EIS analysis system for new energy automobile battery life prediction

Abstract

The invention relates to the technical field of new energy automobile battery management, and particularly discloses an EIS analysis system for new energy automobile battery life prediction, and the system carries out the multi-frequency electrochemical impedance test of a new energy automobile battery through an EIS test device, and obtains the EIS data of the new energy automobile battery corresponding to different monitoring days. Analyzing the EIS data to determine the decline stages of the automobile battery in different monitoring days, and predicting the capacity decline rate of the automobile battery in each future date; external use information of a new energy automobile battery is collected through a sensor and a data interface of the new energy automobile; a result of the decline information analysis module is fused with data of an external information acquisition module, and the remaining life of the new energy automobile battery is predicted; the capacity recession rate of the battery can be predicted more accurately, and the residual life of the battery can be estimated more effectively.

Description

Technical Field

[0001] The invention belongs to the technical field of new energy vehicle battery management and relates to an EIS analysis system for predicting the life of new energy vehicle batteries. Background Art

[0002] With the rapid development of new energy vehicles, the prediction of vehicle battery life has become a key issue. Electrochemical impedance spectroscopy (EIS) is a commonly used analysis tool that can reflect the internal state of a vehicle battery by measuring the impedance variation of the vehicle battery with frequency. Existing vehicle battery management systems usually estimate the state of health (SOH) of vehicle batteries through parameters such as voltage, current, and temperature, but these methods often fail to accurately capture the physical and chemical changes inside vehicle batteries. However, there are still limitations in simply relying on EIS to analyze the life of automobile batteries, because the degradation of automobile batteries is not only related to their internal electrochemical reactions, but also affected by multiple factors such as external usage environment, driving habits, charging mode, etc. Therefore, how to combine multiple information to accurately predict the remaining life of automobile batteries has become an urgent problem to be solved. Summary of the invention

[0003] In view of the above problems existing in the prior art, the present invention provides an EIS analysis system for predicting the battery life of new energy vehicles, which is used to solve the above technical problems.

[0004] In order to achieve the above purpose and other purposes, the technical solution adopted by the present invention is as follows: On one hand, the present invention provides an EIS analysis system for new energy vehicle battery life prediction, including an EIS data test module, a decay rate analysis module, an external information acquisition module, a battery life prediction module and a battery life feedback terminal, wherein the above modules are connected by wired and / or wireless connection to achieve data transmission between the modules; EIS data test module: Use EIS test equipment to perform multi-frequency electrochemical impedance tests on new energy vehicle batteries to obtain EIS data of new energy vehicle batteries corresponding to different monitoring days; A decay rate analysis module: based on the EIS data, determining the decay stage of the vehicle battery on different monitoring days by analyzing the EIS data, and predicting the capacity decay rate of the vehicle battery on various future dates; External information collection module: collects external usage information of new energy vehicle batteries through the sensors and data interfaces of new energy vehicles; Battery life prediction module: combines the results of the decay information analysis module with the data of the external information acquisition module to predict the remaining life of the new energy vehicle battery; Battery life feedback terminal: The prediction results of the remaining life of new energy vehicle batteries are displayed in real time through the human-computer interaction interface for user reference.

[0005] Exemplarily, the EIS data of new energy vehicle batteries corresponding to different monitoring days include electrolyte internal resistance, charge transfer resistance and Warburg impedance.

[0006] Exemplarily, the degradation stage of the vehicle battery on different monitoring days is determined, and the specific determination process is as follows: S3-1, respectively obtain the initial electrolyte internal resistance RS, initial charge transfer resistance RC and initial Warburg impedance ZW of the new energy vehicle battery when it leaves the factory; The difference between the initial electrolyte internal resistance of the new energy vehicle battery at the time of leaving the factory and the electrolyte internal resistance on each monitoring day is calculated to obtain the change in the electrolyte internal resistance corresponding to the initial state on each monitoring day; According to the above calculation method, the change amount of the charge transfer resistance corresponding to the initial state on each monitoring day and the change amount of the Warburg impedance corresponding to the initial state on each monitoring day are obtained respectively; S3-2. Calculate the weighted impedance change rate of new energy vehicle batteries on different monitoring days , They represent the preset weight coefficients, which are used to reflect the relative impact of different EIS data on the degradation of automobile batteries. They represent the changes of the electrolyte internal resistance, charge transfer resistance and Warburg impedance corresponding to the initial state on the i-th monitoring day, respectively, and i is the number of each monitoring day; in , , ; S3-3, the decay stage of the car battery on different monitoring days is determined by the following formula: , JQ1 is the upper limit threshold of the weighted impedance change rate in the initial recession stage, and JQ2 is the upper limit threshold of the weighted impedance change rate in the mid-term recession stage.

