Energy storage battery multi-time scale intelligent fire warning method and device

Abstract

The present application proposes a multi-time scale intelligent fire warning method and device for energy storage batteries, which relate to the field of abnormality detection technology. The multi-time scale intelligent fire warning method for energy storage batteries includes: charging and standing the battery at a first time scale to determine the first equilibrium potential and the second equilibrium potential of the battery, and determining the battery capacity of the battery; determining the degree of battery degradation according to the battery capacity; measuring the voltage of the battery during the charging and discharging process at a second time scale to determine the voltage sample data of the battery, and obtaining the isolation density of the voltage sample data, thereby determining the degree of abnormality of the battery operation; performing environmental monitoring on the environment in which the battery is located at a third time scale to determine the degree of thermal runaway risk of the environment in which the battery is located; determining an alarm strategy for fire warning according to the degree of degradation, the degree of abnormality and the degree of thermal runaway risk, thereby solving the problem of accurate fire detection and warning of energy storage power stations in the prior art.

Description

Technical Field

[0001] The present application relates to the field of anomaly detection technology, and in particular to a multi-time scale intelligent fire warning method and device for energy storage batteries. Background Art

[0002] New energy storage technology is the key to promoting the consumption of clean energy, solving the volatility of new energy power generation and ensuring the stable operation of the power system. Therefore, the development of new energy storage technology has a profound impact on the energy structure and ecological environment.

[0003] At present, electrochemical energy storage such as batteries is developing most rapidly. As a high-efficiency energy storage device, energy storage batteries are widely used in new energy storage and other fields. However, there are certain safety hazards in the operation of batteries. Overcharging, over-discharging, overheating, etc. may lead to battery performance degradation or even safety accidents. Therefore, monitoring and early warning of energy storage batteries are very important. Summary of the invention

[0004] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the first purpose of this application is to propose a multi-time scale intelligent fire warning method for energy storage batteries to achieve accurate fire detection and warning and reduce the occurrence of accidents.

[0006] The second purpose of this application is to propose a multi-time scale intelligent fire warning device for energy storage batteries.

[0007] The third objective of the present application is to provide an electronic device.

[0008] A fourth objective of the present application is to provide a computer-readable storage medium.

[0009] A fifth object of the present application is to provide a computer program product.

[0010] To achieve the above objectives, the first embodiment of the present application proposes a multi-time scale intelligent fire warning method for energy storage batteries, comprising:

[0011] charging and standing a battery at a first time scale to determine a first equilibrium potential and a second equilibrium potential of the battery, and determining a battery capacity of the battery according to the first equilibrium potential and the second equilibrium potential;

[0012] determining a degree of degradation of the battery according to the battery capacity;

[0013] Performing voltage measurement on a battery charge and discharge process at a second time scale, determining voltage sample data of the battery, and acquiring isolation density of the voltage sample data;

[0014] determining the abnormality degree of the battery operation according to the isolation density of the voltage sample data;

[0015] Performing environmental monitoring of the environment in which the battery is located at a third time scale to determine a degree of thermal runaway risk of the environment in which the battery is located;

[0016] An alarm strategy is determined according to the degree of degradation, the degree of abnormality and the degree of thermal runaway risk, and a fire warning is performed according to the alarm strategy.

[0017] To achieve the above-mentioned purpose, the second embodiment of the present application proposes a multi-time scale intelligent fire warning device for energy storage batteries, comprising:

[0018] A first acquisition module, configured to charge and keep a battery stationary at a first time scale, determine a first equilibrium potential and a second equilibrium potential of the battery, and determine a battery capacity of the battery according to the first equilibrium potential and the second equilibrium potential;

[0019] A first evaluation module, configured to determine a degree of degradation of the battery according to the battery capacity;

[0020] a second acquisition module, configured to measure the voltage of the battery during the charge and discharge process at a second time scale, determine voltage sample data of the battery, and acquire the isolation density of the voltage sample data;

[0021] a second evaluation module, configured to determine the abnormality of the battery operation according to the isolation density of the voltage sample data;

[0022] A third assessment module is used to perform environmental monitoring on the environment in which the battery is located at a third time scale to determine the degree of thermal runaway risk of the environment in which the battery is located;

[0023] The early warning module is used to determine an alarm strategy according to the degree of degradation, the degree of abnormality and the degree of thermal runaway risk, and to provide a fire early warning according to the alarm strategy.

[0024] To achieve the above-mentioned purpose, the third aspect of the present application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0025] The memory stores computer-executable instructions;

[0026] The processor executes the computer-executable instructions stored in the memory to implement the method as described in the embodiment of the first aspect.

[0027] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present application proposes a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the method described in the first aspect embodiment.

[0028] To achieve the above-mentioned purpose, the fifth aspect of the present application proposes a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.

[0029] The multi-time scale intelligent fire warning method and device for energy storage batteries provided in the present application obtain the degree of degradation of battery capacity, the degree of abnormality of battery operation, and the degree of thermal runaway risk of the battery environment at different time scales, determine the alarm strategy based on multi-dimensional detection information such as the degree of degradation, the degree of abnormality, and the degree of thermal runaway risk, and perform fire warning based on alarm measurement, thereby improving the accuracy of fire detection and warning, making full use of massive energy storage data, taking into account both long time series and short time periods, and realizing multi-level warning of battery cell degradation, abnormality, and thermal runaway.

