Lithium battery health state rapid assessment method and system

Abstract

The invention relates to a lithium battery health state rapid evaluation method and system. The method comprises the following steps: acquiring voltage, current and temperature of a lithium battery under different cycle lives collected by a sensor; calculating a charging capacity differential curve of the lithium battery according to the voltage and the current of the lithium battery; extracting characteristic parameters from the charging capacity differential curve; pre-processing the acquired temperature signal to obtain a pre-processed temperature; extracting a feature value of the preprocessed temperature, and calculating a correlation degree between the feature value of the temperature and the SOH value of the battery; constructing a training data set by using the temperature characteristic value with the maximum correlation degree and the battery SOH value corresponding to the characteristic parameter; inputting the training data set into a neural network model for training to obtain a battery SOH evaluation model; and evaluating the health state of the target lithium battery by using the battery SOH evaluation model. According to the method, the deep machine learning neural network model is adopted, the complex nonlinear relation between the feature parameters and the SOH can be automatically learned, and the generalization ability of the evaluation model is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of lithium battery health status assessment, and in particular to a method and system for rapid assessment of lithium battery health status. Background Art

[0002] With the advancement of technology and the increasing demand for sustainable development, lithium-ion batteries are increasingly used in fields such as drones, robots, electric vehicles, and energy storage systems. Lithium-ion batteries have become a core component of modern energy solutions due to their high energy density, long cycle life, and relatively low self-discharge rate. However, batteries will inevitably experience performance degradation during use, which makes accurate assessment of the battery's state of health (SOH) crucial.

[0003] SOH is a key indicator for evaluating the performance and safety of lithium-ion batteries, and is an important parameter that reflects the remaining service life and safety risks of batteries. Accurate evaluation of SOH can not only effectively improve the optimization decision of the battery management system (BMS), but also realize the cascade utilization of batteries, thereby extending the battery life cycle in different fields and reducing resource waste and environmental impact.

[0004] At present, traditional SOH evaluation methods usually rely on parameters such as battery capacity decay and internal resistance change. These methods infer the health status of the battery by periodically testing its actual capacity and internal resistance. However, the evaluation methods based on these characteristics have some obvious defects. For example, capacity decay measurement takes a lot of time and is significantly affected by the external environment, and the accuracy of the test results is often insufficient. In addition, the change of internal resistance may be affected by multiple factors such as temperature and current, making the SOH evaluation based on internal resistance unreliable. Summary of the invention

[0005] To solve the above problems, an object of the embodiments of the present invention is to provide a method and system for quickly evaluating the health status of a lithium battery.

[0006] A method for quickly evaluating the health status of a lithium battery, comprising: Step 1: Perform multiple charge and discharge cycle tests on the lithium battery; Step 2: Obtain the voltage, current and temperature of the lithium battery at different cycle lives collected by the sensor; Step 3: Calculate the charging capacity differential curve of the lithium battery according to the voltage and current of the lithium battery; Step 4: Extract characteristic parameters from the charge capacity differential curve; Step 5: preprocess the acquired temperature signal to obtain a preprocessed temperature; Step 6: Extract the characteristic value of the pre-processed temperature and calculate the correlation between the temperature characteristic value and the battery SOH value; Step 7: Construct a training data set using the battery SOH values ​​corresponding to the temperature characteristic values ​​and characteristic parameters with the greatest correlation degree; Step 8: Input the training data set into the neural network model for training to obtain the battery SOH evaluation model; Step 9: Use the battery SOH assessment model to complete the assessment of the health status of the target lithium battery.

[0007] Preferably, the step 4: extracting characteristic parameters from the charge capacity differential curve comprises: Step 4.1: Obtain a preset voltage interval containing a highest peak value in the charge capacity differential curve; Step 4.2: extracting the corresponding capacity difference from the preset voltage interval at equal voltage intervals; Step 4.3: Extract the voltage value of the starting point of the preset voltage interval; Step 4.4: Extract the total capacity corresponding to the preset voltage range; Step 4.5: Extract the peak position, peak height and peak area corresponding to the maximum peak from the charge capacity differential curve; Step 4.6: The capacity difference, the voltage value at the starting point, the corresponding total capacity within the preset voltage range, the peak position, peak height and peak area corresponding to the maximum peak are taken as characteristic parameters.

