Battery life prediction and management system and method based on cycle life modeling

Abstract

The invention discloses a battery life prediction and management system and method based on cycle life modeling, and relates to the technical field of data processing, and the method comprises the steps: collecting and preprocessing battery capacity data in a battery cycle charging process; analyzing change characteristics of battery capacities on two sides of an inflection point in a battery capacity fading process to construct a local nonlinear degradation index; analyzing the difference between a distinguishing inflection point and a capacity regeneration phenomenon in a battery capacity attenuation process based on the local nonlinear degradation index, and constructing an asymmetric attenuation index; based on the asymmetric attenuation index, analyzing the change characteristics of the inflection point in the global situation, and constructing an inflection point significance index; and marking the cycle charging data of the battery based on the inflection point significant index, and taking the marked cycle charging data as a label in a random forest algorithm to predict the service life of the battery. According to the method and the device, the problem of inaccurate inflection point detection caused by the fact that a fixed method for presetting empirical parameters is weak in generalization ability and cannot adapt to complex and changeable actual scenes is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a battery life prediction and management system and method based on cycle life modeling. BACKGROUND

[0002] With the rapid development of electric vehicles, energy storage power stations and consumer electronics, lithium-ion batteries as core energy storage elements have been widely used. The performance of the battery will be irreversibly degraded with use and time, and its cycle life is limited. When the battery capacity decays to a certain extent, it will not meet the normal use requirements, and even may cause safety hazards. Therefore, accurate prediction and management of the health status and remaining useful life of the battery are of vital importance to ensure the safe and reliable operation of the equipment, implement predictive maintenance and reduce the life cycle cost.

[0003] During the decay process of the battery capacity, the formation and growth of the SEI film will cause the nonlinear decay of the battery capacity, resulting in an inflection point in the decay of the battery capacity. Before the inflection point, the battery capacity slowly decreases, and the maintenance frequency can be low. After the inflection point, the battery capacity will rapidly decrease, and the battery needs to be frequently maintained or replaced. That is, the battery capacity has different decay characteristics before and after the inflection point, so different models need to be used for accurate prediction of the battery life. In existing methods, the inflection point of the battery capacity change is usually detected by methods relying on preset empirical parameters, such as decay rate threshold, capacity threshold, etc. However, the battery capacity decay data is usually affected by various factors, such as temperature change, number of charge and discharge cycles, measurement error, etc., and the working conditions and models of different batteries are also different. For example, the decay rate threshold at room temperature may not be applicable at low temperature, making the method relying on fixed preset empirical parameters weak in generalization ability and unable to adapt to complex and variable actual scenarios, ultimately leading to inaccurate detection of the inflection point and difficulty in meeting the actual battery management requirements.

[0004] Therefore, the present application provides a battery life prediction and management system and method based on cycle life modeling. SUMMARY

[0005] The present application aims to provide a battery life prediction and management system and method based on cycle life modeling to solve the problems raised in the background.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical solution: a battery life prediction and management system based on cycle life modeling, comprising: a data preprocessing module for collecting and preprocessing battery capacity data during the battery cycle charging process; A local nonlinear degradation index calculation module analyzes the change characteristics of the battery capacity on both sides of the inflection point in the battery capacity attenuation process to construct a local nonlinear degradation index; An asymmetric attenuation index calculation module analyzes the difference between the inflection point and the capacity regeneration phenomenon in the battery capacity attenuation process based on the local nonlinear degradation index to construct an asymmetric attenuation index. An inflection point significant index calculation module analyzes the change characteristics of the inflection point in the global based on the asymmetric attenuation index to construct an inflection point significant index. A battery life prediction module labels the battery cycle charging data based on the inflection point significant index, takes the label as a tag in a random forest algorithm, and realizes the life prediction of the battery.

[0007] The data preprocessing module further improves the battery test system to perform full life cycle cycle aging tests on multiple groups of lithium ion batteries of the same type, including recording the charge and discharge curve of each cycle at a high sampling frequency, using the ampere-hour integral method to time integrate the current in the discharge process, and constructing an original time series data set with the charge and discharge cycle number as the independent variable and the battery capacity as the dependent variable.

