Battery cell abnormity identification method and device, equipment, storage medium and program product

Abstract

The invention relates to a battery cell abnormity identification method and device, equipment, a storage medium and a program product. The method comprises the following steps: collecting parameters of multiple dimensions of battery clusters in the same series loop at each moment in a charging process; the plurality of dimensions at least comprise voltage, internal resistance and temperature; mapping parameters of multiple dimensions at each moment into a three-dimensional feature space constructed according to the voltage, the internal resistance and the temperature; determining discrete data points according to the density information of each data point in the three-dimensional feature space; and determining the defective battery cell according to the discrete data points. By adopting the method, the abnormal characteristics of the battery cell can be more comprehensively captured, so that the accuracy of identifying the defective battery cell is improved.

Description

Technical Field

[0001] This application relates to the field of battery technology, and in particular to a method, apparatus, computer device, computer-readable storage medium, and computer program product for identifying abnormal battery cells. Background Technology

[0002] In the field of energy storage power stations, battery clusters composed of a large number of cells are the core energy storage units, and their performance stability directly determines the system efficiency and safety. Due to factors such as manufacturing differences and environmental fluctuations, cells will gradually exhibit abnormalities such as capacity decay and a surge in internal resistance. If these abnormalities are not identified in time, they may reduce the system's usable capacity or even cause thermal runaway accidents.

[0003] Current mainstream anomaly identification methods have obvious limitations: traditional threshold methods rely solely on the range of parameters such as voltage and temperature, ignoring the data distribution patterns and trends, resulting in insufficient sensitivity; equivalent circuit models depend on parameters that are difficult to extract, such as internal resistance, leading to low estimation accuracy and making them difficult to apply in practice; while machine learning methods have potential, they require a large amount of labeled data, and parameter tuning is complex and computationally expensive, making them unsuitable for rapid on-site early warning needs. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for identifying battery cell anomalies that can improve the accuracy of battery cell anomaly identification, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a method for identifying abnormal battery cells, including:

[0006] During the charging process, parameters of the battery cluster in the same series circuit in multiple dimensions are collected at various times; the multiple dimensions include at least voltage, internal resistance and temperature;

[0007] The parameters of multiple dimensions at each moment are mapped to a three-dimensional feature space constructed based on the voltage, the internal resistance, and the temperature;

[0008] Based on the density information of each data point in the three-dimensional feature space, discrete data points are determined;

[0009] Defective cells are identified based on the discrete data points.

[0010] In one embodiment, determining discrete data points based on the density information of each data point in the three-dimensional feature space includes:

[0011] For each data point, the local reachability density of the data point and the local reachability density of neighboring data points within the neighborhood of the data point are calculated based on a preset neighborhood size.

[0012] Calculate the local outlier factor of the data point based on the local reachability density of the data point and the local reachability density of the adjacent data points;

[0013] If the local outlier factor is greater than a predetermined threshold, then the data point is determined to be a discrete data point.

[0014] In one embodiment, before mapping the parameters of multiple dimensions at each time moment to a three-dimensional feature space constructed based on the voltage, the internal resistance, and the temperature, the method further includes:

[0015] The parameters of multiple dimensions at each time point are standardized.

[0016] The standardized parameters are mapped to the three-dimensional feature space.

[0017] In one embodiment, after collecting parameters of multiple dimensions of the battery cluster in the same series circuit at various times during the charging process, the method further includes:

[0018] In any dimension, based on the parameters of that dimension, determine the target time with the greatest data dispersion from among the various time points;

[0019] Outlier detection is performed on the parameters at the target time to determine the discrete data points.

[0020] In one embodiment, the method further includes:

[0021] During two different charging processes, the parameters of the battery cluster in the same series circuit at any time point in any dimension are collected;

[0022] Candidate discrete data points are determined based on the parameters collected during each charging process;

[0023] The intersection of the two determined candidate discrete data points is taken as the discrete data point.

[0024] In one embodiment, the method further includes:

[0025] Based on the temperature of the battery cluster, the temperature change rate, extreme temperature change value, and temperature rise per unit charge of individual cells are statistically analyzed.

[0026] Defective cells are identified based on the rate of temperature change, the extreme value of temperature change, and the temperature rise per unit of charge.

