Battery health state assessment method and device, electronic equipment and storage medium

Abstract

The invention discloses a battery health state assessment method and device, electronic equipment and a storage medium, and belongs to the technical field of battery state assessment, and the method comprises the steps: determining a time constant corresponding to each peak value in a time domain distribution diagram of a sample battery impedance spectrum; determining a frequency point corresponding to the peak value according to the time constant, and obtaining dynamic impedance corresponding to the frequency point in the charging and discharging process of the sample battery; constructing a neural network model by taking the dynamic impedance of the battery as input and the residual capacity of the battery as output, and performing iterative training on the neural network model according to the dynamic impedance and the residual capacity of the sample battery to obtain a target neural network model; and performing health state evaluation on the to-be-tested battery based on the target neural network model. According to the method, the frequency point is determined through the time constant corresponding to the peak value of the time domain distribution diagram of the impedance spectrum, the health state of the battery is evaluated according to the dynamic impedance corresponding to the frequency point in the charging and discharging process, and accurate and efficient evaluation of the health state of the battery is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery status assessment, and in particular to a battery health status assessment method, device, electronic device and storage medium. Background Art

[0002] With the widespread use of lithium-ion batteries in daily life, such as portable electronic devices, electric vehicles, and renewable energy storage systems, the battery health status is a quantitative description of the degree of battery performance degradation, which is used to characterize the performance gap between the battery at the current moment and the new state. Battery aging is a long-term gradual process affected by many factors, including temperature, current rate, cut-off voltage, etc. These factors work together inside the battery, causing the battery performance to gradually decline. Therefore, it is of great practical significance to accurately evaluate the battery health status to ensure the safe, efficient and stable operation of the battery throughout its life cycle.

[0003] There are mainly the following traditional battery health status assessment methods: capacity assessment method, which performs a full charge and discharge test on the battery, obtains battery capacity data, and assesses the battery health status. This method has a long charge and discharge time and low efficiency; internal resistance assessment method, DC discharge can only statically measure the battery internal resistance, and judge the battery health status by the change trend of the internal resistance. This method has certain damage to the battery and is easily interfered by other currents, and has low accuracy; electrochemical model assessment method, which uses electrochemical principles to analyze the changes in the health status of the battery during operation. This method is highly complex and requires various internal chemical parameters of the battery. The system equations involve a wide range of aspects and are complex to calculate; the equivalent circuit model assessment method, which equates the battery to a basic circuit model, and uses the circuit model to assess the battery health status. It cannot perform impact analysis on many coupled parameter variables, and has low accuracy.

[0004] Therefore, there is an urgent need for a battery health status assessment method that can evaluate the battery health status through the dynamic impedance corresponding to the frequency point of the peak of the battery impedance spectrum time domain distribution diagram, so as to achieve accurate and efficient battery health status assessment. Summary of the invention

[0005] In view of this, it is necessary to provide a battery health status assessment method, device, electronic device and storage medium, which can evaluate the battery health status through the dynamic impedance corresponding to the frequency point of the peak of the battery impedance spectrum time domain distribution diagram, so as to achieve accurate and efficient battery health status assessment.

[0006] In order to solve the above technical problems, on the one hand, the present invention provides a battery health status assessment method, comprising: Determine the time constant corresponding to each peak in the time domain distribution diagram of the sample battery impedance spectrum; Determine the frequency point corresponding to the peak value according to the time constant, and obtain the dynamic impedance corresponding to the frequency point during the charging and discharging process of the sample battery; Obtaining the remaining capacity of the sample battery, building a neural network model with the battery dynamic impedance as input and the battery remaining capacity as output, iteratively training the neural network model according to the dynamic impedance of the sample battery and the remaining capacity of the sample battery to obtain a fully trained target neural network model; The dynamic impedance of the battery to be tested is obtained, and the health status of the battery to be tested is evaluated based on the target neural network model.

[0007] In a possible implementation, determining the time constant corresponding to each peak in the time domain distribution diagram of the battery impedance spectrum includes: Obtain the frequency domain distributed impedance spectrum of the battery; Based on the relaxation time distribution analysis method, the polarization impedance of the frequency domain distributed impedance spectrum is decomposed according to the relaxation time distribution algorithm, converted into a time domain distributed impedance spectrum, and a time domain distribution diagram of the impedance spectrum is generated; Determining peak values ​​of the time domain distribution diagram of the impedance spectrum; The time constant corresponding to the peak is calculated.

