Battery health condition evaluation method and device based on lossless feature map, computer device, readable storage medium and program product

Abstract

The application relates to a battery health condition evaluation method and device based on a lossless feature map, a computer device, a readable storage medium and a program product. The method comprises the following steps: first, at least one target electrical parameter is screened from a plurality of initial electrical parameters based on a first current value and a first initial value of the plurality of initial electrical parameters; then, at least one target defect characterization parameter corresponding to the at least one target electrical parameter is determined based on the corresponding relationship between the electrical parameters and the defect characterization parameters of the battery; finally, the remaining life of the target battery is predicted based on the determined at least one target defect characterization parameter. In this way, all defect characterization parameters of the target battery do not need to be analyzed, and the remaining life of the target battery can be predicted only by analyzing the target defect characterization parameter, so that the prediction efficiency can be effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery evaluation, in particular to a battery health state evaluation method and device based on non-destructive feature map, computer equipment, readable storage medium and program product. BACKGROUND

[0002] In recent years, high-energy-density and high-power-density lithium ion batteries have been widely used in electric vehicles, smart grids and portable electronic devices. As a core technology of battery life cycle management, health state evaluation has become a key to ensure the safety of battery service and the utilization of the battery.

[0003] At present, CT (Computed Tomography) images of batteries are obtained by scanning the batteries with X-rays, and the health state of the batteries is evaluated, which has become a common technology for evaluating the health state of the batteries. However, this technology needs to analyze all material features and structural features of the batteries in the CT images, and the evaluation efficiency is low. SUMMARY

[0004] Therefore, it is necessary to provide a battery health state evaluation method and device based on non-destructive feature map, computer equipment, readable storage medium and program product, which can improve the evaluation efficiency of the battery health state.

[0005] In a first aspect, the present application provides a battery health state evaluation method based on non-destructive feature map, which comprises:

[0006] obtaining a current feature image of a target battery and first current values of a plurality of initial electrical parameters, and obtaining first initial values of the plurality of initial electrical parameters under the condition that the target battery is not used; wherein the current feature image is a non-destructive feature map of the target battery;

[0007] Based on the first current values and the first initial values, the current change rate of any one of the initial electrical parameters is obtained, and at least one target electrical parameter is selected from the plurality of initial electrical parameters based on the current change rate;

[0008] obtaining the corresponding relationship between the electrical parameters and the defect characterization parameters of the battery;

[0009] Based on the corresponding relationship, at least one target defect characterization parameter corresponding to the at least one target electrical parameter is determined, and a second current value of the target defect characterization parameter is determined based on the current feature image;

[0010] predict the remaining life of the target battery based on the second current value and a preset value range of the target defect characterization parameter; wherein the preset value range is a value range of the target defect characterization parameter when the target battery is in a healthy state.

[0011] In one of the embodiments, the at least one target electrical parameter is selected from the plurality of initial electrical parameters based on the current change rate, including:

[0012] The current change rates are sorted in descending order;

[0013] The initial electrical parameters corresponding to the first preset number of change rates in the sorting result are determined as the target electrical parameters.

[0014] In one of the embodiments, the correspondence between the electrical parameters and the defect characterization parameters of the battery is obtained, including:

[0015] In the process of performing the stress loading test on the sample battery, a first sample feature image and a first sample value of the plurality of initial electrical parameters of the sample battery are obtained at the beginning of the stress loading test, and a second sample feature image and a second sample value of the plurality of initial electrical parameters of the sample battery are obtained at the end of the stress loading test;

[0016] Based on the first sample value and the second sample value, a first sample change rate of any one of the initial electrical parameters in the stress loading test is obtained, and at least one sample electrical parameter is selected from the plurality of initial electrical parameters based on the first sample change rate;

[0017] For the plurality of initial defect characterization parameters, a third sample value of the initial defect characterization parameter in the first sample feature image and a fourth sample value of the initial defect characterization parameter in the second sample feature image are obtained;

[0018] Based on the third sample value and the fourth sample value, a second sample change rate of any one of the initial defect characterization parameters in the stress loading test is obtained, and at least one sample defect characterization parameter is selected from the plurality of initial defect characterization parameters based on the second sample change rate;

[0019] The at least one sample electrical parameter is determined as the electrical parameter corresponding to the at least one sample defect characterization parameter.