[0030] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0032] Figure 1 A schematic diagram of a flow chart of a multi-time scale intelligent fire warning method for energy storage batteries provided in an embodiment of the present application;

[0033] Figure 2 A schematic diagram of a process for obtaining the degree of battery degradation provided in an embodiment of the present application;

[0034] Figure 3 A schematic diagram of a flow chart for obtaining the abnormality degree of battery operation provided in an embodiment of the present application;

[0035] Figure 4 A schematic diagram of a process for obtaining the thermal runaway risk level of a battery environment provided in an embodiment of the present application;

[0036] Figure 5 A schematic flow chart of another multi-time scale intelligent fire warning method for energy storage batteries provided in an embodiment of the present application;

[0037] Figure 6 A schematic structural diagram of a multi-time scale intelligent fire warning device for an energy storage battery provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0039] The following describes the multi-time scale intelligent fire warning method and device for energy storage batteries according to an embodiment of the present application with reference to the accompanying drawings.

[0040] Figure 1 This is a flow chart of a multi-time scale intelligent fire warning method for energy storage batteries provided in an embodiment of the present application. Figure 1 As shown, the multi-time scale intelligent fire warning method for energy storage batteries includes the following steps:

[0041] S101, charging and standing a battery at a first time scale to determine a first equilibrium potential and a second equilibrium potential of the battery, and determining a battery capacity of the battery according to the first equilibrium potential and the second equilibrium potential.

[0042] Optionally, the first time scale may be a longer time scale such as 1 day, 3 days or 5 days, that is, during the operation of the battery, the battery is charged and left to stand periodically at the first time scale.

[0043] In some implementations, charging and letting the battery stand is to charge the battery and let it stand for a period of time after charging, for example, charging the battery to a fixed voltage, letting the battery stand for a fixed time after charging is completed, and obtaining a first equilibrium potential of the battery after standing; charging the battery a second time to a fixed voltage, and letting the battery stand for the same fixed time after charging is completed, and obtaining a second equilibrium potential of the battery after the second standing.

[0044] Optionally, the corresponding state of charge (SOC) can be determined according to the first equilibrium potential and the second equilibrium potential. SOC refers to the ratio of the remaining capacity of the battery to its capacity in a fully charged state, usually expressed as a percentage. The difference between the state of charge of the first equilibrium potential and the state of charge of the second equilibrium potential of two adjacent static times is calculated to obtain the differential state of charge.

[0045] Optionally, the charging quantity between the first equilibrium potential and the second equilibrium potential may also be obtained, and the ratio of the charging quantity to the difference state of charge may be used as the battery capacity of the battery.

[0046] S102, determining the degree of battery degradation according to the battery capacity.

[0047] In some implementations, a battery capacity decay curve corresponding to the battery when it leaves the factory may be obtained. The battery capacity decay curve is an ideal battery capacity corresponding to the battery under different usage durations.

[0048] Get the usage time corresponding to the current battery, determine the corresponding ideal battery capacity in the battery capacity attenuation curve based on the usage time, and determine the degree of battery degradation based on the difference between the current battery capacity and the ideal battery capacity. It can be understood that the greater the difference between the current battery capacity and the ideal battery capacity, the more serious the degree of battery degradation.

[0049] In some implementations, a mapping relationship between the battery capacity difference and the degree of degradation can be determined. The degree of degradation can include the presence of degradation abnormalities and the absence of degradation abnormalities. For example, when the battery capacity difference exceeds the normal attenuation threshold, it is determined that there is a degradation abnormality and the degree of degradation is determined to be 1. When the battery capacity difference does not exceed the normal attenuation threshold, it is determined that there is no degradation abnormality and the degree of degradation is 0.

[0050] S103, measuring the voltage of the battery during the charge and discharge process at a second time scale, determining voltage sample data of the battery, and obtaining isolation density of the voltage sample data.

[0051] Optionally, the second time scale can be a charge and discharge process of the battery, that is, voltage measurement is performed during each charge and discharge process corresponding to the battery to determine that the voltage data during the charge and discharge process constitutes the voltage sample data of the battery; it can be understood that the energy storage power station will include multiple batteries, so the voltage sample data of other batteries in the same batch during a charge and discharge process can be obtained, so as to obtain the isolation density of the voltage sample data of each battery, and the isolation density can represent the probability density of the voltage sample data of the battery appearing in all voltage sample data.

[0052] S104, determining the abnormality degree of the battery operation according to the isolation density of the voltage sample data.

[0053] Optionally, a density threshold can be determined, and the isolation density of the voltage sample data is compared with the density threshold to determine the degree of abnormality in battery operation. In this embodiment, the degree of abnormality can include 0 and 1, that is, the battery operation is abnormal or the battery operation is not abnormal. When the isolation density is less than the density threshold, it is determined that the battery operation is abnormal. When the isolation density is greater than or equal to the density threshold, it is determined that there is no abnormality in the battery operation.

[0054] S105, performing environmental monitoring on the environment in which the battery is located at a third time scale to determine a thermal runaway risk level of the environment in which the battery is located.

[0055] In some implementations, the third time scale may be a shorter time period such as 1 minute, 30 seconds, or 10 seconds, that is, the environment monitoring of the battery environment is performed within a shorter time period.

[0056] Optionally, data such as temperature, smoke, and combustible gas in the battery environment can be obtained for environmental monitoring. Based on the temperature and combustible gas, it can be determined whether the current environment has flammable risks, and based on the smoke, it can be determined whether there is a fire or fire risk in the current environment.

[0057] In some implementations, images of the battery environment can also be captured in real time, and the images can be analyzed to determine whether there are dangerous factors such as fire points in the battery environment. Based on environmental monitoring such as images, temperature, smoke, and combustible gases, it can be determined whether there is a risk of thermal runaway, thereby determining the degree of thermal runaway risk.