[0008] The local nonlinear degradation index is used to reflect the significance of the nonlinear degradation trend of the battery capacity in a local time window, and the construction process of the local nonlinear degradation index includes: Taking the tth cycle charging process as the center, a window with a total length of is recorded as a monitoring window, and the sequence composed of the battery capacity data in the monitoring window is recorded as a battery capacity local monitoring sequence; the sequence is taken as the input of the least square method for linear fitting, and the output is the linear equation after fitting; based on the linear equation, the battery capacity fitting value under different charging times is obtained, the difference between the battery capacity and the battery capacity fitting value is recorded as the fitting residual, the sequence composed of the fitting residual is recorded as the fitting residual sequence, and then the local nonlinear degradation index is obtained.

[0009] The local nonlinear degradation index calculation formula is expressed as: ; Wherein represents the local nonlinear degradation index of the tth cycle charging, represents the maximum value of the absolute value of all elements in the fitting residual sequence, ln() represents the logarithmic function with the natural constant as the base, and is used for smoothing the data in the parentheses, represents the standard deviation of the fitting residual sequence, represents the mean value of the absolute value of all elements in the fitting residual sequence, and 1 represents a hyperparameter, which is used to avoid the result after taking the logarithm is less than 0.

[0010] The application further improves that the asymmetric attenuation index calculation module records the sequence composed of the local nonlinear degradation indexes in the monitoring window as a local nonlinear degradation index monitoring sequence after calculating the local nonlinear degradation index after each charging; the center point of the local battery capacity monitoring sequence is taken as a segmentation point, and the local battery capacity monitoring sequence is segmented into a first sub-sequence and a second sub-sequence to obtain an asymmetric attenuation index.

[0011] The application further improves that the asymmetric attenuation index is calculated as follows: ; Wherein represents the asymmetric attenuation index of the tth cycle charging, represents the mean value of the local nonlinear degradation index monitoring sequence, and respectively represent the range of the first sub-sequence and the second sub-sequence, represents a hyperparameter.

[0012] The application further improves that the inflection point significant index calculation module is used to record the sequence composed of the asymmetric attenuation indexes of all battery capacity data as an asymmetric attenuation index sequence after calculating the asymmetric attenuation index of the battery capacity data after each charging, take the asymmetric attenuation index sequence as the input of the AMPD peak detection algorithm, and output the peak point of the sequence; the total number of the obtained peak points is recorded as K; taking the kth peak point as an example, a neighborhood with the kth peak point as the center and a width of D is recorded as a peak neighborhood to obtain an inflection point significant index.

[0013] The application further improves that the inflection point significant index is constructed as follows: ; Wherein represents the inflection point significant index of the kth peak point in the asymmetric attenuation index sequence, represents the asymmetric attenuation index of the kth peak point, and D represents the width of the peak neighborhood, represents the Euclidean distance between the charging number corresponding to the s th battery capacity data in the peak neighborhood and the charging number corresponding to the kth peak point, represents the asymmetric attenuation index of the s th battery capacity data in the peak neighborhood.

[0014] The application further improves that the battery life prediction module is used for taking the charge number with the maximum inflection point significant index in the whole life cycle of the battery life as the inflection point of the battery life, taking the area before the inflection point as the slow degradation area, and taking the area after the inflection point as the accelerated degradation area; taking the area where the data point is located as the label of the data point, extracting the feature vector of the data point, taking the feature vectors of all data points and the labels as the inputs of the random forest algorithm, training the decision tree in the random forest, after the training is completed, taking the feature vector of the battery capacity data to be predicted as the input of the random forest algorithm after the training is completed, and outputting the classification result of the battery capacity data, that is, the slow degradation area and the accelerated degradation area.

[0015] In another aspect, the application provides a battery life prediction and management method based on cycle life modeling, comprising the following steps: Step S1: collecting battery capacity data in the battery cycle charging process and preprocessing; Step S2: analyzing the change characteristics of the battery capacity on both sides of the inflection point in the battery capacity attenuation process to construct a local nonlinear degradation index; Step S3: analyzing the difference between the inflection point and the capacity regeneration phenomenon in the battery capacity attenuation process based on the local nonlinear degradation index to construct an asymmetric attenuation index; Step S4: analyzing the change characteristics of the inflection point in the global based on the asymmetric attenuation index to construct an inflection point significant index; Step S5: labeling the battery cycle charging data based on the inflection point significant index, taking it as the label in the random forest algorithm, and realizing the life prediction of the battery.

