Abnormality identification method, energy storage device management system and vehicle

Abstract

The invention provides an anomaly recognition method, an energy storage device management system and a vehicle. The method comprises the following steps: acquiring a collected voltage signal of each battery cell of the energy storage device; for each battery cell, superposing a square wave signal on the voltage signal of the battery cell to obtain an enhanced voltage signal; and outputting an abnormality recognition result of the energy storage device based on the enhanced voltage signal, thereby ensuring the accuracy of abnormality recognition, improving the reliability of abnormality recognition, and realizing the timely recognition of the abnormality, thereby avoiding the serious problem of the energy storage device, and ensuring the safety of the energy storage device.

Description

Technical Field

[0001] This invention relates to the field of energy storage technology, specifically to an anomaly identification method, an energy storage device management system, and a vehicle. Background Technology

[0002] During use, energy storage devices such as batteries may experience abnormalities such as thermal runaway or internal short circuits, affecting their safety. Therefore, to ensure safety, it is necessary to identify any abnormalities in the energy storage device.

[0003] In related technologies, the anomaly identification process mainly involves detecting indicator data such as voltage, current, or temperature of the energy storage device to identify whether there is an anomaly. However, in the early stages of an anomaly, the changes in indicator data may be small, and the difference from the indicator data in normal periods may be small, making it impossible to accurately identify whether there is an anomaly in the energy storage device, resulting in low anomaly identification accuracy. Summary of the Invention

[0004] The embodiments of the present invention provide an anomaly identification method, an energy storage device management system, and a vehicle, which can improve the technical problem of low accuracy in anomaly identification.

[0005] In a first aspect, embodiments of the present invention provide an anomaly identification method, comprising:

[0006] Acquire the voltage signal of each cell in the energy storage device;

[0007] For each of the battery cells, a square wave signal is superimposed on the voltage signal of the battery cell to obtain an enhanced voltage signal;

[0008] The abnormality identification result of the energy storage device is output based on the enhanced voltage signal.

[0009] In one embodiment, superimposing a square wave signal onto the voltage signal of the battery cell includes:

[0010] The voltage signal of the battery cell is superimposed with the square wave signal corresponding to the battery cell; wherein, the amplitude of the square wave signal corresponding to the battery cell is determined based on the voltage signal of the battery cell after adjusting the reference amplitude.

[0011] Based on this, for each battery cell, the reference amplitude is adjusted using the cell's voltage signal to determine the amplitude of the corresponding square wave signal, thus achieving adaptive adjustment of the square wave signal for that cell. Then, the cell's voltage signal is superimposed on the corresponding square wave signal, thereby achieving adaptive enhancement of the cell's voltage signal. Furthermore, the reference amplitude ensures that normal voltage signals are not disrupted, thus enhancing abnormal voltage signals and improving the sensitivity of abnormal voltage signal identification.

[0012] In one embodiment, the process of determining the amplitude of the square wave signal corresponding to the aforementioned battery cell may include:

[0013] Based on a preset scaling factor, the standard deviation of the voltage signal corresponding to the battery cell is adjusted to obtain the adjusted voltage data.

[0014] The reference amplitude is adjusted based on the adjusted voltage data to obtain the adjusted amplitude;

[0015] The amplitude of the square wave signal corresponding to the battery cell is determined based on the adjusted amplitude.

[0016] Based on this, by using a preset scaling factor to adjust the voltage standard deviation corresponding to the cell's voltage signal, the influence of the standard deviation on the amplitude can be controlled. Then, based on the adjusted voltage data, the reference amplitude is adjusted to obtain the adjusted amplitude, ensuring that the normal voltage signal is not disrupted, thereby enhancing the abnormal voltage signal. Subsequently, the amplitude of the square wave signal corresponding to the cell can be determined according to the adjusted amplitude, ensuring the reliability of the adaptive adjustment of the square wave signal.

[0017] In one embodiment, the amplitude of the square wave signal is limited between the adjusted amplitude, the preset minimum amplitude, and the preset maximum amplitude to avoid excessive or insufficient disturbance.

[0018] In one embodiment, before superimposing a square wave signal onto the voltage signal of the battery cell, the method further includes:

[0019] The voltage signal of the battery cell is preprocessed to obtain the preprocessed voltage signal of the battery cell; wherein the preprocessing includes one or more of the following: feature extraction processing, voltage filtering processing during discontinuous charging time, and voltage filtering processing within invalid SOC interval;

[0020] The step of superimposing a square wave signal onto the voltage signal of the battery cell includes:

[0021] The preprocessed voltage signal of the battery cell is superimposed with the square wave signal.

[0022] Based on this, for the voltage signal of each battery cell, the voltage signal is first preprocessed to improve its reliability. Then, a square wave signal is superimposed on the preprocessed voltage signal to enhance its accuracy for anomaly detection.

[0023] In one embodiment, the above-mentioned output of the anomaly identification result of the energy storage device based on the enhanced voltage signal includes:

[0024] Based on the enhanced voltage signal of the battery cell, the correlation coefficient between the battery cells of the energy storage device is determined;

[0025] If the correlation coefficient is less than or equal to a first threshold, the anomaly identification result is output; wherein the first threshold is determined based on the correlation coefficient.