[0058] Optionally, each indicator can be compared with a corresponding threshold value, and the degree of thermal runaway risk can be judged based on whether the threshold value is met. The degree of thermal runaway risk can also be divided into 0 and 1, that is, there is a thermal runaway risk and there is no thermal runaway risk. For example, if the concentration of combustible gas exceeds the corresponding threshold value, it is determined that there is a thermal runaway risk, and the degree of thermal runaway risk is determined to be 1.

[0059] S106, determining an alarm strategy according to the degree of degradation, the degree of abnormality and the degree of thermal runaway risk, and performing a fire warning according to the alarm strategy.

[0060] It can be understood that the degree of thermal runaway risk is a real-time detection of whether there is a fire or flammable situation in the battery environment. When the risk of thermal runaway occurs, it indicates that a fire or flammable situation may occur at present, and the alarm strategy can be to start a higher level of warning to remind professionals to deal with it and conduct safety inspections in time; when the battery abnormality is large, it indicates that the battery is operating abnormally during the current charging and discharging process. When the battery degradation degree is large, it indicates that the battery has abnormal power degradation in recent times. Therefore, when the abnormality and degradation degree occur, the alarm measurement can be to start a lower level of warning to remind operation and maintenance personnel to strengthen monitoring.

[0061] In this embodiment, the degradation degree of battery capacity, the abnormality degree of battery operation and the thermal runaway risk degree of the battery environment are evaluated at different time scales, and the alarm strategy is determined based on multi-dimensional detection information such as the degradation degree, abnormality degree and thermal runaway risk degree. Monitoring results at different time scales correspond to alarm strategies of different levels, and fire warnings are performed based on alarm measurements to improve the accuracy of fire detection and warnings. Fully utilize massive energy storage data, take into account both long time series and short time periods, and realize multi-level warnings of battery cell degradation, abnormality and thermal runaway, which is of great significance for ensuring the safe and stable operation of power stations.

[0062] Figure 2 A schematic diagram of a process for obtaining the degree of battery degradation provided in an embodiment of the present application. Figure 2 As shown, the method includes:

[0063] S201, obtaining a voltage-state of charge curve of a battery.

[0064] Optionally, the voltage-state of charge curve can be obtained through experiments. For example, for batteries of the same model and batch, multiple batteries are randomly selected to conduct charge and discharge experiments under typical working conditions under laboratory conditions, and the open circuit voltage (OVC)-SOC curves at different equivalent cycle numbers are obtained at different cycle numbers such as the 1st, 100th, 200th, and 300th cycles. f (OCV).

[0065] S202: Determine a first state of charge corresponding to the first equilibrium potential and a second state of charge corresponding to the second equilibrium potential according to the voltage-state of charge curve.

[0066] In some implementations, the battery can be periodically charged to a set voltage at a first time scale and left to stand for a preset period of time to obtain a first equilibrium potential; the battery can be continuously charged from the first equilibrium potential to a set voltage and left to stand for a preset period of time to obtain a second equilibrium potential.

[0067] Optionally, the preset time period may be 4 hours, that is, the battery is charged to a set voltage and then left to stand for 4 hours to obtain a first equilibrium potential, and the battery is charged to a set voltage and then left to stand for another 4 hours to obtain a second equilibrium potential.

[0068] The OVC-SOC curve of the battery at the corresponding cycle number is determined according to the current battery operation status, so as to obtain the corresponding first state of charge and second state of charge in the OVC-SOC curve based on the first equilibrium potential and the second equilibrium battery.

[0069] Optionally, the first state of charge can be expressed as SOC1= f (V1), V1 is the first equilibrium potential; the second state of charge can be expressed as SOC2= f (V2), V2 is the second equilibrium potential.

[0070] S203, obtaining the charge amount of the battery from the first equilibrium potential to the set voltage, and calculating the difference between the first state of charge and the second state of charge.

[0071] Optionally, the charging capacity can be calculated, for example, by obtaining the charging current and the charging time, and determining the charging capacity according to the product of the charging current and the charging time; the difference between the first state of charge and the second state of charge can be expressed as SOC2-SOC1.

[0072] S204, determining the current capacity of the battery according to the charged power and the difference.

[0073] Optionally, the current capacity may be a ratio of the charged power to the difference, expressed as: C=AH / (SOC2-SOC1), wherein C is the current capacity and AH is the charged power.

[0074] S205: Determine the degree of battery degradation according to the battery capacity.

[0075] Optionally, the battery capacity at different cycle numbers can be obtained, and a capacity decay curve can be plotted based on the battery capacity at different cycle numbers; an ideal decay curve of the battery at a corresponding cycle number can be obtained; and the degree of battery degradation can be determined based on the current capacity of the battery, the capacity decay curve and the ideal decay curve.

[0076] As an example, the battery capacity can be compared with the battery capacity in the ideal attenuation curve under the same number of cycles. If the current battery capacity is significantly different from the ideal attenuation area, it is determined whether the current battery capacity in the capacity attenuation curve has been significantly attenuated. For example, multiple feature points are selected at equal distances, and the attenuation between each two adjacent feature points is determined to obtain the attenuation average value. If the attenuation between the current capacity and the previous adjacent feature point is significantly different from the attenuation average value, it means that the attenuation of the battery deviates from the overall attenuation trend. Therefore, it is determined that the current battery has abnormal degradation, that is, the degree of degradation is 1.

[0077] In some implementations, if the battery capacity differs greatly from the corresponding battery capacity in the ideal attenuation curve, but is consistent with the overall attenuation trend of the current battery, then the degradation of the current battery is determined to be normal; correspondingly, if the battery capacity differs greatly from the overall attenuation trend of the current battery, but is consistent with the corresponding battery capacity in the ideal attenuation curve, then the degradation of the current battery is also determined to be normal, that is, the degree of degradation is 0.

