Battery safety early warning method and device, electronic equipment, storage medium and product

Abstract

The embodiment of the invention provides a safety early warning method and device of a battery, electronic equipment, a storage medium and a product. The method comprises the steps of collecting a plurality of preset battery index data based on a collection period, constructing an index information set matrix according to the plurality of battery index data, and obtaining a battery safety value according to the index information set matrix and a preset reasoning model. And determining a target safety threshold interval in which the battery safety value is located from preset safety threshold intervals, and executing an early warning operation corresponding to the target safety threshold interval according to the target safety threshold interval. According to the method provided by the invention, the false alarm problem caused by single index judgment is effectively reduced, and the accuracy of battery safety early warning is improved.

Description

Technical Field

[0001] This application relates to the field of battery technology, and in particular to a battery safety warning method, device, electronic device, storage medium, and product. Background Technology

[0002] Batteries, as core energy storage components, are widely used in numerous fields, and their safety performance directly affects user safety and the healthy development of the industry. Therefore, establishing a reliable battery safety early warning mechanism has become one of the key issues urgently needing to be addressed in the battery technology field.

[0003] In related technologies, battery safety warnings typically rely on a single monitored indicator. When the value of the monitored indicator exceeds or falls below a set threshold, a safety warning is triggered to alert the user.

[0004] However, the false alarm rate of the above-mentioned early warning methods is relatively high. Summary of the Invention

[0005] This application provides a battery safety warning method, device, electronic device, storage medium, and product to achieve the technical effect of reducing the false alarm rate of warnings.

[0006] In a first aspect, embodiments of this application provide a battery safety warning method, including:

[0007] Based on the collection cycle, multiple preset battery indicator data are collected;

[0008] Construct an indicator information set matrix based on multiple battery indicator data;

[0009] Based on the indicator information set matrix and the preset reasoning model, the battery safety value is obtained;

[0010] The target safety threshold range in which the battery safety value falls is determined from the preset safety threshold range;

[0011] Based on the target safety threshold range, execute the warning operation corresponding to the target safety threshold range.

[0012] In one possible implementation, the battery performance data includes voltage data, temperature data, current data, and the duty cycle of the mixed gas concentration. Based on multiple battery performance data, an performance information set matrix is ​​constructed, including:

[0013] The voltage data is input into a pre-established voltage differential entropy feature model, and the voltage differential entropy of the battery is output.

[0014] The temperature data is input into a pre-established temperature gradient field model, which outputs the temperature gradient of the battery.

[0015] The current data is input into a pre-established characteristic band energy ratio model, and the characteristic band energy ratio of the battery is output.

[0016] An index information set matrix is ​​constructed based on voltage differential entropy, temperature gradient, characteristic frequency band energy ratio, and mixed gas concentration duty cycle.

[0017] In one possible implementation, the battery safety value is obtained based on the indicator information set matrix and a preset inference model, including:

[0018] The confidence level of each battery indicator is determined based on the indicator information set matrix and the preset confidence algorithm.

[0019] Based on the voltage difference entropy of each battery and the preset weighting algorithm, the feature weights of each battery index are determined.

[0020] The confidence level and feature weight of each battery indicator are input into a preset inference model to obtain the battery safety value.

[0021] In one possible implementation, based on a target safety threshold range, an early warning operation corresponding to the target safety threshold range is executed, including:

[0022] Based on the target safety threshold range, the target warning value is determined from the mapping relationship between the preset safety threshold range and the warning value;

[0023] Based on the preset warning strategy for the target warning value, execute the warning operation corresponding to the warning strategy.

[0024] In one possible implementation, before collecting multiple preset battery indicator data based on the collection period, the following steps are also included:

[0025] Obtain the sampling frequency corresponding to each battery indicator data;

[0026] The data collection time is synchronized based on the collection frequency corresponding to each battery indicator data to determine the collection cycle.

[0027] In one possible implementation, the acquisition time synchronization process is performed based on the acquisition frequency corresponding to each battery indicator data to determine the acquisition cycle, including:

[0028] The sampling frequency corresponding to each battery indicator data is input into a preset time synchronization algorithm, and the sampling period is output.