[0026] Based on this, the correlation coefficient between cells is calculated using the enhanced voltage signal of each cell in the energy storage device. If a correlation coefficient is less than or equal to a first threshold, it indicates a cell anomaly, and an anomaly identification result can be output. This first threshold is determined based on the correlation coefficient, enabling adaptive dynamic adjustment of the threshold to ensure its rationality and reduce the probability of false anomaly identification.

[0027] In one embodiment, the first threshold is determined based on the median of the determined correlation coefficient, thereby avoiding setting the threshold too low or too high.

[0028] In one embodiment, the anomaly identification result includes one or more of the following: abnormal battery cell information, abnormal time, and vehicle information to which the abnormal battery cell belongs. Based on this, by outputting the anomaly identification result, relevant personnel can accurately ascertain the specific anomaly.

[0029] In one embodiment, the above-mentioned anomaly identification result indicates that there is an internal short circuit in the cell of the energy storage device, thereby achieving accurate identification of the internal short circuit.

[0030] Secondly, embodiments of the present invention provide an energy storage device management system, which is electrically connected to the energy storage device;

[0031] The energy storage device management system is used to execute the anomaly identification method as described in the first aspect above.

[0032] In one embodiment, the energy storage device management system includes a processor or chip that executes a computer program to implement the anomaly identification method as described in the first aspect above.

[0033] Optionally, the energy storage management system may further include a memory on which the aforementioned computer program is stored.

[0034] Thirdly, embodiments of the present invention provide a chip system for implementing the anomaly identification method described in the first aspect above.

[0035] Fourthly, embodiments of the present invention provide an electronic device, including a memory having a computer program stored thereon;

[0036] A processor is configured to execute the computer program in the memory to implement the anomaly identification method as described above.

[0037] Fifthly, embodiments of the present invention provide a vehicle including the energy storage device management system and energy storage device as described above; or, including the electronic equipment and energy storage device as described above.

[0038] In a sixth aspect, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the anomaly identification method as described in the first aspect above.

[0039] In a seventh aspect, embodiments of the present invention provide a computer program product, including a computer program that, when executed by a processor, implements the anomaly identification method described in the first aspect above.

[0040] The beneficial effects of the embodiments of the present invention are as follows:

[0041] In embodiments of the present invention, by acquiring the voltage signal of each cell in the energy storage device, a square wave signal is superimposed on the voltage signal of each cell to enhance the voltage signal, that is, to increase the degree of voltage signal variation. This ensures that even in the early stages of an anomaly, the degree of voltage signal variation is relatively large, facilitating anomaly identification. Subsequently, the enhanced voltage signal can be used to determine whether an anomaly exists in the energy storage device, outputting a corresponding anomaly identification result. This ensures the accuracy and reliability of anomaly identification, enabling timely anomaly identification and thus preventing serious problems from occurring in the energy storage device, ensuring its safety. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a schematic diagram of a scene architecture provided by an embodiment of the present invention;

[0044] Figure 2 This is a flowchart illustrating an anomaly identification method provided by an embodiment of the present invention;

[0045] Figure 3 This is a schematic diagram of the voltage signal curve of an abnormal battery cell provided by an embodiment of the present invention. Figure 1 ;

[0046] Figure 4 This is a schematic diagram of the voltage signal curve of an abnormal battery cell provided by an embodiment of the present invention. Figure 2 ;

[0047] Figure 5 This is a schematic diagram comparing the correlation coefficients between battery cells according to an embodiment of the present invention;

[0048] Figure 6 This is a comparative schematic diagram of the mean standard deviation of a battery cell provided by an embodiment of the present invention;

[0049] Figures 7-8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention;

[0050] Figure 9 This is a schematic diagram of the chip system provided in an embodiment of the present invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Furthermore, it should be understood that the specific embodiments described herein are only for illustration and explanation of the present invention and are not intended to limit the present invention. In the present invention, unless otherwise stated, directional terms such as "upper" and "lower" generally refer to the upper and lower positions of the device in actual use or operation, specifically the drawing directions in the accompanying drawings; while "inner" and "outer" refer to the outline of the device.

[0052] Batteries (such as lithium-ion batteries) are widely used in electric vehicles (e.g., electric vehicles) due to their high energy density. Figure 1 The vehicle 100 shown is equipped with lithium-ion batteries 10, portable electronic devices, and energy storage systems. However, batteries may experience serious malfunctions such as thermal runaway or internal short circuits under long-term cyclic use or abnormal operating conditions, affecting safety.

[0053] Thermal runaway is usually caused by internal or external factors, such as overcharging, mechanical damage, or decomposition of electrode materials, which leads to a sharp rise in the internal temperature of the battery, which may then cause serious problems such as explosion.

[0054] Internal short circuits are mostly caused by diaphragm damage, impurity doping, or electrode material deposition, resulting in direct contact between the positive and negative electrodes, leading to local overheating or a sudden drop in capacity.

