Battery anomaly detection method and device, equipment, storage medium and program product

Abstract

The invention relates to a battery anomaly detection method, device and equipment, a storage medium and a program product. The method comprises the following steps: acquiring voltage data of each battery in a battery pack in a preset time period, determining an abnormal battery of which the voltage data is greater than or equal to a first threshold value, and dividing the batteries of which the voltage data is less than the first threshold value into a to-be-analyzed set, and determining the dispersion degree of the battery voltage data by calculating the standard deviation of the battery data in the set, if the standard deviation is greater than or equal to a second threshold value, considering that an abnormal value possibly exists, performing analysis through an entropy algorithm, and determining an abnormal battery through the characteristic value of each battery under the entropy algorithm. By setting the first threshold value, the obviously abnormal batteries can be preliminarily screened, then the abnormal possibility of the remaining batteries is determined based on the standard deviation, and finally, the abnormal batteries can be more accurately detected through overall analysis of the entropy algorithm and based on the relevance between the voltage and the thermal runaway, and the thermal runaway risk of the batteries can be timely processed and reduced.

Description

Technical Field

[0001] The present invention relates to the field of battery detection, and in particular to a battery abnormality detection method, device, equipment, storage medium and program product. Background Art

[0002] With the development of the new energy vehicle industry, power batteries such as lithium batteries are being used more and more widely. In actual applications, batteries may experience thermal runaway under complex working conditions, which may cause irreversible damage to the battery or even the vehicle.

[0003] At present, in order to deal with abnormal battery conditions such as battery thermal runaway, the temperature, voltage and other parameters of the battery pack can be monitored, and early warnings can be issued for detected abnormalities. However, the causes of thermal runaway are complex, and battery packs often contain multiple batteries. Conventional monitoring methods are difficult to capture subtle abnormalities in battery packs and can only work when the abnormal conditions are more obvious, resulting in insufficient timeliness and accuracy in battery abnormality detection and early warning. Summary of the invention

[0004] One of the purposes of the present invention is to provide a battery abnormality detection method, device, equipment, storage medium and program product to solve the problem that battery abnormality detection is not timely and accurate enough.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A battery abnormality detection method, comprising:

[0007] Obtaining voltage data of each battery in the battery pack within a preset time period;

[0008] Determine a battery whose voltage data is greater than or equal to a preset first threshold as an abnormal battery;

[0009] Classify the batteries whose voltage data is less than the first threshold into a set to be analyzed, and calculate the standard deviation based on the voltage data of the batteries in the set to be analyzed;

[0010] If the standard deviation is greater than or equal to a preset second threshold, a preset entropy algorithm is used to calculate a characteristic value of each battery in the set to be analyzed, and abnormal batteries are determined from the set to be analyzed according to the characteristic values.

[0011] Further, the characteristic value of each battery in the set to be analyzed is calculated by a preset entropy algorithm, including:

[0012] Establishing a voltage matrix based on the voltage data corresponding to the set to be analyzed;

[0013] Determine a plurality of extreme value intervals according to the maximum value and the minimum value in the voltage matrix;

[0014] The probability that the voltage data of each battery in the set to be analyzed belongs to each extreme value interval is determined, and the Shannon entropy of each battery is calculated based on the probability.

[0015] Further, determining the probability that the voltage data of each battery in the set to be analyzed belongs to each extreme value interval includes:

[0016] Establishing an interval matrix based on the number of elements in each column of the voltage matrix falling into different extreme value intervals;

[0017] A target probability matrix is ​​established according to the relationship between the elements in the interval matrix and the extreme value intervals, and the elements in the target probability matrix represent the probability that the voltage data belongs to each extreme value interval.

[0018] Further, determining abnormal batteries from the set to be analyzed according to the characteristic values ​​includes:

[0019] Acquire a reference probability matrix, wherein the reference probability matrix represents a probability distribution of voltage data of a normal battery;

[0020] The relative entropy between the reference probability matrix and the target probability matrix is ​​calculated, and abnormal batteries are determined from the set to be analyzed according to the relative entropy.

