Battery safety detection method, storage medium and computer equipment

Abstract

The invention relates to the technical field of batteries, particularly provides a battery safety detection method, a storage medium and computer equipment, and aims to solve the problem of poor accuracy of battery safety detection. In order to achieve the purpose, the battery safety detection method provided by the invention comprises the steps of obtaining target data of a battery under a preset working condition; first risk coefficients of the battery are determined according to the target data, the first risk coefficients indicate the possibility of safety risks of the battery, and then a second risk coefficient of the battery is calculated in combination with the multiple first risk coefficients; and then detecting whether the battery is safe according to the second risk coefficient.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a battery safety detection method, storage medium and computer equipment. Background Art

[0002] With the increasing penetration rate of electric vehicles, power battery-related safety accidents have occurred frequently in recent years. Therefore, how to detect battery safety to prevent potential risks has become a research hotspot in the industry.

[0003] In the related art, the safety of the battery is mainly detected by setting a threshold value and collecting data values ​​of the battery, and comparing the threshold value with the data value.

[0004] However, research has found that the accuracy of battery safety testing in related technologies is poor. Summary of the invention

[0005] In order to overcome the above-mentioned defects, the present application is proposed to solve or at least partially solve the technical problem of poor accuracy of battery safety detection.

[0006] In a first aspect, a battery safety detection method is provided, comprising: obtaining target data of a battery under preset operating conditions; determining a first risk coefficient of the battery based on the target data, wherein the first risk coefficient indicates the possibility of a safety risk occurring in the battery; calculating a second risk coefficient of the battery based on a plurality of first risk coefficients; and detecting whether the battery is safe based on the second risk coefficient.

[0007] In a technical solution of the battery safety detection method, the second risk coefficient is positively correlated with the product of the plurality of first risk coefficients.

[0008] In a technical solution of the battery safety detection method, the second risk coefficient and the plurality of first risk coefficients satisfy the following relationship:

[0009] Among them, R total represents the second risk factor R1 represents the first first risk factor…, R n represents the nth first risk coefficient, where n is an integer greater than or equal to 1.

[0010] In a technical solution of the above battery safety detection method, the target data includes pre-marketing data and post-marketing data, and the first risk coefficient includes a first risk coefficient corresponding to the pre-marketing data and a first risk coefficient corresponding to the post-marketing data.

[0011] In a technical solution of the above-mentioned battery safety detection method, the first risk factor is determined based on the failure cause of the battery, and the failure cause includes at least one of lithium plating, internal short circuit self-discharge, abnormal charging voltage difference, differential voltage-capacity outlier and capacity decay outlier.

[0012] In a technical solution of the above-mentioned battery safety detection method, the target data includes battery replacement data and charging data, and the first risk coefficient includes a first risk coefficient corresponding to the battery replacement data and a first risk coefficient corresponding to the charging data.

[0013] In a technical solution of the above-mentioned battery safety detection method, the first risk coefficient corresponds to at least one safety indicator, and the second risk coefficient of the battery is calculated in combination with multiple first risk coefficients, including: for each safety indicator, calculating the second risk coefficient of the safety indicator according to the multiple first risk coefficients of the safety indicator; detecting whether the battery is safe according to the second risk coefficient, including: for each safety indicator, calculating the detection threshold of the safety indicator according to the second risk coefficient of the safety indicator; obtaining the value of each safety indicator; detecting whether the battery is safe according to the value of each safety indicator and the detection threshold of each safety indicator.

[0014] In a technical solution of the above-mentioned battery safety detection method, a detection threshold of the safety indicator is calculated based on the second risk coefficient of the safety indicator, including: in response to detecting that the second risk coefficient is less than or equal to the risk coefficient threshold, determining the preset first threshold as the detection threshold of the safety indicator; in response to detecting that the second risk coefficient is greater than the risk coefficient threshold, determining the second threshold as the detection threshold of the safety indicator, wherein the second threshold depends on the preset first threshold and the second risk coefficient.

[0015] In a second aspect, a computer device is provided, comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein a computer program is stored in the memory, and when the computer program is executed by the at least one processor, a method of implementing any one of the technical solutions of the above-mentioned battery safety detection method is implemented.

[0016] In a third aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored in the computer-readable storage medium, and the program codes are suitable for being loaded and run by a processor to execute any one of the technical solutions of the above-mentioned battery safety detection method.

[0017] The above one or more technical solutions of this application have at least one or more of the following Beneficial effects:

[0018] In the technical solution of the battery safety detection method provided in the present application, target data of the battery is obtained under preset working conditions; a first risk coefficient of the battery is determined according to the target data, wherein the first risk coefficient indicates the possibility of a safety risk in the battery; a second risk coefficient of the battery is calculated by combining multiple first risk coefficients; and whether the battery is safe is detected according to the second risk coefficient. In other words, in the embodiment of the present application, the second risk coefficient can be calculated by combining multiple first risk coefficients, and safety detection using the second risk coefficient is more accurate, which can enable high-risk batteries to be safely identified more timely, thereby improving the accuracy of battery safety detection, thereby improving the safety and reliability of the battery system, and solving the accuracy and false alarm problems of battery safety detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The disclosure of the present application will become easier to understand with reference to the accompanying drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present application. Among them:

[0020] Figure 1 This is a schematic flow chart of the main steps of a battery safety detection method according to an embodiment of the present application;

[0021] Figure 2 is a flow chart of a battery safety detection method according to another embodiment of the present application;

[0022] Figure 3 It is a main structural diagram of a computer device according to an embodiment of the present application.

[0023] Reference numerals:

[0024] 11: memory; 12: processor. DETAILED DESCRIPTION

[0025] Some embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the protection scope of the present application.

[0026] In the description of the present application, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, memory, and may also include software parts, such as program code, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware or a combination of the two. Computer-readable storage media include any suitable medium that can store program code, such as a disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B" and may include only A, only B or A and B. The singular terms "one" and "this" may also include plural forms. "Multiple" means two or more.

[0027] The relevant user personal information that may be involved in the various embodiments of this application is strictly in accordance with the requirements of laws and regulations, following the principles of legality, legitimacy and necessity, based on the reasonable purposes of business scenarios, to process the personal information that users actively provide during the use of products / services or generated due to the use of products / services, as well as the personal information obtained with the user's authorization.

[0028] The user personal information processed by this application will vary depending on the specific product / service scenario, and shall be based on the specific scenario in which the user uses the product / service, and may involve the user's account information, device information, driving information, vehicle information or other related information. This application will treat the user's personal information and its processing with a high degree of diligence.