[0078] In this embodiment, the battery capacity is regularly detected at a longer period, and the battery capacity is compared with the ideal battery capacity and the overall battery capacity change trend, so as to determine whether the current battery degradation trend is normal and obtain the battery degradation degree, thereby providing more accurate battery degradation degree acquisition, and the acquisition of the battery capacity using the first equilibrium potential and the second equilibrium potential does not involve complex calculations, the calculation cost is low, and the degradation degree assessment efficiency is high.

[0079] Figure 3 A schematic diagram of a process for obtaining the abnormality degree of battery operation provided by an embodiment of the present application. Figure 3 As shown, the method includes:

[0080] S301, taking the voltage sample data of all batteries as sample set data.

[0081] S302, randomly selecting a feature from all sample features as a search feature, and taking the value of the search feature of the target battery corresponding to the voltage sample data for solving the isolation density in the sample set data as the target data.

[0082] Optionally, any feature can be selected from the voltage sample data as the search feature. For example, the current voltage sample data is X =[ X 1, X 2,……, X n ],by X 2 is used as the search feature. The battery corresponding to the voltage sample data currently detected and analyzed is the target battery, and the actual data of the search feature corresponding to the target battery is the target data.

[0083] S303, randomly generate first data corresponding to the search feature.

[0084] S304: construct a binary tree using the first data and data corresponding to the search feature in the sample set data.

[0085] The root node of the binary tree is the first data.

[0086] S305, using a binary tree to search for target data, and after the search is completed, using the search path to obtain a first isolation density of the target battery.

[0087] Optionally, the first isolation density of the target battery obtained by searching the path can be expressed as:

[0088]

[0089] in, n is the total number of voltage sample features; n' Indicates the isolation path depth; k is the weight value, the superscript t Indicates t Tree, subscript i and j Respectively represent i Samples and j Isolation operation; m is the number of remaining samples, V is the hypercube volume of the sample set; L is the length of the edge of the hypercube containing the sample; r is the ratio of the current length of the edge of the isolated path to the original hypercube before the search, V 0 is to find the volume of the front hypercube, subscript f Indicatesf Features.

[0090] S306: Use the voltage sample data of the target data on the branch of the binary tree as new sample set data.

[0091] If the target data is in the left subtree of the binary tree, the voltage sample data contained in the left subtree of the binary tree is used as the new sample set data; if the target data is in the right subtree of the binary tree, the voltage sample data contained in the right subtree of the binary tree is used as the new sample set data.

[0092] S307, repeat the calculation using the new sample set data until the target data is completely isolated, or until a preset maximum number of isolation times is reached.

[0093] It can be understood that when the subtree branch where the target data is currently located has only one node, the target data, it is determined that the current target data is completely isolated; the maximum number of isolation times is the number of repeated calculations. For example, if the maximum number of isolation times is 10, then steps S301 to S306 are executed on the target data and repeated 10 times. Even if the target data is not completely isolated, the loop calculation is terminated to obtain the first isolation density, the second isolation density, ... the tenth isolation density corresponding to each repeated cycle.

[0094] S308 , performing weighted summation on the isolation densities of all target batteries obtained to obtain the isolation density of the target battery.

[0095] Optionally, the weighted sum can be calculated as:

[0096]

[0097] in, d i For battery i Isolation density; m' The total number of binary trees used in solving the isolation density.

[0098] S309, determining the abnormality degree of the battery operation according to the isolation density of the voltage sample data.

[0099] Optionally, the isolation density corresponding to all batteries can be obtained, and the average isolation density can be obtained by calculating the average value based on the isolation density; the abnormal degree of battery operation can be determined based on the difference between the isolation density of the battery and the average isolation density; that is, the average isolation density corresponding to all batteries is calculated, and the average isolation density is used as the abnormal threshold to determine whether the isolation density of the battery corresponding voltage sample data is less than the average isolation density. When the isolation density of the battery is less than the average isolation density, the battery operation is determined to be abnormal and the abnormal degree is 1; otherwise, the battery operation is determined to be normal and the abnormal degree is 0.

[0100] In this embodiment, the isolation density of the corresponding battery is obtained using the voltage sample data. The isolation density of each battery is the probability density of the voltage sample data of the battery appearing in all voltage sample data sets. The isolation density is obtained by using integrated learning and parallel calculation of multiple binary trees, which ensures accurate calculation and improves processing efficiency. It is suitable for large-scale data set scenarios, and the degree of battery abnormality is evaluated based on the battery isolation density, which has a wider range of applications.

[0101] Figure 4 A schematic diagram of a process for obtaining the thermal runaway risk level of a battery environment provided in an embodiment of the present application. Figure 4 As shown, the method includes:

[0102] S401, acquiring the concentration and temperature of the combustible gas in the environment of the battery in real time at a third time scale, and determining a gas alarm indication according to the concentration and temperature of the combustible gas.

[0103] Optionally, the third time scale in this embodiment is a time period of real-time acquisition or a shorter time period such as every 5 seconds.

[0104] Optionally, an all-in-one sensor may be arranged to monitor the battery environment, that is, the concentration and temperature of combustible gas in the battery compartment, where the combustible gas includes at least one of hydrogen, carbon monoxide and volatile organic compounds (VOC).

[0105] In some implementations, when the temperature exceeds a preset threshold and any two or more gases detected in the combustible gas exceed the threshold, it is determined that the gas alarm is triggered, that is, the gas alarm indication is a triggered alarm.

[0106] S402, obtaining a real-time image and real-time audio of the battery environment at a third time scale, performing smoke detection and flame detection on the real-time image, performing burst valve sound detection on the real-time audio, and determining an audio and image alarm indication based on the smoke detection results, flame detection results, and burst valve sound detection results.