[0021] Further, calculating the characteristic value of each battery in the set to be analyzed by a preset entropy algorithm, and determining the abnormal battery from the set to be analyzed according to the characteristic value, including:

[0022] Performing variational mode decomposition on the voltage data corresponding to the set to be analyzed to obtain a plurality of eigenmode components;

[0023] Calculate the energy proportion of each essential mode component according to the energy of each eigenmode component;

[0024] An abnormal battery is determined according to a difference between the energy proportion and a preset third threshold.

[0025] Furthermore, it also includes:

[0026] Performing envelope spectrum analysis based on the eigenmode components, and determining abnormal components from the multiple eigenmode components based on the analysis results;

[0027] An abnormal battery is determined from the set to be analyzed according to the abnormal component.

[0028] A battery abnormality detection device, comprising:

[0029] An acquisition module, used to acquire voltage data of each battery in the battery pack within a preset time period;

[0030] A first determination module, configured to determine a battery whose voltage data is greater than or equal to a preset first threshold as an abnormal battery;

[0031] a grouping module, configured to classify batteries whose voltage data is less than the first threshold into a set to be analyzed, and calculate a standard deviation based on the voltage data of the batteries in the set to be analyzed;

[0032] The second determination module is used to calculate the characteristic value of each battery in the set to be analyzed by a preset entropy algorithm when the standard deviation is greater than or equal to a preset second threshold, and determine abnormal batteries from the set to be analyzed according to the characteristic value.

[0033] An electronic device comprises: a processor, and a memory communicatively connected to the processor;

[0034] The memory stores computer-executable instructions;

[0035] The processor executes the computer-executable instructions stored in the memory to implement the battery abnormality detection method as described in any one of the above.

[0036] A computer-readable storage medium comprises: the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to implement the battery abnormality detection method as described in any one of the above when executed by a processor.

[0037] A computer program product comprises a computer program, wherein when the computer program is executed by a processor, the battery abnormality detection method as described in any one of the above items is implemented.

[0038] The beneficial effects of the present invention are as follows: by setting a first threshold, a preliminary screening can be performed based on data such as the voltage value of the battery to determine batteries with obvious abnormalities, and then based on the standard deviation, it is determined whether the remaining batteries may contain abnormal values ​​that are significantly different from normal data. Finally, an entropy algorithm is used to perform an overall analysis of all data of the remaining batteries. Based on the correlation between voltage and thermal runaway, abnormal batteries can be detected more accurately, handled in a timely manner, and the risk of thermal runaway of the battery can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of an application scenario provided for an exemplary embodiment of the present invention;

[0040] Figure 2 A flowchart of a battery abnormality detection method provided by an exemplary embodiment of the present invention;

[0041] Figure 3 A schematic diagram of an entropy algorithm processing flow provided for an exemplary embodiment of the present invention;

[0042] Figure 4 A schematic diagram of a process for determining an abnormal battery provided by an exemplary embodiment of the present invention;

[0043] Figure 5 A specific application diagram of a battery abnormality detection method provided by an exemplary embodiment of the present invention;

[0044] Figure 6 A schematic diagram of a data collection process provided for an exemplary embodiment of the present invention;

[0045] Figure 7 A schematic diagram of a data processing flow provided for an exemplary embodiment of the present invention;

[0046] Figure 8 A schematic diagram of an early warning process provided for an exemplary embodiment of the present invention;

[0047] Fig. 9 A schematic diagram of the structure of a battery abnormality detection device provided by an exemplary embodiment of the present invention;

[0048] Fig.10 A schematic structural diagram of an electronic device provided by an exemplary embodiment of the present invention.

[0049] Through the above drawings, clear embodiments of the present invention have been shown, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present invention in any way, but to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0050] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0051] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0052] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0053] The terms "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, product or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, product or device. In the absence of further restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. For example, if the words first, second, etc. are used to indicate names, they do not indicate any particular order.