[0055] To ensure battery safety, it is necessary to identify anomalies such as thermal runaway and internal short circuits. Related technologies utilize real-time data on voltage, current, and surface temperature to detect anomalies like thermal runaway or internal short circuits, thus achieving battery anomaly identification. For example, features such as voltage drops, abnormal temperature increases, or current fluctuations are used in conjunction with threshold judgment methods for preliminary identification. However, the anomaly identification methods provided by these technologies often lack sufficient sensitivity to perceive the weak signals at the initial stage of an internal short circuit, especially under complex operating conditions (such as high-rate charging and discharging or temperature fluctuations). This can easily lead to false positives or false negatives, reducing the accuracy and reliability of anomaly identification and, to some extent, failing to guarantee battery safety.

[0056] Therefore, to address the aforementioned issues, this application provides an early anomaly identification scheme based on cell voltage. By superimposing a square wave signal onto the cell voltage, the abnormal characteristics are enhanced, thereby improving the sensitivity to weak signals in the early stages of anomalies such as internal short circuits, reducing the probability of false positives and false negatives, and thus improving the reliability and accuracy of anomaly identification, while ensuring the safety of energy storage devices, such as batteries.

[0057] The following is combined Figure 2 This paper details the implementation process of the aforementioned early anomaly identification scheme based on cell voltage, which is the anomaly identification method provided in this application. Figure 2 As shown, the implementation process may include S201-S203.

[0058] S201. Acquire the voltage signal of each cell in the energy storage device.

[0059] In this embodiment, the voltage signal of each cell in the energy storage device is acquired periodically or in real time. For example, the cell voltage signal may be collected by the energy storage device management system (such as a battery management system).

[0060] The voltage signal described above may include multiple voltage values; that is, the voltage signal of the battery cell described in this application is actually a voltage sequence. Each voltage value (or voltage) in the voltage sequence corresponds to a time point (or alternatively, a timestamp), and the time point corresponding to the voltage value represents the time when that voltage value was collected.

[0061] In some embodiments, after obtaining the collected voltage signal of the battery cell, the voltage signal can be preprocessed to obtain a preprocessed voltage signal, thereby ensuring the reliability of the voltage signal. Accordingly, the method described below for determining whether a battery cell is abnormal based on its voltage signal actually determines whether the battery cell is abnormal based on the preprocessed voltage signal. For example, in step S202 below, superimposing a square wave signal onto the battery cell's voltage signal actually involves superimposing a square wave signal onto the preprocessed voltage signal of the battery cell.

[0062] The preprocessing mentioned above includes one or more of the following: feature extraction processing, voltage filtering processing during discontinuous charging time, and voltage filtering processing within the state of charge (SOC) interval.

[0063] Based on this, for the voltage signal of each battery cell, the voltage signal is first preprocessed to improve its quality and thus its reliability. Then, a square wave signal is superimposed on the preprocessed voltage signal to enhance its accuracy for anomaly detection.

[0064] For example, the above feature extraction process may refer to calculating the cube of the difference between the voltage signal of the battery cell and its mean to obtain the voltage feature value of the battery cell. That is, for each voltage value in the voltage sequence of the battery cell, the cube of the difference between the voltage value and the mean of the voltage sequence is calculated to obtain the voltage feature value of the battery cell, so as to capture nonlinear voltage changes caused by anomalies such as internal short circuits.

[0065] Specifically, V' i =(V i -mean(V)) 3 Among them, V i V' represents the i-th voltage value in the voltage sequence. mean(V) represents the mean of the voltage sequence. i This represents the voltage feature value corresponding to the i-th voltage value, which is the voltage signal after feature extraction processing.

[0066] Optionally, the voltage sequence of the aforementioned battery cell can be the voltage (or voltage signal) within a sliding window. The size of the sliding window can be 10 frames, and the step size can be 1 frame.

[0067] It should be noted that the mean of the voltage sequence involved in the above feature extraction is only one example; the mean can also be the median or the mode.

[0068] For example, the voltage filtering process during the aforementioned discontinuous charging period can refer to removing voltage signals from the battery cell whose times fall within the discontinuous charging period, thus eliminating discontinuous charging segments. Specifically, when the time interval between two charges is greater than or equal to a preset time interval, these two charges are determined to be discontinuous. First, continuous charging segments are identified from the raw data (which can be understood as BMS data) using the current less than 0 or battery status field. For example, if the current of all data points between points 1 and 6 is less than 0, then points 1 to 6 can be identified as a continuous charging segment. Then, the time interval between two frames of data for all data points in this continuous charging segment is obtained, which can be understood as the time interval between two data points. If this time interval is greater than or equal to a preset time interval (such as 20 minutes), then the voltage signals within points 1 to 6 are deleted.

[0069] For example, the voltage filtering process within the invalid SOC interval described above means filtering voltage data recorded within the invalid SOC interval. Specifically, after determining a continuous charging segment, if the SOC at the start time of the continuous charging segment (i.e., the initial SOC) is greater than 40%, or the SOC at the end time of the continuous charging segment (i.e., the end SOC) is less than 98%, then the voltage signal within that continuous charging segment is deleted. This continuous charging segment then corresponds to the invalid SOC interval.

[0070] It should be noted that when the above preprocessing includes multiple processes, multiple processes can be performed simultaneously or sequentially. This application does not impose any restrictions on the order of processing.