[0029] Secondly, embodiments of this application provide a battery safety warning device, comprising:

[0030] The data acquisition module is used to collect multiple preset battery indicator data based on the acquisition cycle;

[0031] The processing module is used to construct an indicator information set matrix based on multiple battery indicator data.

[0032] The processing module is also used to obtain the battery safety value based on the indicator information set matrix and the preset inference model;

[0033] The determination module is used to determine the target safety threshold range in which the battery safety value is located from the preset safety threshold range;

[0034] The processing module is also used to execute early warning operations corresponding to the target safety threshold range.

[0035] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0036] The memory stores the instructions that the computer executes;

[0037] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0038] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0039] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0040] The battery safety warning method, device, electronic device, storage medium, and product provided in this application, by collecting multiple battery indicator data based on a collection cycle and constructing an indicator information set matrix, overcomes the limitations of related technologies that rely on single indicator threshold judgments, and can comprehensively capture multimodal data during battery operation. By combining a preset inference model with the indicator information set matrix for comprehensive analysis and calculation to obtain the battery safety value, accurate quantitative assessment of the battery safety status can be achieved. Then, by matching the target safety threshold range corresponding to the battery safety value, corresponding warning operations are executed. This effectively reduces false alarms caused by single indicator judgments and improves the accuracy of battery safety warnings. Attached Figure Description

[0041] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0042] Figure 1This is a schematic diagram of an application scenario provided by an embodiment of this application;

[0043] Figure 2 A schematic flowchart illustrating a battery safety warning method provided in an embodiment of this application;

[0044] Figure 3 A flowchart illustrating a method for constructing an indicator information set matrix provided in an embodiment of this application;

[0045] Figure 4 A flowchart illustrating a method for obtaining a battery safety value provided in an embodiment of this application;

[0046] Figure 5 A flowchart illustrating a method for performing an early warning operation corresponding to a target safety threshold range, provided in an embodiment of this application;

[0047] Figure 6 This is a schematic diagram of the structure of an early warning strategy provided in an embodiment of this application;

[0048] Figure 7 A schematic diagram illustrating a battery safety warning method provided in an embodiment of this application;

[0049] Figure 8 This is a schematic diagram of the structure of a battery safety warning device provided in an embodiment of this application;

[0050] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0051] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0052] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0053] With the advancement of the "dual-carbon" strategy, new energy storage systems based on lithium batteries are being deployed on a large scale in scenarios such as power peak shaving, renewable energy consumption, and user-side energy storage. For example, in wind farms or photovoltaic power plants, energy storage systems improve grid stability through peak shaving and valley filling, and smoothing power fluctuations. On the user side, energy storage systems can realize peak-valley electricity price arbitrage and provide backup power support. However, lithium batteries are susceptible to thermal runaway under extreme conditions such as overcharging, over-discharging, short circuits, mechanical damage, or thermal abuse. This can trigger a chain reaction in the battery pack and even the entire energy storage container, leading to accidents such as fires and explosions, causing significant property damage, personal injury, and environmental pollution. For example, inside an energy storage container, battery modules may generate flammable gases during charging and discharging due to localized overheating, internal short circuits, or electrolyte leaks. If not warned in time, this could create an explosive environment within seconds. Furthermore, energy storage systems are typically deployed in high-temperature, high-humidity, or enclosed environments, further exacerbating the complexity of thermal runaway risks.

[0054] In related technologies, battery safety warnings are typically issued by collecting single-indicator data from devices such as temperature sensors, voltage sensors, or gas concentration detectors, and triggering an alarm based on a preset fixed threshold. For example, an alarm is issued when the battery temperature exceeds a certain threshold.

[0055] However, the above methods do not consider the coupling relationship of multiple parameters. For example, they only judge the risk of thermal runaway by temperature anomalies and ignore the related characteristics such as voltage fluctuations and gas concentration changes, resulting in a high false alarm rate for warnings and failing to meet the actual needs of high-safety batteries.