[0054] Lithium-ion power batteries are a key component of new energy vehicles. In actual use, batteries may experience thermal runaway under complex operating conditions. For example, thermal runaway of power batteries caused by internal short circuits, water immersion or external impacts will lead to increased pressure inside the battery pack and a sharp rise in battery temperature, causing irreversible damage to the power battery and even the vehicle.

[0055] Conventional monitoring methods are often difficult to accurately detect complex thermal runaway causes. For example, in the early stages of a micro short circuit inside a battery, it may only manifest as a very small increase in local temperature. The accuracy of existing temperature sensors is limited, and it is difficult to capture subtle changes and judge them as a prelude to thermal runaway, resulting in a lag in early warning. Therefore, how to detect battery abnormalities in a timely and accurate manner is a major problem.

[0056] Based on the above problems, the present invention provides a battery abnormality detection method, device, equipment, storage medium and program product. The battery abnormality detection method provided by the present invention can analyze the battery status based on the voltage and other data of the battery pack, detect abnormal batteries that may have thermal runaway before the event occurs, and reduce the risk of thermal runaway.

[0057] Figure 1 A schematic diagram of an application scenario provided by the present invention. Figure 1 As shown, a battery pack containing multiple batteries can be deployed in the vehicle to provide power for the vehicle, and the vehicle can also include a control system and a battery management system. Among them, the battery management system can collect relevant data such as the voltage value of the battery pack, and can report the collected data to the control system. The control system can analyze the battery status in the battery pack based on the received data to determine whether there is an abnormality such as thermal runaway.

[0058] The application scenarios mentioned above are only some examples. Those skilled in the art can expand the application to specific business scenarios, and the embodiments of this application do not impose specific limitations on this. Figure 1 For application scenarios, refer to Figures 2 to 6 The interactive method according to the exemplary embodiment of the present invention is described.

[0059] Figure 2 FIG. 1 is a flow chart of a battery abnormality detection method provided by an exemplary embodiment of the present invention. Figure 2 As shown, the method may include:

[0060] Step S201, obtaining voltage data of each battery in a battery pack within a preset time period.

[0061] The voltage data may include the voltage values ​​of the battery at multiple times within a preset period of time, and may also include the rate of change of the voltage value of the battery within the preset period of time.

[0062] Specifically, the vehicle's battery management system can monitor the voltage value of each battery in the battery pack in real time, and collect the voltage value of each battery at a certain sampling frequency to obtain the voltage value of each battery at multiple times. These collected voltage values ​​can be sent to the vehicle's control system for processing.

[0063] In some possible implementations, the voltage change rate of the battery in a preset time period can also be calculated based on the voltage value. For example, the voltage value of the battery at time T1 is U1, and the voltage value at time T2 is U2, then the voltage change rate in the period from T1 to T2 is (U2-U1) / (T2-T1).

[0064] Step S202: Determine a battery whose voltage data is greater than or equal to a preset first threshold as an abnormal battery.

[0065] Exemplarily, the voltage data is a voltage value, and the voltage values ​​of all batteries in the battery pack at various moments are traversed. If the voltage value of any battery at a certain moment is greater than or equal to a first threshold set for the voltage, the battery can be determined as an abnormal battery with a risk of thermal runaway, and identification information such as the number of the abnormal battery can be output.

[0066] Exemplarily, the voltage data is the voltage change rate, and the voltage change rates of all batteries in the battery pack are traversed. If the voltage change rate of any battery is greater than or equal to the first threshold set for the voltage change, the battery can be determined as an abnormal battery with a risk of thermal runaway, and identification information such as the number of the abnormal battery can be output.

[0067] Step S203: classify the batteries whose voltage data is less than the first threshold into a set to be analyzed, and calculate the standard deviation based on the voltage data of the batteries in the set to be analyzed.

[0068] Specifically, for batteries whose voltage data is less than the first threshold, these batteries can be classified as a set to be further analyzed, and the standard deviation of the voltage data of all batteries in the set can be calculated. If the voltage data is a voltage value, the standard deviation of the voltage value of the batteries in the set at each moment is calculated; if the voltage data is a voltage change rate, the standard deviation of the voltage change rate of the batteries in the set is calculated; if the voltage data contains both a voltage value and a voltage change rate, the standard deviation corresponding to the voltage value and the standard deviation corresponding to the voltage change rate are calculated respectively.