[0008] Preferably, the step 5: preprocessing the acquired temperature signal to obtain a preprocessed temperature includes: Step 5.1: Use the wavelet mother function to perform wavelet transform on the temperature signal to obtain the wavelet coefficients at each scale; Step 5.2: Get the maximum value of the wavelet coefficient at each scale; Step 5.3: Determine the threshold value according to the maximum value of the wavelet coefficient; Step 5.4: Process the wavelet coefficients that are greater than or equal to the threshold using the first threshold function; Step 5.5: Change the wavelet coefficients that are less than the threshold to 0; Step 5.6: Get the negative number of the threshold, and process the wavelet coefficients whose negative numbers are less than the threshold using the second threshold function to obtain the processed wavelet coefficients; Step 5.7: Reconstruct the processed wavelet coefficients to obtain the preprocessed temperature.

[0009] Preferably, the step 5.3: determining the threshold value according to the maximum value of the wavelet coefficients comprises: Step 5.3.1: Determine the correction coefficient according to the maximum value of the wavelet coefficient and the sum of the wavelet coefficients at each decomposition scale; Step 5.3.2: Determine a threshold using a correction factor; wherein the threshold is:

[0010] in, represents the proportionality coefficient, represents the maximum value of the kth wavelet coefficient at the jth scale, represents the number of wavelet coefficients at the jth scale, represents the standard deviation, represents the threshold value, Indicates the correction factor.

[0011] Preferably, in step 5.4, the wavelet coefficients greater than or equal to the threshold are processed using a first threshold function; wherein the first threshold function is:

[0012] in, represents the kth wavelet coefficient at the jth scale after processing, represents the kth wavelet coefficient at the jth scale, Represents the adjustment factor.

[0013] Preferably, in step 5.6, the wavelet coefficients that are negative numbers less than the threshold are processed using a second threshold function; wherein the second threshold function is:

[0014] in, represents the kth wavelet coefficient at the jth scale after processing, represents the kth wavelet coefficient at the jth scale, Represents the adjustment factor.

[0015] Preferably, the step 6: extracting the characteristic value of the pre-processed temperature and calculating the correlation between the temperature characteristic value and the battery SOH value includes: Step 6.1: Take a symmetrical interval centered on any point on the pre-treated temperature curve; Step 6.2: Take the temperature change rate, temperature mean, maximum temperature, minimum temperature and temperature amplitude of the symmetrical interval as temperature characteristic values; Step 6.3: Calculate the correlation between each temperature characteristic value and the battery SOH value; the correlation calculation formula is:

[0016] in, Indicates the degree of association, represents the i-th temperature eigenvalue, represents the mean of the temperature characteristic values, represents the i-th SOH value, Indicates the average value of SOH.

[0017] The present invention also provides a lithium battery health status rapid assessment system, comprising: A test module, used to perform multiple charge and discharge cycle tests on lithium batteries; A data acquisition module is used to obtain the voltage, current and temperature of the lithium battery at different cycle lives collected by the sensor; A charging capacity differential curve building module, used for calculating the charging capacity differential curve of the lithium battery according to the voltage and current of the lithium battery; A characteristic parameter extraction module, used to extract characteristic parameters from a charging capacity differential curve; A temperature preprocessing module, used to preprocess the acquired temperature signal to obtain a preprocessed temperature; A correlation degree calculation module is used to extract the characteristic value of the pre-processed temperature and calculate the correlation degree between the temperature characteristic value and the battery SOH value; A training data set construction module is used to construct a training data set using the temperature characteristic values ​​and battery SOH values ​​corresponding to the characteristic parameters with the greatest correlation degree; A training module is used to input the training data set into the neural network model for training to obtain a battery SOH evaluation model; The evaluation module is used to evaluate the health status of the target lithium battery using the battery SOH evaluation model.