[0029] This application attaches great importance to the security of user personal information and has taken reasonable and feasible security protection measures that meet industry standards to protect user information and prevent personal information from being accessed, disclosed, used, modified, damaged or lost without authorization.

[0030] In the related art, the safety of the battery is mainly detected by setting a threshold value and collecting the data value of the battery, and comparing the threshold value with the data value. For example, a drop voltage threshold is set, and if the drop voltage of the battery is greater than or equal to the drop voltage threshold, it is determined that the battery has a safety risk.

[0031] However, in the related art, the threshold used to detect whether the battery is safe is fixed. For example, the same threshold is used for different lifespans, different health levels or different usage conditions. However, with the different lifespans, different health levels or different usage conditions of the battery, the probability of safety risks in the battery is also different. Therefore, setting a fixed threshold to detect whether the battery is safe may not be able to detect some batteries with higher safety hazards. In other words, in the related art, it is difficult to adapt to the changes in the battery's state throughout its life cycle, and it is impossible to identify risks in time for batteries with deviations, which leads to the problem of poor accuracy of battery safety detection, which in turn easily leads to false alarms or omissions of battery abnormalities, thus reducing the accuracy and reliability of battery safety detection.

[0032] In view of this, the embodiments of the present application provide a battery safety detection method, storage medium and computer equipment, which can enable high-risk batteries to be safely identified more timely, improve the accuracy of battery safety detection, and further improve the safety and reliability of the battery system, and can solve the accuracy and false alarm problems of battery safety detection.

[0033] See attached Figure 1 , Figure 1 FIG. 1 is a flow chart of the main steps of a battery safety detection method according to an embodiment of the present application. Figure 1 As shown, the battery safety detection method in the embodiment of the present application mainly includes the following steps S101 to S104.

[0034] Step S101: Under a preset working condition, obtain target data of the battery.

[0035] Among them, the preset operating conditions may include but are not limited to charging conditions, static conditions and driving conditions. The battery may also be referred to as a battery pack. Optionally, the battery may include but is not limited to a power battery, a battery that has passed 3C certification, or a battery cell that constitutes the power battery or the battery that has passed 3C certification, etc., which are not limited here. Among them, the target battery data may be referred to as battery-related data, and the battery-related data may be data related to the battery. In an embodiment of the present application, the target data is used to calculate the possibility of a safety risk to the battery.

[0036] Step S102: determining a first risk factor of the battery according to the target data, wherein the first risk factor indicates the possibility of a safety risk occurring in the battery.

[0037] In the embodiment of the present application, the first risk coefficient of the battery is determined according to the target data of the battery, thereby determining the possibility of the battery having a safety risk. In a possible implementation, the greater the first risk coefficient, the higher the possibility of the battery having a safety risk.

[0038] S103: Calculate a second risk coefficient of the battery by combining multiple first risk coefficients.

[0039] In the embodiment of the present application, the second risk coefficient of the battery is calculated in combination with multiple first risk coefficients, and the second risk coefficient can be understood as a coefficient obtained by integrating multiple first risk coefficients, that is, the second risk coefficient is considered comprehensively based on multiple first risk coefficients.

[0040] S104: Detect whether the battery is safe according to the second risk factor.

[0041] In an embodiment of the present application, target data of a battery is obtained under preset working conditions; a first risk coefficient of the battery is determined according to the target data, wherein the first risk coefficient indicates the possibility of a safety risk occurring in the battery; a second risk coefficient of the battery is calculated by combining multiple first risk coefficients; and whether the battery is safe is detected according to the second risk coefficient. In this way, the second risk coefficient can be determined by combining multiple first risk coefficients, and the second risk coefficient is more accurate. Accordingly, the result of safety detection using the second risk coefficient is also more accurate, so that high-risk batteries can be safely identified more timely, thereby improving the accuracy of battery safety detection, thereby improving the safety and reliability of the battery system, and solving the accuracy and false alarm problems of battery safety detection.

[0042] In a possible implementation, detecting whether the battery is safe according to the second risk factor may be performed by determining a detection threshold of a safety indicator according to the second risk factor, thereby detecting whether the battery is safe according to the detection threshold of the safety indicator.

[0043] Among them, the safety index may refer to a quantitative index that measures the safety of a system, product or service. In an embodiment of the present application, the safety index is used to measure the safety index of the battery. Optionally, the safety index of the embodiment of the present application may be one or more, and the one or more safety indicators may include but are not limited to at least one of voltage or temperature, which is not limited here. Among them, the safety index detection threshold may refer to a threshold used to detect whether the battery is safe.

[0044] It should be noted that, in the embodiment of the present application, the security indicator detection thresholds corresponding to different second risk coefficients may be different. For example, when the second risk coefficient is coefficient 1, the corresponding security indicator detection threshold is threshold 1, and when the second risk coefficient is coefficient 2, the corresponding security indicator detection threshold is threshold 2. In addition, the security indicator detection threshold may be determined according to the coefficient interval in which the second risk coefficient is located. For example, when the second risk coefficient is in coefficient interval 1, the corresponding security indicator detection threshold is threshold 1, and when the second risk coefficient is in coefficient interval 2, the corresponding security indicator detection threshold is threshold 2. Among them, coefficient interval 1 and coefficient interval 2 can be divided according to the coefficient threshold, for example, the interval less than the coefficient threshold is coefficient interval 1, and the interval greater than the coefficient threshold is coefficient interval 2.

[0045] In the embodiment of the present application, the detection threshold of the safety indicator is determined by the second risk coefficient, and the safety indicator detection thresholds corresponding to different second risk coefficients may be different. In other words, the safety indicator detection threshold in the embodiment of the present application can be dynamically adjusted.

[0046] It should be noted that, in this embodiment, when calculating the first risk coefficient through battery-related data, the battery-related data used to calculate the first risk coefficient may be selected, and then the battery-related data is processed through an algorithm or model to calculate the first risk coefficient.

[0047] Exemplarily, in a possible implementation, for each battery-related data, a safe numerical range of the battery-related data is pre-set. If the value of the battery-related data is within the safe numerical range, the risk value (also referred to as the first risk coefficient) is A. If the value of the battery-related data is outside the safe numerical range, the risk value is B. For example, the voltage of the battery when fully charged is 4.0V, and the pre-set voltage range when fully charged is 4.2V-4.4V. At this time, the risk value of the battery is B. For another example, the voltage of the battery when fully discharged is 2.7V, and the pre-set voltage range when fully discharged is 2.3V-2.7V. At this time, the risk value of the battery is A. Then, the risk values ​​corresponding to each battery data are merged to obtain the second risk coefficient.