[0069] It is understandable that there may be a situation where the voltage data of each battery in the battery pack is less than the first threshold. In this case, the set to be analyzed includes all the batteries in the battery pack.

[0070] Step S204: if the standard deviation is greater than or equal to a preset second threshold, a preset entropy algorithm is used to calculate a characteristic value of each battery in the set to be analyzed, and abnormal batteries are determined from the set to be analyzed according to the characteristic values.

[0071] Among them, the entropy algorithm can be used to calculate Shannon entropy, relative entropy, cross entropy, energy entropy and envelope entropy, etc.

[0072] In this embodiment, the discrete degree of the battery voltage can be determined by calculating the standard deviation of the voltage data of the battery to be analyzed in the set. If the standard deviation is greater than the preset second threshold, it can be considered that there may be abnormal values ​​in these voltage data. At this time, the entropy algorithm (at least one of the Shannon entropy, energy entropy and envelope entropy algorithms) can be further used to analyze all voltage data, and the specific battery with abnormality can be determined according to the entropy characteristic value of the battery. If the standard deviation is less than the second threshold, it can be considered that the voltage of each battery in the current time window tends to be stable as a whole, and it is not necessary to use the entropy algorithm for processing. Compared with the entropy algorithm processing, the workload of calculating the standard deviation is small, the speed is fast, and the efficiency is high. In this way, the abnormal detection of the current time window can be quickly ended when the standard deviation is small, and the voltage data of the next time window can be processed, thereby improving the efficiency of abnormal detection.

[0073] In some possible implementations, multiple entropy algorithms can be used to calculate the characteristic values ​​of batteries in the set to be analyzed, and the batteries that may exist in the set can be determined based on the characteristic values ​​of each entropy algorithm. The intersection of the determination results of all entropy algorithms is taken to obtain the final abnormal battery.

[0074] The battery anomaly detection method provided in this embodiment can determine abnormal batteries whose voltage data is greater than or equal to the first threshold value by obtaining the voltage data of each battery in the battery pack within a preset time period. It can also classify batteries whose voltage data is less than the first threshold value as a set to be analyzed, and determine the degree of discreteness of the battery voltage data by calculating the standard deviation of the battery data in the set. If the standard deviation is greater than or equal to the second threshold value, it is considered that there may be an abnormal value. The data of the batteries in the set can be further analyzed by an entropy algorithm, and the abnormal battery can be determined by the characteristic value of each battery under the entropy algorithm. By setting the first threshold value, a preliminary screening can be performed based on data such as the battery voltage value to determine batteries with more obvious abnormalities, and then based on the standard deviation, it can be determined whether the remaining batteries may contain abnormal values ​​that are significantly different from normal data. Finally, all data of the remaining batteries are analyzed as a whole through the entropy algorithm. Based on the correlation between voltage and thermal runaway, abnormal batteries can be detected more accurately, handled in a timely manner, and the risk of battery thermal runaway can be reduced.

[0075] In one embodiment, Figure 3 As shown, the characteristic value of each battery in the set to be analyzed is calculated by a preset entropy algorithm, including:

[0076] Step S301: establishing a voltage matrix based on voltage data corresponding to the set to be analyzed.

[0077] Exemplarily, based on the voltage values ​​of all batteries in the set to be analyzed, a time window may be selected, and the following voltage matrix A may be established according to the time corresponding to the voltage value.

[0078]

[0079] Where t can represent the length of the time window, n can represent the number of batteries in the set to be analyzed. i,j It can represent the voltage value of the jth battery at the i-th index in the current time window. The first row of the matrix A can represent the voltage values ​​of all batteries at the first moment, and the first column can represent all voltage values ​​of the first battery at t moments.

[0080] Step S302: determining a plurality of extreme value intervals according to the maximum value and the minimum value in the voltage matrix.