[0007] For example, the capacity decay rate of a car battery at each future date is predicted, and the specific prediction process is as follows: Filter out the EIS data of the same type of automobile battery corresponding to each historical monitoring day from the historical database, and arrange them in descending order according to the order of the historical monitoring days; Get the total number of historical monitoring days N, calculate it, and get the calculation result of historical monitoring days ; Select the first n historical monitoring days from the historical monitoring days corresponding to the sorted same type of automobile batteries as the model input date, and select the last Nn historical monitoring days from the historical monitoring days corresponding to the sorted same type of automobile batteries as the model prediction date; All EIS data of each model input date are input into each convolutional neural network model, which is fitted, and the model output value of each convolutional neural network model corresponding to each model prediction date is output; The model output value of each convolutional neural network model corresponding to each model prediction date is subtracted from the EIS data of each model prediction date, and the variance is calculated to obtain the output error variance corresponding to each convolutional neural network model. The output error variances are arranged in ascending order, and the convolutional neural network model with the smallest output error variance is selected as the target convolutional neural network model. The EIS data of new energy vehicle batteries corresponding to different monitoring days are input into the target convolutional neural network model, and the EIS data of the vehicle batteries corresponding to each future date are output; Extract the electrolyte internal resistance of the car battery corresponding to each future date based on the EIS data of the car battery corresponding to each future date , Charge transfer resistance and Warburg impedance , T is the date corresponding to the last monitoring day, c is the number of preset interval days △i between T and each future date, c ranges from 1 to W, △i is the preset interval days; This calculates the capacity decay rate of the car battery at various future dates , W is the total number of preset interval days △i between T and each future date, Respectively represent the preset empirical coefficients, , , ; are the electrolyte internal resistance, charge transfer resistance and Warburg impedance at the c+1th future date respectively; It is the stage impact rate factor corresponding to the recession stage of each future date.

[0008] Exemplarily, the process of obtaining the stage impact rate factor corresponding to the recession stage of each future date is as follows: Based on the calculation principle of the decay stage of the car battery on different monitoring days, the decay stage of the car battery on each future date can be calculated in the same way; When the decay stage of the car battery at a future date is determined to be the initial decay stage, the stage impact rate factor corresponding to the decay stage at the future date is , RS' and RC' represent the electrolyte internal resistance and charge transfer resistance of the car battery corresponding to the future date, respectively; When the decline stage of the car battery at a future date is determined to be the mid-term decline stage, the stage impact rate factor corresponding to the decline stage at the future date is , ZW' represents the Warburg impedance of the car battery corresponding to the future date; When the decay stage of the car battery at a future date is determined to be the late decay stage, the stage impact rate factor corresponding to the decay stage at the future date is ; in They represent the calculation proportional constants of the predefined early decay stage, middle decay stage, and late decay stage respectively; The decay stage of the car battery at each future date is matched with the stage impact rate factor corresponding to the decay stage at the corresponding future date, so as to obtain the stage impact rate factor corresponding to the decay stage at each future date. , The specific value is or .

[0009] Exemplarily, the external usage information of the new energy vehicle battery includes driving habit information and charging mode information; The driving habit information includes acceleration frequency, deceleration frequency, and average vehicle speed; The charging mode information includes fast charging frequency, slow charging frequency, and charging current.

[0010] For example, the remaining life of a new energy vehicle battery is predicted, and the specific prediction process is as follows: Obtain the capacity RL of the new energy vehicle battery corresponding to the last monitoring day and the capacity decay rate of the vehicle battery on each future date , calculate the estimated remaining life of new energy vehicle batteries , is a constant related to the battery degradation rate, RL' represents the initial capacity of the battery; Acceleration frequency based on new energy vehicle batteries , deceleration frequency , average speed , fast charging frequency , Slow charging frequency And the charging current ; Calculate the life of new energy vehicle batteries and calculate the weakening value , They are weight coefficients, which represent the weight of each external usage information on battery life; A temperature correction term is introduced to describe the impact of the average temperature of the battery life of new energy vehicle batteries corresponding to the use environment, and the predicted life reduction value of new energy vehicle batteries is obtained. , e is the natural constant, R is the gas constant, E is the activation energy, and T is the absolute temperature; The estimated remaining life of the new energy vehicle battery is subtracted from the predicted life reduction value of the new energy vehicle battery to obtain the remaining life of the new energy vehicle battery.