[0016] Compared with the prior art, the application has the following beneficial effects: 1. The application first analyzes the change characteristics of the battery capacity on both sides of the inflection point in the battery capacity attenuation process, constructs a local nonlinear degradation index according to the change of the residual error, analyzes the asymmetric change of the attenuation rate before and after the inflection point, identifies the change characteristics of the battery capacity regeneration phenomenon and the real inflection point, and further constructs an asymmetric attenuation index for distinguishing the capacity regeneration phenomenon and the inflection point; 2. The inflection point significant index is constructed by analyzing the isolation of the inflection point in the global, analyzing the difference between the peak point of the asymmetric attenuation index and other points in the neighborhood, evaluating the significant degree of the isolation of the candidate peak point, and avoiding the judgment error of the inflection point caused by the pseudo-peak of the local strong disturbance; 3. The inflection point is identified based on the inflection point significant index, the battery capacity data is labeled, and the feature vector is extracted as the input of the random forest algorithm, the decision tree is trained, and then the accurate classification of the battery capacity change is realized, different prediction models are used based on the classification result, the high-precision and high-robustness division and prediction of the battery health state stage are realized, and reliable decision basis is provided for the predictive maintenance and management of the battery life. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 A battery life prediction and management system framework based on cycle life modeling is provided. Figure 2 A battery life prediction and management method flowchart based on cycle life modeling is provided. DETAILED DESCRIPTION

[0018] The technical solutions of the present application will be described in detail below with the help of the drawings and specific embodiments. It should be understood that the embodiments and specific features in the embodiments are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application. In the case of no conflict, the technical features in the embodiments and the embodiments can be combined with each other.

[0019] The term "and / or" is only a description of the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent three cases of A alone, A and B together, and B alone.

[0020] Embodiment 1 Figure 1 A battery life prediction and management system framework based on cycle life modeling is disclosed in the present embodiment, which comprises: The data preprocessing module collects and preprocesses the battery capacity data in the battery cycle charging process; the data is obtained through battery cycle test experiment, and the specific steps are as follows: a high-precision battery test system is used to test a plurality of groups of lithium ion batteries of the same type for full life cycle cycle aging test. The test is carried out in a constant temperature and humidity box to eliminate the interference of environmental temperature. Standard constant current-constant voltage charging and constant current discharging mode is adopted. Through the voltage and current sensors directly communicating with the battery management system, the charge and discharge curves of each cycle are recorded at a high sampling frequency. The current during discharging is time-integrated using ampere-hour integration method, and the current actual capacity corresponding to each cycle period is accurately calculated. Thus, the original time series data set with the number of charge and discharge cycles as the independent variable and the battery capacity as the dependent variable is constructed.

[0021] After obtaining the original data set, necessary preprocessing is required to eliminate abnormal data and noise interference. First, the outlier detection method based on the R- criterion is used to eliminate extreme abnormal capacity values caused by accidental device communication interruption or sensor jump. Subsequently, in order to smooth the local capacity jitter caused by measurement noise and slight working condition fluctuations, while preserving the macro trend of capacity degradation, the application adopts the Savitzky-Golay filtering algorithm to smooth the capacity sequence. This method can effectively filter out noise while accurately preserving the shape, width and peak value of the curve, etc. key features, providing a high-quality data basis for subsequent calculation.

[0022] A local nonlinear degradation index calculation module analyzes the change characteristics of the battery capacity on both sides of the inflection point in the battery capacity attenuation process to construct a local nonlinear degradation index. In the process of battery capacity attenuation, before the inflection point, the degradation is dominated by relatively single and stable electrochemical mechanisms such as SEI film growth, and the capacity decline trend shows a high degree of local linearity or quasi-linearity, and the decay rate changes gently. After the inflection point, various mechanisms such as lithium extraction from the negative electrode are coupled to dominate, and the degradation enters another accelerated phase with a faster rate but also a relatively stable rate. The inflection point is an unstable transition point between the two stable states, so the battery capacity change before and after the inflection point can be better fitted by a linear change trend, and the effect of linear fitting on the battery capacity change near the inflection point is poor.