[0008] In one possible implementation, the relaxation time distribution algorithm is formulated as follows: , in, Impedance function, is the time constant, is the time constant distribution function, is the ohmic internal resistance of the electrochemical system, is an imaginary unit, is the relaxed definite integral.

[0009] In one possible implementation, the frequency point is calculated as: , in, is the frequency, is the time constant.

[0010] In a possible implementation, obtaining the dynamic impedance corresponding to the frequency point during the charging and discharging process of the sample battery includes: Charge and discharge the sample battery; Monitor the changes in frequency parameters and dynamic impedance during the charge and discharge process of the sample battery; The dynamic impedance corresponding to each of the frequency points is obtained.

[0011] In one possible implementation, a neural network model is constructed with the battery dynamic impedance as input and the battery remaining capacity as output, including: Based on the radial basis function, a radial basis function layer of a neural network is constructed according to the battery dynamic impedance and the center point of the battery dynamic impedance; Based on the radial basis function neural network, the battery dynamic impedance is taken as input and the remaining capacity of the battery is taken as output, and a neural network model is constructed in combination with the radial basis function layer.

[0012] In one possible implementation, the expression of the radial basis function layer is: , in, For the input samples, For the The center of the radial basis function, is the width parameter of the radial basis function.

[0013] In a second aspect, the present invention further provides a battery health status assessment device, comprising: A time constant confirmation module is used to determine the time constant corresponding to each peak in the time domain distribution diagram of the sample battery impedance spectrum; A dynamic impedance confirmation module, used to determine the frequency point corresponding to the peak value according to the time constant, and obtain the dynamic impedance corresponding to the frequency point during the charging and discharging process of the sample battery; A model generation module is used to obtain the remaining capacity of the sample battery, construct a neural network model with the battery dynamic impedance as input and the battery remaining capacity as output, and iteratively train the neural network model according to the dynamic impedance of the sample battery and the remaining capacity of the sample battery to obtain a fully trained target neural network model; The health status assessment module is used to obtain the dynamic impedance of the battery to be tested and to perform health status assessment on the battery to be tested based on the target neural network model.

[0014] In a third aspect, the present invention also provides an electronic device, comprising a memory and a processor, wherein the memory is used to store programs and data; the processor is coupled to the memory, and is used to execute the program stored in the memory, to implement the battery health status assessment method as described above, and / or to implement the battery health status assessment as described above.

[0015] In a fourth aspect, the present invention further provides a computer storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the battery health status assessment method as described above.

[0016] The beneficial effects of the present invention are as follows: first, determine the time constant corresponding to each peak in the time domain distribution diagram of the impedance spectrum of the sample battery; then, determine the frequency point corresponding to the peak according to the time constant, and obtain the dynamic impedance corresponding to the frequency point during the charging and discharging process of the sample battery; then, obtain the remaining capacity of the sample battery, take the dynamic impedance of the battery as input and the remaining capacity of the battery as output to build a neural network model, iteratively train the neural network model according to the dynamic impedance of the sample battery and the remaining capacity of the sample battery, and obtain a fully trained target neural network model; finally, obtain the dynamic impedance of the battery to be tested, and perform a health status assessment on the battery to be tested based on the target neural network model. The present invention analyzes the time constant corresponding to each peak in the time domain distribution diagram of the battery impedance spectrum, calculates the frequency point corresponding to the peak, obtains the dynamic impedance corresponding to each frequency point during the charging and discharging process of the sample battery, builds a neural network model according to each dynamic impedance of the sample battery and the remaining capacity of the sample battery, and iteratively trains the neural network model to obtain the final target neural network model, which can quickly and accurately evaluate the health status of the battery to be tested, thereby improving the accuracy and efficiency of the battery health status assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 work.

[0018] Figure 1 A schematic diagram of a flow chart of an embodiment of a battery health status assessment method provided by the present invention; Figure 2 For the present invention Figure 1 A schematic flow chart of an embodiment of step S101; Figure 3 For the present invention Figure 1 A flowchart of an embodiment of step S102; Figure 4 For the present invention Figure 1 A flowchart of an embodiment of step S103; Figure 5 A schematic diagram of the structure of an embodiment of an electronic device for evaluating the battery health status provided by the present invention; Figure 6 A schematic diagram of the structure of an embodiment of a battery health status assessment storage medium provided by the present invention. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] In the description of the embodiments of the present invention, unless otherwise specified, "multiple" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone.