[0011] An EIS analysis device for new energy vehicle battery life prediction, including a processor, a memory and a communication bus; The memory stores a computer-readable program executable by the processor; The communication bus realizes the connection and communication between the processor and the memory; When the processor executes the computer-readable program, it is executed to implement the EIS analysis system for new energy vehicle battery life prediction as described in the present invention.

[0012] A computer-readable storage medium, characterized in that: the computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the EIS analysis system for new energy vehicle battery life prediction as described in the present invention.

[0013] As described above, the EIS analysis system for new energy vehicle battery life prediction provided by the present invention has at least the following beneficial effects: The EIS analysis system for predicting the life of new energy vehicle batteries provided by the present invention performs multi-frequency electrochemical impedance testing on new energy vehicle batteries through EIS testing equipment to obtain EIS data corresponding to different monitoring days of new energy vehicle batteries; by analyzing the EIS data, the decay stage of the vehicle battery on different monitoring days is determined, and the capacity decay rate of the vehicle battery on each future date is predicted; through the sensors and data interfaces of new energy vehicles, the external use information of the new energy vehicle battery is collected; the results of the decay information analysis module are fused with the data of the external information acquisition module to predict the remaining life of the new energy vehicle battery; the advantage of this method is that the EIS data can provide detailed information on the electrochemical reaction inside the battery and reveal the microscopic mechanism of battery aging, while the external use information reflects the operating state of the battery under actual working conditions. By fusing and analyzing these two types of data, not only can the capacity decay rate of the battery be predicted more accurately, but also the remaining life of the battery can be estimated more effectively. This comprehensive analysis method can improve the accuracy and reliability of the prediction, help car owners and operators optimize the use and maintenance strategies of batteries, extend battery life, reduce operating costs, and ensure the safety and performance stability of new energy vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for describing the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 It is a schematic diagram of the connection of various modules of the system of the present invention. DETAILED DESCRIPTION

[0016] The above contents in combination with the implementation of the present invention are merely examples and explanations of the concept of the present invention. The technical personnel in the relevant technical field may make various modifications or supplements to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they shall all fall within the protection scope of the present invention.

[0017] Example 1 See also Figure 1 As shown, the EIS analysis system for new energy vehicle battery life prediction includes an EIS data test module, a decay rate analysis module, an external information acquisition module, a battery life prediction module and a battery life feedback terminal. The above modules are connected by wired and / or wireless connection to achieve data transmission between the modules; EIS data test module: Use EIS test equipment to perform multi-frequency electrochemical impedance tests on new energy vehicle batteries to obtain EIS data of new energy vehicle batteries corresponding to different monitoring days; Based on the above scheme, the EIS data of new energy vehicle batteries corresponding to different monitoring days include electrolyte internal resistance, charge transfer resistance and Warburg impedance.

[0018] A decay rate analysis module: based on the EIS data, determining the decay stage of the vehicle battery on different monitoring days by analyzing the EIS data, and predicting the capacity decay rate of the vehicle battery on various future dates; Based on the above scheme, the degradation stage of the vehicle battery on different monitoring days is determined. The specific determination process is as follows: S3-1, respectively obtain the initial electrolyte internal resistance RS, initial charge transfer resistance RC and initial Warburg impedance ZW of the new energy vehicle battery when it leaves the factory; The difference between the initial electrolyte internal resistance of the new energy vehicle battery at the time of leaving the factory and the electrolyte internal resistance on each monitoring day is calculated to obtain the change in the electrolyte internal resistance corresponding to the initial state on each monitoring day; According to the above calculation method, the change amount of the charge transfer resistance corresponding to the initial state on each monitoring day and the change amount of the Warburg impedance corresponding to the initial state on each monitoring day are obtained respectively; S3-2. Calculate the weighted impedance change rate of new energy vehicle batteries on different monitoring days , They represent the preset weight coefficients, which are used to reflect the relative impact of different EIS data on the degradation of automobile batteries. They represent the changes of the electrolyte internal resistance, charge transfer resistance and Warburg impedance corresponding to the initial state on the i-th monitoring day, respectively, and i is the number of each monitoring day; in , , ; S3-3, the decay stage of the car battery on different monitoring days is determined by the following formula: , JQ1 is the upper limit threshold of the weighted impedance change rate in the initial recession stage, and JQ2 is the upper limit threshold of the weighted impedance change rate in the mid-term recession stage.