[0023] Based on the above analysis, the application constructs a local nonlinear degradation index to reflect the significance of the nonlinear degradation trend of the battery capacity within a local time window. The construction process of the local nonlinear degradation index is as follows: Taking the tth cycle charging process as an example, the tth cycle charging process is taken as the center, and the total length of the window is The window is called a monitoring window, and the size of L is 10 in this application, which can be selected according to the situation. The sequence composed of the battery capacity data in the monitoring window is called the battery capacity local monitoring sequence. The sequence is input into the least squares method for linear fitting, and the output is the linear equation after fitting. Based on the linear equation, the battery capacity fitting value at different charging times is obtained, and the difference between the battery capacity and the fitting value is called the fitting residual. The sequence composed of the fitting residual is called the fitting residual sequence. The least squares method is a known technology, which will not be described here.

[0024] Based on the above processing steps, the calculation method of the local nonlinear degradation index in the application is as follows: ; Where represents the local nonlinear degradation index of the tth cycle charging, represents the maximum value of the absolute value of all elements in the fitting residual sequence, ln() represents the logarithmic function with the natural constant as the base, and is used for smoothing the data in the parentheses, represents the standard deviation of the fitting residual sequence, represents the mean value of the absolute value of all elements in the fitting residual sequence, 1 represents a hyperparameter, and is used to avoid The result after taking the logarithm is less than 0, which can be selected according to the situation.

[0025] In the degradation process of the battery capacity, if the tth cycle charging is the inflection point of the battery capacity change, the change rate of the battery capacity on both sides of the inflection point has a significant difference, so that the fitting effect of the fitted linear equation on the local monitoring sequence of the battery capacity is worse, and the residual term is larger, corresponding is larger; when using the least square method for linear fitting, the fitted straight line will pass through the middle part of the data, and if the inflection point characteristics of t time are more obvious, the change characteristics of the concave function are more significant, so that when the fitted straight line crosses the battery capacity change curve, a smaller residual is generated near the intersection point, and a larger residual is generated at other points, corresponding to the larger standard deviation of the fitting residual sequence, the mean value of the absolute value of all elements in the fitting residual sequence, so that the finally calculated local nonlinear degradation index is larger.

[0026] The asymmetric attenuation index calculation module analyzes the difference between the inflection point and the capacity regeneration phenomenon in the battery capacity attenuation process based on the local nonlinear degradation index, and constructs an asymmetric attenuation index. In the degradation process of the battery capacity, due to the physical rebalancing process inside the battery during static or rest, the battery capacity appears regeneration phenomenon, such as the redistribution and diffusion of active lithium ions inside the electrode material, so that part of the temporarily inactive lithium ions can participate in the electrochemical reaction again, which macroscopically shows a temporary and small amplitude rise in the long-term decay trend of the capacity, and may show the change characteristics of the inflection point in the local monitoring window. The inflection point is an irreversible turning point of the state adjustment, which marks the irreversible turning point of the dominant degradation mechanism inside the battery, which is usually from the linear degradation dominated by the slow growth of SEI film to the nonlinear malignant degradation with self-accelerating effect caused by negative electrode lithium precipitation. That is, capacity regeneration is a reversible and local physical state adjustment, which does not change the long-term degradation rate of the battery, while the inflection point is an irreversible and global opening of the electrochemical failure mode, which permanently and significantly increases the degradation rate of the battery.

[0027] The local nonlinear degradation index obtained by the above steps reflects the linear degradation rule of the battery capacity in a local monitoring window, and needs to further distinguish the battery capacity regeneration phenomenon from the true inflection point of the battery capacity. Therefore, based on the local nonlinear degradation index, an asymmetric attenuation index is constructed in the application, and the construction process is as follows: The local nonlinear degradation index after each charging is calculated according to the above steps, and a sequence composed of the local nonlinear degradation indexes in the monitoring window is recorded as a local nonlinear degradation index monitoring sequence. The center point of the local battery capacity monitoring sequence is taken as a segmentation point, and the local battery capacity monitoring sequence is segmented into a first subsequence and a second subsequence.

[0028] Based on the above processing steps, the calculation method of the asymmetric attenuation index in the application is as follows: ; Among them, denotes the asymmetric attenuation index of the tth cycle charging, denotes the mean value of the local nonlinear degradation index monitoring sequence, and denote the range of the first subsequence and the second subsequence respectively, denotes a hyperparameter, which is used to avoid the denominator being zero to cause the calculation to be impossible. In the application, the value is 0.1, which can be selected according to the situation.