[0071] S202. For each cell, superimpose a square wave signal onto the voltage signal of the cell to obtain an enhanced voltage signal.

[0072] In this embodiment, since the voltage signal of the battery cell is actually a voltage sequence, the enhanced voltage signal described above is also a voltage sequence. The square wave signal is superimposed on the voltage sequence through periodic perturbation (e.g., a period of 2 frames) to obtain the enhanced voltage sequence of the battery cell, making the voltage sequence changes more obvious and easier to identify anomalies.

[0073] In some embodiments, the square wave signal described above may correspond to a battery cell. For each battery cell, the voltage signal of that cell is superimposed with the square wave signal corresponding to that cell. The amplitude of the square wave signal corresponding to that cell is determined based on the voltage signal of that cell after adjusting a reference amplitude.

[0074] Based on this, for each battery cell, the reference amplitude is adjusted using the cell's voltage signal to determine the amplitude of the corresponding square wave signal, thus achieving adaptive adjustment of the square wave signal for that cell. Then, the cell's voltage signal is superimposed on the corresponding square wave signal, thereby achieving adaptive enhancement of the cell's voltage signal. Furthermore, the reference amplitude ensures that normal voltage signals are not disrupted, thus effectively enhancing abnormal voltage signals and improving the sensitivity of abnormal voltage signal identification.

[0075] For example, the adaptive square wave signal corresponding to the battery cell can be determined using Formula 1, V'(t, c) = V(t, c) + A(t) * sign(phase(t)).

[0076] Where V(t, c) is the original voltage value of cell c at time t (in fact, it represents the enhanced voltage value of cell c at time t).

[0077] A(t) represents the amplitude of the square wave signal. phase(t) represents the period of the square wave signal.

[0078] A(t)*sign(phase(t)) is a periodic perturbation signal (i.e., a square wave signal) whose value switches between -A(t) and +A(t), and the period can be 2 frames (i.e., it alternates once every 2 frames).

[0079] Optionally, the aforementioned phase(t) is used to control the periodicity of the square wave signal, and it can be determined by formula two, phase(t) = floor(t / 2) mod 2. The value of phase(t) can be 0 or 1. Correspondingly, it can be converted to -1 or +1 by sign(phase(t)) = 2*phase(t)-1.

[0080] It is understood that the period of the square wave signal mentioned above is 2, which is just an example. Of course, the period of the square wave signal can also be other values, such as 4. This application does not limit it.

[0081] In some embodiments, the process of determining the amplitude of the square wave signal corresponding to the battery cell may include:

[0082] For each battery cell, the standard deviation of the voltage signal corresponding to that cell is adjusted based on a preset scaling factor to obtain adjusted voltage data. Then, the reference amplitude is adjusted based on the adjusted voltage data to obtain the adjusted amplitude. Finally, the amplitude of the square wave signal corresponding to the battery cell is determined based on the adjusted amplitude.

[0083] Based on this, by setting a scaling factor, the standard deviation of the voltage signal corresponding to the battery cell is adjusted, thus controlling the degree of influence of the standard deviation on the amplitude. Then, based on the adjusted voltage data, the reference amplitude is adjusted to obtain the adjusted amplitude, achieving adaptive adjustment of the square wave signal amplitude. This ensures that the normal voltage signal is not disrupted, thereby enhancing abnormal voltage signals. Subsequently, the amplitude of the square wave signal corresponding to the battery cell can be determined based on the adjusted amplitude, ensuring the reliability of the adaptive adjustment of the square wave signal.

[0084] Optionally, the amplitude of the square wave signal is limited to between the adjusted amplitude, the preset minimum amplitude, and the preset maximum amplitude to avoid excessive or insufficient disturbance.

[0085] For example, the amplitude of the square wave signal can be determined using Formula 3, A(t) = clip(A_base + k*sigma(t), A_min, A_max), which is an adaptive square wave signal.

[0086] Here, A_base represents the reference amplitude, ensuring that disturbances do not disrupt the normal voltage signal. The value of A_base can be set according to requirements, such as A_base = 10. -5 That is, 1e-5.

[0087] sigma(t) is the standard deviation of the voltage sequence at time t, that is, the standard deviation of the voltage at time t, which reflects the severity of voltage fluctuations. The standard deviation of the voltage at time t can be calculated based on the voltage sequence within a previous period, such as the previous 10 frames of a sliding window.

[0088] k represents the preset scaling factor, which controls the degree to which the standard deviation affects the amplitude of the square wave signal. k can be set according to the actual situation, such as k = 0.001.

[0089] A_min represents the preset minimum amplitude, and A_max represents the preset maximum amplitude. Both A_min and A_max can be set according to actual conditions. For example, A_min = 10. -7 A_max = 10 -4 .

[0090] The `clip()` function is used to limit the range of values ​​in an array. By using the `clip()` function, the range can be limited to between `A_min` and `A_max`, preventing excessive or insufficient fluctuations.