[0081] For example, all elements in the voltage matrix can be traversed to determine the maximum voltage x max and the minimum value x min , so the voltage extreme range is [x min , x max ], and the range can be further divided into multiple extreme value intervals. Exemplarily, the extreme value interval can be expressed as: (x min +(b-1)×(x max -xmin ) / m,x min +b×(x max -x min ) / m], or, [x min +(b-1)×(x max -x min ) / m,x min +b×(x max -x min ) / m). Wherein, m may represent the number of extreme value intervals, b=1,2,…,m. In some possible examples, m may be equal to t.

[0082] Step S303, determining the probability that the voltage data of each battery in the set to be analyzed belongs to each extreme value interval, and calculating the Shannon entropy of each battery based on the probability.

[0083] In some possible implementations, determining the probability that the voltage data of each battery in the set to be analyzed belongs to each extreme value interval may include: establishing an interval matrix based on the number of elements in each column of the voltage matrix falling into different extreme value intervals; and establishing a target probability matrix based on the relationship between the elements in the interval matrix and the extreme value intervals.

[0084] Among them, the elements in the target probability matrix represent the probability that the voltage data belongs to each extreme value interval.

[0085] Exemplarily, the number of element values ​​in each column of the matrix A that belong to each extreme value interval can be calculated, and the following interval matrix B can be established.

[0086]

[0087] Among them, b i,j It can represent the number of elements in the j-th column of matrix A that belong to the i-th extreme value interval.

[0088] After obtaining the interval matrix B, the following target probability matrix P can be further determined based on the matrix B.

[0089]

[0090] Among them, p i,j Can represent b i,j The proportion of the number of i,j It can be expressed as the following formula.

[0091]

[0092] Furthermore, the Shannon entropy matrix H(A) may be calculated based on the following formula.

[0093]

[0094] The above Shannon entropy matrix H(A) contains n values, each value represents the Shannon entropy of a battery. i ) can be p i,j .

[0095] In some possible implementations, such as Figure 3 As shown, determining abnormal batteries from the set to be analyzed based on the characteristic values ​​may include:

[0096] Step S304: Obtain a reference probability matrix.

[0097] The reference probability matrix represents the probability distribution of the voltage data of a normal battery.

[0098] Exemplarily, the voltage data of a normal battery pack during a preset time period when no abnormalities occur can be obtained. The normal battery pack contains the same number of batteries as the battery pack to be detected in the above embodiment. Referring to the method for obtaining the target probability matrix P for the above battery pack, the corresponding reference probability matrix Q can be obtained based on the voltage data of the normal battery pack.

[0099] Step S305 , calculating the relative entropy between the reference probability matrix and the target probability matrix, and determining abnormal batteries from the set to be analyzed according to the relative entropy.

[0100] Exemplarily, the relative entropy of the target probability matrix P and the reference probability matrix Q may be calculated based on the following formula.

[0101]

[0102] Among them, D KL It can represent relative entropy, that is, KL divergence.

[0103] By calculating the relative entropy, the difference between the voltage data of the normal battery pack and the voltage data of the battery pack to be tested can be evaluated, so that the abnormal battery can be determined more accurately.

[0104] This embodiment uses Shannon entropy and relative entropy as characteristic values ​​to determine the state of the battery. Within a time window, the larger the Shannon entropy value of a battery, the greater the amount of information represented by the battery, and the stronger the randomness and uncertainty. Based on the correlation between voltage and thermal runaway, the probability of thermal runaway failure of the battery in this time window and the following time will be greater. By calculating the relative entropy with the normal battery pack, the battery abnormality can be compositely judged, providing reliable support for this solution.

[0105] In one embodiment, Figure 4 As shown, the characteristic value of each battery in the set to be analyzed is calculated by a preset entropy algorithm, and the abnormal battery is determined from the set to be analyzed according to the characteristic value, including:

[0106] Step S401 , performing variational mode decomposition on voltage data corresponding to the set to be analyzed to obtain a plurality of intrinsic mode components.

[0107] Step S402: Calculate the energy proportion of each intrinsic modal component according to the energy of each eigenmodal component.