[0020] In one of the embodiments, the at least one sample electrical parameter is selected from the plurality of initial electrical parameters based on the first sample change rate, including:

[0021] The first sample change rates are sorted in descending order;

[0022] The initial electrical parameters corresponding to the first second preset number of change rates in the sorting result are determined as sample electrical parameters.

[0023] In one of the embodiments, based on the second sample change rate, at least one sample defect characterization parameter is selected from the plurality of initial defect characterization parameters, including:

[0024] For any one of the initial defect characterization parameters, a preset change rate range corresponding to the initial defect characterization parameter is obtained.

[0025] In the case that the second sample change rate of the initial defect characterization parameter is not within the preset change rate range, the initial defect characterization parameter is determined as a sample defect characterization parameter.

[0026] In one of the embodiments, based on the second current value and a preset value range of the target defect characterization parameter, the remaining life of the target battery is predicted, including:

[0027] For the target defect characterization parameter whose second current value is not within the corresponding preset value range, the number of the target defect characterization parameters and the feature type of the battery features characterized are determined.

[0028] Based on the number and the feature type, the failure risk level of the target battery is determined, and the remaining life of the target battery is predicted based on the failure risk level.

[0029] In a second aspect, the application further provides a battery health condition evaluation device based on non-destructive feature map, the device comprising:

[0030] A first acquisition module is configured to acquire a current feature image of a target battery and first current values of a plurality of initial electrical parameters, and to acquire first initial values of the plurality of initial electrical parameters in the case that the target battery is not used; wherein the current feature image is a non-destructive feature map of the target battery.

[0031] A second acquisition module is configured to acquire a current change rate of any one of the initial electrical parameters based on the first current values and the first initial values, and to select at least one target electrical parameter from the plurality of initial electrical parameters based on the current change rate.

[0032] A third acquisition module is configured to acquire a corresponding relationship between electrical parameters and defect characterization parameters of a battery.

[0033] A determination module is configured to determine at least one target defect characterization parameter corresponding to the at least one target electrical parameter based on the corresponding relationship, and to determine a second current value of the target defect characterization parameter based on the current feature image.

[0034] The prediction module is configured to predict the remaining life of the target battery based on the second current value and a preset value range of the target defect characterization parameter; and the preset value range is a value range of the target defect characterization parameter when the target battery is in a healthy state.

[0035] In a third aspect, the present application provides a computer device. The computer device comprises a memory and a processor. The memory stores a computer program. The processor executes the computer program to implement the steps of the method in any one of the above embodiments.

[0036] In a fourth aspect, the present application provides a computer readable storage medium. The computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the steps of the method in any one of the above embodiments.

[0037] In a fifth aspect, the present application provides a computer program product. The computer program product comprises a computer program. The computer program is executed by a processor to implement the steps of the method in any one of the above embodiments.

[0038] The above battery health condition evaluation method, device, computer device, readable storage medium and program product based on non-destructive feature map, acquire a current feature image of a target battery and first current values of a plurality of initial electrical parameters, and acquire first initial values of the plurality of initial electrical parameters when the target battery is not used; the current feature image is a non-destructive feature map of the target battery; based on the first current values and the first initial values, a current change rate of any one of the initial electrical parameters is acquired, and at least one target electrical parameter is selected from the plurality of initial electrical parameters based on the current change rate; a corresponding relationship between the electrical parameters and defect characterization parameters of the battery is acquired; based on the corresponding relationship, at least one target defect characterization parameter corresponding to the at least one target electrical parameter is determined, and a second current value of the target defect characterization parameter is determined based on the current feature image; the remaining life of the target battery is predicted based on the second current value and a preset value range of the target defect characterization parameter. The method provided by the present application first selects at least one target electrical parameter from a plurality of initial electrical parameters based on first current values and first initial values of the plurality of initial electrical parameters, then determines at least one target defect characterization parameter corresponding to the at least one target electrical parameter based on the corresponding relationship between the electrical parameters and defect characterization parameters of the battery, and finally predicts the remaining life of the target battery based on the at least one target defect characterization parameter determined, so that the remaining life of the target battery can be predicted by analyzing only the target defect characterization parameter without analyzing all defect characterization parameters of the target battery, thereby effectively improving the prediction efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application or the related art. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0040] Figure 1 A flowchart of a battery health condition evaluation method based on a non-destructive feature map in an embodiment;