[0021] The descriptions of "first", "second", etc. involved in the embodiments of the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" or "second" may explicitly or implicitly include at least one of the features.

[0022] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] The present invention provides a battery health status assessment method, device, electronic device and storage medium, which are described below respectively.

[0024] Figure 1 A flowchart of an embodiment of a battery health status assessment method provided by the present invention is shown in FIG. Figure 1 As shown, the battery health status assessment method includes: S101, determining the time constant corresponding to each peak in the time domain distribution diagram of the sample battery impedance spectrum; S102, determining the frequency point corresponding to the peak value according to the time constant, and obtaining the dynamic impedance corresponding to the frequency point during the charging and discharging process of the sample battery; S103, obtaining the remaining capacity of the sample battery, building a neural network model with the battery dynamic impedance as input and the battery remaining capacity as output, iteratively training the neural network model according to the dynamic impedance of the sample battery and the remaining capacity of the sample battery, and obtaining a fully trained target neural network model; S104, obtaining the dynamic impedance of the battery to be tested, and evaluating the health status of the battery to be tested based on the target neural network model.

[0025] Specifically, electrochemical tools are first used to measure the impedance performance of the battery at different frequencies to obtain a frequency impedance spectrum, which is then mathematically transformed into a time domain impedance spectrum to generate a time domain distribution diagram. The time domain distribution diagram is analyzed to identify each peak (i.e., the point where the impedance suddenly changes). The time constants corresponding to these peaks reflect the time scales of different physical and chemical processes inside the battery. Then, the corresponding frequency points are calculated based on the time constant. The time constant and frequency are in an inverse relationship, i.e., the larger the time constant, the lower the corresponding frequency. The dynamic impedance at these frequency points is then measured during the charge and discharge process of the sample battery. Dynamic impedance is the impedance response of a battery at a specific frequency, which reflects the combined effects of components such as the battery's internal resistance and capacitance. Then, the remaining capacity of the sample battery is obtained through laboratory measurements or a battery management system (BMS). The dynamic impedance of the battery is used as input and the remaining capacity of the battery is used as output to build a neural network model. Through iterative training, the model is repeatedly adjusted using known dynamic impedance and remaining capacity data until the model's prediction accuracy meets the requirements, thereby obtaining a fully trained target neural network model. Finally, the dynamic impedance of the battery to be tested at the same frequency point is obtained using the same measurement method as that used in training the target neural network model. These dynamic impedances are input into the fully trained target neural network model. The model will output the predicted remaining capacity, and the health status of the battery is evaluated based on the predicted remaining capacity.

[0026] This embodiment analyzes the time constant corresponding to each peak in the time domain distribution diagram of the battery impedance spectrum, calculates the frequency point corresponding to the peak, obtains the dynamic impedance corresponding to each frequency point during the charging and discharging process of the sample battery, constructs a neural network model according to the dynamic impedances of the sample battery and the remaining capacity of the sample battery, and iteratively trains the neural network model to obtain the final target neural network model. The target neural network model can quickly and accurately evaluate the health status of the battery under test, thereby improving the accuracy and efficiency of the battery health status evaluation.

[0027] In some embodiments of the present invention, Figure 2 As shown, Figure 2 The present invention provides Figure 1 The flowchart of an embodiment of step S101 in the embodiment includes: S201, obtaining a frequency domain distributed impedance spectrum of the battery; S202, based on the relaxation time distribution analysis method, decompose the polarization impedance of the frequency domain distributed impedance spectrum according to the relaxation time distribution algorithm, convert it into a time domain distributed impedance spectrum, and generate a time domain distribution diagram of the impedance spectrum; S203, determining each peak value of the time domain distribution diagram of the impedance spectrum; S204: Calculate the time constant corresponding to the peak value.