[0018] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps in the above-mentioned method for rapidly assessing the health status of a lithium battery.

[0019] The invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned method for rapid assessment of the health status of a lithium battery are implemented.

[0020] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects: The present invention relates to a method for quickly evaluating the health status of a lithium battery. Compared with the prior art, the present invention adopts a deep machine learning neural network model, which can automatically learn the complex nonlinear relationship between characteristic parameters and SOH, thereby improving the generalization ability of the evaluation model.

[0021] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A flow chart of a method for quickly assessing the health status of a lithium battery in an embodiment of the present invention; Figure 2 This is a schematic diagram of a method for quickly assessing the health status of a lithium battery in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0025] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0026] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0027] See also Figure 1-2, a method for quickly evaluating the health status of a lithium battery, comprising: Step 1: Perform multiple charge and discharge cycle tests on the lithium battery; Step 2: Obtain the voltage, current and temperature of the lithium battery at different cycle lives collected by the sensor; Step 3: Calculate the charging capacity differential curve of the lithium battery according to the voltage and current of the lithium battery; Step 4: Extract characteristic parameters from the charge capacity differential curve; The peak value of the lithium battery charging capacity differential curve (△Q / △VV curve) can reflect the key characteristics of the battery's internal chemical reactions, material activity and aging process. In particular, the highest peak value (mainly including three main characteristics of peak position, peak height and peak area) can not only reflect the most important chemical reaction characteristics inside the battery, but also has a high correlation with the battery's full charge capacity.

[0028] The charge capacity differential curve (△Q / △VV curve) of lithium batteries reflects the capacity change of the battery at different voltages, where the peak corresponds to the phase change reaction inside the battery. As the battery ages, the active substances inside the battery decrease, the electrolyte decomposes, causing the phase change reaction to change, thus causing the peak of the charge IC curve to change.

[0029] Research shows that the differential curve of the charging capacity of lithium iron phosphate generally has only one peak (between 3.4V and 3.5V), while the differential curve of the charging capacity of ternary lithium batteries usually has multiple peaks, among which the highest peak (between 3.6V and 3.9V) has a high correlation with the maximum discharge capacity of the battery (i.e. SOH). As the battery ages, the voltage value of the peak will gradually decrease, the peak height will gradually decrease, and the peak area will also gradually decrease.

[0030] Furthermore, characteristic parameters are extracted from the charge capacity differential curve, including: Step 4.1: Obtain a preset voltage interval containing a highest peak value in the charge capacity differential curve; Step 4.2: extracting the corresponding capacity difference from the preset voltage interval at equal voltage intervals; In the embodiment of the present invention, a 0.4V voltage interval curve (20*0.02V=0.4V) containing the highest peak value is extracted from the charge capacity differential curve, and corresponding capacity differences are extracted at equal voltage intervals (0.02V). These differences reflect the capacity changes of the battery at different voltages.

[0031] Step 4.3: Extract the voltage value of the starting point of the preset voltage interval; Get the voltage value at the starting point of the 0.4V interval of the charge capacity differential curve.

[0032] Step 4.4: Extract the total capacity corresponding to the preset voltage range; Extract the total capacity corresponding to the 0.4V voltage interval (e.g. 3.4-3.8, or 3.5V-3.9V) from the charge capacity differential curve.

[0033] Step 4.5: Extract the peak position, peak height and peak area corresponding to the maximum peak from the charge capacity differential curve; Step 4.6: The capacity difference, the voltage value at the starting point, the corresponding total capacity within the preset voltage range, the peak position, peak height and peak area corresponding to the maximum peak are taken as characteristic parameters.

[0034] Step 5: preprocess the acquired temperature signal to obtain a preprocessed temperature; Furthermore, step 5 includes: Step 5.1: Use the wavelet mother function to perform wavelet transform on the temperature signal to obtain the wavelet coefficients at each scale; Step 5.2: Get the maximum value of the wavelet coefficient at each scale; Step 5.3: Determine the threshold value according to the maximum value of the wavelet coefficient; In step 5.3, include: Step 5.3.1: Determine the correction coefficient according to the maximum value of the wavelet coefficient and the sum of the wavelet coefficients at each decomposition scale; Step 5.3.2: Determine a threshold using a correction factor; wherein the threshold is:

[0035] in, represents the proportionality coefficient, represents the maximum value of the kth wavelet coefficient at the jth scale, represents the number of wavelet coefficients at the jth scale, represents the standard deviation of the noise, represents the threshold value, Indicates the correction factor.