[0108] Step S403: determining an abnormal battery according to a difference between the energy proportion and a preset third threshold value.

[0109] Specifically, the algorithm can be used to perform VMD (Variational Mode Decomposition) processing on the voltage data of all batteries in the analysis set, and multiple IMFs (Intrinsic Mode Functions) can be obtained after processing. Then, the energy of a single IMF and the total energy are calculated, so that the energy proportion of each IMF can be calculated, and the energy proportion can be further compared with the preset energy threshold. If the difference is too large, the corresponding battery will be regarded as an abnormal battery.

[0110] In some possible implementations, after obtaining the IMF, it may also include: performing envelope spectrum analysis based on the intrinsic mode components, and determining abnormal components from multiple intrinsic mode components based on the analysis results; and determining abnormal batteries from the set to be analyzed based on the abnormal components.

[0111] To further illustrate the implementation scenario of the battery abnormality detection method provided by the present invention, a specific example is provided below for illustration.

[0112] In this example, based on the battery abnormality detection method of the present invention, a power battery early warning model that can be used for the entire vehicle (hereinafter referred to as the "value-rate" model) is specifically provided. The model can analyze the abnormal fluctuation correlation relationship of characteristic parameters such as the voltage and voltage change rate of the battery pack before an accident occurs.

[0113] Figure 5 A specific application diagram of a battery abnormality detection method provided by an exemplary embodiment of the present invention. Figure 5 As shown, the solution may involve a battery management system BMS, a regional controller VIU, and an experience domain controller EDC. In the BMS, an information acquisition module may be deployed to monitor the voltage value of the power battery pack in real time (the sampling frequency may be 0.1 Hz) and transmit it to the VIU. In the VIU, a model processing module may be deployed to process the data received by the VIU and perform abnormality detection. In the EDC, an early warning module may be deployed. The early warning model may process the fault information (such as abnormal batteries, etc.) determined by the model processing module, determine whether thermal runaway occurs, and display it.

[0114] Figure 6A data collection process diagram is provided for an exemplary embodiment of the present invention. Figure 6 As shown, on the BMS side, the voltage value of the power battery pack can be monitored at a specific sampling frequency (such as 0.1 Hz) by deploying information acquisition modules (such as sensors, etc.). The BMS can send the voltage value information to the regional controller VIU through the CAN (Controller Area Network) communication network, thereby providing basic data for subsequent data processing processes.

[0115] Figure 7 A data processing flow diagram is provided for an exemplary embodiment of the present invention. Figure 7 As shown, after the regional controller VIU receives the voltage data sent by the BMS, the model processing module can process the data according to the following link.

[0116] (1) Voltage value judgment: If the voltage value is ≥4.4V, it is judged as level 1 risk and the faulty single cell battery number is output.

[0117] (2) Voltage value determination: 4.4V>voltage value ≥4.25V, it is determined as a level 2 risk and the faulty single cell battery number is output.

[0118] (3) Voltage change rate determination: If the voltage change rate threshold of any single cell is greater than 3%, it is determined to be a level 3 risk and the faulty single cell number is output.

[0119] (4) Entropy algorithm judgment: The entropy algorithm detects abnormal value fluctuations, determines it as a level 4 risk, and outputs the faulty single cell battery number.

[0120] When the regional controller VIU processes data, when the entropy algorithm is used to detect the voltage of a single cell that is about to experience a thermal runaway failure, it can be processed using the Shannon entropy, relative entropy, envelope entropy, and energy entropy algorithms, and the problematic single cell numbers can be output in the form of intersection.

[0121] Figure 8 A schematic diagram of an early warning process provided by an exemplary embodiment of the present invention. Figure 8 As shown, when the experience domain EDC receives the thermal runaway risk level information and the single battery label information that may have problems sent by VIU through the Ethernet communication network ETH, a multi-modal prompt mechanism can be activated. For example, users can intuitively understand the urgency of the thermal runaway risk through text, voice, flashing lights, etc. In addition, EDC can also consider the user's in-depth understanding of the battery status and the need to prevent thermal runaway, thereby providing the corresponding interface and allowing users to view the historical data of the power battery pack voltage value in real time after authorization.