[0048] As another example, in another possible implementation, the battery-related data for training can be used as the input of the model, and then the risk value of the pre-labeled battery-related data for training can be used as the label for model training, so that a model can be trained to obtain the corresponding risk coefficient based on the input battery-related data.

[0049] The second risk coefficient is positively correlated with a product result of the plurality of first risk coefficients.

[0050] Exemplarily, the second risk factor and the plurality of first risk factors satisfy the following relationship:

[0051]

[0052] Among them, R total represents the second risk factor, R1 represents the first first risk factor, R n represents the nth first risk coefficient, where n is an integer greater than or equal to 1.

[0053] In another possible implementation, the second risk coefficient may be obtained by performing weighted average calculation on multiple first risk coefficients.

[0054] For example, the second risk coefficient can be obtained by weighted averaging the risk sub-coefficients (also called first risk coefficients) corresponding to each set of data. total =R 1 *X1+…+R n *Xn. Where n is a positive integer, R total represents the second risk factor, which can also be called the comprehensive risk factor, R1 represents the first first risk factor…, R n represents the nth first risk coefficient, X1 represents the weight corresponding to R1, ..., Xn represents the corresponding R n The corresponding weight.

[0055] In a possible implementation, acquiring target data may include acquiring a plurality of battery-related data based on battery attributes.

[0056] Among them, the battery properties can be the properties of the battery itself. Battery properties can include but are not limited to chemical properties, material properties and electrical properties. Among them, chemical properties are related to the battery's capacity, voltage, energy density and cycle life. Material properties are related to performance such as energy density and cycle life. Electrical properties are related to parameters such as electromotive force, capacity, and internal resistance.

[0057] Correspondingly, determining the second risk coefficient of the battery according to the target data of the battery includes: dividing the acquired multiple battery-related data into multiple groups of data based on preset conditions related to the battery properties; determining the risk sub-coefficient (also called the first risk sub-coefficient) corresponding to each group of data; and determining the second risk coefficient according to the risk sub-coefficients corresponding to each group.

[0058] The preset condition may be a pre-set condition. In the embodiment of the present application, the preset condition is used to divide the data. That is, the preset condition defines the division dimension of the battery-related data, and the battery-related data can be divided according to the preset condition, and the preset condition may be, for example, at least one of division by time, division by failure cause, division by working condition, and division by environment.

[0059] It should be noted that, when divided by time, battery-related data may include but is not limited to part or all of the full life cycle data. Among them, the full life cycle data can be understood as at least one item of production data or operation data within a cycle, and the starting point and end point of the cycle can be set according to actual conditions, without limitation here. Exemplarily, the starting point of the cycle may be the time when the battery starts production, the time when the battery is put on the production line, or the time when the battery is put on the market, etc., without limitation here. Optionally, the full life cycle data may include but is not limited to static data before the battery is put on the market: such as battery design data, production data or test data, or dynamic data after the battery is put on the market: for example, driving, charging or static data at the vehicle end and the battery swap station end. These data are the basis for detecting and evaluating battery performance and safety status.

[0060] It should be noted that, according to the classification of failure causes, the failure causes may include but are not limited to lithium deposition, internal short circuit self-discharge, abnormal charging voltage difference, differential voltage-capacity outlier and capacity decay outlier, and the battery-related data may be divided into data for determining lithium deposition, data for determining internal short circuit self-discharge, data for determining abnormal charging voltage difference, data for determining differential voltage-capacity outlier or data for determining capacity decay outlier. Among them, the data for determining the above-mentioned failure causes may include but are not limited to at least one of the battery voltage data, current data, temperature data, the charging method used by the battery (such as fast charging or slow charging) or charging parameters (such as charging current, charging voltage, charging power or charging time, etc.).

[0061] It should be noted that, when divided according to the operating conditions of the battery, the battery-related data can be divided into driving data (also known as driving conditions or data under driving state), charging data (also known as charging conditions or data under charging state) or static data (also known as static conditions or data under static state).

[0062] It should be noted that, when divided according to the environment, battery-related data can be divided into data located in the charging station environment and data located in the battery swap station environment.

[0063] In an embodiment of the present application, based on each group of data, the risk sub-coefficient corresponding to the group of data is determined, and then the second risk coefficient is determined based on the risk sub-coefficients corresponding to each group. This can be understood as fusing the risk sub-coefficients corresponding to each group to obtain the second risk coefficient. For example, the second risk coefficient may be positively correlated with the risk sub-coefficients corresponding to each group of data.

[0064] In an embodiment of the present application, the multiple battery-related data obtained are divided into multiple groups of data based on preset conditions related to the battery properties, and then the risk sub-coefficient corresponding to each group of data is determined, and then the second risk coefficient is determined according to the risk sub-coefficient corresponding to each group. This can improve the calculation accuracy of the second risk coefficient, and then improve the calculation accuracy of the threshold, thereby improving the accuracy of safety detection.

[0065] It should be understood that the specific risk sub-coefficient and the data used to calculate the risk sub-coefficient can be set as needed and are not specifically limited here.

[0066] In a possible implementation, the target data includes pre-marketing data and post-marketing data, and the first risk coefficient includes a first risk coefficient corresponding to the pre-marketing data and a first risk coefficient corresponding to the post-marketing data.

[0067] In the embodiment of the present application, the multiple data are divided into battery pre-marketing data and battery post-marketing data, and the risk sub-coefficient corresponding to the battery pre-marketing data and the risk sub-coefficient corresponding to the battery post-marketing data can be calculated.

[0068] Then, the second risk coefficient of the battery is calculated according to the risk sub-coefficient corresponding to the pre-marketing data and the risk sub-coefficient corresponding to the post-marketing data. Specifically, the risk sub-coefficient corresponding to the pre-marketing data of the battery and the risk sub-coefficient corresponding to the post-marketing data of the battery are merged to obtain the second risk coefficient.

[0069] For example, in the present embodiment, R 1 It can represent the risk sub-coefficient corresponding to the data before the battery is put on the market, R 2 It can represent the risk sub-coefficient corresponding to the data of the battery after it is put on the market.

[0070] Optionally, it can be R 2 The corresponding weight is greater than R 1 The corresponding weight.