[0036] In wavelet decomposition, the useful signal energy will be concentrated in a few larger coefficients, while the noise components will be more evenly distributed in the wavelet domain. When the value is large, it means that there are a small number of coefficients with large values ​​in this layer, indicating that this layer contains more useful signals; When the value is small, it means that there are a large number of coefficients with small values ​​in this layer, indicating that the layer contains more noise. The value increases as the noise content decreases. The traditional threshold value is modified.

[0037] From the above formula, we can see that As the number of layers increases, the threshold gradually decreases, which conforms to the general rule that noise decreases as the number of decomposition layers increases. It changes linearly with the noise content and is used to correct the estimated global noise, which is more consistent with the noise distribution of the disturbance signal in practice.

[0038] Step 5.4: Process the wavelet coefficients that are greater than or equal to the threshold using the first threshold function; In step 5.4, the wavelet coefficients greater than or equal to the threshold are processed using a first threshold function; wherein the first threshold function is:

[0039] in, represents the kth wavelet coefficient at the jth scale after processing, represents the kth wavelet coefficient at the jth scale, Represents the adjustment factor.

[0040] Step 5.5: Change the wavelet coefficients that are less than the threshold to 0; Step 5.6: Get the negative number of the threshold, and process the wavelet coefficients whose negative numbers are less than the threshold using the second threshold function to obtain the processed wavelet coefficients; In step 5.6, the wavelet coefficients that are negative numbers less than the threshold are processed using a second threshold function; wherein the second threshold function is:

[0041] in, represents the kth wavelet coefficient at the jth scale after processing, represents the kth wavelet coefficient at the jth scale, Represents the adjustment factor.

[0042] when When it approaches 0, the above threshold function is equivalent to the hard threshold function; when When it approaches positive infinity, it can be equivalent to a soft threshold function; therefore, the present invention can be adjusted The value of makes the above threshold function have the characteristics of both hard and soft threshold functions, so that it can more effectively suppress noise while retaining useful signals.

[0043] Step 5.7: Reconstruct the processed wavelet coefficients to obtain the preprocessed temperature.

[0044] Step 6: Extract the characteristic value of the pre-processed temperature and calculate the correlation between the temperature characteristic value and the battery SOH value; Furthermore, step 6 includes: Step 6.1: Take a symmetrical interval centered on any point on the pre-treated temperature curve; In the embodiment of the present invention, the symmetry interval is ±0.4.

[0045] Step 6.2: Take the temperature change rate, temperature mean, maximum temperature, minimum temperature and temperature amplitude of the symmetrical interval as temperature characteristic values; Step 6.3: Calculate the correlation between each temperature characteristic value and the battery SOH value; the correlation degree calculation formula is:

[0046] in, Indicates the degree of association, represents the i-th temperature characteristic value, represents the mean of the temperature characteristic values, represents the i-th SOH value, Indicates the average value of SOH.

[0047] Step 7: Construct a training data set using the battery SOH values ​​corresponding to the temperature characteristic values ​​and characteristic parameters with the greatest correlation degree; Step 8: Input the training data set into the neural network model for training to obtain the battery SOH evaluation model; The present invention adopts a fully connected neural network (FCNN) as an evaluation model, and uses a back propagation algorithm to train the FCNN model to obtain a battery SOH evaluation model.

[0048] Step 9: Use the battery SOH assessment model to complete the assessment of the health status of the target lithium battery.

[0049] According to the embodiments provided by the present invention, the present invention discloses the following technical effects: 1. The present invention utilizes the charge capacity differential curve (△Q / △VV curve) to extract the battery aging characteristic parameters, which can more comprehensively reflect the battery aging state and improve the SOH evaluation accuracy.