[0122] Fig. 9The following is a schematic diagram of a battery abnormality detection device provided by an exemplary embodiment of the present invention. Fig. 9 As shown, the battery abnormality detection device 900 may include:

[0123] The acquisition module 901 is used to acquire voltage data of each battery in the battery pack within a preset time period.

[0124] The first determination module 902 is configured to determine a battery whose voltage data is greater than or equal to a preset first threshold as an abnormal battery.

[0125] The grouping module 903 is configured to classify the batteries whose voltage data is less than the first threshold into a set to be analyzed, and calculate the standard deviation based on the voltage data of the batteries in the set to be analyzed.

[0126] The second determination module 904 is used to calculate the characteristic value of each battery in the set to be analyzed by a preset entropy algorithm when the standard deviation is greater than or equal to a preset second threshold, and determine abnormal batteries from the set to be analyzed according to the characteristic value.

[0127] In one embodiment, the second determination module 904 is also used to: establish a voltage matrix based on the voltage data corresponding to the set to be analyzed; determine multiple extreme value intervals according to the maximum and minimum values ​​in the voltage matrix; determine the probability that the voltage data of each battery in the set to be analyzed belongs to each extreme value interval, and calculate the Shannon entropy of each battery based on the probability.

[0128] In one embodiment, the second determination module 904 is also used to: obtain a reference probability matrix, which represents the probability distribution of voltage data of normal batteries; calculate the relative entropy between the reference probability matrix and the target probability matrix, and determine abnormal batteries from the set to be analyzed based on the relative entropy.

[0129] In one embodiment, the second determination module 904 is also used to: perform variational modal decomposition on the voltage data corresponding to the set to be analyzed to obtain multiple intrinsic modal components; calculate the energy proportion of each intrinsic modal component based on the energy of each intrinsic modal component; and determine the abnormal battery based on the difference between the energy proportion and a preset third threshold.

[0130] In one embodiment, the second determination module 904 is also used to: obtain the safety indicator to be analyzed; determine the index score of the autonomous driving vehicle under the safety indicator based on the operating data and the environmental data; and calculate the risk score of the autonomous driving vehicle based on the weight of the safety indicator and the index score.

[0131] In one embodiment, the second determination module 904 is further used to: perform envelope spectrum analysis based on the intrinsic mode components, and determine abnormal components from the multiple intrinsic mode components based on the analysis results; and determine abnormal batteries from the set to be analyzed based on the abnormal components.

[0132] The battery abnormality detection device provided in this embodiment is used to execute the technical solution in any of the aforementioned method embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0133] It should be understood that the above device embodiments are only illustrative, and the device of the present invention can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0134] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present invention may be integrated into one unit / module, or each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0135] Fig.10 FIG. 1 is a schematic diagram of a structure of an electronic device provided by an exemplary embodiment of the present invention. Fig.10 As shown, the electronic device 100 includes:

[0136] Processor 101, memory 102, and communication interface 103;

[0137] The memory 102 is used to store executable instructions of the processor 101; the executable instructions may be computer-executable instructions;

[0138] The processor 101 is configured to execute the technical solution in any of the aforementioned method embodiments by executing the executable instructions.

[0139] Optionally, the memory 102 may be independent or integrated with the processor 101 .

[0140] Optionally, when the memory 102 is a device independent of the processor 101, the electronic device 100 may further include:

[0141] The bus 104 , the memory 102 and the communication interface 103 are connected to the processor 101 via the bus 104 and communicate with each other. The communication interface 103 is used to communicate with other devices.

[0142] Optionally, the communication interface 103 may be implemented by a transceiver. The communication interface is used to implement communication between the database access device and other devices (such as a client, a read-write library, and a read-only library). The memory may include a random access memory (RAM) and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage.

[0143] The bus 104 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0144] The above-mentioned processor can be a general-purpose processor, including a central processing unit CPU, a network processor (NP), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0145] The electronic device is used to execute the technical solution in any of the aforementioned method embodiments, and its implementation principle and technical effect are similar and will not be repeated here.