[0091] It should be noted that limiting the amplitude of the square wave signal to the adjusted amplitude, the preset minimum amplitude, and the preset maximum amplitude is only one possible way to determine the amplitude of the square wave signal. The amplitude of the square wave signal can also be determined in other ways, such as directly using the adjusted amplitude as the amplitude of the square wave signal, thereby achieving rapid determination of the amplitude of the square wave signal.

[0092] Furthermore, the aforementioned square wave signal, which undergoes adaptive adjustment, is merely an example; the square wave signal can also be emitted without adaptive adjustment. In other words, the voltage signals of all battery cells are superimposed with a uniformly preset square wave signal.

[0093] In this embodiment, an adaptive square wave signal is superimposed on the voltage sequence of the battery cell to enhance abnormal features, highlighting minute changes caused by anomalies such as internal short circuits. In other words, the square wave signal is superimposed on the voltage sequence through periodic perturbation (with a period of 2 frames), ensuring that abnormal features are more easily identified under complex operating conditions (such as high-rate charging and discharging), thereby improving the reliability and accuracy of anomaly identification using the enhanced voltage signal. For example, Figure 3 This is the voltage curve of an abnormal battery cell without a superimposed square wave signal. Figure 4 This is the voltage curve of an abnormal battery cell with a superimposed square wave signal. Compared to... Figure 3 , Figure 4 The voltage signal after 10-01 changes significantly, making it easy to identify abnormalities in the battery cell.

[0094] S203, Based on the enhanced voltage signal, output the anomaly identification result of the energy storage device.

[0095] In this embodiment of the application, for each cell, after obtaining the enhanced voltage signal of the cell, the enhanced voltage signal of the cell is used to identify whether the cell is abnormal. In the case of an abnormal cell, the abnormality identification result can be output, so as to realize timely warning in the early stage of the abnormality. This allows relevant personnel to be aware of the abnormality of the energy storage device in a timely manner, and then resolve the abnormality in a timely manner, avoiding serious problems such as the failure of the energy storage device, and ensuring the safety of the energy storage device.

[0096] In some embodiments, the correlation coefficient between battery cells can be used to identify whether a battery cell is abnormal. The correlation coefficient between the battery cells of the energy storage device is determined based on the enhanced voltage signal of the battery cells.

[0097] If the correlation coefficient is less than or equal to the first threshold, the anomaly identification result is output; where the first threshold is determined based on the correlation coefficient.

[0098] Furthermore, if all correlation coefficients are greater than the first threshold, it indicates that each cell is normal, meaning the energy storage device is normal. In this case, a normal identification result for the energy storage device can be output so that the user is aware that the energy storage device is still usable. Of course, a normal identification result can also be omitted; even without an abnormal identification result, the user can still know that the energy storage device is normal.

[0099] Based on this, the correlation coefficient between cells is calculated using the enhanced voltage signal of each cell in the energy storage device. If a correlation coefficient is less than or equal to a first threshold, it indicates a cell anomaly, and an anomaly identification result can be output. This first threshold is determined based on the correlation coefficient, enabling adaptive dynamic adjustment of the threshold to ensure its rationality and reduce the probability of false anomaly identification.

[0100] Optionally, the battery cells are numbered sequentially. The correlation coefficients between the aforementioned battery cells are actually the correlation coefficients between adjacent battery cells. For example, an energy storage device includes 6 battery cells, numbered 1-6. Then, the correlation coefficients between battery cells 2 and 1, 3 and 2, 5 and 4, and 5 and 6 are calculated.

[0101] In some embodiments, the first threshold is determined based on the median of the determined correlation coefficients, thereby avoiding setting the threshold too low or too high. For example, the first threshold can be determined using Formula 4, Threshold = Median(Corr) - m. Here, Threshold represents the first threshold, and Corr represents all calculated correlation coefficients, such as the correlation coefficients between cell 2 and cell 1, cell 3 and cell 2, cell 5 and cell 4, and cell 5 and cell 6 mentioned above.

[0102] m represents the preset adjustment value. m can be set according to the actual situation, such as m being 0.5.

[0103] In this embodiment, the abnormality of a battery cell is determined based on the correlation coefficient between the cells and a dynamic threshold. This threshold (i.e., the aforementioned first threshold) can be adaptively adjusted according to operating parameters, thereby adjusting the judgment criteria and effectively improving detection accuracy in complex scenarios. Furthermore, it effectively overcomes the limitation of static thresholds easily leading to misjudgments or missed judgments under dynamic operating conditions. Through adaptive signal processing and a dynamic threshold mechanism, the robustness and adaptability of the detection are significantly improved.

[0104] In some embodiments, when a battery cell malfunction is identified, a corresponding malfunction identification result can be output. This result may include one or more of the following: malfunctioning battery cell information, malfunction time, and vehicle information to which the malfunctioning battery cell belongs. Based on this, by outputting the malfunction identification result, relevant personnel can accurately understand the specific malfunction and resolve it promptly.

[0105] The abnormal cell information mentioned above can be the cell number.

[0106] The anomaly time can be the time of the cell's first anomaly. Since a cell may remain in an abnormal state after an anomaly occurs, it will continue to be detected. For persistent anomalies, users are generally concerned with the time of the anomaly's first occurrence; therefore, the first anomaly time can be output so that relevant personnel can effectively know when the anomaly started.