[0050] 2. The present invention adopts a deep machine learning neural network model, which can automatically learn the complex nonlinear relationship between feature parameters and SOH, and improve the generalization ability of the evaluation model.

[0051] 3. The method of the present invention is simple and easy to implement. By adopting the feature extraction of the local charge capacity differential curve in the 0.4V range and the deep neural network, it can quickly and accurately evaluate the SOH of the battery in a short time, and provide technical support for the optimization of the battery management system (BMS) and the cascade utilization of the battery.

[0052] The present invention also provides a lithium battery health status rapid assessment system, comprising: A test module, used to perform multiple charge and discharge cycle tests on lithium batteries; A data acquisition module is used to obtain the voltage, current and temperature of the lithium battery at different cycle lives collected by the sensor; A charging capacity differential curve building module, used for calculating the charging capacity differential curve of the lithium battery according to the voltage and current of the lithium battery; A characteristic parameter extraction module, used to extract characteristic parameters from a charging capacity differential curve; A temperature preprocessing module, used to preprocess the acquired temperature signal to obtain a preprocessed temperature; A correlation degree calculation module is used to extract the characteristic value of the pre-processed temperature and calculate the correlation degree between the temperature characteristic value and the battery SOH value; A training data set construction module is used to construct a training data set using the temperature characteristic values ​​and battery SOH values ​​corresponding to the characteristic parameters with the greatest correlation degree; A training module is used to input the training data set into the neural network model for training to obtain a battery SOH evaluation model; The evaluation module is used to evaluate the health status of the target lithium battery using the battery SOH evaluation model.

[0053] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps in the above-mentioned method for rapidly assessing the health status of a lithium battery. Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the method for rapidly assessing the health status of a lithium battery described in the above-mentioned technical solution, and are not elaborated herein.

[0054] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned method for quickly assessing the health status of a lithium battery are implemented. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present invention are the same as the beneficial effects of the method for quickly assessing the health status of a lithium battery described in the above-mentioned technical solution, which will not be repeated here.

[0055] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technical solution that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for rapid assessment of the health status of a lithium battery, characterized in that: include: Step 1: Perform multiple charge and discharge cycle tests on the lithium battery; Step 2: Obtain the voltage, current and temperature of the lithium battery at different cycle lives collected by the sensor; Step 3: Calculate the charging capacity differential curve of the lithium battery according to the voltage and current of the lithium battery; Step 4: Extract characteristic parameters from the charge capacity differential curve; Step 5: preprocess the acquired temperature signal to obtain a preprocessed temperature; Step 6: Extract the characteristic value of the pre-processed temperature and calculate the correlation between the temperature characteristic value and the battery SOH value; Step 7: Construct a training data set using the battery SOH values ​​corresponding to the temperature characteristic values ​​and characteristic parameters with the greatest correlation degree; Step 8: Input the training data set into the neural network model for training to obtain the battery SOH evaluation model; Step 9: Use the battery SOH assessment model to complete the assessment of the health status of the target lithium battery.

2. A method for rapid assessment of the health status of a lithium battery according to claim 1, characterized in that: The step 4: extracting characteristic parameters from the charge capacity differential curve includes: Step 4.1: Obtain a preset voltage interval containing a highest peak value in the charge capacity differential curve; Step 4.2: extracting the corresponding capacity difference from the preset voltage interval at equal voltage intervals; Step 4.3: Extract the voltage value of the starting point of the preset voltage interval; Step 4.4: Extract the total capacity corresponding to the preset voltage range; Step 4.5: Extract the peak position, peak height and peak area corresponding to the maximum peak from the charge capacity differential curve; Step 4.6: The capacity difference, the voltage value at the starting point, the corresponding total capacity within the preset voltage range, the peak position, peak height and peak area corresponding to the maximum peak are taken as characteristic parameters.