[0028] Specifically, first, through appearance inspection, batteries with bloating, mechanical damage, corrosion, and thermal dissolution are eliminated, and sample batteries in good working condition with no obvious signs of damage or aging are screened out; then, the battery is connected to a discharge tester at 25°C, and data such as voltage, current, and time during the constant current discharge process are recorded, where the constant current during the discharge process is 2% to 5% of the nominal capacity, and the state of charge (SOC) range of the discharge process is 0% to 10%. During the discharge process, an impedance tester is used to perform impedance measurement at different state of charge (SOC) points (such as 0%, 2.5%, 5%, 7.5%, 10%, etc.). During the impedance measurement, a small AC signal (sine wave) is applied to the battery, and the voltage and current responses generated at both ends of the battery are measured. According to the frequency change and the corresponding phase and amplitude change of the AC signal, the complex impedance of the battery is calculated, that is, the frequency domain impedance spectrum is obtained, and the impedance spectrum data at each state of charge (SOC) point is recorded. At the same time, the voltage, current, time, impedance and other data during the discharge process are sorted and analyzed using data recording and analysis software, and the impedance spectrum is further fitted to obtain the final frequency domain distributed impedance spectrum.

[0029] Furthermore, the relaxation time distribution analysis method is to decompose the polarization impedance of the frequency domain distributed impedance spectrum to generate a time domain distribution diagram of the impedance spectrum. The frequency domain impedance spectrum includes real and imaginary parts as a function of frequency. The frequency domain impedance spectrum data is converted to the time domain through mathematical changes, such as Fourier transform or its inverse transform, to extract the relaxation time distribution function, which describes the impedance contribution corresponding to different relaxation times. The time domain distribution diagram of the impedance spectrum is drawn according to the relaxation time distribution function. In the time domain distribution diagram, the peak position of the impedance is identified, and for each peak, the corresponding time point (i.e., time constant) is determined. This is usually the time coordinate of the peak occurrence, and the time constant can also be determined more accurately using a peak detection algorithm.

[0030] This embodiment converts the frequency domain impedance spectrum of the battery into a time domain impedance spectrum, and determines the time constant at the impedance peak according to the time domain impedance spectrum, thereby providing an accurate basis for subsequent analysis of the battery performance.

[0031] In some embodiments of the present invention, the relaxation time distribution algorithm is formulated as follows: , in, Impedance function, is the time constant, is the time constant distribution function, is the ohmic internal resistance of the electrochemical system, is an imaginary unit, is the relaxed definite integral.

[0032] It should be noted that, , is the relaxation time distribution function, that is, the time constant distribution function, The integrated part represents the polarization impedance.

[0033] In some embodiments of the present invention, the calculation formula of the frequency point is: , in, is the frequency, is the time constant.

[0034] It should be noted that a larger time constant corresponds to a lower frequency, while a smaller time constant corresponds to a higher frequency. After determining the time constant corresponding to the impedance peak in the impedance spectrum time domain distribution diagram, the frequency point corresponding to the peak can be calculated based on this time constant.

[0035] In some embodiments of the present invention, Figure 3 As shown, Figure 3 The present invention provides Figure 1 The flowchart of an embodiment of step S102 in the embodiment includes: S301, charging and discharging the sample battery; S302, monitoring the changes in frequency parameters and dynamic impedance during the charging and discharging process of the sample battery; S303: Obtain the dynamic impedance corresponding to each of the frequency points.

[0036] Specifically, after multiple sample batteries were left to stand at room temperature for a sufficiently long time, charge and discharge tests were performed at 0.3C ~ 1C. A sinusoidal frequency signal was applied to the battery through an external excitation device to measure the impedance, and the charging and discharging process was monitored by a measuring instrument, and the impedance data of the battery at each frequency point was recorded. The dynamic impedance corresponding to the peak frequency point is closely related to the health state of the battery. The ohmic impedance in the high-frequency zone will increase slightly as the health state of the battery declines, reacting to changes in the electrolyte and electrode contact resistance; the charge transfer impedance in the medium-frequency zone is significantly affected by SOH, and the loss of active materials or the thickening of the SEI film will cause it to increase; the diffusion impedance in the low-frequency zone increases due to the aggravation of SOH decay and the limited ion diffusion. It can be seen that the dynamic impedance data of the battery can accurately reflect the health state of the battery.

[0037] This embodiment obtains dynamic impedance data corresponding to the peak frequency point based on the calculated frequency point corresponding to the peak value by monitoring the charging and discharging process of the sample battery, thereby providing an accurate basis for evaluating the health status of the battery.

[0038] In some embodiments of the present invention, Figure 4 As shown, Figure 4 The present invention provides Figure 1 The flowchart of an embodiment of step S103 in the embodiment includes: S401, based on the radial basis function, constructing a radial basis function layer of a neural network according to the battery dynamic impedance and the center point of the battery dynamic impedance; S402, based on a radial basis function neural network, with the battery dynamic impedance as input and the battery remaining capacity as output, a neural network model is constructed in combination with the radial basis function layer.