[0107] In some implementations, computer vision technology or spectrum detection methods can be used to continuously detect smoke images and valve explosion sounds in the battery compartment. For example, smoke and flame images are used as training samples to train a smoke and flame detection model, and multiple battery valve explosion sounds are used as training samples to train an audio detection model. During the operation of the battery in the battery compartment, real-time monitoring is performed according to the smoke and flame detection model and the audio detection model. When the smoke and flame detection model or the audio detection model detects flame, smoke, or valve explosion sounds, an image and audio signal alarm is triggered, that is, the audio and image alarm indication is a triggered alarm.

[0108] S403, obtaining the expansion force in the battery pack in real time at a third time scale, and determining an expansion force alarm indication according to the expansion force.

[0109] Optionally, a pressure sensor may be arranged in the battery pack to continuously detect the expansion force in the battery pack. When a preset situation occurs, an expansion force alarm is triggered, that is, the expansion force alarm indicates a triggered alarm. Optionally, the preset situation may include: (1) the expansion force is greater than a preset expansion force threshold; (2) the expansion force gradually increases and then decreases rapidly.

[0110] S404, determining the degree of thermal runaway risk based on the gas alarm indication, the audio and image alarm indication, and the expansion force alarm indication.

[0111] In some implementations, when any one of the gas alarm indication, audio and image alarm indication, and expansion force alarm indication triggers an alarm, it is determined that there is a risk of thermal runaway, and the corresponding thermal runaway risk level is 1. Correspondingly, if none of the gas alarm indication, audio and image alarm indication, and expansion force alarm indication indicate a triggered alarm, the thermal runaway risk level is determined to be 0.

[0112] In this embodiment, the temperature and combustible gas of the battery environment are detected in real time, and the presence of flames and smoke is determined based on real-time image acquisition. Thermal runaway risk warning is performed in combination with the expansion force in the battery pack, so that unsafe factors in the battery environment can be discovered in time and alarm processing can be carried out in time, so as to more comprehensively monitor and warn of potential safety hazards in the energy storage power station and reduce the probability of accidents.

[0113] Figure 5 A schematic diagram of another multi-time scale intelligent fire warning method for energy storage batteries provided in an embodiment of the present application. Figure 5 As shown, the method includes:

[0114] S501, charging and leaving a battery stationary at a first time scale to determine a first equilibrium potential and a second equilibrium potential of the battery.

[0115] S502, obtaining a voltage-state of charge curve of the battery.

[0116] S503: Determine, according to the voltage-state of charge curve, a first state of charge corresponding to the first equilibrium potential and a second state of charge corresponding to the second equilibrium potential.

[0117] S504, obtaining the charge amount of the battery from the first equilibrium potential to the set voltage, and calculating the difference between the first state of charge and the second state of charge.

[0118] S505, determining the current capacity of the battery according to the charged power and the difference, and determining the degree of battery degradation according to the battery capacity.

[0119] S506, measuring the voltage of the battery during the charge and discharge process at a second time scale, determining voltage sample data of the battery, and taking the voltage sample data of all batteries as sample set data.

[0120] S507, randomly selecting a feature from all sample features as a search feature, and taking the value of the search feature of the target battery corresponding to the voltage sample data for solving the isolation density in the sample set data as the target data.

[0121] S508, randomly generate first data corresponding to the search feature, and construct a binary tree using the first data and data corresponding to the search feature in the sample set data.

[0122] S509, using a binary tree to search for target data, and after the search is completed, using the search path to obtain a first isolation density of the target battery.

[0123] S510: Use the voltage sample data of the target data on the branch of the binary tree as new sample set data.

[0124] S511, repeat the calculation using the new sample set data until the target data is completely isolated, or until the preset maximum isolation times are reached.

[0125] S512: Perform a weighted summation on the isolation densities of all target batteries obtained to obtain the isolation density of the target battery.

[0126] S513, determining the abnormality degree of the battery operation according to the isolation density of the voltage sample data.

[0127] S514, acquiring the concentration and temperature of the combustible gas in the environment of the battery in real time at a third time scale, and determining a gas alarm indication according to the concentration and temperature of the combustible gas.

[0128] S515, obtaining a real-time image and real-time audio of the battery environment at a third time scale, performing smoke detection and flame detection on the real-time image, performing burst valve sound detection on the real-time audio, and determining an audio image alarm indication based on the smoke detection results, flame detection results, and burst valve sound detection results.

[0129] S516, obtaining the expansion force in the battery pack in real time at a third time scale, and determining an expansion force alarm indication according to the expansion force.

[0130] S517, determining the degree of thermal runaway risk based on the gas alarm indication, the audio and image alarm indication, and the expansion force alarm indication.

[0131] In the embodiment of the present application, the implementation method of step S501 to step S517 can be implemented by any method in the embodiments of the present disclosure, which is not limited here and will not be repeated.

[0132] S518, determine the alarm strategy according to the degree of degradation, abnormality and thermal runaway risk, and issue a fire warning according to the alarm strategy.

[0133] Optionally, in response to the degree of degradation being greater than a first threshold, or the degree of abnormality being greater than a second threshold, and the degree of thermal runaway risk being less than or equal to a third threshold, the alarm strategy is determined to be a first-level warning; in response to the degree of degradation being greater than the first threshold and the degree of abnormality being greater than the second threshold, and the degree of thermal runaway risk being less than or equal to a third threshold, the alarm strategy is determined to be a second-level warning; in response to the degree of thermal runaway risk being greater than the third threshold, the alarm strategy is determined to be a third-level warning.

[0134] In some implementations, the first-level warning can be used to prompt operation and maintenance personnel to strengthen monitoring, the second-level warning can be used to prompt operation and maintenance personnel to conduct timely safety inspections, and the third-level warning can be used to prompt operation and maintenance personnel to immediately cut off the power supply and send it to the fire host for firefighting processing.