[0041] Figure 2 A flowchart of a target electrical parameter screening method in an embodiment;

[0042] Figure 3 A flowchart of a battery health condition evaluation method based on a non-destructive feature map in another embodiment;

[0043] Figure 4 A block diagram of a battery health condition evaluation device based on a non-destructive feature map in an embodiment;

[0044] Figure 5 An internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of the present application clearer, the following will further describe the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0046] It should be noted that the terms "first", "second", etc. used in the present application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "include" and "have" and any variations thereof used in the present application are intended to cover non-exclusive inclusion. The term "multiple" used in the present application refers to two and more than two. The term "and / or" used in the present application refers to one of the solutions, or any combination of multiple solutions.

[0047] In an embodiment, as shown in Figure 1 A battery health condition evaluation method based on a non-destructive feature map is provided. The embodiment takes the method applied to a terminal as an example. It should be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and can be realized through the interaction of the terminal and the server. In the embodiment, the method includes the following steps:

[0048] S102. Obtain the current feature image of the target battery and the first current values ​​of various initial electrical parameters, and obtain the first initial values ​​of various initial electrical parameters when the target battery is not in use; wherein, the current feature image is the non-destructive feature map of the target battery.

[0049] Among them, various electrical parameters may include, but are not limited to, battery capacity decay, internal resistance / impedance, voltage, and rate performance; the first initial value is the value of the initial electrical parameters of the target battery in a healthy state; the non-destructive feature map of the battery refers to a set of two-dimensional or three-dimensional spatial data that can comprehensively reflect the internal structure, component distribution, and state parameters of the battery, obtained through non-destructive testing technology.

[0050] Optionally, the structural and material characteristics of the battery can be determined through the characteristic images of the battery, thereby identifying defects in the battery; the characteristic images can be, but are not limited to, CT images or neutron diffraction images.

[0051] S104. Based on the first current value and the first initial value, obtain the current rate of change of any initial electrical parameter, and select at least one target electrical parameter from multiple initial electrical parameters based on the current rate of change.

[0052] Optionally, the absolute value of the difference between the first current value and the first initial value is determined, and the ratio between the absolute value of this difference and the first initial value is determined as the current rate of change.

[0053] Optionally, by determining the current rate of change of different initial electrical parameters, the values ​​of different initial electrical parameters can be transformed to the same scale for comparison, thereby enabling a more accurate selection of at least one target electrical parameter that has the greatest impact on the current health status of the target battery from multiple initial electrical parameters.

[0054] S106. Obtain the correspondence between the battery's electrical parameters and defect characterization parameters.

[0055] Among them, the defect characterization parameters are used to characterize the material defects or structural defects of the battery. The defect characterization parameters may include, but are not limited to, battery cycle decay, lithium-ion diffusion coefficient, electrode material thickening, electrode bending angle and electrode gap.

[0056] Optionally, each correspondence corresponds to a type of battery failure behavior. The electrical parameters and defect characterization parameters in the correspondence are at least one electrical parameter and at least one defect characterization parameter that have the greatest impact on the battery in the corresponding failure behavior. Among them, the battery failure behavior refers to the phenomenon that the battery's performance (such as capacity, energy density, power output) is significantly reduced or completely lost due to material degradation, uncontrolled interface reaction, mechanical damage, etc. during charge-discharge cycles or use.

[0057] S108, determining at least one target defect characterization parameter corresponding to the at least one target electrical parameter based on the correspondence, and determining a second current value of the target defect characterization parameter based on the current feature image.

[0058] Optionally, the second current value of the target defect characterization parameter can be determined by analyzing the material characteristics and structural characteristics of the target battery in the current feature image.