[0071] In an embodiment of the present application, by dividing multiple data into pre-marketing data and post-marketing data, that is, dividing the data from different time dimensions, the influence of different time dimensions can be taken into account when calculating the second risk coefficient, thereby improving the calculation accuracy of the second risk coefficient and further improving the accuracy of safety detection.

[0072] In another possible implementation, the first risk factor is determined based on a failure cause of the battery, and the failure cause includes at least one of lithium plating, internal short circuit self-discharge, abnormal charging voltage difference, differential voltage-capacity outlier, and capacity decay outlier.

[0073] In the embodiment of the present application, multiple data are divided into data corresponding to different failure causes, and the risk sub-coefficients corresponding to the different failure causes can be calculated, and then the second risk coefficient of the battery is calculated according to the risk sub-coefficients corresponding to each failure cause. Specifically, the risk sub-coefficients corresponding to different failure causes are merged to obtain the second risk coefficient.

[0074] It should be noted that the reasons for battery failure may include but are not limited to at least one of lithium deposition, internal short circuit self-discharge, abnormal charge voltage difference, differential voltage-capacity outlier or capacity decay outlier. The above failures may further cause problems such as thermal runaway and reduced battery life. The following is a further explanation of each failure reason.

[0075] Lithium deposition: Taking lithium batteries as an example, during the charging process, lithium ions are released from the positive electrode, migrate to the negative electrode through the electrolyte, and are embedded in the negative electrode to form lithium metal. However, in some abnormal cases, such as insufficient lithium embedding space at the negative electrode, excessive resistance to lithium embedding, or lithium ions are released from the positive electrode too quickly but cannot be embedded in the negative electrode in equal amounts, lithium ions will gain electrons on the surface of the negative electrode to form silvery white metallic lithium, which is the lithium deposition phenomenon.

[0076] Internal short circuit self-discharge: refers to the phenomenon that a direct short circuit occurs between the positive and negative electrodes inside the battery, causing the battery to self-discharge.

[0077] Abnormal charging voltage difference: It means that during the charging process of the battery, due to various reasons, the voltage difference between battery cells or battery packs exceeds the normal range.

[0078] Differential voltage-capacity (dQ / dV) outlier: refers to the abnormal fluctuation or deviation of the differential voltage-capacity curve from the normal range during the battery charging and discharging process.

[0079] Capacity decay outlier: refers to the risk caused by a significant and abnormal decrease in the capacity of the battery relative to the initial capacity or expected capacity during use. This risk has a certain impact on the performance, life of the battery and the reliability of the entire battery system.

[0080] Optionally, in an embodiment of the present application, the multiple groups of data may include at least two groups of data including a first group of data for determining a lithium plating risk sub-coefficient, a second group of data for determining an internal short circuit self-discharge risk sub-coefficient, a third group of data for determining a charging voltage difference abnormal risk sub-coefficient, a fourth group of data for determining a differential voltage-capacity outlier risk sub-coefficient, or a fifth group of data for determining a capacity decay outlier risk sub-coefficient.

[0081] Optionally, the first set of data may include voltage data. Specifically, during the charge and discharge process of the battery, the voltage changes over time. In certain specific charge and discharge stages, the voltage remains at a relatively stable platform value, which are called voltage platforms. Lithium precipitation will cause changes in the internal resistance of the battery, thereby affecting the voltage platform. Especially during the charging process, when lithium precipitation occurs, there will be obvious inflection points or fluctuations in the voltage platform. By detecting the changes in these voltage platforms, it can be determined whether the battery has lithium precipitation. The greater the change in the voltage platform, the greater the lithium precipitation risk sub-coefficient.

[0082] Optionally, the second set of data may include at least one of voltage data or temperature data. Specifically, in a battery pack, if a battery cell has an internal short circuit, its voltage may be significantly different from that of other normal battery cells. By monitoring the voltage of each battery cell in the battery pack, batteries with abnormal voltages can be discovered in a timely manner to determine whether they have a risk of internal short circuit self-discharge. In addition, an internal short circuit can cause a large amount of heat to be generated inside the battery, causing the battery temperature to rise. Therefore, by monitoring the temperature changes of the battery, it is also possible to determine whether the battery has a risk of internal short circuit self-discharge. The greater the difference between the voltage or temperature of a battery cell and the voltage or temperature of other normal battery cells, the greater the internal short circuit self-discharge risk sub-coefficient corresponding to the battery.

[0083] Optionally, the third set of data may include charging voltage data. Specifically, if the voltage difference of the battery fluctuates frequently or increases suddenly during charging, it may mean that there is a fault or aging inside the battery, resulting in an increased risk of abnormal charging voltage difference. The corresponding abnormal charging voltage difference risk sub-coefficient is larger.

[0084] Optionally, the fourth set of data may include differential voltage-capacity curves corresponding to each of the multiple batteries, and then the differential voltage-capacity curves corresponding to each of the multiple batteries are fitted, and the battery corresponding to the curve deviating from the fitting result is considered to have a higher differential voltage-capacity outlier risk sub-coefficient. For example, the risk sub-coefficient deviating from the fitting result is higher than the risk sub-coefficient matching the fitting result.

[0085] Optionally, the fifth group of data may include the capacity decay conditions corresponding to each of the multiple batteries, and then the capacity decay conditions corresponding to each of the multiple batteries are fitted, and the battery corresponding to the capacity decay deviating from the fitting result is considered to have a higher capacity decay outlier risk sub-coefficient.

[0086] For example, in the present embodiment, R 1 It can represent the risk sub-coefficient corresponding to one of the failure causes, R 2 It can represent the risk sub-coefficient corresponding to another failure cause.

[0087] Taking the failure causes including lithium deposition and internal short circuit self-discharge as an example, R total =R li *X1+R ISC *X2. Among them, R li Represents the risk sub-coefficient corresponding to lithium deposition, R ISC represents the risk sub-coefficient corresponding to internal short circuit self-discharge, X1 represents the weight of the risk sub-coefficient corresponding to lithium deposition, and X2 represents the weight of the risk sub-coefficient corresponding to internal short circuit self-discharge. Optionally, 1≤R li ≤10.1≤R ISC ≤10.

[0088] Taking the failure causes including lithium deposition and internal short circuit self-discharge as an example,

[0089] In an embodiment of the present application, by determining the risk sub-coefficient corresponding to each set of data in multiple sets of data of the battery, and then determining the second risk coefficient based on the risk sub-coefficient corresponding to each set of data, the accuracy of determining the second risk coefficient can be improved, thereby improving the accuracy of battery safety testing.