[0056] Therefore, addressing the problems in related technologies, this application proposes a battery safety early warning method. Specifically, multiple preset battery indicator data are collected according to a collection cycle, and an indicator information set matrix is ​​constructed using the battery indicator data to integrate multi-dimensional data and reflect parameter coupling relationships. A preset inference model is used to calculate the battery safety value and determine the target safety threshold range to which the battery safety value belongs, thereby executing an early warning operation corresponding to the target safety threshold range. By using multiple indicators in synergy, the deficiencies of single-indicator early warning are compensated for, thus achieving more accurate battery safety early warning.

[0057] To facilitate understanding of the method of this application, an exemplary application scenario is provided below, taking the application in the field of new energy vehicles as an example, such as... Figure 1 As shown, Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of this application. The application scenario includes a power battery pack 01 that provides power to a vehicle and an on-board battery management system 02 that performs control and early warning functions.

[0058] During vehicle operation, the on-board battery management system 02 synchronously collects multiple key battery indicator data through various sensors based on a collection cycle, and integrates these multi-dimensional data to construct an indicator information matrix. By calling a preset inference model to perform calculations on this matrix, a quantified battery safety value is output. From a preset multi-level safety threshold range, the target safety threshold range to which the battery safety value belongs is located, and the corresponding warning operation is executed, thereby effectively reducing false alarms.

[0059] It is understood that the above examples are for illustrative purposes only and do not limit this application. The specific details can be determined based on the actual application situation.

[0060] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0061] Please see Figure 2 , Figure 2 This is a flowchart illustrating a battery safety warning method provided in an embodiment of this application. The execution subject of this method can be a battery safety warning device. This battery safety warning device can be implemented through a computer program, or through a medium storing the relevant computer program, such as a USB flash drive and / or optical disc, or through a physical device integrating or installing the relevant computer program, such as a chip or electronic device. The electronic device can be a battery management system, a server, a server cluster, a smart terminal, etc. The method can include:

[0062] S201. Based on the acquisition cycle, acquire multiple preset battery indicator data.

[0063] In this embodiment, the execution entity is a battery management system, which is pre-configured with a multi-source data acquisition system, including an Energy Management Unit (EMU), a Battery Management Unit (BMU), a Battery Cluster Management Unit (BCMU), a module expansion force sensor, and a fire detector.

[0064] Before collecting multiple preset battery indicator data based on the collection cycle, the collection cycle needs to be determined first.

[0065] One possible approach is to obtain the sampling frequency corresponding to each battery indicator data, and perform sampling time synchronization processing based on the sampling frequency corresponding to each battery indicator data to determine the sampling cycle.

[0066] In this embodiment, battery performance data includes, but is not limited to: voltage data, temperature data, current data, and mixed gas concentration duty cycle, and may also include module expansion force, etc.

[0067] The EMU inputs the acquisition frequency corresponding to each battery indicator data into a preset time synchronization algorithm and outputs the acquisition cycle.

[0068] Specifically, the preset time synchronization algorithm is shown in the following formula (1):

[0069] (1)

[0070] in, Indicates the data collection period; Indicates the voltage sampling frequency; Indicates the frequency at which temperature is collected; The sampling frequency indicating the concentration of the mixed gas; This indicates the sampling frequency of the module's expansion force; This indicates the preset synchronization coefficient, which can be a value less than or equal to 100us.

[0071] It is understood that the indicators in the above formula (1) can be flexibly adjusted according to the actual application situation, and this application does not impose any restrictions.

[0072] After determining the sampling period, the EMU will send the sampling period to the BMU, BCMU, module expansion force sensor, and fire detector to collect the corresponding data.

[0073] The BMU (Battery Management Unit) collects the real-time cell voltage (V) and temperature (T) of individual battery cells based on the acquisition cycle and uploads them to the BCMU. The BCMU collects the battery cluster current through a Hall sensor based on the acquisition cycle. The module expansion force sensor collects the module expansion force of the battery based on the acquisition cycle. The fire detector collects the duty cycle of the concentration of mixed gases such as volatile organic compounds (VOCs), carbon monoxide (CO), and hydrogen (H2).