[0027] Secondly, this application also provides a battery cell anomaly identification device, comprising:

[0028] The data acquisition module is used to collect parameters of multiple dimensions of the battery cluster in the same series circuit at various times during the charging process; the multiple dimensions include at least voltage, internal resistance and temperature;

[0029] The data mapping module is used to map parameters of multiple dimensions at each moment to a three-dimensional feature space constructed based on the voltage, the internal resistance, and the temperature.

[0030] The discrete point determination module is used to determine discrete data points based on the density information of each data point in the three-dimensional feature space.

[0031] An anomaly location module is used to determine defective battery cells based on the discrete data points.

[0032] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0033] During the charging process, parameters of the battery cluster in the same series circuit in multiple dimensions are collected at various times; the multiple dimensions include at least voltage, internal resistance and temperature;

[0034] The parameters of multiple dimensions at each moment are mapped to a three-dimensional feature space constructed based on the voltage, the internal resistance, and the temperature;

[0035] Based on the density information of each data point in the three-dimensional feature space, discrete data points are determined;

[0036] Defective cells are identified based on the discrete data points.

[0037] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0038] During the charging process, parameters of the battery cluster in the same series circuit in multiple dimensions are collected at various times; the multiple dimensions include at least voltage, internal resistance and temperature;

[0039] The parameters of multiple dimensions at each moment are mapped to a three-dimensional feature space constructed based on the voltage, the internal resistance, and the temperature;

[0040] Based on the density information of each data point in the three-dimensional feature space, discrete data points are determined;

[0041] Defective cells are identified based on the discrete data points.

[0042] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0043] During the charging process, parameters of the battery cluster in the same series circuit in multiple dimensions are collected at various times; the multiple dimensions include at least voltage, internal resistance and temperature;

[0044] The parameters of multiple dimensions at each moment are mapped to a three-dimensional feature space constructed based on the voltage, the internal resistance, and the temperature;

[0045] Based on the density information of each data point in the three-dimensional feature space, discrete data points are determined;

[0046] Defective cells are identified based on the discrete data points.

[0047] The aforementioned cell anomaly identification method, device, computer equipment, computer-readable storage medium, and computer program product collect parameters of multiple dimensions of a battery cluster in the same series circuit at various times during the charging process; these multiple dimensions include at least voltage, internal resistance, and temperature; the parameters of these multiple dimensions at each time moment are mapped to a three-dimensional feature space constructed based on voltage, internal resistance, and temperature; discrete data points are determined based on the density information of each data point in the three-dimensional feature space; and defective cells are identified based on the discrete data points. This method simultaneously considers three key parameters: voltage, internal resistance, and temperature, which reflect the state of the cell from different perspectives. Voltage reflects the electrochemical state of the cell, internal resistance reflects the internal losses of the cell, and temperature is closely related to the cell's heating and safety. By mapping them to a three-dimensional feature space for analysis, the method avoids the potential bias of single-parameter detection, and can more comprehensively capture the abnormal characteristics of the cell, thereby improving the accuracy of defective cell identification. Furthermore, this method determines discrete data points by analyzing the density of data points in the three-dimensional feature space, without requiring a pre-set data distribution model, and can adapt to the complex and variable distribution of cell parameters in the battery cluster. Whether it is the concentrated distribution of normal cell parameters or the dispersed distribution of defective cell parameters, density analysis can effectively identify anomalies, enhancing the applicability and robustness of the method. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1This is a flowchart illustrating a battery cell anomaly identification method in one embodiment;

[0050] Figure 2 This is a schematic diagram of the discrete data point identification process in one embodiment;

[0051] Figure 3 This is a flowchart illustrating a cell anomaly identification method in another embodiment;

[0052] Figure 4 This is a structural block diagram of a battery cell anomaly identification device in one embodiment;

[0053] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. It should be noted that the terms "comprising" and "having," and any variations thereof, as used in this application, are intended to cover non-exclusive inclusion.

[0055] In one embodiment, such as Figure 1 As shown, a method for identifying abnormal battery cells is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0056] Step S110: Collect parameters of multiple dimensions of the battery cluster in the same series circuit at various times during the charging process; the multiple dimensions include at least voltage, internal resistance and temperature.