[0135] In this embodiment, the degree of degradation of battery capacity, the degree of abnormality of battery operation and the degree of thermal runaway risk of the battery environment are evaluated at different time scales, the battery capacity is regularly detected at a longer period, and the battery capacity is compared with the ideal battery capacity and the overall battery capacity change trend to determine whether the current battery degradation trend is normal, providing more accurate acquisition of battery degradation degree, using integrated learning and parallel calculation of multiple binary trees to obtain isolation density, thereby determining the degree of abnormality, ensuring accurate calculation and improving processing efficiency, and detecting the temperature and combustible gas in the battery environment in real time and The presence of flames and smoke is determined based on real-time image acquisition, and a thermal runaway risk warning is issued in combination with the expansion force in the battery pack, so as to promptly discover unsafe factors in the battery environment and promptly issue an alarm. The alarm strategy is determined based on multi-dimensional detection information such as the degree of degradation, degree of abnormality, and degree of thermal runaway risk. Monitoring results at different time scales correspond to different levels of alarm strategies, and fire warnings are issued based on alarm measurements to improve the accuracy of fire detection and warnings. This makes full use of massive energy storage data, takes into account both long time series and short time periods, and realizes multi-level warnings of battery cell degradation, abnormalities, and thermal runaway, which is of great significance for ensuring the safe and stable operation of power stations.

[0136] In order to implement the above embodiments, the present application also proposes a multi-time scale intelligent fire warning device for energy storage batteries.

[0137] Figure 6This is a schematic diagram of the structure of a multi-time scale intelligent fire warning device for energy storage batteries provided in an embodiment of the present application. Figure 6 As shown, the energy storage battery multi-time scale intelligent fire warning device 600 includes:

[0138] A first acquisition module 601 is used to charge and keep the battery stationary at a first time scale, determine a first equilibrium potential and a second equilibrium potential of the battery, and determine a battery capacity of the battery according to the first equilibrium potential and the second equilibrium potential;

[0139] A first evaluation module 602, configured to determine a degree of battery degradation according to battery capacity;

[0140] A second acquisition module 603 is used to measure the voltage of the battery during the charging and discharging process at a second time scale, determine the voltage sample data of the battery, and obtain the isolation density of the voltage sample data;

[0141] A second evaluation module 604, configured to determine the abnormality of battery operation according to the isolation density of the voltage sample data;

[0142] A third evaluation module 605 is used to perform environmental monitoring on the environment in which the battery is located at a third time scale to determine the degree of thermal runaway risk of the environment in which the battery is located;

[0143] The early warning module 606 is used to determine an alarm strategy according to the degree of degradation, abnormality and thermal runaway risk, and to issue a fire early warning according to the alarm strategy.

[0144] Furthermore, in a possible implementation of the embodiment of the present application, the first acquisition module 601 includes:

[0145] Periodically charging the battery to a set voltage at a first time scale, and leaving it to stand for a preset period of time to obtain a first equilibrium potential;

[0146] The battery is continuously charged from the first equilibrium potential to a set voltage, and is left to stand for a preset period of time to obtain a second equilibrium potential.

[0147] Furthermore, in a possible implementation of the embodiment of the present application, the first acquisition module 601 includes:

[0148] Obtaining the voltage-state of charge curve of the battery;

[0149] Determining, according to the voltage-state of charge curve, a first state of charge corresponding to the first equilibrium potential and a second state of charge corresponding to the second equilibrium potential;

[0150] Acquire the charge quantity of the battery from the first equilibrium potential to the set voltage, and calculate the difference between the first state of charge and the second state of charge;

[0151] Determine the current capacity of the battery based on the charge level and the difference.

[0152] Furthermore, in a possible implementation of the embodiment of the present application, the first evaluation module 602 includes:

[0153] Obtain the battery capacity of the battery at different cycle times, and draw a capacity decay curve according to the battery capacity of the battery at different cycle times;

[0154] Obtain the ideal attenuation curve of the battery at the corresponding number of cycles;

[0155] The degree of battery degradation is determined based on the current capacity of the battery, the capacity decay curve, and the ideal decay curve.

[0156] Furthermore, in a possible implementation of the embodiment of the present application, the second acquisition module 603 includes:

[0157] The voltage sample data of all batteries are taken as sample set data;

[0158] A feature is randomly selected from all sample features as a search feature, and the value of the search feature of the target battery corresponding to the voltage sample data for solving the isolation density in the sample set data is used as the target data;

[0159] Randomly generate first data corresponding to the search feature;

[0160] Constructing a binary tree using the first data and data corresponding to the search feature in the sample set data, wherein the root node of the binary tree is the first data;

[0161] Use the binary tree to search for target data, and after the search is completed, use the search path to obtain the first isolation density of the target battery;

[0162] The voltage sample data of the target data on the branch of the binary tree is used as new sample set data;

[0163] Repeat the above steps with new sample set data until the target data is completely isolated, or the preset maximum number of isolation times is reached;

[0164] The isolation densities of all target batteries are weighted and summed to obtain the isolation density of the target battery.

[0165] Furthermore, in a possible implementation of the embodiment of the present application, the second acquisition module 603 includes:

[0166]

[0167] in, Indicates the isolation path depth; is the weight value, the superscript Indicates Tree, subscript and Respectively represent Samples and An isolation operation.

[0168] Furthermore, in a possible implementation of the embodiment of the present application, the second evaluation module 604 includes:

[0169] Obtain the isolation density corresponding to all batteries, and calculate the average value according to the isolation density to obtain the average isolation density;

[0170] The degree of abnormality in battery operation is determined based on the difference between the isolation density of the battery and the average isolation density.