[0074] S202. Construct an indicator information set matrix based on multiple battery indicator data.

[0075] Please see Figure 3 , Figure 3 This application provides a flowchart illustrating a method for constructing an indicator information set matrix, which may include the following steps:

[0076] S301. Input the voltage data into the pre-established voltage differential entropy feature model and output the battery voltage differential entropy.

[0077] In this step, feature extraction is performed to obtain time-domain features, with voltage differential entropy being the time-domain feature.

[0078] Obtain the voltage time-series data V of a single cell based on the acquisition period ϑt. i (t), where t represents a time point. For the voltage at each time point, calculate its change over the time interval ϑt. The change can be obtained using the following formula (2):

[0079] (2)

[0080] in, Indicates a time interval; This indicates the phase zero point voltage of a single cell during a time interval. The change within.

[0081] Will The range of values ​​is divided into N intervals, and the statistics within each interval are calculated. The frequency of occurrence is used as the probability that the voltage change takes the corresponding value in the h-th interval. (h=1,2,……,N) where the following conditions must be met. .

[0082] The above results The pre-established voltage differential entropy characteristic model is given by the following formula (3):

[0083] (3)

[0084] in, This represents the voltage differential entropy.

[0085] S302. Input the temperature data into the pre-established temperature gradient field model and output the temperature gradient of the battery.

[0086] The battery temperature monitoring area is divided into a two-dimensional grid. The target point i to be calculated is selected as the center of the grid, and the left and right adjacent points (horizontal direction) and the up and down adjacent points (vertical direction) of this point are determined. The temperatures of the horizontal adjacent points corresponding to the center point i are obtained, as well as the temperature of the right adjacent point. Temperature of the left adjacent point Temperature of adjacent points in the vertical direction: Temperature of the upper adjacent point and the temperature of the next adjacent point Define the horizontal spacing of the two-dimensional grid, i.e., the distance between the left and right adjacent points. Vertical spacing is the distance between adjacent points. .

[0087] Input the above temperature data and grid spacing into the pre-established temperature gradient field model, i.e., the following formulas (4) and (5), to calculate the horizontal gradient component and the vertical gradient component respectively:

[0088] Horizontal gradient components: (4)

[0089] Vertical gradient components: (5)

[0090] Combining the horizontal and vertical gradient components yields the temperature gradient vector at center point i. .

[0091] S303. Input the current data into the pre-established characteristic frequency band energy ratio model and output the characteristic frequency band energy ratio of the battery.

[0092] In this step, feature extraction is performed to obtain frequency domain features, and the characteristic frequency band energy ratio of the battery is the frequency domain feature.

[0093] Obtain the original time-domain current signal I(t) of the battery, and simultaneously determine the current sampling frequency. .

[0094] Determine the parameters of the Morlet wavelet transform, including the center value of the wavelet frequency. Its value can be 6, and the scale parameter a and translation parameter can also be 6. , The time shift of the signal, the scale parameter a, can be obtained by the following formula (6):

[0095] (6)

[0096] Perform Morlet wavelet transform on the current signal to convert the original current time-domain signal I(t), the scaling parameter a, and the translation parameter into a single signal. Input the Morlet wavelet transform formula (7) to calculate the wavelet coefficients. :

[0097] (7)

[0098] in, This represents the complex conjugate of the wavelet function.

[0099] To calculate the baseline energy, calculate the squared modulus of the wavelet coefficients when the scale parameter a=0, i.e., the baseline energy. .

[0100] Will and The characteristic band energy ratio is obtained by inputting it into the pre-established characteristic band energy ratio model, i.e., the following formula (8). :

[0101] (8)

[0102] S304. Construct an index information set matrix based on voltage differential entropy, temperature gradient, characteristic frequency band energy ratio, and mixed gas concentration duty cycle.

[0103] The acquired voltage differential entropy, temperature gradient, mixed gas concentration duty cycle, and characteristic frequency band energy ratio are integrated into a structured information set, providing a unified multi-parameter input basis for subsequent model analysis.