[0146] An embodiment of the present invention further provides a readable storage medium, which may be a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the technical solution provided by any of the aforementioned method embodiments is implemented.

[0147] An embodiment of the present invention further provides a computer program product, including a computer program, which is used to implement the technical solution provided by any of the aforementioned method embodiments when executed by a processor.

[0148] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0149] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not 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 specification.

[0150] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention is indicated by the following claims.

[0151] The above embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Any equivalent substitution or change made by a person skilled in the art based on the present invention is within the protection scope of the present invention.

Claims

1. A battery abnormality detection method, characterized in that: include: Obtaining voltage data of each battery in the battery pack within a preset time period; Determine a battery whose voltage data is greater than or equal to a preset first threshold as an abnormal battery; Classify the batteries whose voltage data is less than the first threshold into a set to be analyzed, and calculate the standard deviation based on the voltage data of the batteries in the set to be analyzed; If the standard deviation is greater than or equal to a preset second threshold, a preset entropy algorithm is used to calculate a characteristic value of each battery in the set to be analyzed, and abnormal batteries are determined from the set to be analyzed according to the characteristic values.

2. The battery abnormality detection method according to claim 1, characterized in that: The calculating the characteristic value of each battery in the set to be analyzed by using a preset entropy algorithm includes: Establishing a voltage matrix based on the voltage data corresponding to the set to be analyzed; Determine a plurality of extreme value intervals according to the maximum value and the minimum value in the voltage matrix; The probability that the voltage data of each battery in the set to be analyzed belongs to each extreme value interval is determined, and the Shannon entropy of each battery is calculated based on the probability.

3. The battery abnormality detection method according to claim 2, characterized in that: The determining the probability that the voltage data of each battery in the set to be analyzed belongs to each extreme value interval includes: Establishing an interval matrix based on the number of elements in each column of the voltage matrix falling into different extreme value intervals; A target probability matrix is ​​established according to the relationship between the elements in the interval matrix and the extreme value intervals, and the elements in the target probability matrix represent the probability that the voltage data belongs to each extreme value interval.

4. The battery abnormality detection method according to claim 3, characterized in that: The step of determining abnormal batteries from the set to be analyzed according to the characteristic values ​​includes: Acquire a reference probability matrix, wherein the reference probability matrix represents a probability distribution of voltage data of a normal battery; The relative entropy between the reference probability matrix and the target probability matrix is ​​calculated, and abnormal batteries are determined from the set to be analyzed according to the relative entropy.

5. The battery abnormality detection method according to any one of claims 1 to 4, characterized in that: The step of calculating the characteristic value of each battery in the set to be analyzed by using a preset entropy algorithm, and determining abnormal batteries from the set to be analyzed according to the characteristic value, includes: Performing variational mode decomposition on the voltage data corresponding to the set to be analyzed to obtain a plurality of eigenmode components; Calculate the energy proportion of each essential mode component according to the energy of each eigenmode component; An abnormal battery is determined according to a difference between the energy proportion and a preset third threshold.

6. The battery abnormality detection method according to claim 5, characterized in that: Also includes: Performing envelope spectrum analysis based on the eigenmode components, and determining abnormal components from the multiple eigenmode components based on the analysis results; An abnormal battery is determined from the set to be analyzed according to the abnormal component.

7. A battery abnormality detection device, characterized in that: include: An acquisition module, used to acquire voltage data of each battery in the battery pack within a preset time period; A first determination module, configured to determine a battery whose voltage data is greater than or equal to a preset first threshold as an abnormal battery; a grouping module, configured to classify batteries whose voltage data is less than the first threshold into a set to be analyzed, and calculate a standard deviation based on the voltage data of the batteries in the set to be analyzed; The second determination module is used to calculate the characteristic value of each battery in the set to be analyzed by a preset entropy algorithm when the standard deviation is greater than or equal to a preset second threshold, and determine abnormal batteries from the set to be analyzed according to the characteristic value.

8. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when being executed by a processor.

Images