[0059] Optionally, the current feature image can be input into a pre-trained convolutional neural network to output the second current value of the target defect characterization parameter; wherein the convolutional neural network comprises a feature extraction module and a Transformer structure.

[0060] S110, predicting the remaining life of the target battery based on the second current value and a preset value range of the target defect characterization parameter; wherein the preset value range is a value range of the target defect characterization parameter when the target battery is in a healthy state.

[0061] Optionally, the preset value range of the target defect characterization parameter can be but is not limited to: 5%~10% attenuation per cycle of the battery, lithium ion diffusion coefficient less than 10 -10 cm 2 s -1 , electrode material thickening 2%~5%, pole piece bending angle greater than 5°~10°, and pole piece gap increase of 10%~20%.

[0062] Optionally, the failure behavior of the target battery can be determined by judging whether the second current value of the target defect characterization parameter is within the corresponding preset value range, and the remaining life of the target battery can be predicted according to the determined failure behavior.

[0063] In the battery health condition evaluation method based on the nondestructive feature map, the first current values of the current feature image of the target battery and the plurality of initial electrical parameters are obtained, and the first initial values of the plurality of initial electrical parameters under the condition that the target battery is not used are obtained. The current change rate of any initial electrical parameter is obtained based on the first current values and the first initial values, and at least one target electrical parameter is selected from the plurality of initial electrical parameters based on the current change rate. The corresponding relationship between the electrical parameters and the defect characterization parameters of the battery is obtained. At least one target defect characterization parameter corresponding to the at least one target electrical parameter is determined based on the corresponding relationship, and the second current value of the target defect characterization parameter is determined based on the current feature image. The remaining life of the target battery is predicted based on the second current value and the preset value range of the target defect characterization parameter. The method provided in the application first selects at least one target electrical parameter from the plurality of initial electrical parameters based on the first current values and the first initial values of the plurality of initial electrical parameters, then determines at least one target defect characterization parameter corresponding to the at least one target electrical parameter based on the corresponding relationship between the electrical parameters and the defect characterization parameters of the battery, and finally predicts the remaining life of the target battery based on the at least one target defect characterization parameter determined, so that the remaining life of the target battery can be predicted by analyzing only the target defect characterization parameter without analyzing all defect characterization parameters of the target battery, thereby effectively improving the prediction efficiency.

[0064] In some embodiments, as shown in FIG. 2A, the at least one target electrical parameter is selected from the plurality of initial electrical parameters based on the current change rate, including: Figure 2

[0065] S202, the current change rates are sorted in descending order.

[0066] S204, the initial electrical parameters corresponding to the first preset number of change rates in the sorting result are determined as the target electrical parameters.

[0067] Optionally, the greater the current change rate, the greater the influence of the corresponding initial electrical parameter on the current health status of the target battery, and these initial electrical parameters need to be analyzed in the process of predicting the life of the target battery, so these initial electrical parameters are determined as the target electrical parameters.

[0068] In this embodiment, the current change rates are sorted in descending order, and the initial electrical parameters corresponding to the first preset number of change rates in the sorting result are determined as the target electrical parameters, so that the target electrical parameters with the greatest influence on the current health status of the target battery can be determined, thereby making the life prediction of the target battery more accurate.

[0069] ​In some embodiments, the correspondence between the electrical parameter and the defect characterization parameter of the battery is obtained by: obtaining, at a starting time of a stress loading test on a sample battery, a first sample feature image and first sample values of a plurality of initial electrical parameters of the sample battery, and obtaining, at an ending time of the stress loading test, a second sample feature image and second sample values of the plurality of initial electrical parameters; obtaining, based on the first sample values and the second sample values, a first sample change rate of any one of the initial electrical parameters in the stress loading test, and selecting, based on the first sample change rate, at least one sample electrical parameter from the plurality of initial electrical parameters; obtaining, for a plurality of initial defect characterization parameters, third sample values of the initial defect characterization parameters in the first sample feature image and fourth sample values of the initial defect characterization parameters in the second sample feature image; obtaining, based on the third sample values and the fourth sample values, a second sample change rate of any one of the initial defect characterization parameters in the stress loading test, and selecting, based on the second sample change rate, at least one sample defect characterization parameter from the plurality of initial defect characterization parameters; and determining the at least one sample electrical parameter as the electrical parameter corresponding to the at least one sample defect characterization parameter.