[0104] The constructed indicator information set matrix E is shown in the following formula (9):

[0105] (9)

[0106] in, Represents voltage differential entropy; Represents the temperature gradient; Indicates the duty cycle of the mixed gas concentration; This indicates the energy ratio of the characteristic frequency band.

[0107] S203. Based on the indicator information set matrix and the preset reasoning model, obtain the battery safety value.

[0108] Optionally, the preset inference model can be a Petri net inference model.

[0109] Please see Figure 4 , Figure 4 This is a flowchart illustrating a method for obtaining a battery safety value according to an embodiment of this application. The method may include the following steps:

[0110] S401. Determine the confidence level of each battery indicator based on the indicator information set matrix and the preset confidence level algorithm.

[0111] From the constructed matrix of indicator information In the process, extract the original observation value of each indicator and record it as follows: k=1,2,3,4.

[0112] The parameters of the confidence algorithm are determined by pre-setting the two parameters of the membership function Sigmoid, namely the sensitivity coefficient. and offset coefficient The sensitivity coefficient reflects the degree to which the corresponding indicator is sensitive to changes, while the offset coefficient... The threshold / critical value reflecting the corresponding indicator needs to be determined in advance for each indicator. Configuration.

[0113] For each indicator's original observation value, substitute it into the preset confidence algorithm, i.e., the following formula (10), to calculate its confidence level. :

[0114] (10)

[0115] Repeat the above steps to calculate the confidence levels of voltage differential entropy, temperature gradient, mixed gas concentration duty cycle, and characteristic frequency band energy ratio in the indicator information set matrix, and finally obtain the confidence level of each battery indicator.

[0116] S402. Determine the feature weights of each battery index based on the voltage difference entropy of each battery and the preset weighting algorithm.

[0117] Feature weights of each battery indicator It can be obtained through the following formula (11):

[0118] (11)

[0119] in, This represents the entropy of the k-th voltage difference; This represents the entropy of the m-th voltage difference.

[0120] S403. Input the confidence level of each battery indicator and the feature weight of each battery indicator into the preset inference model to obtain the battery safety value.

[0121] The pre-defined reasoning model is shown in the following formula (12):

[0122] (12)

[0123] in, ; Indicates the battery safety value; This represents a weighted operator, defined as a multiplication operator. ; This represents an aggregation operator, defined as an addition operation.

[0124] S204. Determine the target safety threshold range where the battery safety value is located from the preset safety threshold range.

[0125] In this embodiment, multiple safety threshold ranges are preset. Therefore, based on the battery safety value, the corresponding target safety threshold range can be determined from the preset safety threshold ranges.

[0126] S205. Based on the target safety threshold range, execute the warning operation corresponding to the target safety threshold range.

[0127] The specific implementation process will be described in detail in the following embodiments. Please refer to the following embodiments.

[0128] In the above embodiments of this application, by collecting multiple battery indicator data based on a collection cycle and constructing an indicator information set matrix, the limitations of related technologies that rely on single indicator threshold judgments are overcome, enabling comprehensive capture of multimodal data during battery operation. By combining a preset inference model with the indicator information set matrix for comprehensive analysis and calculation to obtain the battery safety value, accurate quantitative assessment of the battery safety status can be achieved. Furthermore, by matching the target safety threshold range corresponding to the battery safety value, corresponding early warning operations are executed. This effectively reduces false alarms caused by single indicator judgments and improves the accuracy of battery safety early warnings.

[0129] Furthermore, based on the above embodiments, the following embodiments illustrate the process of performing a warning operation corresponding to the target safety threshold range.

[0130] Please see Figure 5 , Figure 5 A flowchart illustrating a method for performing an early warning operation corresponding to a target safety threshold range, provided in this application embodiment, includes:

[0131] S501. Based on the target safety threshold range, determine the target warning value from the mapping relationship between the preset safety threshold range and the warning value.

[0132] For example, if the target safety threshold range in which the battery safety value falls is the first range, for example... Based on the mapping relationship between the preset safety threshold range and the warning value, the target warning value R corresponding to the first range is determined to be 0.