[0057] In practice, this can be achieved by using voltage sensors, internal resistance testers, and temperature sensors for each individual cell in the series circuit. After the battery cluster begins charging, parameters such as voltage, internal resistance, and temperature for each cell can be collected in real time at a set sampling frequency. During the data collection process, the time information of each collection point must be recorded simultaneously so that the parameters can be correlated with the specific moment later.

[0058] In some embodiments, current parameters of the battery cells can also be acquired using current sensors. The consistency of current data of battery clusters with the same parallel circuit is compared, and data differences are compared by means of mean, range, variance, etc., thereby comparing differences in cluster current circulation, persistent cumulative charge and discharge differences, internal resistance differences, etc.

[0059] Step S120: Map the parameters of multiple dimensions at each time point to a three-dimensional feature space constructed based on voltage, internal resistance and temperature.

[0060] For example, a three-dimensional feature space is constructed with voltage as the X-axis, internal resistance as the Y-axis, and temperature as the Z-axis. For each individual cell at each time point, the voltage, internal resistance, and temperature values ​​are mapped onto the three-dimensional feature space as a three-dimensional coordinate point.

[0061] After the above processing, the parameters of all individual cells in the battery cluster at each moment are formed into a set of data points in the three-dimensional feature space, and the data points at different moments constitute a dynamic distribution state in space.

[0062] Step S130: Determine discrete data points based on the density information of each data point in the three-dimensional feature space.

[0063] In practice, for each data point in the three-dimensional feature space, the density information of each data point can be calculated using density calculation methods to determine the discrete data points.

[0064] For example, the k-nearest neighbor density estimation method can be used to calculate the average distance of the k nearest neighbor data points around each data point. The smaller the average distance, the higher the density of the area where the data point is located; conversely, the larger the average distance, the lower the density. The value of k can be determined according to the amount and distribution of data.

[0065] In some embodiments, the rate of change of parameters in each dimension can be statistically analyzed within the same time period to compare the differences between each cell and locate defective cells.

[0066] Step S140: Determine the defective battery cell based on the discrete data points.

[0067] In a specific implementation, after determining the discrete data points, the cells corresponding to the discrete data points are identified as defective cells. In some embodiments, defective cells can be classified into severely defective cells and generally defective cells based on the degree of discreteness of the cells.

[0068] Handling of severely defective battery cells: If the data of a severely defective battery cell deviates from the average value of a normal battery cell by more than the threshold m, it is determined that the severely defective battery cell must be replaced and its use should be stopped as soon as possible; if the deviation is within (n, m] (n < m), it is determined that the severely defective battery cell needs to be replaced as soon as possible; if the deviation is between [0, n], it is determined that the severely defective battery cell can still be operated.

[0069] For handling general defective cells: general defective cells are handled by equalization. The degree to which the voltage of a general defective cell deviates from the average voltage of a normal cell is denoted as 'a'. The SOC range corresponding to the degree of deviation 'a' is obtained by looking up a table. The equalization time is calculated based on the equalization current. Cell equalization is performed during the idle time.

[0070] In some embodiments, the number of times or duration for which each cell is marked as a discrete data point throughout the entire charging process can be counted. If a cell is marked as a discrete data point at multiple times, or if discrete data points appear during critical charging phases (such as fast charging or near full charge) with significant dispersion, the cell can be identified as a defective cell. In some embodiments, historical data of the cell can also be analyzed. If the characteristics of a cell being identified as a discrete data point during this charging process are similar to those of previously identified defective cells, it is further confirmed as a defective cell, thereby improving the accuracy of the determination.

[0071] The aforementioned method for identifying abnormal battery cells involves collecting parameters from multiple dimensions of a battery cluster within the same series circuit at various times during the charging process. These multiple dimensions include at least voltage, internal resistance, and temperature. The parameters at each time point are mapped to a three-dimensional feature space constructed based on voltage, internal resistance, and temperature. Discrete data points are determined based on the density information of each data point in the three-dimensional feature space. Defective battery cells are then identified based on these discrete data points. This method simultaneously considers three key parameters: voltage, internal resistance, and temperature. These three parameters reflect the state of the battery cell from different perspectives. Voltage reflects the electrochemical state of the cell, internal resistance reflects the internal losses of the cell, and temperature is closely related to the cell's heating and safety. By mapping these parameters to a three-dimensional feature space for analysis, the method avoids the potential limitations of single-parameter detection, enabling a more comprehensive capture of abnormal cell characteristics and thus improving the accuracy of defective cell identification. Furthermore, by analyzing the density of data points in the three-dimensional feature space to determine discrete data points, this method eliminates the need for a pre-defined data distribution model and can adapt to the complex and variable distribution of cell parameters within a battery cluster. Whether it is the concentrated distribution of normal cell parameters or the dispersed distribution of defective cell parameters, density analysis can effectively identify anomalies, enhancing the applicability and robustness of the method.