[0039] Specifically, the radial basis function layer is the core part of the radial basis function neural network, which uses a set of radial basis functions (such as Gaussian functions) as nonlinear transformation units. The function center is selected from the battery dynamic impedance data by clustering methods or other methods.

[0040] Furthermore, the input layer of the neural network model receives the dynamic impedance data of the battery. In the radial basis function layer, the input data is mapped to a high-dimensional space according to the radial basis function. The output layer receives the output of the radial basis function layer and outputs the remaining capacity of the battery. In the process of iterative training of the neural network model, 80% of the data are selected as the training data set, 20% of the data are selected as the test data set, and a suitable loss function is selected. The dynamic impedance of the sample battery is used as the input of the model. The neural network model outputs the remaining capacity of the battery. The loss value of the remaining capacity output by the model and the actual measured remaining capacity is calculated according to the loss function. The parameter settings of the neural network model are adjusted according to the loss value. Finally, 20% of the test data set is used to evaluate the performance of the trained model. The hyperparameters (such as the center of the radial basis function, the width parameter, the learning rate, etc.) are adjusted by grid search, random search or Bayesian optimization to improve the model performance. Finally, the trained model only needs to find the impedance data corresponding to the peak frequency point to output the remaining capacity of the battery. The remaining capacity of the battery can directly reflect the health status of the battery. When the health status of the battery decreases, its remaining capacity will also decrease.

[0041] This embodiment constructs a neural network model through radial basis functions and radial basis function neural networks, predicts the remaining capacity of the battery according to the dynamic impedance of the battery, and then evaluates the health status of the battery. It can realize fast and accurate evaluation of the health status of the battery, greatly improving the efficiency and accuracy of the battery health status evaluation.

[0042] In some embodiments of the present invention, the expression of the radial basis function layer is: , in, For the input samples, For the The center of the radial basis function, is the width parameter of the radial basis function.

[0043] Specifically, in the radial basis function neural network, the radial basis function layer uses the radial basis function as the activation function. In the radial basis function layer, the input vector of the neural network model is mapped to a scalar value, realizing nonlinear transformation of the input data and extracting the features of the input data, thereby improving the performance of the entire neural network.

[0044] In order to better implement the battery health status evaluation method in the embodiment of the present invention, based on the battery health status evaluation method, correspondingly, Figure 5 As shown, the embodiment of the present invention further provides a battery health status assessment device 500 including: A time constant confirmation module 501 is used to determine the time constant corresponding to each peak in the time domain distribution diagram of the sample battery impedance spectrum; A dynamic impedance confirmation module 502, configured to determine the frequency point corresponding to the peak value according to the time constant, and obtain the dynamic impedance corresponding to the frequency point during the charging and discharging process of the sample battery; The model generation module 503 is used to obtain the remaining capacity of the sample battery, construct a neural network model with the battery dynamic impedance as input and the battery remaining capacity as output, and iteratively train the neural network model according to the dynamic impedance of the sample battery and the remaining capacity of the sample battery to obtain a fully trained target neural network model; The health status assessment module 504 is used to obtain the dynamic impedance of the battery to be tested and perform health status assessment on the battery to be tested based on the target neural network model.

[0045] The battery health status assessment device 500 provided in the above embodiment can implement the technical solution described in the above battery health status assessment method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above battery health status assessment method embodiment, which will not be repeated here.

[0046] In the embodiment of the present invention, the battery health status evaluation device may be an independent server, or a server network or server cluster composed of servers. For example, the battery health status evaluation device described in the embodiment of the present invention includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud server composed of a plurality of servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0047] The present invention also provides a battery health status assessment electronic device, such as Figure 6 As shown, Figure 6This is a structural block diagram of an embodiment of a battery health status assessment device provided by the present invention. The battery health status assessment device 600 can be a computing device such as a mobile terminal, a desktop computer, a notebook, a PDA, and a server. The battery health status assessment device 600 includes a processor 601 and a memory 602, wherein the memory 602 stores a battery health status assessment program 603.