[0171] Further, in a possible implementation of the embodiment of the present application, the third evaluation module 605 includes:

[0172] Acquire the concentration and temperature of the combustible gas in the environment of the battery in real time at a third time scale, where the combustible gas includes at least one of hydrogen, carbon monoxide and volatile organic compounds (VOC);

[0173] Determine the gas alarm indication based on the concentration and temperature of the combustible gas;

[0174] Acquire real-time images and real-time audio of the battery environment at a third time scale, perform smoke detection and flame detection on the real-time images, and perform valve explosion sound detection on the real-time audio;

[0175] Determine the audio and visual alarm indication based on the smoke detection results, flame detection results and explosion valve sound detection results;

[0176] obtaining an expansion force in the battery pack in real time at a third time scale, and determining an expansion force alarm indication according to the expansion force;

[0177] Determine the degree of thermal runaway risk based on the gas alarm indication, audio and image alarm indication, and expansion force alarm indication.

[0178] Furthermore, in a possible implementation of the embodiment of the present application, the early warning module 606 includes:

[0179] In response to the degradation degree being greater than the first threshold, or the abnormality degree being greater than the second threshold, and the thermal runaway risk degree being less than or equal to the third threshold, determining the alarm strategy to be a first-level warning;

[0180] In response to the degradation degree being greater than the first threshold and the abnormality degree being greater than the second threshold, and the thermal runaway risk degree being less than or equal to the third threshold, determining the alarm strategy to be a level 2 warning;

[0181] In response to the thermal runaway risk level being greater than a third threshold, determining the alarm strategy as a third-level warning.

[0182] It should be noted that the aforementioned explanation of the embodiment of the multi-time-scale intelligent fire warning method for energy storage batteries is also applicable to the multi-time-scale intelligent fire warning device for energy storage batteries of this embodiment, and will not be repeated here.

[0183] In the embodiments of the present application, the degree of degradation of the battery capacity, the degree of abnormality of the battery operation, and the degree of thermal runaway risk of the battery environment are evaluated at different time scales, the battery capacity is regularly detected at a longer period, and the battery capacity is compared with the ideal battery capacity and the overall battery capacity change trend to determine whether the current battery degradation trend is normal, thereby providing more accurate acquisition of the battery degradation degree, utilizing integrated learning and parallel calculation of multiple binary trees to obtain the isolation density, thereby determining the degree of abnormality, ensuring accurate calculations while improving processing efficiency, and detecting the temperature and combustible gas in the battery environment in real time, It also determines whether there is flame and smoke based on real-time image acquisition, and issues a thermal runaway risk warning based on the expansion force in the battery pack, so as to promptly discover unsafe factors in the battery environment and promptly issue an alarm. It determines the alarm strategy based on multi-dimensional detection information such as the degree of degradation, degree of abnormality, and degree of thermal runaway risk. Monitoring results at different time scales correspond to different levels of alarm strategies, and issues fire warnings based on alarm measurements, improving the accuracy of fire detection and warnings. It makes full use of massive energy storage data, takes into account both long time series and short time periods, and realizes multi-level warnings of cell degradation, abnormality, and thermal runaway, which is of great significance for ensuring the safe and stable operation of power stations.

[0184] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: 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 provided by the above embodiments.

[0185] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0186] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0187] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0188] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0189] The present application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, the present disclosure is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, the risk can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.

[0190] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they contradict each other.

[0191] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0192] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0193] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0194] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0195] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0196] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0197] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A multi-time scale intelligent fire warning method for energy storage batteries, characterized in that: The following steps are involved: charging and standing a battery at a first time scale to determine a first equilibrium potential and a second equilibrium potential of the battery, and determining a battery capacity of the battery according to the first equilibrium potential and the second equilibrium potential; determining a degree of degradation of the battery according to the battery capacity; Performing voltage measurement on a battery charge and discharge process at a second time scale, determining voltage sample data of the battery, and acquiring isolation density of the voltage sample data; determining the abnormality degree of the battery operation according to the isolation density of the voltage sample data; Performing environmental monitoring of the environment in which the battery is located at a third time scale to determine a degree of thermal runaway risk of the environment in which the battery is located; determining an alarm strategy according to the degree of degradation, the degree of abnormality and the degree of thermal runaway risk, and performing a fire warning according to the alarm strategy; Wherein, determining a first equilibrium potential and a second equilibrium potential of the battery, and determining a battery capacity of the battery according to the first equilibrium potential and the second equilibrium potential, comprises: Periodically charging the battery to a set voltage at a first time scale, and leaving it to stand for a preset period of time to obtain a first equilibrium potential; Continue charging the battery from the first equilibrium potential to the set voltage, and let it stand for the preset time period to obtain a second equilibrium potential; Obtaining a voltage-state of charge curve of the battery; determining, according to the voltage-state of charge curve, a first state of charge corresponding to the first equilibrium potential and a second state of charge corresponding to the second equilibrium potential; Acquire the charge amount of the battery from the first equilibrium potential to the set voltage, and calculate the difference between the first state of charge and the second state of charge; determining a current capacity of the battery according to the charged power and the difference; The obtaining the isolation density of the voltage sample data includes: The voltage sample data of all batteries are taken as sample set data; Randomly select a feature from all sample features as a search feature, and use the value of the search feature of the target battery corresponding to the voltage sample data for solving the isolation density in the sample set data as the target data; Randomly generate first data corresponding to the search feature; Constructing a binary tree using the first data and data corresponding to the search feature in the sample set data, wherein the root node of the binary tree is the first data; Searching for the target data using the binary tree, and after the search is completed, obtaining the first isolation density of the target battery using the search path; Taking the voltage sample data of the target data on the branch of the binary tree as new sample set data; Repeat the above steps using the new sample set data until the target data is completely isolated, or a preset maximum number of isolation times is reached; The isolation densities of all the target batteries are obtained by weighted summation to obtain the isolation density of the target battery.