[0133] If the battery safety value falls within the target safety threshold range of the second range, for example... Based on the mapping relationship between the preset safety threshold range and the warning value, the target warning value R corresponding to the second range is determined to be 1.

[0134] If the battery safety value falls within the target safety threshold range of the third range, for example... Based on the mapping relationship between the preset safety threshold range and the warning value, the target warning value R corresponding to the third range is determined to be 2.

[0135] If the battery safety value falls within the fourth safety threshold range, for example... Based on the mapping relationship between the preset safety threshold range and the warning value, the target warning value R corresponding to the fourth range is determined to be 3.

[0136] S502. Based on the preset warning strategy of the target warning value, execute the warning operation corresponding to the warning strategy.

[0137] If R=0, it will operate normally.

[0138] If R=1, the EMU will activate the local audible and visual alarm mechanism. The response time can be preset, for example, the response time ≤1 second. If it exceeds this time, the operation of R=3 will be executed.

[0139] If R=2, the EMU will activate the local audible and visual alarm for fire protection. At the same time, the EMU will upload the alarm to the Energy Management System (EMS) and send a power reduction command to the EMS. The EMS will then control the Power Conversion System (PCS) to operate at a step power reduction. The response time can be 300ms. If this time is exceeded, the system warning and linkage protection will end.

[0140] If R=3, the EMU activates the fire suppression system to spray fire extinguishing material through the puncture valve. At the same time, the EMU sends a main circuit cutoff control command to the Battery Management System (BMS), which then sequentially cuts off the main circuit switches, ending the linkage warning.

[0141] The following will combine Figure 6 For a brief explanation of the above steps, please refer to [link / reference]. Figure 6 , Figure 6 This is a schematic diagram of the structure of an early warning strategy provided in an embodiment of this application.

[0142] The Energy Management Unit (EMU) is the control center. It is connected to the Energy Management System (EMS) via Ethernet, to the Energy Storage Converter (PCS) via CAN bus and dry contact, and to the fire protection system via the Recommended Standard 485 (RS485) interface. It also connects to the Battery Cluster Management Unit (BCMU) cluster via CAN bus. The BCMU includes multiple first to Nth battery cluster management units, and each battery cluster management unit includes multiple battery packs. Each battery pack is connected to the fire protection system.

[0143] The BCMU manages the BMUs of the corresponding battery pack. For example, the first battery cluster management unit BCMU1 is associated with battery packs BMU1-BMU4. The BMU collects data from individual cells and interacts with interfaces such as the Cell Parameter Feedback (CPF) and the Fire Alarm Hardwire Interface (FHI) through the CPF.

[0144] The EMU triggers different operations based on the warning value R. When R=2, it links the EMS and PCS to reduce power. When R=3, it triggers the fire protection system and controls the BMS to cut off the main circuit, etc.

[0145] In the above embodiments of this application, the risk level determination logic is clarified by the correspondence between threshold ranges and warning values. Furthermore, by relying on differentiated strategies corresponding to different warning values, the stability of battery system operation and the timeliness of fault handling are taken into account, effectively improving the accuracy and efficiency of battery system safety protection.

[0146] To facilitate understanding of the method in this application, a brief explanation is provided below using a complete example. Please refer to [link / reference]. Figure 7 , Figure 7 This is a schematic diagram of a battery safety warning method provided in an embodiment of this application.

[0147] In this application, a multi-source data acquisition system is pre-configured for collecting the following types of data.

[0148] The Energy Management Unit (EMU) acquires the collection frequency of various parameters, establishes a timestamp alignment mechanism, determines a unified synchronous collection cycle, and then distributes the cycle to each collection module for multi-source data collection, thereby ensuring the temporal consistency of the data.

[0149] The BMU collects voltage and temperature data of individual cells, the BCMU collects current data of battery clusters, the fire detector collects concentration data of mixed gas, and the module expansion force sensor collects internal expansion force data of battery modules.

[0150] The Energy Management Unit (EMU) extracts the following information based on a pre-established feature model.