[0029] When the battery capacity regeneration phenomenon occurs, although the change of the battery capacity will also show the shape characteristics of the concave function, so that the calculated local nonlinear degradation index is relatively large, it is only a small upward trend in the long-term attenuation trend, and after the upward trend, it will slowly decrease, which is different from the rapid downward trend after the inflection point. That is, when the battery capacity regeneration phenomenon occurs, the difference between the range of the first subsequence and the range of the second subsequence is relatively small, so that is small, so that the finally calculated asymmetric attenuation index is small; if the battery capacity reaches the true inflection point, before the inflection point, the battery capacity slowly decreases, and after the inflection point, the battery capacity rapidly decreases, so that the battery capacity data near the inflection point does not satisfy the linear degradation characteristics, the corresponding local nonlinear degradation index is large, and the range of the second subsequence will be significantly larger than the range of the first subsequence, corresponding to is large, so that the finally calculated asymmetric attenuation index is large.

[0030] An inflection point significant index calculation module is configured to analyze the change characteristics of the inflection point in the whole based on the asymmetric attenuation index, and construct an inflection point significant index. In the full life cycle of the battery, the inflection point of the battery capacity change is an isolated and significant time, the asymmetric decay index obtained by the above steps reflects the similarity between the local change characteristics and the inflection point characteristics of the battery capacity, and therefore for the global battery capacity data, the asymmetric decay index near the inflection point will have a significant isolated peak value. In the actual charging and discharging process, some battery capacity data may be disturbed due to noise factors, causing the asymmetric decay index to have a false peak value, and if the charging number corresponding to the maximum asymmetric decay index is directly selected as the inflection point, a misjudgment may occur. Therefore, the inflection point significance index is constructed based on the asymmetric decay index in the present application, which is used to identify the true inflection point of the battery capacity change, and the construction process of the inflection point significance index is as follows: According to the same processing as described above, the asymmetric decay index of the battery capacity data after each charging is calculated, and the sequence formed by the asymmetric decay indices of all battery capacity data is denoted as the asymmetric decay index sequence, which is used as the input of the AMPD peak value detection algorithm, and the output is the peak value point of the sequence. The total number of peak value points obtained is denoted as K, and the kth peak value point is taken as an example. The neighborhood with the kth peak value point as the center and the width D is denoted as the peak value neighborhood. The AMPD peak value detection algorithm is a known technology, and will not be described here.

[0031] Based on the above processing steps, the construction process of the inflection point significance index in the present application is as follows: ; Wherein represents the inflection point significance index of the kth peak value point in the asymmetric decay index sequence, represents the asymmetric decay index of the kth peak value point, and D represents the width of the peak value neighborhood, which is 10 in the present application and can be selected according to the situation, represents the Euclidean distance between the charging number corresponding to the s th battery capacity data in the peak value neighborhood and the charging number corresponding to the kth peak value point, represents the asymmetric decay index of the s th battery capacity data in the peak value neighborhood.

[0032] If the battery capacity reaches the inflection point, the asymmetric decay index of the peak value point will be significantly greater than that of other points in the peak value neighborhood, i.e. significantly greater than , so that the calculated inflection point significance index is larger; if the peak value of the obtained asymmetric decay index is noise or random disturbance, the significance of the asymmetric decay index of the peak value point compared with other points in the peak value neighborhood is weaker, i.e. will not be significantly greater than , so that the calculated inflection point significance index is smaller.

[0033] The battery life prediction module labels the battery cycle charging data based on the inflection point significance index, takes the label as the random forest algorithm, and realizes the life prediction of the battery.

[0034] In the data set, the charging number with the maximum inflection point significance index in the whole life cycle of the battery life is taken as the inflection point of the battery life, the area before the inflection point is recorded as the slow degradation area, and the area after the inflection point is recorded as the accelerated degradation area. The area where the data point is located is taken as the label of the data point, and the feature vector of the data point is extracted. The feature vectors and labels of all data points are taken as the input of the random forest algorithm. The decision tree in the random forest is trained. After the training is completed, the feature vector of the battery capacity data to be predicted is extracted as the input of the trained random forest algorithm, and the output is the classification result of the battery capacity data, that is, the slow degradation area and the accelerated degradation area. The data point is the battery capacity under the charging number, and the feature vector of the data point is a vector composed of the local nonlinear degradation index, the asymmetric attenuation index and the battery capacity value.

