check and vehicle-to-grid interaction control method based on SSA and Autoformer according to claim 5, characterized in that, The process of using the Autoformer model to process historical charging data specifically includes: ； in: As the output variable for future vehicle-to-everything (V2X) interaction coefficients, Let F represent the prediction error, and let F be the prediction function determined by the Autoformer model. The input variable is the historical vehicle-to-vehicle interaction coefficient; ； in: For the predicted depth of charge adjustment factor, For the predicted depth of discharge adjustment coefficient, The coefficient for reducing the predicted vehicle-to-network interaction time; ； in: Battery health status index, For the current charging depth, For the current discharge depth, For the current vehicle-to-network interaction time interval, For the current battery temperature, For current electric vehicle charging and discharging power, The current charging depth adjustment coefficient, For the current discharge depth adjustment coefficient, This is a coefficient that shortens the current vehicle-to-network interaction time.

7. The battery health check and vehicle-to-grid interaction control method based on SSA and Autoformer according to claim 1, characterized in that, The specific steps for predicting the charge / discharge depth adjustment coefficient and the interaction time reduction coefficient during the vehicle-to-grid interaction process include: The long-term and short-term features of the input data are extracted through the autocorrelation mechanism and recursive decomposition module of the Autoformer model. The generated prediction output expression is: ； in: For future vehicle-to-everything (V2X) interaction coefficients, For historical vehicle-to-everything (V2X) interaction coefficients; The expression for the analytical prediction result is: ； in: For the predicted depth of charge adjustment factor, For the predicted depth of discharge adjustment coefficient, The coefficient for shortening the predicted vehicle-to-network interaction time. This refers to the Autoformer prediction model. , , For a more specific Autoformer prediction model; The predicted adjustment coefficient , , Substituting into the following formula, the expression for dynamically adjusting the charge / discharge depth and interaction time interval for the next cycle is: ； in: Battery health status index, For the predicted depth of charging, For the predicted depth of discharge, For the predicted vehicle-to-network interaction time interval, , It is the minimum depth of charge and discharge. It is the maximum vehicle-to-network interaction time interval.

8. The battery health check and vehicle-to-grid interaction control method based on SSA and Autoformer according to claim 1, characterized in that, In step 5, the Battery Health Index (BHI) generates a battery maintenance strategy, including the following steps: Battery maintenance strategies are generated based on the Battery Health Index (BHI). The strategy is categorized according to the BHI value using the following expression: ； The corresponding maintenance strategy is as follows: when At the same time, the charging and discharging strategy remains unchanged, allowing high-frequency vehicle-to-grid interaction; when Limit the depth of charge and discharge to and and reduce the frequency of interaction; when At that time, only shallow charging and discharging are allowed, and vehicle-to-grid interaction is limited to the lowest frequency.

9. The battery health check and vehicle-to-grid interaction control method based on SSA and Autoformer according to claim 8, characterized in that, Adjust the vehicle-to-everything (V2X) interaction control parameters according to BHI, including: Interaction time interval The expression is: ； in: This refers to the battery health status index. Interaction time interval Adjust the coefficient for interaction time. The maximum interaction time interval is preset. The expression for depth of charge / discharge is: ； in: , For depth of charge and discharge, , For the charge / discharge depth adjustment coefficient, , Minimum depth of charge / discharge; and According to the BHI classification expression: ； Interaction time interval The specific adjustments are calculated using the following formula: ； in: This represents the actual maximum interaction time interval.

Images