[0151] The Energy Management Unit (EMU) obtains the voltage differential entropy characteristic value based on the voltage differential entropy model and the collected voltage data. The EMU obtains the temperature gradient vector based on the temperature gradient field model and the collected temperature data. The EMU obtains the characteristic frequency band energy ratio based on the characteristic frequency band energy ratio model and the collected current data.

[0152] The EMU integrates the calculated characteristic values, such as voltage differential entropy, temperature gradient, mixed gas concentration duty cycle, and characteristic frequency band energy ratio, into an index information set matrix.

[0153] The EMU uses the Sigmoid function to quantify the confidence level of each feature value in the indicator information set matrix, thereby obtaining the confidence level of each battery indicator. The EMU uses the entropy weight method to calculate the feature weights and obtains the battery safety value λrisk based on a preset inference model, such as the Petri net inference model, thus completing the quantitative assessment of the battery safety status.

[0154] The EMU compares the battery safety value λrisk with preset multi-segment dynamic thresholds, determines the warning value R, and executes the corresponding linkage operation:

[0155] like If the warning value R is 0, it is determined to be a safe state and the system is operating normally.

[0156] like If the warning value R is 1, it is determined to be a minor alarm, and the EMU will activate the local audible and visual alarm mechanism.

[0157] like If the warning value R is 2, it is determined to be a moderate alarm. The EMU will simultaneously execute the following actions: activate the fire alarm with sound and light, upload the alarm to the EMS, and send a power reduction command to the EMS. After receiving the command, the EMS will control the PCS to complete the step power reduction operation within a preset time, such as 300ms.

[0158] like If the warning value R is 3, it is judged as a serious risk. The EMU triggers the fire extinguishing system and simultaneously sends a command to the BMS to cut off the main circuit. The BMS then sequentially cuts off the main circuit switches.

[0159] Once the operations at each level are completed or there is no response after a timeout, the system's early warning and linkage protection process ends.

[0160] The specific implementation process of each step is described in the above embodiments. Please refer to the above embodiments. This embodiment will not repeat the description.

[0161] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of a battery safety warning device provided in an embodiment of this application, as shown below. Figure 8 As shown, it includes:

[0162] The acquisition module 801 is used to acquire multiple preset battery indicator data based on the acquisition period.

[0163] The processing module 802 is used to construct an indicator information set matrix based on multiple battery indicator data.

[0164] The processing module 802 is also used to obtain the battery safety value based on the indicator information set matrix and the preset inference model.

[0165] The determination module 803 is used to determine the target safety threshold range in which the battery safety value is located from the preset safety threshold range.

[0166] The processing module 802 is also used to perform a warning operation corresponding to the target safety threshold range based on the target safety threshold range.

[0167] In one possible implementation, the battery performance data includes voltage data, temperature data, current data, and the duty cycle of the mixed gas concentration. The processing module 802 is specifically used for:

[0168] The voltage data is input into a pre-established voltage differential entropy feature model, and the voltage differential entropy of the battery is output.

[0169] Temperature data is input into a pre-established temperature gradient field model, which outputs the temperature gradient of the battery.

[0170] The current data is input into a pre-established characteristic band energy ratio model, and the characteristic band energy ratio of the battery is output.

[0171] An index information set matrix is ​​constructed based on voltage differential entropy, temperature gradient, characteristic frequency band energy ratio, and mixed gas concentration duty cycle.

[0172] In one possible implementation, processing module 802 is specifically used for:

[0173] The confidence level of each battery indicator is determined based on the indicator information set matrix and the preset confidence algorithm.

[0174] The feature weights of each battery index are determined based on the voltage difference entropy of each battery and the preset weighting algorithm.

[0175] The confidence level and feature weight of each battery indicator are input into a preset inference model to obtain the battery safety value.

[0176] In one possible implementation, processing module 802 is specifically used for:

[0177] Based on the target safety threshold range, the target warning value is determined from the mapping relationship between the preset safety threshold range and the warning value.

[0178] Based on the preset warning strategy for the target warning value, execute the warning operation corresponding to the warning strategy.

[0179] In one possible implementation, before collecting multiple preset battery indicator data based on the collection period, the processing module 802 is specifically used for:

[0180] Obtain the sampling frequency corresponding to each battery indicator data.