[0072] In one exemplary embodiment, such as Figure 2 As shown, step S130 determines discrete data points based on the density of each data point in the three-dimensional feature space, including:

[0073] Step S131: For each data point, calculate the local reachability density of the data point and the local reachability density of adjacent data points in the neighborhood of the data point according to the preset neighborhood size.

[0074] Step S132: Calculate the local outlier factor of the data point based on the local reachability density of the data point and the local reachability density of the adjacent data points;

[0075] Step S133: If the local outlier factor is greater than a predetermined threshold, then the data point is determined to be a discrete data point.

[0076] Local reachability density measures the density within the neighborhood of each data point. A higher local reachability density indicates a denser neighborhood for the data point, and vice versa.

[0077] Among them, the local outlier factor reflects the difference in the density of a sample point relative to its neighboring samples. The larger the value, the more likely the point is to be an outlier.

[0078] In specific implementation, for each data point, its neighboring data points within the neighborhood are determined according to a preset neighborhood size. The reachability distance from each of the data points within the neighborhood to the data point is calculated. The local reachability density of the data point is obtained by calculating the reciprocal of the average reachability distance from all data points within the neighborhood to the data point. Similarly, the local reachability density of all neighboring data points within the neighborhood of the data point is calculated in the same way. Then, the average ratio of the local reachability density of all neighboring data points within the neighborhood of the data point to the local reachability density of the data point itself is calculated as the local outlier factor of the data point. Further, discrete data points are determined based on the magnitude of this local outlier factor. Specifically, a threshold can be set; if the local outlier factor of any data point is greater than the threshold, then the data point is determined to be a discrete data point.

[0079] In some embodiments, after determining the local outlier factor, cell defects can be classified and managed according to the local outlier factor. For example, a cell with a local outlier factor value slightly higher than the normal range may be a "potential defect" (such as slight aging) and requires close monitoring; a cell with an extremely high local outlier factor value may be a "serious defect" (such as internal short circuit) and needs to be replaced immediately. This classification capability avoids a "one-size-fits-all" judgment and improves the pertinence and economy of maintenance strategies.

[0080] In this embodiment, the local outlier factor of each data point is calculated to determine whether it is an outlier. That is, by comparing the density difference between each data point and its neighboring data points, data points with sparse surrounding samples and significant differences from their neighbors are identified, thereby realizing the defect detection of the battery cell. This local density detection method can adapt to the diverse abnormal patterns in the battery system, does not require a preset data distribution model, and can reduce the missed or false judgments caused by the complexity of data distribution.

[0081] In an exemplary embodiment, before step S120 maps the parameters of multiple dimensions at each time moment to a three-dimensional feature space constructed based on voltage, internal resistance, and temperature, the method further includes: standardizing the parameters of multiple dimensions at each time moment; and mapping the standardized parameters to the three-dimensional feature space.

[0082] In this embodiment, considering that voltage, internal resistance and temperature have different dimensions and numerical ranges, in order to give the three equal weights in the three-dimensional feature space, the data needs to be standardized and mapped to the [0,1] interval.

[0083] In an exemplary embodiment, after collecting parameters of multiple dimensions of the battery cluster in the same series circuit at various times during the charging process, the method further includes: determining the target time with the greatest data dispersion from various times based on the parameters of that dimension in any given dimension; and performing outlier detection on the parameters at the target time to determine discrete data points.

[0084] The target time with the greatest data dispersion indicates that the overall data fluctuation is more drastic at a particular moment during the charging process. It describes the characteristics of a single point in time, reflecting the overall distribution of the data at that moment. For example, the voltage of a single battery cell may change abruptly before and after this moment.