[0090] In a possible implementation, acquiring multiple battery-related data based on battery properties includes acquiring multiple data based on different battery operating conditions. Accordingly, dividing the acquired battery-related data into multiple groups of data based on preset conditions related to the battery properties includes: dividing the data corresponding to different operating conditions into multiple groups of data based on the battery operating condition.

[0091] Optionally, the battery operating condition may include but is not limited to a stationary operating condition, a driving operating condition or a charging operating condition. Among them, the stationary operating condition may refer to a condition in which the battery is in a stationary state. The driving operating condition may refer to a condition in which the battery is in a discharging condition, thereby driving the vehicle in which the battery is installed. The charging operating condition may refer to a condition in which the battery is in a charging state. Exemplarily, taking multiple operating conditions including a stationary operating condition, a driving operating condition and a charging operating condition as an example, the data under the stationary operating condition may be obtained, and then the second risk coefficient under the stationary operating condition may be calculated using the data under the stationary operating condition, and then the safety index detection threshold 1 under the stationary operating condition may be determined based on the second risk coefficient under the stationary operating condition. Similarly, the data under the driving condition may be obtained to calculate the safety index detection threshold 2 under the driving condition, and the data under the charging condition may be obtained to calculate the safety index detection threshold 3 under the charging condition.

[0092] It should be noted that, for how to use battery data to obtain the safety indicator detection threshold under different working conditions, reference can be made to the description of the above embodiment, which will not be elaborated here.

[0093] It should be understood that the working conditions of the embodiments of the present application can be divided as needed and are not limited here.

[0094] In an embodiment of the present application, multiple data are divided into data corresponding to different working conditions, and then the risk sub-coefficients corresponding to the different working conditions can be calculated. Then, the risk sub-coefficients corresponding to the different working conditions are merged to obtain a second risk coefficient.

[0095] For example, in the present embodiment, R 1 It can represent the risk sub-coefficient corresponding to the static condition, R 2 It can represent the risk sub-coefficient corresponding to the driving condition, R 3 It can represent the risk sub-coefficient corresponding to the charging condition.

[0096] In an embodiment of the present application, by dividing multiple data into data corresponding to different working conditions, that is, dividing the data from the dimensions of different working conditions, the influence of different working condition dimensions can be taken into account when calculating the second risk coefficient, thereby improving the calculation accuracy of the second risk coefficient and further improving the accuracy of safety detection.

[0097] In another possible implementation, the operating conditions may not be differentiated, or the operating conditions may be differentiated but the data of one of the operating conditions may be used to calculate the threshold value, which can improve the efficiency of battery safety detection.

[0098] In a possible implementation, the target data includes battery replacement data and charging data, and the first risk coefficient includes a first risk coefficient corresponding to the battery replacement data and a first risk coefficient corresponding to the charging data.

[0099] In an embodiment of the present application, multiple data are divided into data corresponding to different environments where the battery is located, and the risk sub-coefficients corresponding to different environments can be calculated. For example, the risk sub-coefficients corresponding to the charging station environment or the battery swap station environment can be calculated, and then the second risk coefficient of the battery can be calculated based on the first risk coefficient corresponding to the battery swap data and the first risk coefficient corresponding to the charging data.

[0100] For example, in the present embodiment, R 1 It can represent the risk sub-coefficient of data in the charging station environment, R 2 It can represent the risk sub-coefficient corresponding to the data in the battery swap station environment.

[0101] In an embodiment of the present application, by dividing multiple data into data under a charging station environment and data under a battery swap station environment, that is, dividing the data from the dimensions of different environments, the influence of different environmental dimensions can be considered when calculating the second risk coefficient, thereby improving the calculation accuracy of the second risk coefficient and further improving the accuracy of safety detection.

[0102] The following embodiment is based on any of the above embodiments and uses the fusion of multiple dimensions to illustrate the calculation of the second risk coefficient.

[0103] In a possible implementation, the data is divided into pre-marketing data and post-marketing data. Among them, the pre-marketing data and the post-marketing data are further divided into data under the charging station environment and data under the battery swap station environment, respectively. The data under the charging station environment and the data under the battery swap station environment can be divided into data related to different failure causes, for example, data related to lithium plating and data related to internal short circuit self-discharge. Among them, the data related to lithium plating may include voltage data under static state, voltage data under charging, and voltage data under driving, and the data related to internal short circuit self-discharge may include voltage data under static state, voltage data under charging, and voltage data under driving. Then, for lithium plating, the risk coefficient of lithium plating under static state can be determined based on the voltage data under static state, the risk coefficient of lithium plating under charging can be determined based on the voltage data under charging, and the risk coefficient of lithium plating under driving can be determined based on the voltage data under driving, and then the risk coefficient of lithium plating under different working conditions can be fused to obtain the risk coefficient of lithium plating. Similarly, based on the data of internal short circuit self-discharge under different working conditions, the risk coefficient of internal short circuit self-discharge under different working conditions, and then the risk coefficient of internal short circuit self-discharge under different working conditions is fused to obtain the risk coefficient of internal short circuit self-discharge. Then, based on the internal short-circuit self-discharge risk coefficient in the charging station environment and the lithium plating risk coefficient in the charging station environment, the risk coefficient corresponding to the data in the charging station environment can be integrated to obtain the risk coefficient. Similarly, the risk coefficient corresponding to the data in the battery swap station environment can be obtained. Then, based on the charging station environment risk coefficient and the battery swap station environment risk coefficient corresponding to the data before the battery was launched on the market, the risk coefficient corresponding to the data before the battery was launched on the market can be integrated. Similarly, the risk coefficient corresponding to the data after the battery is launched on the market can be obtained. Then, the risk coefficient corresponding to the data before the battery was launched on the market and the risk coefficient corresponding to the data after the battery was launched on the market are integrated to obtain the second risk coefficient.

[0104] In an embodiment of the present application, data may be divided according to one or more dimensions, so that when data is divided according to multiple dimensions, the accuracy of the calculated second risk coefficient is improved, thereby improving the accuracy of battery safety detection.

[0105] It should be understood that the order of division of different dimensions can be set as needed and is not limited here. For another example, the data is divided into pre-marketing data and post-marketing data. Among them, the pre-marketing data and the post-marketing data are respectively divided into data under the charging station environment and data under the battery swap station environment, and the data under the charging station environment and the data under the battery swap station environment are respectively divided into data under different working conditions, and the data under different working conditions are further divided into data with different failure causes. Correspondingly, the order of calculating the risk coefficients of different dimensions is different.