[0070] The stress loading test of the battery refers to a test method for simulating the mechanical action on the battery in actual use or extreme conditions by applying mechanical stress (such as compression, bending, stretching, vibration, etc.), and studying the electrochemical performance, structural integrity and safety of the battery.

[0071] Optionally, the sample electrical parameter and the sample defect characterization parameter are respectively the electrical parameter and the defect characterization parameter that change the most during the stress loading test. It can be considered that the sample electrical parameter and the sample defect characterization parameter have the greatest impact on the sample battery during the stress loading test, and thus it can be considered that the at least one sample electrical parameter and the at least one sample defect characterization parameter correspond to each other.

[0072] In this embodiment, by determining the at least one sample electrical parameter as the electrical parameter corresponding to the at least one sample defect characterization parameter, the correspondence between the electrical parameter and the defect characterization parameter of the battery can be more accurately determined, so that the life of the target battery can be more accurately predicted based on the correspondence.

[0073] In some embodiments, the at least one sample electrical parameter is selected from the plurality of initial electrical parameters based on the first sample change rate, including: sorting the first sample change rates in descending order; and determining the initial electrical parameters corresponding to the first second preset number of change rates in the sorting result as the sample electrical parameters.

[0074] Optionally, the greater the first sample change rate, the greater the influence of the corresponding initial electrical parameter on the health state of the sample battery during the stress loading test, and thus the initial electrical parameter is determined as the sample electrical parameter.

[0075] In this embodiment, the first sample change rates are sorted in descending order, and the initial electrical parameters corresponding to the first second preset number of change rates in the sorting result are determined as the sample electrical parameters, so that the sample electrical parameter with the greatest influence on the health state of the sample battery can be determined.

[0076] In some embodiments, based on the second sample change rate, at least one sample defect characterization parameter is selected from a plurality of initial defect characterization parameters, including: for any one initial defect characterization parameter, a preset change rate range corresponding to the initial defect characterization parameter is obtained; in a case where the second sample change rate of the initial defect characterization parameter is not within the preset change rate range, the initial defect characterization parameter is determined as the sample defect characterization parameter.

[0077] Optionally, the second sample change rate of the initial defect characterization parameter is not within the preset change rate range, indicating that the initial defect characterization parameter has a large change during the stress loading test, and thus it needs to be focused on and analyzed, and thus it is determined as the sample defect characterization parameter.

[0078] In this embodiment, for any one initial defect characterization parameter, a preset change rate range corresponding to the initial defect characterization parameter is obtained, and in a case where the second sample change rate of the initial defect characterization parameter is not within the preset change rate range, the initial defect characterization parameter is determined as the sample defect characterization parameter, so that the sample defect characterization parameter with the greatest influence on the health state of the sample battery can be determined.

[0079] In some embodiments, based on the second current value and a preset value range of the target defect characterization parameter, the remaining life of the target battery is predicted, including: for the target defect characterization parameter whose second current value is not within the corresponding preset value range, determining the number of target defect characterization parameters and the feature type of the battery feature represented thereby; determining the failure risk level of the target battery based on the number and the feature type, and predicting the remaining life of the target battery based on the failure risk level.

[0080] Optionally, the greater the number of target defect characterization parameters that are not within the corresponding preset value range, the worse the health condition of the target battery, the greater the failure risk, and the higher the failure risk level, and thus it can be determined that the remaining life of the target battery is shorter.

[0081] In this embodiment, based on the number of target defect characterization parameters and the feature type of the battery feature represented thereby, the remaining life of the target battery is predicted, so that the prediction result is more accurate.