[0019] Based on the above scheme, the capacity decay rate of the car battery at each future date is predicted. The specific prediction process is as follows: Filter out the EIS data of the same type of automobile battery corresponding to each historical monitoring day from the historical database, and arrange them in descending order according to the order of the historical monitoring days; Get the total number of historical monitoring days N, calculate it, and get the calculation result of historical monitoring days ; Select the first n historical monitoring days from the historical monitoring days corresponding to the sorted same type of automobile batteries as the model input date, and select the last Nn historical monitoring days from the historical monitoring days corresponding to the sorted same type of automobile batteries as the model prediction date; All EIS data of each model input date are input into each convolutional neural network model, which is fitted, and the model output value of each convolutional neural network model corresponding to each model prediction date is output; The model output value of each convolutional neural network model corresponding to each model prediction date is subtracted from the EIS data of each model prediction date, and the variance is calculated to obtain the output error variance corresponding to each convolutional neural network model. The output error variances are arranged in ascending order, and the convolutional neural network model with the smallest output error variance is selected as the target convolutional neural network model. The EIS data of new energy vehicle batteries corresponding to different monitoring days are input into the target convolutional neural network model, and the EIS data of the vehicle batteries corresponding to each future date are output; Extract the electrolyte internal resistance of the car battery corresponding to each future date based on the EIS data of the car battery corresponding to each future date , Charge transfer resistance and Warburg impedance , T is the date corresponding to the last monitoring day, c is the number of preset interval days △i between T and each future date, c ranges from 1 to W, △i is the preset interval days; This calculates the capacity decay rate of the car battery at various future dates , W is the total number of preset interval days △i between T and each future date, Respectively represent the preset empirical coefficients, , , ; are the electrolyte internal resistance, charge transfer resistance and Warburg impedance at the c+1th future date respectively; It is the stage impact rate factor corresponding to the recession stage of each future date.

[0020] Based on the above scheme, the process of obtaining the stage impact rate factor corresponding to the recession stage of each future date is as follows: Based on the calculation principle of the decay stage of the car battery on different monitoring days, the decay stage of the car battery on each future date can be calculated in the same way; When the decay stage of the car battery at a future date is determined to be the initial decay stage, the stage impact rate factor corresponding to the decay stage at the future date is , RS' and RC' represent the electrolyte internal resistance and charge transfer resistance of the car battery corresponding to the future date, respectively; When the decline stage of the car battery at a future date is determined to be the mid-term decline stage, the stage impact rate factor corresponding to the decline stage at the future date is , ZW' represents the Warburg impedance of the car battery corresponding to the future date; When the decay stage of the car battery at a future date is determined to be the late decay stage, the stage impact rate factor corresponding to the decay stage at the future date is ; in They represent the calculation proportional constants of the predefined early decay stage, middle decay stage, and late decay stage respectively; The proportional constant needs to be obtained by fitting experimental data, and may vary depending on factors such as battery type and usage conditions; The decay stage of the car battery at each future date is matched with the stage impact rate factor corresponding to the decay stage at the corresponding future date, so as to obtain the stage impact rate factor corresponding to the decay stage at each future date. , The specific value is or .

[0021] The capacity decay of the battery is closely related to the increase of internal impedance. The internal resistance of the electrolyte, the charge transfer resistance and the Warburg impedance represent the effects of different electrochemical processes on battery performance: Electrolyte internal resistance: mainly affects the migration speed of ions in the electrolyte. An increase in internal resistance usually means slower ion migration, resulting in capacity decay.

[0022] Charge transfer resistance: reflects the reaction rate on the electrode surface. An increase in charge transfer resistance usually means that the electrochemical reaction becomes difficult, affecting the charging and discharging efficiency of the battery.