[0107] The vehicle information to which the aforementioned abnormal battery cell belongs may include the vehicle identification number (VIN).

[0108] For example, the above-mentioned output of anomaly identification results may include one or more of the following: displaying the anomaly identification results, outputting the anomaly identification results via voice, and sending the anomaly identification results to the target device. Furthermore, the anomaly identification results may be generated according to a certain format, realizing the generation of formatted anomaly records. Based on this, by outputting formatted anomaly records, the energy storage device management system can easily trigger real-time warnings, enhancing the safety of electric vehicles and energy storage devices.

[0109] In some embodiments, the process of determining the abnormal battery cell may include: if the correlation coefficient between two battery cells is less than or equal to a first threshold, it indicates that there is an abnormal battery cell between the two battery cells; therefore, for one of the two battery cells (or referred to as battery cell A), the correlation coefficient between battery cell A and battery cell B is calculated. Battery cell C may be a normal battery cell other than these two.

[0110] If the correlation coefficient between cell A and cell B is greater than the first threshold, it indicates that both cell A and cell B are normal, while cell A and cell C are abnormal. Therefore, cell C is abnormal.

[0111] If the correlation coefficient between cell A and cell B is less than or equal to the first threshold, since cell B is normal, it can be directly determined that cell A is abnormal, but it cannot be determined whether cell C is abnormal.

[0112] Therefore, the correlation coefficient between cell C and cell D can be calculated to determine whether cell C is abnormal. Cell D is a normal cell other than cell A and cell C. For example, if the correlation coefficient between cell C and cell D is less than or equal to a first threshold, cell C is determined to be abnormal. If the correlation coefficient between cell C and cell D is greater than the first threshold, cell C is considered normal.

[0113] For example, an energy storage device includes six cells, numbered 1-6. If the correlation coefficient between cell 3 and cell 2 is less than or equal to a first threshold, it indicates that there is an abnormal cell between cell 3 and cell 2. Cell 3 can be classified as cell A, and cell 2 can be classified as cell C.

[0114] Furthermore, the correlation coefficient between cell 4 and cell 5 is greater than the first threshold, meaning that both cell 4 and cell 5 are normal cells. Therefore, cell 4 can be considered as cell B.

[0115] If the correlation coefficient between cell 3 and cell 4 is greater than the first threshold, it indicates that both cell 3 and cell 4 are normal cells. However, since there is an abnormal cell between cell 3 and cell 2, cell 2 is an abnormal cell.

[0116] If the correlation coefficient between cell 3 and cell 4 is less than or equal to the first threshold, it indicates that cell 3 is an abnormal cell. Therefore, it is possible to further determine whether cell 2 is an abnormal cell. For example, cell 5 is designated as cell D. The correlation coefficient between cell 5 and cell 2 is calculated.

[0117] If the correlation coefficient between cell 5 and cell 2 is greater than the first threshold, both cell 5 and cell 2 are normal. If the correlation coefficient between cell 5 and cell 2 is less than or equal to the first threshold, cell 2 is abnormal.

[0118] It should be understood that the above example of designating cell 4 as cell B and cell 5 as cell D is merely one example. It could also be any other normal cell from cells 1-6, excluding cells 2 and 3, designated as cell B and cell D. For example, cell 4 could be designated as cell D.

[0119] In some embodiments, when determining the abnormal cell among two battery cells, as described above, it can be done by first determining whether one of the two cells is normal, for example, determining whether cell A is normal. Alternatively, it can be done by simultaneously determining whether both cells are normal, i.e., calculating the correlation coefficient between cell A and cell B, and calculating the correlation coefficient between cell C and cell D.

[0120] Next, the correlation coefficient between cell A and cell B is used to determine whether cell A is abnormal, and the correlation coefficient between cell C and cell D is used to determine whether cell C is abnormal. The process of using correlation coefficients to determine whether a cell is abnormal can be referred to the relevant content above, and will not be repeated here.

[0121] In this embodiment, anomaly detection is performed using the correlation coefficient between the enhanced voltage sequences of the battery cells. Under normal operating conditions, the voltage changes of the battery cells are synchronized, and the correlation coefficient remains relatively high, such as close to 1. When anomalies such as internal short circuits occur, the voltage anomalies of local battery cells are amplified, leading to a significant decrease in the correlation coefficient (as shown in Table 1). In other words, by adaptively superimposing a square wave signal on the voltage fluctuation amplitude, the anomaly characteristics are enhanced, ensuring a high correlation coefficient under normal conditions and a rapid decrease in the correlation coefficient during anomalies, thereby improving the sensitivity, reliability, and accuracy of anomaly identification. For example, as... Figure 5 As shown, before the anomaly occurred, the correlation coefficient calculated based on the voltage signal with the superimposed square wave signal remained close to 1, compared to the correlation coefficient calculated based on the voltage signal without the superimposed square wave signal. Furthermore, when the anomaly occurred, the correlation coefficient calculated based on the voltage signal with the superimposed square wave signal decreased significantly.