[0082] In one embodiment, as shown in Figure 3 Another battery health condition assessment method based on non-destructive feature map is provided, which includes the following contents:

[0083] (1) S1: Multi-dimensional and multi-scale X-ray non-destructive characterization technology. High-resolution X-ray CT technology is used to characterize the battery body space in multiple dimensions, forming a structure and material property covering centimeter to sub-micron, providing a spatial resolution of up to 50 μm~0.5 μm, the X-ray energy can be adjusted in the range of 20 kV~220 kV, and the single scanning time is 15 minutes~120 minutes. Three-dimensional reconstruction technology and defect extraction algorithm of CT scanning graph are developed to realize intuitive simulation and analysis of material defects, with a reconstruction error of 1%~5% and a defect recognition accuracy of more than 95%~98%.

[0084] (2) S2: Sensitivity parameter identification and feature map association. The battery is attenuated by 5%~10% per cycle, the lithium ion diffusion coefficient is less than 10 -10 cm 2 s -1 , the electrode material thickens by 2%~5%, the electrode sheet bending angle is greater than 5°~10°, and the electrode sheet gap increases by 10%~20% are defined as failure threshold. Extract key parameters such as battery capacity attenuation, internal resistance / impedance, voltage, and rate performance as sensitive parameters. Based on the non-destructive feature map (such as electrode material expansion, electrode sheet bending, and electrode sheet gap), the corresponding relationship between the above parameters and CT non-destructive map is established.

[0085] (3) S3: Health state assessment model driven by artificial intelligence. The feature extraction module of convolutional neural network and the multi-task learning framework of Transformer structure are used to extract features and classify non-destructive characterization data. Combined with the failure mechanism of the battery, a three-way relationship model of "sensitive parameters-feature map-failure behavior" is constructed. Develop a battery safety evaluation model to predict the remaining life and failure risk level of the battery according to historical data and real-time input, and realize the deduction and risk quantification of the battery failure behavior. The overall prediction accuracy of the model is 95%~98%, and the average early warning time is 24 hours~48 hours before failure.

[0086] (4) S4: Experimental verification and optimization. A series of experiments are designed to verify the accuracy and reliability of the model, and through iterative optimization algorithm, the evaluation accuracy and efficiency are improved. The test set contains 500~1000 groups of battery operation data, and the average error of the remaining life predicted by the model is less than 10%~20%.

[0087] It should be understood that although each step in the flowchart involved in the above-described embodiments is shown in sequence according to the arrow, the steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowchart involved in the above-described embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time but can be executed at different times, and the execution of the steps or stages is not necessarily sequential but can be performed alternately or alternately with at least some of the other steps or steps or stages in other steps. It can be understood that the steps in different embodiments can be freely combined as needed, and various non-contradictory schemes formed by the combination are within the scope of protection of the present application.

[0088] Based on the same inventive concept, the embodiments of the present application also provide a non-destructive feature map-based battery health condition evaluation device for implementing the above-mentioned non-destructive feature map-based battery health condition evaluation method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more non-destructive feature map-based battery health condition evaluation device embodiments provided below can refer to the limitations of the non-destructive feature map-based battery health condition evaluation method described above, and will not be repeated here.

[0089] In one exemplary embodiment, as shown in Figure 4 A non-destructive feature map-based battery health condition evaluation device 400 is provided, comprising: a first acquisition module 401, a second acquisition module 402, a third acquisition module 403, a determination module 404, and a prediction module 405, wherein:

[0090] The first acquisition module 401 is configured to acquire a current feature image of the target battery and first current values of a plurality of initial electrical parameters, and to acquire first initial values of the plurality of initial electrical parameters when the target battery is not used; wherein the current feature image is a non-destructive feature map of the target battery.

[0091] The second acquisition module 402 is configured to acquire a current change rate of any one of the initial electrical parameters based on the first current values and the first initial values, and to select at least one target electrical parameter from the plurality of initial electrical parameters based on the current change rate.

[0092] The third acquisition module 403 is configured to acquire a correspondence between the electrical parameters of the battery and the defect characterization parameters.

[0093] The determining module 404 is configured to determine at least one target defect characterization parameter corresponding to the at least one target electrical parameter based on the correspondence, and determine a second current value of the target defect characterization parameter based on the current feature image.