[0106] It should be noted that the fusion method in the embodiment of the present application can be a weighted average or a multiplication and then root taking method, which is not limited here.

[0107] The first risk coefficient corresponds to at least one safety indicator, and a second risk coefficient of the battery is calculated by combining multiple first risk coefficients, including:

[0108] For each safety indicator, a second risk coefficient of the safety indicator of the battery is calculated according to a plurality of first risk coefficients of the safety indicator.

[0109] Accordingly, detecting whether the battery is safe according to the second risk factor includes:

[0110] For each safety indicator, a detection threshold of the safety indicator is calculated according to a second risk coefficient of the safety indicator; a value of each safety indicator is obtained; and whether the battery is safe is detected according to the value of each safety indicator and the detection threshold of each safety indicator.

[0111] In an embodiment of the present application, the second risk coefficient of each safety indicator can be calculated through multiple first risk coefficients of each safety indicator, and then the detection threshold corresponding to each safety indicator can be calculated according to the second risk coefficient of each safety indicator. Then, whether the battery is safe is detected according to the numerical value of each safety indicator and the detection threshold of each safety indicator. Since safety detection is performed through each safety indicator, the accuracy of battery safety detection can be further improved.

[0112] Exemplarily, the values ​​of N safety indicators at different times may be collected, where N is an integer not less than 2; and whether the battery is safe may be detected based on changes in the values ​​of the N safety indicators and detection thresholds of the safety indicators.

[0113] In an embodiment of the present application, the data value of the safety indicator is obtained, and then the safety of the battery is detected based on the change between the data values ​​and the safety indicator detection threshold. Since the safety of the battery is detected by using the values ​​of multiple safety indicators, the accuracy of the battery safety detection can be improved.

[0114] In another possible implementation, the safety of the battery may be detected by using fewer values ​​of safety indicators, which can reduce the time required for obtaining data and thus improve the efficiency of battery safety detection.

[0115] In a possible implementation, the N safety indicators are a characterization indicator; detecting whether the battery is safe according to the change between the values ​​of the N safety indicators and the safety indicator detection threshold includes:

[0116] Arrange the values ​​of N safety indicators in order of collection time, where N is an integer not less than 3; when the absolute values ​​of the differences between adjacent values ​​in the values ​​of the N safety indicators are greater than or equal to the safety indicator detection threshold and the values ​​of the N safety indicators change monotonically, determine that the battery is unsafe; when the absolute value of the difference between adjacent values ​​in the values ​​of the N safety indicators is less than the safety indicator detection threshold or the values ​​of the N safety indicators do not change monotonically, determine that the battery is safe.

[0117] Among them, the values ​​of the N safety indicators change monotonically, and the change trend of any two adjacent data values ​​in the values ​​of the N safety indicators may be the same. The change trend may be gradually decreasing or gradually increasing, which is related to the specific safety indicator and is not limited here. Optionally, the safety indicator may include voltage or temperature. Taking the safety indicator including voltage as an example, it means that the battery's continuous drop voltage is large, which means that the power of the battery is rapidly decaying. For another example, taking the safety indicator including temperature as an example, it means that the battery's continuous temperature rise is large, which means that the battery has a thermal runaway safety problem.

[0118] For voltage, if multiple voltage values ​​change monotonically, and the monotonically change is gradually decreasing, and the absolute values ​​of the differences between adjacent voltage values ​​are greater than or equal to the voltage detection threshold, the battery is determined to be unsafe. For temperature, if multiple temperature values ​​change monotonically, and the monotonically change is gradually increasing, and the absolute values ​​of the differences between adjacent temperature values ​​are greater than or equal to the temperature detection threshold, the battery is determined to be unsafe.

[0119] Exemplarily, assuming that the voltage detection threshold is 0.5V, the values ​​of the N safety indicators are 5V, 4V, 3V, and 2.4V, respectively, and it can be determined that the battery is unsafe.

[0120] In a possible implementation, the N security indicators are multiple indicators;

[0121] The battery safety is detected based on the changes in the values ​​of N safety indicators and the safety indicator detection thresholds, including:

[0122] Arrange the values ​​corresponding to any indicator in the order of collection time, where the number of values ​​of any indicator is not less than 3 integers;

[0123] When the absolute values ​​of the differences between the adjacent values ​​of any indicator are greater than or equal to the safety indicator detection threshold and the value of any indicator changes monotonically, it is determined that the battery is unsafe;

[0124] The battery is determined to be safe when the absolute value of the difference between adjacent values ​​of each indicator in the multiple indicators is less than the safety indicator detection threshold or the value of each indicator does not change monotonically.

[0125] Exemplarily, assuming that the multiple indicators include a voltage indicator (referred to as voltage) and a temperature indicator (referred to as temperature), if multiple voltage values ​​change monotonically, and the monotonically change is gradually decreasing, and the absolute values ​​of the differences between adjacent voltage values ​​are greater than or equal to the voltage detection threshold; or, multiple temperature values ​​change monotonically, and the monotonically change is gradually increasing, and the absolute values ​​of the differences between adjacent temperature values ​​are greater than or equal to the temperature detection threshold, then the battery is determined to be unsafe.

[0126] In this embodiment, multiple safety indicators can be used to determine whether the battery has a safety abnormality. For example, the battery is considered to be in a safe state only when every safety indicator determines that the battery is safe; when one of the safety indicators determines that the battery has a safety problem, the battery is considered to have a safety problem. Since multiple safety indicators are used to determine whether the battery is safe, the accuracy of battery safety detection can be improved.

[0127] It should be understood that in the embodiment of the present application, if it is determined that there is a safety problem with the battery, an alarm can be issued. Taking the safety indicator as voltage as an example, assuming that based on the calculation of data under different working conditions, Rli of a battery pack is 3.6 and RISC is 2.3, then If the original safety monitoring alarm logic is: if the total voltage of the battery pack drops by 2V and lasts for 5 data points, that is, the voltage of the 5 data points continues to drop, and the voltage drop between any two of the 5 data points exceeds 2V, then an alarm is triggered; after adopting the solution of the embodiment of the present application, the logic for the battery pack is changed to: if the total voltage of the battery pack drops by 0.69V and lasts for 5 data points, that is, the voltage of the 5 data points continues to drop, and the voltage drop between any two adjacent data points of the 5 data points exceeds 0.69V, then an alarm is triggered.