[0122] Table 1

[0123] Date Minimum correlation coefficient Date Minimum correlation coefficient 2024-3-23 0.991633912 2024-4-13 0.991767257 2024-3-28 0.992416767 2024-4-27 0.999204355 2024-4-5 0.991401658 2024-4-27 0.999286271 2024-4-13 0.992417142 2024-7-11 0.495748031 (anomaly)

[0124] Furthermore, compared to the mean standard deviation calculated based on the voltage signal without superimposed square wave signals for each cell, the mean standard deviation calculated based on the voltage signal with superimposed square wave signals for each cell showed a smaller increase before the anomaly occurred. However, after the anomaly occurred, the mean standard deviation calculated based on the voltage signal with superimposed square wave signals for each cell showed a larger increase. See [link to relevant documentation]. Figure 6 .

[0125] In some embodiments, the voltage rank change can also be calculated based on the voltage signal of the battery cell. The voltage rank change reflects the anomaly in the relative voltage position between battery cells, thereby enhancing the significance of the anomaly.

[0126] In some embodiments, the identification of cell anomalies using correlation coefficients described above is merely an example. Other methods can also be used, such as statistical verification, machine learning models (e.g., neural networks, support vector machines, XGBoost, decision trees, and random forests), and time series analysis (e.g., moving averages, exponential smoothing, and multinomial fitting). Taking the machine learning model approach as an example, for each cell, the enhanced voltage signal of the cell is input into the machine learning model to determine whether the cell is abnormal.

[0127] In some embodiments, the aforementioned anomaly may be an internal short circuit, enabling accurate identification of internal short circuit anomalies in their early stages, thus providing reliable technical support for early warning of thermal runaway. Of course, the anomaly may also be other types, and this application does not limit it.

[0128] This application provides an anomaly identification method that can adapt to various operating conditions, such as high-rate charging and discharging, temperature fluctuations, and other complex conditions, demonstrating strong generalization ability. It also reduces the false positive rate of anomalies and ensures the stability of identification under complex conditions such as high-rate charging and discharging. Furthermore, it is applicable to various scenarios such as electric vehicles and energy storage devices, providing efficient anomaly identification and response capabilities.

[0129] For example, Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention is shown. Figure 7 As shown, the electronic device 500 may include a processor 510. Optionally, the electronic device may also include a memory 520. Exemplarily, the device is a computing device.

[0130] Processor 510 may include one or more processing units, such as application processor (AP), modem processor, graphics processing unit (GPU), image signal processor (ISP), controller, video codec, digital signal processor (DSP), baseband processor, and / or neural network processing unit (NPU). These different processing units may be independent devices or integrated into one or more processors.

[0131] The controller can generate operation control signals based on the instruction opcode and timing signals to complete the control of instruction fetching and execution.

[0132] The processor 510 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 510 is a cache memory. This memory can store instructions or data that the processor 510 has just used or that are used repeatedly. If the processor 510 needs to use the instruction or data again, it can directly retrieve it from the memory. This avoids repeated accesses, reduces the waiting time of the processor 510, and thus improves the efficiency of the system.

[0133] In some embodiments, processor 510 may include one or more interfaces. These one or more interfaces may be used to connect processor 510 to memory 520.

[0134] The memory 520 can be used to store computer executable program code, which includes instructions. The memory 520 may include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as image playback functionality), etc. The data storage area may store data created during the use of the electronic device 500, etc. The processor 510 executes various functional applications and data processing of the electronic device 500 by running instructions stored in the memory 520 and / or instructions stored in memory located within the processor.

[0135] It is understood that the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on the device. In other embodiments of the present invention, the device may include... Figure 7 The diagram shows more or fewer components, or combinations of components, or separate components, or different arrangements of components. The components shown can be implemented in hardware, software, or a combination of both.

[0136] like Figure 8 The diagram shown is a structural schematic of an electronic device provided in an embodiment of the present invention. This electronic device 2200 can be used to implement the methods described in the above method embodiments. For example, the electronic device 2200 may specifically include a processing unit 2201.

[0137] The processing unit 2201 is used to support the electronic device 2200 in performing operations. Figures 2 to 6 The processing function described in any one of the following statements.

[0138] Optional, Figure 8 The illustrated electronic device 2200 may also include a communication unit ( Figure 8 (Not shown in the image), this communication unit is used to support the electronic device 2200 in performing the steps of communication between the device and other devices in the embodiments of the present invention.

[0139] Optional, Figure 8 The illustrated electronic device 2200 may further include a storage unit 2203 that stores programs or instructions. When the processing unit 2201 executes the program or instructions, it causes... Figure 8 The electronic device 2200 shown can perform the method described in the above-described method embodiments.

[0140] Figure 8 The technical effects of the electronic device 2200 shown can be referred to the technical effects of the method shown in the above method embodiments, and will not be repeated here. Figure 8The processing unit 2201 involved in the illustrated electronic device 2200 can be implemented by a processor or processor-related circuit components, and can be a processor or a processing module. The communication unit can be implemented by a transceiver or transceiver-related circuit components, and can be a transceiver or a transceiver module.