[0023] Warburg impedance: related to the diffusion process, representing the diffusion limitation of ions in the electrode material. An increase in Warburg impedance indicates that the diffusion process is limited, which in turn affects the capacity.

[0024] External information collection module: collects external usage information of new energy vehicle batteries through the sensors and data interfaces of new energy vehicles; Preferably, based on the above scheme, the external usage information of the new energy vehicle battery includes driving habit information and charging mode information; The driving habit information includes acceleration frequency, deceleration frequency, and average vehicle speed; The charging mode information includes fast charging frequency, slow charging frequency, and charging current.

[0025] Battery life prediction module: combines the results of the decay information analysis module with the data of the external information acquisition module to predict the remaining life of the new energy vehicle battery; Based on the above scheme, the remaining life of the new energy vehicle battery is predicted. The specific prediction process is as follows: Obtain the capacity RL of the new energy vehicle battery corresponding to the last monitoring day and the capacity decay rate of the vehicle battery on each future date , calculate the estimated remaining life of new energy vehicle batteries , is a constant related to the battery degradation rate, RL' represents the initial capacity of the battery; The meaning of 0.2 in the above formula is that the life of new energy vehicle batteries is usually defined as the time point when the battery capacity decays to 80% of the initial capacity. When the capacity decays to 80%, it means the battery life ends; Acceleration frequency based on new energy vehicle batteries , deceleration frequency , average speed , fast charging frequency , Slow charging frequency And the charging current ; Calculate the life of new energy vehicle batteries and calculate the weakening value , They are weight coefficients, which represent the weight of each external usage information on battery life; The final life calculation reduction value is obtained by weighted linear combination of six parameters (acceleration frequency, deceleration frequency, average vehicle speed, fast charging frequency, slow charging frequency, and charging current). These weight coefficients can be obtained by fitting experimental data or empirical data; (Weight of acceleration frequency): Frequent acceleration will increase the instantaneous discharge current of the battery, increase the electrochemical stress and heat generation of the battery, and thus accelerate the aging of the battery. The value of should be proportional to the impact of the acceleration frequency on battery life; (Weight of deceleration frequency): Regenerative braking during deceleration causes the battery to receive a large instantaneous charging current, which may cause certain electrochemical stress on the battery. Reflects the impact of deceleration on battery life; (Weight of average vehicle speed): A higher average vehicle speed usually means higher energy consumption and discharge rate, causing the battery to operate at a high discharge current, increasing the heat generation of the battery, and thus accelerating the aging of the battery. Therefore, Reflects the impact of vehicle speed on battery life; (Weight of fast charging frequency): Fast charging causes the battery to charge at a high current, generating more heat and accelerating battery aging. Frequent fast charging will significantly shorten the battery life, so Should be larger; (Weight of slow charging frequency): Slow charging puts less electrochemical stress on the battery and therefore has less impact on battery life. It should be small, but still have some impact; (Charging current weight): The size of the charging current directly affects the heat generation and electrochemical stress inside the battery. A larger charging current will accelerate battery aging, so Should be proportional to the charging current; A temperature correction term is introduced to describe the impact of the average temperature of the battery life of new energy vehicle batteries corresponding to the use environment, and the predicted life reduction value of new energy vehicle batteries is obtained. , e is a natural constant, R is a gas constant, E is the activation energy related to battery aging, and T is the absolute temperature; The life of a battery is not only affected by driving habits and charging patterns, but also significantly affected by temperature. Batteries age faster at high temperatures, while at low temperatures, the chemical reaction rate of the battery is reduced, which may lead to performance degradation. Therefore, temperature is an important factor affecting battery life.

[0026] The aging process of batteries can be described by the Arrhenius equation, which is usually used to describe the effect of temperature on the rate of chemical reactions. For batteries, rising temperatures will accelerate the chemical reactions and side reactions inside the battery, thereby accelerating the aging of the battery. Indicates the actual life of the battery at a specific temperature. The higher the temperature, the faster the battery ages and the shorter the life. The Arrhenius equation can be used to describe the effect of temperature on battery life. The estimated remaining life of the new energy vehicle battery is subtracted from the predicted life reduction value of the new energy vehicle battery to obtain the remaining life of the new energy vehicle battery.