[0128] The following embodiment describes how to determine the safety indicator detection threshold based on any of the above embodiments.

[0129] In a possible implementation, calculating the detection threshold of the safety indicator according to the second risk coefficient of the safety indicator includes:

[0130] In response to detecting that the second risk coefficient is less than or equal to the risk coefficient threshold, the preset first threshold is determined as the detection threshold of the safety indicator; in response to detecting that the second risk coefficient is greater than the risk coefficient threshold, the second threshold is determined as the detection threshold of the safety indicator, wherein the second threshold depends on the preset first threshold and the second risk coefficient.

[0131] In the embodiment of the present application, the risk factor threshold can be used as a basis or reference for determining whether a battery has a potential safety risk. If the second risk factor is less than or equal to the risk factor threshold, the detection threshold of the safety indicator can be set to the first threshold regardless of the specific value of the second risk factor, and if the second risk factor is greater than the risk factor threshold, the detection threshold of the safety indicator will be set to the second threshold according to the second risk factor and the first threshold. In this way, the problem of overly complex threshold settings caused by setting each threshold according to each second risk factor can be reduced, thereby improving the efficiency of setting the safety indicator detection threshold, and thus improving the efficiency of battery safety detection.

[0132] In another possible implementation, a separate threshold may be set for each second risk factor, which can improve the accuracy of battery safety detection.

[0133] In a possible implementation, the second threshold is positively correlated with the first threshold, and the second threshold is negatively correlated with the second risk coefficient.

[0134] Optionally, the second threshold is related to the ratio between the first threshold and the second risk factor. Exemplarily, the second threshold = first threshold / second risk factor. Or, the second threshold = correction factor 1 * first threshold / second risk factor. Wherein, the correction factor 1 is a number between 0 and 1, and the greater the difference between the second risk factor and the risk factor threshold, the smaller the correction factor 1. Taking the safety indicator as voltage as an example, the second threshold = A / Rtotal V, A is the first threshold.

[0135] Optionally, the safety index detection threshold can be adjusted downward in proportion to the first threshold value according to the size of the second risk coefficient. For example, the second threshold value = the first threshold value * (1-the proportion of downward adjustment), and the proportion of downward adjustment is related to the size of the second risk coefficient. The larger the second risk coefficient, the larger the proportion of downward adjustment. In the embodiment of the present application, a corresponding relationship between the risk coefficient and the proportion of downward adjustment can be set, so that the proportion of downward adjustment corresponding to the second risk coefficient can be determined through the mapping relationship.

[0136] It should be noted that in the embodiment of the present application, the larger the second risk coefficient is, the smaller the second threshold is, and accordingly it is easier to detect that there is a safety problem with the battery, that is, it is easier to detect that the battery is unsafe, which can improve the accuracy of battery safety detection.

[0137] In general, the risk factor calculation method based on the battery life cycle data in the embodiment of the present application can achieve more timely fault identification for high-risk batteries by dynamically adjusting the threshold of the safety monitoring algorithm, thereby improving the safety and reliability of the battery system and solving the accuracy and false alarm problems of battery monitoring.

[0138] In the above embodiment, the following key aspects are mainly included:

[0139] Full life cycle data fusion: First of all, it involves the collection and fusion of battery data throughout its life cycle, including but not limited to: (1) Static data before the battery is put on the market: battery design, production or test data, etc. (2) Dynamic data after the battery is put on the market: driving, charging, and static data at the vehicle end and the battery swap station end. These data are the basis for monitoring and evaluating battery performance and safety status.

[0140] Risk factor calculation: Based on the full life cycle data, multiple high-order calculation characteristic values ​​are obtained to further comprehensively calculate the risk factor of the battery, evaluate the performance, health status and potential failure risks of each battery, and thus quantitatively reflect the current safety status and potential problems of the battery.

[0141] The multiple high-order values ​​may be, for example, multiple data, such as a set of data used to calculate each risk sub-coefficient, and the characteristic value may be a feature or a risk sub-coefficient extracted from the data and used to calculate the risk sub-coefficient.

[0142] Dynamic threshold adjustment: The embodiment of the present application dynamically adjusts the threshold of the safety monitoring algorithm according to the risk factor of the battery. This means that the alarm threshold of the battery with a high risk factor will be lowered to identify potential faults or dangerous situations more promptly, thereby improving the accuracy of the monitoring system.

[0143] Real-time and intelligent: This application can better adapt to the dynamic changes of battery status and improve the real-time and intelligent nature of monitoring. By adjusting the threshold according to the risk factor in real time, the system can respond to potential problems more quickly and improve the reliability of monitoring.

[0144] In order to facilitate understanding of this solution, the following embodiment provides another flow chart to illustrate the solution of the embodiment of this application. Figure 2 , Figure 2 FIG. 1 is a flow chart of a battery safety detection method according to another embodiment of the present application. Figure 2 The method shown may include steps S201 to S209.

[0145] Step S201, start testing the market-side battery pack.

[0146] The market-side battery pack may be a factory-produced battery pack or a sold battery pack. The battery pack detection in the embodiment of the present application may be a safety detection of the battery pack, for example, obtaining data of the battery pack and then detecting the safety of the battery pack.

[0147] Step S202: Calculate the risk factor of a single failure of each battery pack.

[0148] Each failure corresponds to a safety risk, such as the risk factor of a failure due to lithium deposition or the risk factor of a failure due to internal short circuit. This step can refer to the description of the above embodiment and will not be described in detail here.

[0149] Step S203: Calculate the comprehensive risk factor of each battery pack.

[0150] The method of calculating the comprehensive risk coefficient may refer to the description of the above embodiment and will not be elaborated here.

[0151] Step S204: Whether there is a potential security risk.

[0152] In the embodiment of the present application, the comprehensive risk coefficient can be compared with the risk coefficient threshold to determine whether a potential safety risk occurs. For example, if the comprehensive risk coefficient is greater than the risk coefficient threshold, a potential safety risk occurs; if the comprehensive risk coefficient is less than the risk coefficient threshold, it can be considered that no potential safety risk occurs.

[0153] In the embodiment of the present application, if yes, that is, a potential security risk occurs, then S206 is executed; if no, that is, no potential security risk occurs, then S205 is executed.

[0154] Step S205: Use a standard safety alarm threshold for the battery pack.