3. A method for rapid assessment of the health status of a lithium battery according to claim 2, characterized in that: The step 5: preprocessing the acquired temperature signal to obtain a preprocessed temperature, comprises: Step 5.1: Use the wavelet mother function to perform wavelet transform on the temperature signal to obtain the wavelet coefficients at each scale; Step 5.2: Get the maximum value of the wavelet coefficient at each scale; Step 5.3: Determine the threshold value according to the maximum value of the wavelet coefficient; Step 5.4: Process the wavelet coefficients that are greater than or equal to the threshold using the first threshold function; Step 5.5: Change the wavelet coefficients that are less than the threshold to 0; Step 5.6: Get the negative number of the threshold, and process the wavelet coefficients whose negative numbers are less than the threshold using the second threshold function to obtain the processed wavelet coefficients; Step 5.7: Reconstruct the processed wavelet coefficients to obtain the preprocessed temperature.

4. A method for rapid assessment of the health status of a lithium battery according to claim 3, characterized in that: The step 5.3: determining a threshold value according to the maximum value of the wavelet coefficients comprises: Step 5.3.1: Determine the correction coefficient according to the maximum value of the wavelet coefficient and the sum of the wavelet coefficients at each decomposition scale; Step 5.3.2: Determine a threshold using a correction factor; wherein the threshold is: ； in, represents the proportionality coefficient, represents the maximum value of the kth wavelet coefficient at the jth scale, represents the number of wavelet coefficients at the jth scale, represents the standard deviation, represents the threshold value, Indicates the correction factor.

5. A method for rapid assessment of the health status of a lithium battery according to claim 4, characterized in that: In step 5.4, the wavelet coefficients greater than or equal to the threshold are processed using a first threshold function; wherein the first threshold function is: ； in, represents the kth wavelet coefficient at the jth scale after processing, represents the kth wavelet coefficient at the jth scale, Represents the adjustment factor.

6. A method for rapid assessment of the health status of a lithium battery according to claim 4, characterized in that: In step 5.6, the wavelet coefficients that are negative numbers less than the threshold are processed using a second threshold function; wherein the second threshold function is: ； in, represents the kth wavelet coefficient at the jth scale after processing, represents the kth wavelet coefficient at the jth scale, Represents the adjustment factor.

7. A method for rapid assessment of lithium battery health status according to claim 1, characterized in that: The step 6: extracting the characteristic value of the pre-processed temperature and calculating the correlation between the temperature characteristic value and the battery SOH value includes: Step 6.1: Take a symmetrical interval centered on any point on the pre-treated temperature curve; Step 6.2: Take the temperature change rate, temperature mean, maximum temperature, minimum temperature and temperature amplitude of the symmetrical interval as temperature characteristic values; Step 6.3: Calculate the correlation between each temperature characteristic value and the battery SOH value; the correlation degree calculation formula is: ； in, Indicates the degree of association, represents the i-th temperature characteristic value, represents the mean of the temperature characteristic values, represents the i-th SOH value, Indicates the average value of SOH.

8. A lithium battery health status rapid assessment system, characterized in that: include: A test module, used to perform multiple charge and discharge cycle tests on lithium batteries; A data acquisition module is used to obtain the voltage, current and temperature of the lithium battery at different cycle lives collected by the sensor; A charging capacity differential curve building module, used for calculating the charging capacity differential curve of the lithium battery according to the voltage and current of the lithium battery; A characteristic parameter extraction module, used to extract characteristic parameters from a charging capacity differential curve; A temperature preprocessing module, used to preprocess the acquired temperature signal to obtain a preprocessed temperature; A correlation degree calculation module is used to extract the characteristic value of the pre-processed temperature and calculate the correlation degree between the temperature characteristic value and the battery SOH value; A training data set construction module is used to construct a training data set using the temperature characteristic values ​​and battery SOH values ​​corresponding to the characteristic parameters with the greatest correlation degree; A training module is used to input the training data set into the neural network model for training to obtain a battery SOH evaluation model; The evaluation module is used to evaluate the health status of the target lithium battery using the battery SOH evaluation model.

9. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the method for quickly assessing the health status of a lithium battery as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in a method for quickly assessing the health status of a lithium battery as described in any one of claims 1 to 7 are implemented.

Images