WO2023133682A1

WO2023133682A1 - Battery detection method, apparatus, device, storage medium and computer program product

Info

Publication number: WO2023133682A1
Application number: PCT/CN2022/071323
Authority: WO
Inventors: 刘宏阳; 赵薇
Original assignee: 宁德时代新能源科技股份有限公司
Priority date: 2022-01-11
Filing date: 2022-01-11
Publication date: 2023-07-20
Also published as: CN117157545A

Abstract

A battery detection method, an apparatus (200), a device, a storage medium, and a computer program product. The battery detection method comprises: acquiring first operation data of a first battery (110); according to the first operation data and a fault detection model corresponding to the first battery, determining a first detection result of the first battery (120), wherein the first detection result comprises a first score that a target fault occurs in the first battery; and according to the first score and a time influence factor that the target fault occurs in the first battery, determining a second detection result of the first battery (130), wherein the time influence factor is determined according to time information that the target fault occurs in the first battery within a first preset time period. The problems of low detection precision and a high false alarm rate of a battery fault detection result can be solved.

Description

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

technical field

The present application relates to the battery field, in particular to a battery detection method, device, equipment, storage medium and computer program product.

Background technique

With the continuous development of science and technology, batteries are more and more widely used in daily production and life, and the safety performance of batteries has attracted more and more attention. In the application process of the battery, the operating state of the battery is often detected by collecting the power consumption parameters generated by the battery to determine whether the battery is faulty.

However, the current commonly used detection methods, such as using the same detection model to detect the faults of batteries in different application environments, can only get a rough judgment result on whether the battery is faulty, which leads to low detection accuracy of the detection results , and the false alarm rate is high, which is not conducive to improving the safety of battery applications.

Contents of the invention

In view of the above problems, the present application provides a battery detection method, device, equipment, storage medium and computer program product to solve the problems of low detection accuracy and high false alarm rate of battery failure detection results.

In a first aspect, the present application provides a battery detection method, including:

acquiring first operating data of the first battery;

Determining a first detection result of the first battery according to the fault detection model corresponding to the first battery and the first operating data, wherein the first detection result includes a first score of a target failure of the first battery;

Determine the second detection result of the first battery according to the first score and the time impact factor of the target failure of the first battery, wherein the time impact factor is based on the time information of the target failure of the first battery within the first preset time period Sure.

In the technical solution of the embodiment of the present application, for the first operating data generated by the first battery, the first detection result of the first battery is determined according to the fault detection model corresponding to the first battery and the first operating data, wherein the first detection The result includes the first score of the target failure of the first battery, so as to realize the preliminary detection of the first battery. Next, the preliminary detection result is adjusted according to the influence factor of the target failure time of the first battery to obtain the second detection result , since the time impact factor is determined according to the time information of the target failure of the first battery within the first preset time period, the second test results in order to improve the reliability of the test results.

In some embodiments, determining the second detection result of the first battery according to the first score and the impact factor of the target failure time of the first battery includes:

According to the first score and the time impact factor of the target failure of the first battery, determine the second score of the target failure of the first battery;

When the second score is greater than the preset fault threshold, the second detection result includes early warning information that the target fault occurs in the first battery.

According to the embodiment of the present application, the first score is adjusted by the time influence factor, and after the second score is obtained, the detection result is determined based on the second score and the preset fault threshold, so that the difference between the detection results of whether the target fault occurs can be determined. The difference between them is more obvious, which is convenient for issuing accurate early warning information.

In some embodiments, before according to the first score and the time-influencing factor of the target failure of the first battery, the method further includes:

Acquiring first time information when a target failure occurs on the first battery within a first preset time period and second time information when first operating data is collected;

The time impact factor is determined according to the difference between the first time information and the second time information, wherein the magnitude of the time influence factor is negatively correlated with the magnitude of the difference.