[0027] Battery life feedback terminal: The prediction results of the remaining life of new energy vehicle batteries are displayed in real time through the human-computer interaction interface for user reference.

[0028] Example 2 An EIS analysis device for new energy vehicle battery life prediction, including a processor, a memory and a communication bus; The memory stores a computer-readable program executable by the processor; The communication bus realizes the connection and communication between the processor and the memory; When the processor executes the computer-readable program, it is executed to implement the EIS analysis system for new energy vehicle battery life prediction as described in the present invention.

[0029] Example 3 A computer-readable storage medium, characterized in that: the computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the EIS analysis system for new energy vehicle battery life prediction as described in the present invention.

[0030] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0031] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0032] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0033] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. The EIS analysis system for new energy vehicle battery life prediction is characterized by: It includes an EIS data test module, a decay rate analysis module, an external information acquisition module, a battery life prediction module and a battery life feedback terminal, and the above modules are connected by wired and / or wireless connection to achieve data transmission between the modules; EIS data test module: Use EIS test equipment to perform multi-frequency electrochemical impedance tests on new energy vehicle batteries to obtain EIS data of new energy vehicle batteries corresponding to different monitoring days; A decay rate analysis module: based on the EIS data, determining the decay stage of the vehicle battery on different monitoring days by analyzing the EIS data, and predicting the capacity decay rate of the vehicle battery on various future dates; External information collection module: collects external usage information of new energy vehicle batteries through the sensors and data interfaces of new energy vehicles; Battery life prediction module: combines the results of the decay information analysis module with the data of the external information acquisition module to predict the remaining life of the new energy vehicle battery; Battery life feedback terminal: The prediction results of the remaining life of new energy vehicle batteries are displayed in real time through the human-computer interaction interface for user reference.

2. The EIS analysis system for new energy vehicle battery life prediction according to claim 1, characterized in that: The EIS data of new energy vehicle batteries corresponding to different monitoring days include electrolyte internal resistance, charge transfer resistance and Warburg impedance.

3. The EIS analysis system for new energy vehicle battery life prediction according to claim 1, characterized in that: Determine the degradation stage of the car battery on different monitoring days. The specific determination process is as follows: Obtain the initial electrolyte internal resistance RS, initial charge transfer resistance RC and initial Warburg impedance ZW of the new energy vehicle battery at the time of leaving the factory respectively; The difference between the initial electrolyte internal resistance of the new energy vehicle battery at the time of leaving the factory and the electrolyte internal resistance on each monitoring day is calculated to obtain the change in the electrolyte internal resistance corresponding to the initial state on each monitoring day; According to the above calculation method, the change amount of the charge transfer resistance corresponding to the initial state on each monitoring day and the change amount of the Warburg impedance corresponding to the initial state on each monitoring day are obtained respectively; Calculate the weighted impedance change rate of new energy vehicle batteries on different monitoring days , They represent the preset weight coefficients, which are used to reflect the relative impact of different EIS data on the degradation of automobile batteries. They represent the changes of the electrolyte internal resistance, charge transfer resistance and Warburg impedance corresponding to the initial state on the i-th monitoring day, respectively, and i is the number of each monitoring day; in , , ; The decay stage of the car battery on different monitoring days is determined by the following formula: , JQ1 is the upper limit threshold of the weighted impedance change rate in the initial recession stage, and JQ2 is the upper limit threshold of the weighted impedance change rate in the mid-term recession stage.