[0155] Among them, the standard safety alarm threshold can refer to the description of the first threshold in the above embodiment, and will not be repeated here.

[0156] Step S206: Determine the safety alarm threshold reduction ratio based on the comprehensive risk factor.

[0157] How to determine the safety alarm threshold reduction ratio based on the comprehensive risk factor can refer to the description of the above embodiment, which will not be repeated here. For example, the greater the comprehensive risk factor, the greater the safety alarm threshold reduction, and the greater the corresponding reduction ratio.

[0158] Step S207: Use a proportionally lowered safety alarm threshold for the battery pack.

[0159] The security alarm threshold adjusted downward in proportion may also be referred to as a dynamic threshold. The dynamic threshold may refer to the description of the second threshold in the above embodiment, and will not be described in detail here.

[0160] Step S208: Perform safety detection on the market-side battery pack using the dynamic threshold.

[0161] Among them, how to use the dynamic threshold to perform safety detection on the battery pack can refer to the description of the above embodiment, which will not be repeated here.

[0162] Step S209: Push the alarm result to the operation end.

[0163] The operation end may be a server or a terminal device for recording the operation data of the battery pack, etc.

[0164] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effect of the present application, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders. These adjusted schemes are equivalent to the technical schemes described in this application, and therefore will also fall within the scope of protection of this application.

[0165] It is understood by those skilled in the art that all or part of the processes in the method for implementing the above-mentioned embodiment of the present application can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of each of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable storage media may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal and software distribution medium, etc. that can carry computer program code.

[0166] Another aspect of the present application also provides a computer-readable storage medium. In an embodiment of a computer-readable storage medium according to the present application, the computer-readable storage medium can be configured to store a program for executing the battery safety detection method of the above-mentioned method embodiment, and the program can be loaded and run by the processor to implement the above-mentioned battery safety detection method. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present application. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present application is a non-temporary computer-readable storage medium.

[0167] Another aspect of the present application provides a computer device.

[0168] In an embodiment of a computer device according to the present application, the computer device may include at least one processor; and a memory connected to the at least one processor; wherein a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the method of any of the above embodiments is implemented. The computer device of the present application may include driving equipment, smart cars, robots, mobile phones, tablet computers, desktops, laptops, handheld computers, notebook computers, vehicle-mounted equipment, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), augmented reality (AR) and virtual reality (VR) devices. See the attached Figure 3 , Figure 3 FIG. 4 exemplarily shows that the memory 11 and the processor 12 are communicatively connected via a bus.

[0169] In some embodiments of the present application, a computer device is used to implement the method of any of the above embodiments. The computer device may also be referred to as an electronic device.

[0170] Another aspect of the present application also provides a battery safety detection device, including: an acquisition module, configured to acquire target data of the battery under preset working conditions; a first determination module, configured to determine a first risk factor of the battery according to the target data, wherein the first risk factor indicates the possibility of a safety risk of the battery; a second determination module, configured to calculate a second risk factor of the battery by combining multiple first risk factors; a safety detection module, configured to detect whether the battery is safe according to the second risk factor. The above-mentioned battery safety detection device is used to perform Figure 1 The battery safety detection method embodiment shown in the figure has similar technical principles, technical problems solved and technical effects produced. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process and related instructions of the battery safety detection device can refer to the contents described in the embodiment of the battery safety detection method, which will not be repeated here.

[0171] An embodiment of the present application provides a computer program product, which includes a computer program code. When the computer program code runs on an electronic device, the electronic device executes a method in any of the above embodiments.

[0172] So far, the technical solution of the present application has been described in conjunction with an embodiment shown in the accompanying drawings, but it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Without departing from the principles of the present application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present application.

Claims

1. A battery safety detection method, characterized in that: include: Under a preset working condition, obtaining target data of the battery; determining a first risk factor of the battery according to the target data, wherein the first risk factor indicates a possibility that a safety risk may occur to the battery; Calculating a second risk coefficient of the battery by combining a plurality of the first risk coefficients; Whether the battery is safe is detected according to the second risk factor.

2. The method according to claim 1, characterized in that The second risk coefficient is positively correlated with a product result of a plurality of the first risk coefficients.

3. The method according to claim 2, characterized in that The second risk factor and the plurality of the first risk factors satisfy the following relationship: Among them, the R total represents the second risk factor, R1 represents the first risk factor, R n represents the nth first risk coefficient, where n is an integer greater than or equal to 1.

4. The method according to any one of claims 1 to 3, characterized in that The target data includes pre-marketing data and post-marketing data, and the first risk coefficient includes the first risk coefficient corresponding to the pre-marketing data and the first risk coefficient corresponding to the post-marketing data.

5. The method according to any one of claims 1 to 3, characterized in that: The first risk factor is determined based on a failure cause of the battery, wherein the failure cause includes at least one of lithium plating, internal short circuit self-discharge, abnormal charging voltage difference, differential voltage-capacity outlier, and capacity decay outlier.

6. The method according to any one of claims 1 to 3, characterized in that: The target data includes battery replacement data and charging data, and the first risk coefficient includes the first risk coefficient corresponding to the battery replacement data and the first risk coefficient corresponding to the charging data.

7. The method according to any one of claims 1 to 3, characterized in that The first risk coefficient corresponds to at least one safety indicator, and the combining of a plurality of the first risk coefficients to calculate the second risk coefficient of the battery includes: For each of the safety indicators, calculating a second risk coefficient of the safety indicator according to a plurality of the first risk coefficients of the safety indicator; The detecting whether the battery is safe according to the second risk factor includes: For each of the safety indicators, calculating a detection threshold of the safety indicator according to the second risk coefficient of the safety indicator; Obtaining the value of each of the safety indicators; Whether the battery is safe is detected according to the value of each safety indicator and the detection threshold of each safety indicator.

8. The method according to claim 7, characterized in that The step of calculating the detection threshold of the safety indicator according to the second risk coefficient of the safety indicator comprises: In response to detecting that the second risk factor is less than or equal to a risk factor threshold, determining a preset first threshold as a detection threshold of the safety indicator; In response to detecting that the second risk factor is greater than the risk factor threshold, a second threshold is determined as a detection threshold of the safety indicator, wherein the second threshold depends on the preset first threshold and the second risk factor.

9. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the battery safety detection method according to any one of claims 1 to 8.

10. A computer device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores a computer program, and when the computer program is executed by the at least one processor, the battery safety detection method according to any one of claims 1 to 8 is implemented.

Images