[0085] Discrete data points refer to outliers that significantly deviate from the overall distribution at the moment when the data dispersion is greatest. They describe the characteristics of the data points and are the most extreme individuals within the overall discrete data at that moment.

[0086] In practical implementation, for any dimension, data within that dimension during the charging process can be extracted, and a sliding window can be used to calculate the data dispersion at each time point, thereby determining the time with the greatest data dispersion. For example, the local standard deviation at each time point can be calculated using a sliding window to characterize the data dispersion at each time point, further determining the time with the largest local standard deviation as the target time. The sliding window can be set based on the amount of data collected. Furthermore, a normal distribution or Nair's detection method can be used to detect outliers in the parameters at the target time, identifying discrete data points.

[0087] For example, taking cell temperature as an example, the cell temperatures in the same series circuit are collected, and continuous charging and discharging temperature data are extracted, denoted as [Tcs, Tce]. Differential calculations are performed on the data within the [Tcs, Tce] time interval to obtain continuous charging and discharging temperature difference data. The time point Tcl with the greatest dispersion of the charging and discharging temperature difference data within the [Tcs, Tce] time interval is detected. Then, outliers at time Tcl are calculated using a normal distribution or the Nair test method, denoted as {Cellc}. The cells corresponding to the {Cellc} set are the defective cells.

[0088] In this embodiment, it is considered that the "normal range" of parameters such as voltage, internal resistance, and temperature of the battery cell will change with the charging stage (for example, the voltage is low and stable in the early stage of charging, and may fluctuate in the middle stage due to polarization effect). An outlier at a certain moment may be normal data at other moments. That is, data anomalies in the battery cell charging process may be a superposition of anomalies in the time dimension (overall fluctuation at a certain moment) and anomalies in the data dimension (individual extreme values ​​at that moment). Therefore, this embodiment first locks in the "moment with the greatest dispersion" and then detects outliers in the local data distribution at that moment, thereby ensuring the accuracy of anomaly detection.

[0089] In an exemplary embodiment, the method further includes: collecting parameters of the battery cluster in the same series circuit at any dimension at various times during two different charging processes; determining candidate discrete data points based on the parameters collected during each charging process; and taking the intersection of the two determined candidate discrete data points as the discrete data point.

[0090] In specific matters, the determination of discrete data points in any dimension can be achieved by performing two discrete data point identification operations, i.e., performing two charging operations. During each charging process, data in that dimension is collected. Following the method described in the previous embodiment, the target time with the greatest data dispersion is first determined, and then the discrete data points at the target time are determined. The discrete data points obtained from the two charging operations are recorded as candidate discrete data points. The intersection of the two candidate discrete data points is obtained as the discrete data point.

[0091] For example, taking cell voltage as an example, the first data acquisition: the cell terminal voltage in the same series circuit is acquired, the voltage data of the complete charging process is captured, and the time is recorded as [Tcs, Tce]. The time point Tcl with the largest dispersion in the time period [Tcs, Tce] is obtained. The outlier point at time Tcl is calculated by normal distribution or Nair detection method and denoted as {Cellc}.

[0092] Second data acquisition: Capture the voltage data of the complete charging process, and record the time as [Tds, Tde]. Obtain the time point Tdl with the greatest dispersion within the time period [Tds, Tde]. Calculate the outlier at time Tdl using the normal distribution or Nair detection method, and denot it as {Celld}.

[0093] Take the intersection of {Cellc} and {Celld} as discrete data points, and denote the cells corresponding to the discrete data points as severely defective cells.

[0094] In this embodiment, by performing two charging operations, two discrete data points are determined. The intersection of the two determined discrete data points is taken as the final discrete data point. This avoids the randomness of a single identification result, improves the accuracy of the determined discrete data points, and thus improves the positioning accuracy of defective battery cells.

[0095] In an exemplary embodiment, the method further includes: statistically analyzing the temperature change rate, extreme temperature change value, and temperature rise per unit charge of individual cells based on the temperature of the battery cluster; and identifying defective cells based on the temperature change rate, extreme temperature change value, and temperature rise per unit charge.

[0096] In practical implementation, for each individual cell in the battery cluster, the rate of temperature change can be calculated within a preset time window, or the instantaneous rate of change can be calculated using a sliding window. During charging and discharging, the highest and lowest temperatures of each individual cell can be recorded and their differences calculated to obtain the extreme values ​​of temperature change. The ratio of temperature change to charge change can be statistically analyzed to determine the temperature rise per unit charge. Furthermore, based on the rate of temperature change, the extreme values ​​of temperature change, and the temperature rise per unit charge, defective cells can be identified.