[0094] The predicting module 405 is configured to predict the remaining life of the target battery based on the second current value and a preset value range of the target defect characterization parameter, wherein the preset value range is a value range of the target defect characterization parameter when the target battery is in a healthy state.

[0095] In some embodiments, the second obtaining module 402 is further configured to sort the current change rates in descending order, and determine the initial electrical parameters corresponding to the first preset number of change rates in the sorting result as the target electrical parameters.

[0096] In some embodiments, the third obtaining module 403 comprises:

[0097] The first obtaining unit is configured to obtain a first sample feature image of the sample battery and first sample values of the plurality of initial electrical parameters at a starting moment of the stress loading test, and obtain a second sample feature image of the sample battery and second sample values of the plurality of initial electrical parameters at an ending moment of the stress loading test.

[0098] The second obtaining unit is configured to obtain a first sample change rate of any one of the initial electrical parameters in the stress loading test based on the first sample values and the second sample values, and select at least one sample electrical parameter from the plurality of initial electrical parameters based on the first sample change rate.

[0099] The third obtaining unit is configured to obtain third sample values of the initial defect characterization parameters in the first sample feature image and fourth sample values of the initial defect characterization parameters in the second sample feature image for the plurality of initial defect characterization parameters.

[0100] The fourth obtaining unit is configured to obtain a second sample change rate of any one of the initial defect characterization parameters in the stress loading test based on the third sample values and the fourth sample values, and select at least one sample defect characterization parameter from the plurality of initial defect characterization parameters based on the second sample change rate.

[0101] The determining unit is configured to determine the at least one sample electrical parameter as an electrical parameter corresponding to the at least one sample defect characterization parameter.

[0102] In some embodiments, the second obtaining unit is further configured to sort the first sample change rates in descending order, and determine the initial electrical parameters corresponding to the second preset number of change rates in the sorting result as the sample electrical parameters.

[0103] In some embodiments, the fourth obtaining unit is further configured to, for any one of the initial defect characterization parameters, obtain a preset variation rate range corresponding to the initial defect characterization parameter; and in a case where the second sample variation rate of the initial defect characterization parameter is not within the preset variation rate range, determine the initial defect characterization parameter as the sample defect characterization parameter.

[0104] In some embodiments, the prediction module 405 is further configured to, for a target defect characterization parameter whose second current value is not within the corresponding preset value range, determine a quantity of the target defect characterization parameters and a feature type of the battery feature characterized by the target defect characterization parameters; determine a failure risk level of the target battery based on the quantity and the feature type, and predict the remaining life of the target battery based on the failure risk level.

[0105] The above various modules in the battery health condition assessment based on the nondestructive feature map can be realized by software, hardware, and combinations thereof, in whole or in part. The above various modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform the operations corresponding to the above various modules.

[0106] In one exemplary embodiment, a computer device is provided, which can be a terminal, and an internal structure diagram thereof can be as shown in Figure 5 The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to perform wired or wireless communication with external terminals, and the wireless communication can be achieved through WIFI, mobile cellular network, near field communication (NFC), or other technologies. The computer program is executed by the processor to implement a battery health condition assessment method based on a nondestructive feature map.

[0107] Those skilled in the art can understand that Figure 5The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0108] In an embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method embodiments when executing the computer program.

[0109] In an embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program implementing the steps in the above method embodiments when executed by a processor.

[0110] In an embodiment, a computer program product is provided, including a computer program, and the computer program implementing the steps in the above method embodiments when executed by a processor.

[0111] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0112] Those skilled 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. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0113] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present application.

[0114] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A battery state of health assessment method based on lossless feature map, characterized in that, The method comprises: obtaining a current characteristic image of a target battery and first current values of a plurality of initial electrical parameters, and obtaining first initial values of the plurality of initial electrical parameters in a case where the target battery is not used; wherein the current characteristic image is a non-destructive characteristic spectrum of the target battery; based on the first current values and the first initial values, obtaining a current change rate of any one of the initial electrical parameters, and based on the current change rate, screening at least one target electrical parameter from the plurality of initial electrical parameters; obtaining a corresponding relationship between electrical parameters and defect characterization parameters of the battery; based on the corresponding relationship, determining at least one target defect characterization parameter corresponding to the at least one target electrical parameter, and based on the current characteristic image, determining second current values of the target defect characterization parameters; based on the second current values and a preset value range of the target defect characterization parameters, predicting a remaining life of the target battery; wherein the preset value range is a value range of the target defect characterization parameters in a case where the target battery is in a healthy state; the method further comprises:

2. The method of claim 1, wherein, determining a number of the target defect characterization parameters and a feature type of a battery feature represented by the target defect characterization parameters, for the target defect characterization parameters whose second current values are not within the corresponding preset value range; determining a failure risk level of the target battery based on the number and the feature type, and predicting the remaining life of the target battery based on the failure risk level. the method further comprises: sorting the current change rates in descending order; 3. The method of claim 1, wherein, determining the initial electrical parameters corresponding to the first preset number of change rates in the sorting result as the target electrical parameters. the method further comprises: in a process of performing a stress loading test on a sample battery, obtaining a first sample characteristic image of the sample battery and first sample values of the plurality of initial electrical parameters at a start time of the stress loading test, and obtaining a second sample characteristic image of the sample battery and second sample values of the plurality of initial electrical parameters at an end time of the stress loading test; based on the first sample values and the second sample values, obtaining a first sample change rate of any one of the initial electrical parameters in the stress loading test, and based on the first sample change rate, screening at least one sample electrical parameter from the plurality of initial electrical parameters; for a plurality of initial defect characterization parameters, obtaining third sample values of the initial defect characterization parameters in the first sample characteristic image and fourth sample values of the initial defect characterization parameters in the second sample characteristic image; obtaining a second sample change rate of any one initial defect characterization parameter in the stress loading test based on the third sample value and the fourth sample value, and screening at least one sample defect characterization parameter from the plurality of initial defect characterization parameters based on the second sample change rate; determining the at least one sample electrical parameter as an electrical parameter corresponding to the at least one sample defect characterization parameter.

4. The method of claim 3, wherein, The screening of the at least one sample electrical parameter from the plurality of initial electrical parameters based on the first sample change rate comprises: sorting the first sample change rates in descending order; determining the initial electrical parameters corresponding to the first sample change rates in the top second preset number as the sample electrical parameters.

5. The method of claim 3, wherein, The screening of the at least one sample defect characterization parameter from the plurality of initial defect characterization parameters based on the second sample change rate comprises: obtaining a preset change rate range of any one initial defect characterization parameter; determining the initial defect characterization parameter as the sample defect characterization parameter in a case where the second sample change rate of the initial defect characterization parameter is not within the preset change rate range.

6. A device for battery state of health estimation based on lossless feature map, characterized in that, The device comprises: a first obtaining module configured to obtain a current feature image of a target battery and first current values of a plurality of initial electrical parameters, and obtain first initial values of the plurality of initial electrical parameters in a case where the target battery is not used, wherein the current feature image is a non-destructive feature spectrum of the target battery; a second obtaining module configured to obtain a current change rate of any one initial electrical parameter based on the first current values and the first initial values, and screen at least one target electrical parameter from the plurality of initial electrical parameters based on the current change rate; a third obtaining module configured to obtain a correspondence between electrical parameters and defect characterization parameters of a battery; a determining module configured to determine at least one target defect characterization parameter corresponding to the at least one target electrical parameter based on the correspondence, and determine a second current value of the target defect characterization parameter based on the current feature image; a predicting module configured to predict a remaining life of the target battery based on the second current value and a preset value range of the target defect characterization parameter, wherein the preset value range is a value range of the target defect characterization parameter in a case where the target battery is in a healthy state; The predicting module is further configured to, for a target defect characterization parameter whose second current value is not within a corresponding preset value range, determine a quantity of the target defect characterization parameter and a feature type of a battery feature represented by the target defect characterization parameter, determine a failure risk level of the target battery based on the quantity and the feature type, and predict the remaining life of the target battery based on the failure risk level. 7.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-6 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 5.

9. A computer program product comprising a computer program, characterized in that, The computer program, which is executed by a processor, implements the steps of the method according to any one of claims 1 to 5.

Images