[0181] The data collection time is synchronized based on the collection frequency corresponding to each battery indicator data to determine the collection cycle.

[0182] In one possible implementation, processing module 802 is specifically used for:

[0183] The sampling frequency corresponding to each battery indicator data is input into a preset time synchronization algorithm, and the sampling period is output.

[0184] The battery safety warning device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0185] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 9 As shown, the electronic device provided in this embodiment includes at least one processor 901 and a memory 902. Optionally, the device further includes a communication component 903. The processor 901, memory 902, and communication component 903 are connected via a bus 904.

[0186] In a specific implementation, at least one processor 901 executes computer execution instructions stored in memory 902, causing at least one processor 901 to perform the above-described method.

[0187] The specific implementation process of processor 901 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0188] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0189] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0190] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0191] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0192] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0193] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0194] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0195] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0196] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0197] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0198] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0199] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0200] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A safety warning method of a battery, characterized by, The method comprises the following steps: collecting preset battery index data based on a collection cycle; constructing an index information set matrix according to the battery index data; obtaining a battery safety value according to the index information set matrix and a preset inference model; determining a target safety threshold interval in which the battery safety value is located from preset safety threshold intervals; performing a warning operation corresponding to the target safety threshold interval according to the target safety threshold interval.

2. The method of claim 1, wherein, The battery index data comprises voltage data, temperature data, current data and a mixed gas concentration duty cycle, and the constructing of the index information set matrix according to the battery index data comprises the following steps: inputting the voltage data into a pre-established voltage differential entropy feature model to output the voltage differential entropy of the battery; inputting the temperature data into a pre-established temperature gradient field model to output the temperature gradient of the battery; inputting the current data into a pre-established feature frequency band energy ratio model to output the feature frequency band energy ratio of the battery; constructing the index information set matrix according to the voltage differential entropy, the temperature gradient, the feature frequency band energy ratio and the mixed gas concentration duty cycle.

3. The method of claim 1, wherein, The obtaining of the battery safety value according to the index information set matrix and the preset inference model comprises the following steps: determining the confidence degree of each battery index according to the index information set matrix and a preset confidence degree algorithm; determining the feature weight of each battery index according to the voltage differential entropy of the battery and a preset weight algorithm; inputting the confidence degree of each battery index and the feature weight of each battery index into a preset inference model to obtain the battery safety value.

4. The method of claim 1, wherein, The performing of the warning operation corresponding to the target safety threshold interval according to the target safety threshold interval comprises the following steps: determining a target warning value from a mapping relationship between the preset safety threshold intervals and warning values according to the target safety threshold interval; performing a warning operation corresponding to a preset warning strategy according to the target warning value.

5. The method of claim 1, wherein, Before the collecting of the preset battery index data based on the collection cycle, the method further comprises the following steps: obtaining the collection frequency corresponding to each battery index data; determining a collection cycle through collection time synchronization processing according to the collection frequency corresponding to each battery index data.

6. The method of claim 5, wherein, The determining of the collection cycle through the collection time synchronization processing according to the collection frequency corresponding to each battery index data comprises the following steps: inputting the collection frequency corresponding to each battery index data into a preset time synchronization algorithm to output the collection cycle.

7. A safety warning device for a battery, characterized by The method comprises the following steps: a collection module, configured to collect preset battery index data based on a collection cycle; a processing module, configured to construct an index information set matrix according to the battery index data; the processing module is further configured to obtain a battery safety value according to the index information set matrix and a preset inference model; a determination module, configured to determine a target safety threshold interval in which the battery safety value is located from preset safety threshold intervals; the processing module is further configured to perform a warning operation corresponding to the target safety threshold interval according to the target safety threshold interval.

8. An electronic device, comprising: The method comprises the following steps: a memory, a processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored by the memory, so that the processor executes the method according to any one of claims 1-6.

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

10. A computer program product, characterised in that, The computer program is executed by the processor to implement the method according to any one of claims 1-6. The computer program is executed by the processor to implement the method according to any one of claims 1-6.

Images