[0097] In some embodiments, corresponding presets can be set for the rate of temperature change, the extreme value of temperature change, and the temperature rise per unit of electricity. If all three indicators exceed the corresponding preset values, the corresponding battery cell is marked as a defective battery cell.

[0098] In some embodiments, the defect probability of the battery cell is obtained by processing the temperature change rate, the extreme value of temperature change, and the temperature rise per unit of electricity into a pre-trained neural network model.

[0099] In some embodiments, a multidimensional vector space is constructed by using three indicators—temperature change rate, temperature change extreme value, and temperature rise per unit charge—as features. Then, a clustering algorithm is used to cluster the data of each cell, and the cells corresponding to the noise points obtained after clustering are regarded as defective cells.

[0100] In this embodiment, defective cells are identified by analyzing the temperature-related characteristics (temperature change rate, temperature change extreme value, and temperature rise per unit charge) of individual cells within the battery cluster. The combination of these three temperature indicators can more comprehensively depict the abnormal state of the cells, reduce misjudgments, and accurately locate defective cells.

[0101] refer to Figure 3 The following is a flowchart illustrating a cell anomaly identification method according to another embodiment. In this embodiment, the method includes the following steps:

[0102] Step S310: Collect parameters of multiple dimensions of the battery cluster in the same series circuit at various times during the charging process; the multiple dimensions include at least voltage, internal resistance and temperature;

[0103] Step S320: Standardize the parameters of multiple dimensions at each time step;

[0104] Step S330: Map the standardized parameters at each time step to a three-dimensional feature space constructed based on voltage, internal resistance, and temperature.

[0105] Step S340: For each data point in the three-dimensional feature space, calculate the local reachability density of the data point and the local reachability density of neighboring data points in the neighborhood of the data point according to the preset neighborhood size.

[0106] Step S350: Calculate the local outlier factor of the data point based on the local reachability density of the data point and the local reachability density of its neighboring data points;

[0107] Step S360: If the local outlier factor is greater than a predetermined threshold, then the data point is determined to be a discrete data point.

[0108] Step S370: Determine the defective battery cell based on the discrete data points.

[0109] This method considers three key parameters simultaneously: voltage, internal resistance, and temperature. These three parameters reflect the cell's state from different perspectives. Voltage reflects the cell's electrochemical state, internal resistance reflects the cell's internal losses, and temperature is closely related to the cell's heating and safety. By mapping these parameters to a three-dimensional feature space for analysis, the method avoids the limitations of single-parameter detection, enabling a more comprehensive capture of abnormal cell characteristics and improving the accuracy of defective cell identification. Furthermore, this method determines discrete data points by analyzing the density of data points in the three-dimensional feature space, eliminating the need for a pre-defined data distribution model and adapting to the complex and varied distribution of cell parameters within battery clusters. Whether the parameters of normal cells are concentrated or the parameters of defective cells are dispersed, density analysis can effectively identify anomalies, enhancing the method's applicability and robustness.

[0110] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0111] Based on the same inventive concept, this application also provides a battery cell anomaly identification device for implementing the aforementioned battery cell anomaly identification method. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more battery cell anomaly identification device embodiments provided below can be found in the limitations of the battery cell anomaly identification method described above, and will not be repeated here.

[0112] In one exemplary embodiment, such as Figure 4 As shown, a battery cell anomaly identification device is provided, comprising:

[0113] The data acquisition module 410 is used to acquire parameters of multiple dimensions of the battery cluster in the same series circuit at various times during the charging process; the multiple dimensions include at least voltage, internal resistance and temperature;

[0114] The data mapping module 420 is used to map parameters of multiple dimensions at each time moment to a three-dimensional feature space constructed based on voltage, internal resistance and temperature;

[0115] The discrete point determination module 430 is used to determine discrete data points based on the density information of each data point in the three-dimensional feature space.

[0116] The anomaly location module 440 is used to identify defective battery cells based on discrete data points.