According to the embodiment of the present application, by combining the difference between the first time information and the second time information, the size of the time influence factor can be determined, so that different time influence factors can be determined according to different time spans, so as to realize adaptive adjustment of the second time influence factor. If one score is obtained, the second score with higher reliability is obtained, which is conducive to improving the reliability of battery detection results and reducing the false alarm rate of battery failure.

In some embodiments, determining the time impact factor according to the difference between the first time information and the second time information includes:

According to the preset time decay formula and the difference between the first time information and the second time information, the time impact factor is determined, wherein the preset time decay formula is:

T=C×e ^-Δt

Wherein, T is a time influence factor, Δt is a difference between the first time information and the second time information, and C is a preset constant.

According to the embodiment of the present application, by combining the difference between the first time information and the second time information, and the preset time decay formula, it is possible to determine different time influence factors according to different time spans, so as to realize adaptive adjustment of the second One point is beneficial to improve the reliability of battery test results.

In some embodiments, before determining the first detection result of the first battery according to the fault detection model corresponding to the first battery and the first operating data, the method further includes:

Acquiring a plurality of second operating data generated by the first battery within a second preset time period, and a second detection result corresponding to each second operating data;

According to the plurality of second operating data and the second detection result corresponding to each second operating data, the initial fault detection model is updated and trained to obtain the fault detection model corresponding to the first battery.

According to the embodiment of the present application, by combining the historical operating data generated by the first battery itself, the initial fault detection model is updated and trained to obtain the fault detection model corresponding to the first battery, which can reduce the training cost; and based on the fault corresponding to the first battery The detection model can realize one-to-one battery fault detection, which is conducive to improving the accuracy of detection results.

In some embodiments, the second detection result includes early warning information that the target failure occurs in the first battery or the target failure does not occur in the first battery; according to a plurality of second operating data and the second detection result corresponding to each second operating data, Update and train the initial fault detection model to obtain the fault detection model corresponding to the first battery, including:

updating the first training samples of the initial fault detection model according to the plurality of first operating data and the second detection results corresponding to each second operating data to obtain second training samples;

The initial fault detection model is updated and trained according to the second training sample to obtain a fault detection model corresponding to the first battery.

In some embodiments, the second training samples include a plurality of second operating data of the first battery and a plurality of third operating data of the second battery, each second operating data corresponds to a second detection result, and each third The third detection result corresponding to the operation data;

The initial fault detection model is updated and trained according to the second training sample, and the fault detection model corresponding to the first battery is obtained, including:

According to the multiple second operating data of the first battery and the multiple third operating data of the second battery, the second detection result corresponding to each second operating data, and the third detection result corresponding to each third operating data, determine The first score of the target failure of the first battery, wherein the first score is used to represent the first probability of the target failure of the first battery when the first operating data meets the preset failure judgment condition.

According to the embodiment of the present application, by updating and training the initial fault detection model based on the operating data generated by the first battery itself, the fault detection model corresponding to the first battery can be obtained, which can reduce training costs and improve the accuracy of fault detection.

In a second aspect, the present application provides a battery detection device, including:

an acquisition module, configured to acquire the first operating data of the first battery;

A processing module, configured to determine a first detection result of the first battery according to the fault detection model corresponding to the first battery and the first operating data, wherein the first detection result includes a first score of a target failure of the first battery;

The processing module is further configured to determine the second detection result of the first battery according to the first score and the time impact factor of the target failure of the first battery, wherein the time impact factor is based on the first battery's failure within the first preset time period The time information of the occurrence of the target failure is determined.

According to an embodiment of the present application, for the first operating data generated by the first battery, the first detection result of the first battery is determined according to the fault detection model corresponding to the first battery and the first operating data, wherein the first detection result includes the first The first score of the target failure of a battery, so as to realize the preliminary detection of the first battery. Next, the preliminary detection result is adjusted according to the influence factor of the target failure time of the first battery, and the second detection result is obtained. Due to the time The impact factor is determined according to the time information of the target failure of the first battery within the first preset time period, therefore, the second detection result can be generated in combination with the occurrence of the target failure of the first battery itself within the first preset time period, In order to improve the reliability of the detection results.