4. The EIS analysis system for new energy vehicle battery life prediction according to claim 1, characterized in that: Predict the capacity decay rate of the car battery at various future dates. The specific prediction process is as follows: Filter out the EIS data of the same type of automobile battery corresponding to each historical monitoring day from the historical database, and arrange them in descending order according to the order of the historical monitoring days; Get the total number of historical monitoring days N, calculate it, and get the calculation result of historical monitoring days ; Select the first n historical monitoring days from the historical monitoring days corresponding to the sorted same type of automobile batteries as the model input date, and select the last Nn historical monitoring days from the historical monitoring days corresponding to the sorted same type of automobile batteries as the model prediction date; All EIS data of each model input date are input into each convolutional neural network model, which is fitted, and the model output value of each convolutional neural network model corresponding to each model prediction date is output; The model output value of each convolutional neural network model corresponding to each model prediction date is subtracted from the EIS data of each model prediction date, and the variance is calculated to obtain the output error variance corresponding to each convolutional neural network model. The output error variances are arranged in ascending order, and the convolutional neural network model with the smallest output error variance is selected as the target convolutional neural network model. The EIS data of new energy vehicle batteries corresponding to different monitoring days are input into the target convolutional neural network model, and the EIS data of the vehicle batteries corresponding to each future date are output; Extract the electrolyte internal resistance of the car battery corresponding to each future date based on the EIS data of the car battery corresponding to each future date , Charge transfer resistance and Warburg impedance , T is the date corresponding to the last monitoring day, c is the number of preset interval days △i between T and each future date, c ranges from 1 to W, △i is the preset interval days; This calculates the capacity decay rate of the car battery at various future dates , W is the total number of preset interval days △i between T and each future date, Respectively represent the preset empirical coefficients, , , ; are the electrolyte internal resistance, charge transfer resistance and Warburg impedance at the c+1th future date respectively; It is the stage impact rate factor corresponding to the recession stage of each future date.

5. The EIS analysis system for new energy vehicle battery life prediction according to claim 4, characterized in that: The process of obtaining the stage impact rate factor corresponding to the recession stage of each future date is as follows: Based on the calculation principle of the decay stage of the car battery on different monitoring days, the decay stage of the car battery on each future date can be calculated in the same way; When the decay stage of the car battery at a future date is determined to be the initial decay stage, the stage impact rate factor corresponding to the decay stage at the future date is , RS' and RC' represent the electrolyte internal resistance and charge transfer resistance of the car battery corresponding to the future date, respectively; When the decline stage of the car battery at a future date is determined to be the mid-term decline stage, the stage impact rate factor corresponding to the decline stage at the future date is , ZW' represents the Warburg impedance of the car battery corresponding to the future date; When the decay stage of the car battery at a future date is determined to be the late decay stage, the stage impact rate factor corresponding to the decay stage at the future date is ; in They represent the calculation proportional constants of the predefined early decay stage, middle decay stage, and late decay stage respectively; The decay stage of the car battery at each future date is matched with the stage impact rate factor corresponding to the decay stage at the corresponding future date, so as to obtain the stage impact rate factor corresponding to the decay stage at each future date. , The specific value is or .

6. The EIS analysis system for new energy vehicle battery life prediction according to claim 1, characterized in that: External usage information of new energy vehicle batteries includes driving habits information and charging mode information; The driving habit information includes acceleration frequency, deceleration frequency, and average vehicle speed; The charging mode information includes fast charging frequency, slow charging frequency, and charging current.

7. The EIS analysis system for new energy vehicle battery life prediction according to claim 6, characterized in that: Predict the remaining life of new energy vehicle batteries. The specific prediction process is as follows: Obtain the capacity RL of the new energy vehicle battery corresponding to the last monitoring day and the capacity decay rate of the vehicle battery on each future date , calculate the estimated remaining life of new energy vehicle batteries , is a constant related to the battery degradation rate, RL' represents the initial capacity of the battery; Acceleration frequency based on new energy vehicle batteries , deceleration frequency , average speed , fast charging frequency , Slow charging frequency And the charging current ; Calculate the life of new energy vehicle batteries and calculate the weakening value , They are weight coefficients, which represent the weight of each external usage information on battery life; A temperature correction term is introduced to describe the impact of the average temperature of the battery life of new energy vehicle batteries in the corresponding use environment, and the predicted life reduction value of new energy vehicle batteries is obtained. , e is the natural constant, R is the gas constant, E is the activation energy, and T is the absolute temperature; The estimated remaining life of the new energy vehicle battery is subtracted from the predicted life reduction value of the new energy vehicle battery to obtain the remaining life of the new energy vehicle battery.

8. An EIS analysis device for predicting the battery life of new energy vehicles, characterized in that: It is implemented based on the EIS analysis system for new energy vehicle battery life prediction according to any one of claims 1 to 7, comprising a processor, a memory and a communication bus; The memory stores a computer-readable program executable by the processor; The communication bus realizes the connection and communication between the processor and the memory; When the processor executes the computer-readable program, it is executed to implement the EIS analysis system for new energy vehicle battery life prediction as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the EIS analysis system for new energy vehicle battery life prediction as described in any one of claims 1-7.

Images