[0117] In one embodiment, the discrete point determination module 430 is further configured to, for each data point, calculate the local reachability density of the data point and the local reachability density of adjacent data points in the neighborhood of the data point according to a preset neighborhood size; calculate the local outlier factor of the data point according to the local reachability density of the data point and the local reachability density of adjacent data points; and determine the data point as a discrete data point if the local outlier factor is greater than a predetermined threshold.

[0118] In one embodiment, the device further includes a data processing module for standardizing parameters of multiple dimensions at each time step and mapping the standardized parameters to a three-dimensional feature space.

[0119] In one embodiment, the discrete point determination module 430 is further configured to determine the target time with the greatest data dispersion from various times based on the parameters of that dimension in any dimension; and to perform outlier detection on the parameters at the target time to determine discrete data points.

[0120] In one embodiment, the discrete point determination module 430 is further configured to collect parameters of the battery cluster in the same series circuit at any time during two different charging processes; determine candidate discrete data points based on the parameters collected during each charging process; and take the intersection of the two determined candidate discrete data points as the discrete data point.

[0121] In one embodiment, the anomaly location module 440 is further configured to, based on the temperature of the battery cluster, statistically analyze the temperature change rate, extreme temperature change value, and temperature rise per unit charge of individual cells; and to determine defective cells based on the temperature change rate, extreme temperature change value, and temperature rise per unit charge.

[0122] Each module in the aforementioned battery cell anomaly identification device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0123] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for identifying abnormal battery cells. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0124] Those skilled in the art will understand that Figure 5The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0125] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0126] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0127] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0128] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0129] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0130] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for identifying abnormal battery cells, characterized in that, The method includes: During the charging process, parameters of the battery cluster in the same series circuit in multiple dimensions are collected at various times; the multiple dimensions include at least voltage, internal resistance and temperature; The parameters of multiple dimensions at each moment are mapped to a three-dimensional feature space constructed based on the voltage, the internal resistance, and the temperature; Based on the density information of each data point in the three-dimensional feature space, discrete data points are determined; Defective cells are identified based on the discrete data points.

2. The method according to claim 1, characterized in that, The step of determining discrete data points based on the density information of each data point in the three-dimensional feature space includes: For each data point, the local reachability density of the data point and the local reachability density of neighboring data points within the neighborhood of the data point are calculated based on a preset neighborhood size. Calculate the local outlier factor of the data point based on the local reachability density of the data point and the local reachability density of the adjacent data points; If the local outlier factor is greater than a predetermined threshold, then the data point is determined to be a discrete data point.

3. The method according to claim 1, characterized in that, Before mapping the parameters of multiple dimensions at each moment to a three-dimensional feature space constructed based on the voltage, the internal resistance, and the temperature, the method further includes: The parameters of multiple dimensions at each time point are standardized. The standardized parameters are mapped to the three-dimensional feature space.

4. The method according to claim 1, characterized in that, After collecting parameters of multiple dimensions of the battery cluster in the same series circuit at various times during the charging process, the method also includes: In any dimension, based on the parameters of that dimension, determine the target time with the greatest data dispersion from among the various time points; Outlier detection is performed on the parameters at the target time to determine the discrete data points.

5. The method according to claim 4, characterized in that, The method further includes: During two different charging processes, the parameters of the battery cluster in the same series circuit at any time point in any dimension are collected; Candidate discrete data points are determined based on the parameters collected during each charging process; The intersection of the two determined candidate discrete data points is taken as the discrete data point.

6. The method according to claim 1, characterized in that, The method further includes: Based on the temperature of the battery cluster, the temperature change rate, extreme temperature change value, and temperature rise per unit charge of individual cells are statistically analyzed. Defective cells are identified based on the rate of temperature change, the extreme value of temperature change, and the temperature rise per unit charge.

7. A battery cell anomaly identification device, characterized in that, The device includes: The data acquisition module is used to collect parameters of multiple dimensions of the battery cluster in the same series circuit at various times during the charging process; the multiple dimensions include at least voltage, internal resistance and temperature; The data mapping module is used to map parameters of multiple dimensions at each moment to a three-dimensional feature space constructed based on the voltage, the internal resistance, and the temperature. The discrete point determination module is used to determine discrete data points based on the density information of each data point in the three-dimensional feature space. An anomaly location module is used to determine defective battery cells based on the discrete data points.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images