[0048] In some embodiments, the memory 602 may be an internal storage unit of a computer device, such as a hard disk or memory of a computer device. In other embodiments, the memory 602 may also be an external storage device of a computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device. Furthermore, the memory 602 may also include both an internal storage unit of a computer device and an external storage device. The memory 602 is used to store application software and various types of data installed on the computer device, such as program codes installed on the computer device. The memory 602 may also be used to temporarily store data that has been output or is to be output. In one embodiment, the battery health status assessment program 603 may be executed by the processor 601, thereby realizing the battery health status assessment method, device, electronic device and storage device of each embodiment of the present invention.

[0049] In some embodiments, the processor 601 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 602, such as executing a battery health status assessment program.

[0050] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0051] The battery health status assessment method, device, electronic device and storage device provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A battery health status assessment method, characterized in that: include: Determine the time constant corresponding to each peak in the time domain distribution diagram of the sample battery impedance spectrum; Determine the frequency point corresponding to the peak value according to the time constant, and obtain the dynamic impedance corresponding to the frequency point during the charging and discharging process of the sample battery; Obtaining the remaining capacity of the sample battery, building a neural network model with the battery dynamic impedance as input and the battery remaining capacity as output, iteratively training the neural network model according to the dynamic impedance of the sample battery and the remaining capacity of the sample battery to obtain a fully trained target neural network model; The dynamic impedance of the battery to be tested is obtained, and the health status of the battery to be tested is evaluated based on the target neural network model.

2. The battery health status assessment method according to claim 1, characterized in that: Determine the time constant corresponding to each peak in the time domain distribution diagram of the sample battery impedance spectrum, including: Obtaining the frequency domain distributed impedance spectrum of the sample battery; Based on the relaxation time distribution analysis method, the polarization impedance of the frequency domain distributed impedance spectrum is decomposed according to the relaxation time distribution algorithm, converted into a time domain distributed impedance spectrum, and a time domain distribution diagram of the impedance spectrum is generated; Determining peak values ​​of the time domain distribution diagram of the impedance spectrum; The time constant corresponding to the peak is calculated.

3. The battery health status assessment method according to claim 2, characterized in that: The formula for the relaxation time distribution algorithm is: ， in, Impedance function, is the time constant, is the time constant distribution function, is the ohmic internal resistance of the electrochemical system, is an imaginary unit, is the relaxed definite integral.

4. The battery health status assessment method according to claim 3, characterized in that: The calculation formula of the frequency point is: ， in, is the frequency, is the time constant.

5. The battery health status assessment method according to claim 4, characterized in that: Obtaining the dynamic impedance corresponding to the frequency point during the charging and discharging process of the sample battery, including: Charge and discharge the sample battery; The frequency change of the sample battery during the charging and discharging process is detected, and the dynamic impedance corresponding to each frequency point is recorded.

6. The battery health status assessment method according to claim 5, characterized in that: The neural network model is constructed with the battery dynamic impedance as input and the battery remaining capacity as output, including: Based on the radial basis function, a radial basis function layer of a neural network is constructed according to the battery dynamic impedance and the center point of the battery dynamic impedance; Based on the radial basis function neural network, the battery dynamic impedance is taken as input and the remaining capacity of the battery is taken as output, and a neural network model is constructed in combination with the radial basis function layer.

7. The battery health status assessment method according to claim 6, characterized in that: The expression of the radial basis function layer is: ， in, For the input samples, For the The center of the radial basis function, is the width parameter of the radial basis function.

8. A battery health status assessment device, characterized in that: include: A time constant confirmation module is used to determine the time constant corresponding to each peak in the time domain distribution diagram of the sample battery impedance spectrum; A dynamic impedance confirmation module, used to determine the frequency point corresponding to the peak value according to the time constant, and obtain the dynamic impedance corresponding to the frequency point during the charging and discharging process of the sample battery; A model generation module is used to obtain the remaining capacity of the sample battery, construct a neural network model with the battery dynamic impedance as input and the battery remaining capacity as output, and iteratively train the neural network model according to the dynamic impedance of the sample battery and the remaining capacity of the sample battery to obtain a fully trained target neural network model; The health status assessment module is used to obtain the dynamic impedance of the battery to be tested and to perform health status assessment on the battery to be tested based on the target neural network model.

9. An electronic device for evaluating the battery health status, characterized in that: It comprises a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the battery health status assessment method as claimed in any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: The storage medium stores computer program instructions, and when the computer program instructions are executed by a computer, the computer is enabled to execute the battery health status assessment method according to any one of claims 1 to 7.

Images