[0035] If the classification result of the battery capacity data to be predicted is the slow degradation area, the capacity attenuation in this area is gentle, the trend is close to linear, and the noise influence is relatively controllable, so the autoregressive model with simple calculation and stable performance can be selected to predict the battery life. If the classification result of the battery capacity data to be predicted is the accelerated degradation area, the battery capacity attenuation speed in this area is fast, and the nonlinear feature is significant, so the Gaussian process regression model with strong nonlinear mapping capability is selected to predict the battery life. At this time, the battery capacity has appeared accelerated attenuation, and the chance may affect the use of the equipment, so a targeted alarm is sent to remind the relevant staff to replace and process in time.

[0036] Through the above steps, the attenuation characteristics of the battery capacity in different stages are segmented and modeled and predicted, and high-precision prediction and management of the battery life are realized.

[0037] The threshold value and weight setting value can be set by default according to the application, or can be set by the person skilled in the art.

[0038] Embodiment 2 Figure 2 A flow chart of a battery life prediction and management method based on cycle life modeling is shown, which is based on the same inventive concept as embodiment 1. The application provides a battery life prediction and management method based on cycle life modeling, which comprises: Step S1: collecting battery capacity data in the battery cycle charging process and preprocessing.

[0039] Step S2: Analyzing the change characteristics of the battery capacity on both sides of the inflection point in the battery capacity attenuation process to construct a local nonlinear degradation index.

[0040] Step S3: Analyzing the difference between the inflection point and the capacity regeneration phenomenon in the battery capacity attenuation process based on the local nonlinear degradation index to construct an asymmetric attenuation index.

[0041] Step S4: Analyzing the change characteristics of the inflection point in the global based on the asymmetric attenuation index to construct an inflection point significant index.

[0042] Step S5: Labeling the battery cycle charging data based on the inflection point significant index, taking it as a label in the random forest algorithm, and realizing the life prediction of the battery.

[0043] Those skilled in the art will understand that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0044] The present application is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The means for performing the functions specified in a flow or multiple flows and / or blocks

[0045] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction means, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The means for performing the functions specified in a flow or multiple flows and / or blocks

[0046] These computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are generated to realize the computer-implemented processes in the computer or other programmable devices, and the instructions executed in the computer or other programmable devices provide steps for implementing the functions specified in the flowchart Figure 1 one flow or multiple flows and / or the functions specified in the block Figure 1 one flow or multiple flows and / or the functions specified in the block

[0047] The embodiments of the present application are described above with reference to the accompanying drawings, but the present application is not limited to the specific embodiments described above, and the specific embodiments described above are merely illustrative, but not restrictive, and those of ordinary skill in the art can make many forms under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims, which are all within the protection of the present application.

Claims

1. A battery life prediction and management system based on cycle life modeling, characterized in that: include: The data preprocessing module collects and preprocesses battery capacity data during the battery cycle charging process. The local nonlinear degradation index calculation module analyzes the characteristics of battery capacity changes on both sides of the inflection point during battery capacity decay to construct a local nonlinear degradation index. The asymmetric degradation index calculation module analyzes the difference between the inflection point and the capacity regeneration phenomenon during the battery capacity degradation process based on the local nonlinear degradation index, and constructs the asymmetric degradation index. The inflection point significance index calculation module analyzes the global variation characteristics of inflection points based on the asymmetric decay index and constructs an inflection point significance index. The battery life prediction module labels battery cycle charging data based on the inflection point significance index and uses it as a label in the random forest algorithm to predict battery life.

2. The battery life prediction and management system based on cycle life modeling according to claim 1, characterized in that: The data preprocessing module uses a high-precision battery testing system to conduct full life cycle aging tests on multiple groups of lithium-ion batteries of the same model. This includes recording the charge-discharge curves of each cycle at a high sampling frequency, using the ampere-hour integration method to integrate the current during the discharge process over time, and constructing an original time series dataset with the number of charge-discharge cycles as the independent variable and the battery capacity as the dependent variable.

3. The battery life prediction and management system based on cycle life modeling according to claim 2, characterized in that: The local nonlinear degradation index is used to reflect the significance of the nonlinear degradation trend of battery capacity within a local time window. The construction process of the local nonlinear degradation index includes: Taking the t-th charging cycle as the center, the total length is The window is denoted as the monitoring window, and the sequence of battery capacity data within the monitoring window is denoted as the local monitoring sequence of battery capacity. This sequence is used as the input of the least squares method for linear fitting, and the output is the fitted linear equation. Based on the linear equation, the fitted values ​​of battery capacity under different charging cycles are obtained. The difference between the battery capacity and the fitted value of battery capacity is denoted as the fitting residual. The sequence of the fitting residuals is denoted as the fitting residual sequence, and then the local nonlinear degradation index is obtained.