2. The method according to claim 1, characterized in that The determining the degree of degradation of the battery according to the battery capacity includes: Obtaining the battery capacity of the battery at different cycle times, and drawing a capacity decay curve according to the battery capacity of the battery at different cycle times; Obtaining an ideal attenuation curve of the battery at a corresponding number of cycles; The degree of degradation of the battery is determined according to the current capacity of the battery, the capacity decay curve, and the ideal decay curve.

3. The method according to claim 1, characterized in that The method of obtaining the first isolation density of the target lithium battery by searching the path includes: in, n' Indicates the isolation path depth; k is the weight value, the superscript t Indicates t Tree, subscript i and j Respectively represent i Samples and j An isolation operation.

4. The method according to claim 3, characterized in that The determining, according to the isolation density of the voltage sample data, the abnormal degree of the battery operation includes: Obtaining the isolation density corresponding to each of the batteries, and calculating an average value according to the isolation density to obtain an average isolation density; The abnormality degree of the battery operation is determined according to the difference between the isolation density of the battery and the average isolation density.

5. The method according to claim 1, characterized in that The performing environmental monitoring on the environment in which the battery is located at a third time scale to determine the degree of thermal runaway risk of the environment in which the battery is located includes: Acquiring in real time at a third time scale the concentration and temperature of a combustible gas in an environment where the battery is located, the combustible gas comprising at least one of hydrogen, carbon monoxide, and volatile organic compounds (VOCs); determining a gas alarm indication based on the concentration and temperature of the combustible gas; Acquire a real-time image and real-time audio of the environment in which the battery is located at a third time scale, and perform smoke detection and flame detection on the real-time image, and perform valve explosion sound detection on the real-time audio; Determine the audio and visual alarm indication based on the smoke detection results, flame detection results and explosion valve sound detection results; acquiring an expansion force in the battery pack in real time at a third time scale, and determining an expansion force alarm indication according to the expansion force; The degree of thermal runaway risk is determined based on the gas alarm indication, the audio and image alarm indication, and the expansion force alarm indication.

6. The method according to any one of claims 1 to 5, characterized in that The determining of an alarm strategy according to the degradation degree, the abnormality degree and the thermal runaway risk degree includes: In response to the degradation degree being greater than a first threshold, or the abnormality degree being greater than a second threshold, and the thermal runaway risk degree being less than or equal to a third threshold, determining that the alarm strategy is a first-level warning; In response to the degradation degree being greater than a first threshold and the abnormality degree being greater than a second threshold, and the thermal runaway risk degree being less than or equal to a third threshold, determining that the alarm strategy is a level 2 warning; In response to the thermal runaway risk level being greater than a third threshold, determining the alarm strategy as a third-level warning.

7. A multi-time scale intelligent fire warning device for energy storage batteries, characterized in that: include: A first acquisition module, configured to charge and keep a battery stationary at a first time scale, determine a first equilibrium potential and a second equilibrium potential of the battery, and determine a battery capacity of the battery according to the first equilibrium potential and the second equilibrium potential; A first evaluation module, configured to determine a degree of degradation of the battery according to the battery capacity; a second acquisition module, configured to measure the voltage of the battery during the charge and discharge process at a second time scale, determine voltage sample data of the battery, and acquire the isolation density of the voltage sample data; A second evaluation module, configured to determine the abnormality of the battery operation according to the isolation density of the voltage sample data; A third assessment module is used to perform environmental monitoring on the environment in which the battery is located at a third time scale to determine the degree of thermal runaway risk of the environment in which the battery is located; an early warning module, configured to determine an alarm strategy according to the degree of degradation, the degree of abnormality and the degree of thermal runaway risk, and to provide a fire early warning according to the alarm strategy; Wherein, the first acquisition module determines a first equilibrium potential and a second equilibrium potential of the battery, and determines a battery capacity of the battery according to the first equilibrium potential and the second equilibrium potential, including: Periodically charging the battery to a set voltage at a first time scale, and leaving it to stand for a preset period of time to obtain a first equilibrium potential; Continue charging the battery from the first equilibrium potential to the set voltage, and let it stand for the preset time period to obtain a second equilibrium potential; Obtaining a voltage-state of charge curve of the battery; determining, according to the voltage-state of charge curve, a first state of charge corresponding to the first equilibrium potential and a second state of charge corresponding to the second equilibrium potential; Acquire the charge amount of the battery from the first equilibrium potential to the set voltage, and calculate the difference between the first state of charge and the second state of charge; determining a current capacity of the battery according to the charged power and the difference; The second acquisition module acquires the isolation density of the voltage sample data, including: The voltage sample data of all batteries are taken as sample set data; Randomly select a feature from all sample features as a search feature, and use the value of the search feature of the target battery corresponding to the voltage sample data for solving the isolation density in the sample set data as the target data; Randomly generate first data corresponding to the search feature; Constructing a binary tree using the first data and data corresponding to the search feature in the sample set data, wherein the root node of the binary tree is the first data; Searching for the target data using the binary tree, and after the search is completed, obtaining the first isolation density of the target battery using the search path; Taking the voltage sample data of the target data on the branch of the binary tree as new sample set data; Repeat the above steps using the new sample set data until the target data is completely isolated, or a preset maximum number of isolation times is reached; The isolation densities of all the target batteries are obtained by weighted summation to obtain the isolation density of the target battery.

Images