[0141] This invention also provides a chip system (or chip), such as... Figure 9 As shown, the chip system includes at least one processor 2301 and at least one interface circuit 2302. The processor 2301 and the interface circuit 2302 are interconnected via lines. For example, the interface circuit 2302 can be used to receive signals from other devices. As another example, the interface circuit 2302 can be used to send signals to other devices (e.g., the processor 2301). Exemplarily, the interface circuit 2302 can read instructions stored in memory and send those instructions to the processor 2301. When the instructions are executed by the processor 2301, the device can perform the various steps executed by the device in the above embodiments. Of course, the chip system may also include other discrete components, and this embodiment of the invention does not specifically limit this.

[0142] Optionally, the chip system may include one or more processors. These processors can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor, implemented by reading software code stored in memory.

[0143] Optionally, the chip system may contain one or more memories. These memories may be integrated with the processor or separated from it; this invention is not limiting. For example, the memory may be a non-transient processor, such as a read-only memory (ROM), which may be integrated with the processor on the same chip or disposed on different chips. This invention does not specifically limit the type of memory or the arrangement of the memory and processor.

[0144] For example, the chip system may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a micro controller unit (MCU), a programmable logic device (PLD), or other integrated chips.

[0145] In some embodiments, the aforementioned electronic device may be a computer, vehicle terminal, or other device with data processing capabilities. Additionally, the aforementioned electronic device may also include an energy storage device management system (or alternatively, the electronic device may function as an energy storage device management system), which is connected to an energy storage device, such as a battery (e.g., a lithium-ion battery), and the energy storage device management system is a battery management system.

[0146] In some embodiments, this application provides a vehicle capable of performing the methods described above. Exemplarily, the vehicle includes the described electronic equipment and energy storage device. Alternatively, the vehicle includes the described energy storage device management system and energy storage device.

[0147] In some embodiments, this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method described above.

[0148] In some embodiments, this application provides a computer program product including a computer program that, when executed by a processor, implements the method described above.

[0149] It should be understood that each step in the above method embodiments can be completed by integrated logic circuits in the processor hardware or by instructions in software form. The method steps disclosed in the embodiments of the present invention can be directly manifested as being executed by a hardware processor, or being executed by a combination of hardware and software modules in the processor.

[0150] The embodiments of the present invention have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

[0151] The embodiments of the present invention have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. An anomaly identification method, characterized in that, include: Acquire the voltage signal of each cell in the energy storage device; For each of the battery cells, a square wave signal is superimposed on the voltage signal of the battery cell to obtain an enhanced voltage signal; The abnormality identification result of the energy storage device is output based on the enhanced voltage signal.

2. The method according to claim 1, characterized in that, The step of superimposing a square wave signal onto the voltage signal of the battery cell includes: The voltage signal of the battery cell is superimposed with the square wave signal corresponding to the battery cell; wherein, the amplitude of the square wave signal corresponding to the battery cell is determined based on the voltage signal of the battery cell after adjusting the reference amplitude.

3. The method according to claim 2, characterized in that, The method further includes: Based on a preset scaling factor, the standard deviation of the voltage signal corresponding to the battery cell is adjusted to obtain the adjusted voltage data. The reference amplitude is adjusted based on the adjusted voltage data to obtain the adjusted amplitude; The amplitude of the square wave signal corresponding to the battery cell is determined based on the adjusted amplitude.

4. The method according to claim 3, characterized in that, The amplitude of the square wave signal is limited between the adjusted amplitude, the preset minimum amplitude, and the preset maximum amplitude.

5. The method according to any one of claims 1 to 4, characterized in that, Before superimposing a square wave signal onto the voltage signal of the battery cell, the method further includes: The voltage signal of the battery cell is preprocessed to obtain the preprocessed voltage signal of the battery cell; wherein the preprocessing includes one or more of the following: feature extraction processing, voltage filtering processing during discontinuous charging time, and voltage filtering processing within the invalid state of charge interval. The step of superimposing a square wave signal onto the voltage signal of the battery cell includes: The preprocessed voltage signal of the battery cell is superimposed with the square wave signal.

6. The method according to any one of claims 1 to 5, characterized in that, The step of outputting the anomaly identification result of the energy storage device based on the enhanced voltage signal includes: Based on the enhanced voltage signal of the battery cell, the correlation coefficient between the battery cells of the energy storage device is determined; If the correlation coefficient is less than or equal to a first threshold, the anomaly identification result is output; wherein the first threshold is determined based on the correlation coefficient.

7. The method according to claim 6, characterized in that, The first threshold is determined based on the median of the determined correlation coefficient.

8. The method according to claim 6 or 7, characterized in that, The anomaly identification results include one or more of the following: abnormal battery cell information, abnormal time, and vehicle information to which the abnormal battery cell belongs.

9. The method according to any one of claims 1 to 8, characterized in that, The anomaly identification result indicates that there is an internal short circuit in the battery cell of the energy storage device.

10. An energy storage device management system, characterized in that, The energy storage device management system is electrically connected to the energy storage device; The energy storage device management system is used to perform the method as described in any one of claims 1 to 9.

11. A vehicle, characterized in that, Includes the energy storage device management system and energy storage device as described in claim 10.

12. 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 method as described in any one of claims 1 to 9.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 9.

Images