4. A battery life prediction and management system based on cycle life modeling according to claim 3, characterized in that: The formula for calculating the local nonlinear degradation index is expressed as follows: ； in This represents the local nonlinear degradation exponent during the t-th charging cycle. This represents the maximum absolute value of all elements in the fitted residual sequence. `ln()` represents the logarithmic function with base to the natural constant, used to smooth the data within the parentheses. This represents the standard deviation of the fitted residual sequence. This represents the mean of the absolute values ​​of all elements in the fitted residual sequence, and 1 represents a hyperparameter used to avoid... The result after taking the logarithm is less than 0.

5. A battery life prediction and management system based on cycle life modeling according to claim 4, characterized in that: After calculating the local nonlinear degradation index after each charge, the asymmetric degradation index calculation module records the sequence of the local nonlinear degradation index within the monitoring window as the local nonlinear degradation index monitoring sequence; using the center point of the local battery capacity monitoring sequence as the dividing point, the local battery capacity monitoring sequence is divided into a first subsequence and a second subsequence to obtain the asymmetric degradation index.

6. A battery life prediction and management system based on cycle life modeling according to claim 5, characterized in that: The asymmetric decay exponent is calculated as follows: ； in This represents the asymmetric decay exponent during the t-th charging cycle. This represents the mean of the local nonlinear degradation index monitoring sequence. and Let represent the ranges of the first and second subsequences, respectively. This represents hyperparameters.

7. A battery life prediction and management system based on cycle life modeling according to claim 6, characterized in that: The inflection point significance index calculation module is used to calculate the asymmetric decay index of battery capacity data after each charge, and then record the sequence of asymmetric decay indices of all battery capacity data as the asymmetric decay index sequence. This sequence is used as the input of the AMPD peak detection algorithm, and the output is the peak point of the sequence. The total number of peak points is recorded as K. Taking the k-th peak point as an example, the neighborhood with the k-th peak point as the center and a width of D is recorded as the peak neighborhood, thus obtaining the inflection point significance index.

8. A battery life prediction and management system based on cycle life modeling according to claim 7, characterized in that: The process of constructing the inflection point significance index is as follows: ； in This represents the significance index of the inflection point at the k-th peak in an asymmetric decay index sequence. Let represent the asymmetric decay exponent at the k-th peak point, and D represent the width of the peak neighborhood. This represents the Euclidean distance between the number of charges corresponding to the s-th battery capacity data point and the number of charges corresponding to the k-th peak point within the peak neighborhood. It represents the asymmetric degradation exponent of the s-th battery capacity data within the peak neighborhood.

9. A battery life prediction and management system based on cycle life modeling according to claim 8, characterized in that: The battery life prediction module uses the number of charging cycles with the highest significance index during the entire battery lifespan as the inflection point. The region before the inflection point is designated as the slow degradation zone, and the region after the inflection point as the accelerated degradation zone. The region containing a data point is used as its label, and the feature vector of the data point is extracted. All feature vectors and labels of all data points are used as input to a random forest algorithm to train the decision tree in the random forest. After training, for the battery capacity data to be predicted, its feature vector is extracted. The input to the Random Forest algorithm after training is the output of the battery capacity data classification results, namely the slow degradation region and the accelerated degradation region.

10. A battery life prediction and management method based on cycle life modeling, used to execute a battery life prediction and management system based on cycle life modeling as described in any one of claims 1-9, characterized in that: Includes the following steps: Step S1: Collect battery capacity data during the battery cycle charging process and perform preprocessing; Step S2: Analyze the characteristics of battery capacity change on both sides of the inflection point during battery capacity decay to construct a local nonlinear degradation index; Step S3: Based on the analysis of the local nonlinear degradation index, construct an asymmetric degradation index to distinguish the difference between the inflection point and the capacity regeneration phenomenon during the battery capacity decay process; Step S4: Construct an inflection point significance index based on the global variation characteristics of the inflection point analysis using the asymmetric decay index; Step S5: Label the battery cycle charging data based on the inflection point significance index and use it as a label in the random forest algorithm to predict the battery life.

Images