In a third aspect, the present application provides a battery testing device, which includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the first aspect or any implementable mode of the first aspect can be realized. The battery testing method described above.

In a fourth aspect, the present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the first aspect or any implementable manner of the first aspect can be realized. The battery testing method described above.

In the fifth aspect, the embodiment of the present application provides a computer program product, when the instructions of the computer program product are executed by the processor of the electronic device, the electronic device executes the first aspect or any implementable manner of the first aspect. The battery test method described in.

The above description is only an overview of the technical solution of the present application. In order to better understand the technical means of the present application, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the present application more obvious and understandable , the following specifically cites the specific implementation manner of the present application.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the application. Also throughout the drawings, the same reference numerals are used to designate the same components. In the attached picture:

FIG. 1 is a schematic flow chart of a battery detection method provided in an embodiment of the present application;

Fig. 2 is a schematic structural diagram of a battery testing device provided in an embodiment of the present application;

Fig. 3 is a schematic structural diagram of a battery testing device provided by an embodiment of the present application.

Detailed ways

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the application; the terms used herein are only for the purpose of describing specific embodiments, and are not intended to To limit this application; the terms "comprising" and "having" and any variations thereof in the specification and claims of this application and the description of the above drawings are intended to cover a non-exclusive inclusion.

In the description of the embodiments of the present application, technical terms such as "first" and "second" are only used to distinguish different objects, and should not be understood as indicating or implying relative importance or implicitly indicating the number, specificity, or specificity of the indicated technical features. Sequential or primary-secondary relationship. In the description of the embodiments of the present application, "plurality" means two or more, unless otherwise specifically defined.

Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The occurrences of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is understood explicitly and implicitly by those skilled in the art that the embodiments described herein can be combined with other embodiments.

In the description of the embodiment of the present application, the term "and/or" is only a kind of association relationship describing the association object, which means that there may be three kinds of relationships, such as A and/or B, which may mean: there is A alone, and A exists at the same time and B, there are three cases of B alone. In addition, the character "/" in this article generally indicates that the contextual objects are an "or" relationship.

In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two), similarly, "multiple groups" refers to more than two groups (including two), and "multiple pieces" refers to More than two pieces (including two pieces).

In the description of the embodiments of the present application, unless otherwise specified and limited, the first feature may be in direct contact with the first feature or the second feature "on" or "under" the second feature. Indirect contact through intermediaries. Moreover, "above", "above" and "above" the first feature on the second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. "Below", "beneath" and "beneath" the first feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is less horizontally than the second feature.

With the continuous development of science and technology, batteries are more and more widely used in daily production and life. Batteries are not only used in energy storage power systems such as water power, fire power, wind power and solar power plants, but also widely used in electric bicycles, electric Motorcycles, electric vehicles and other electric vehicles, as well as military equipment and aerospace and other fields. With the continuous expansion of battery application fields, its market demand is also constantly expanding. The safety performance of batteries is also getting more and more attention. The battery mentioned in the embodiments of the present application refers to a single physical module including one or more battery cells to provide higher voltage and capacity. For example, the battery mentioned in this application may include a battery module or a battery pack, and the like.

In the application process of the battery, the operating state of the battery is often detected by collecting the power consumption parameters generated by the battery to determine whether the battery is faulty.

The inventors of the present application have noticed that the current commonly used battery detection method usually trains the historical data of all batteries to obtain a unified model parameter. However, there are inconsistencies between different batteries due to differences in production/storage/transportation/use conditions, so the sensitivity of each battery characteristic is different. For example, some batteries often have excessive temperature differences during historical use. However, the battery can still be used normally; some batteries have not experienced the characteristics of excessive temperature difference during the historical use process, but when the characteristic of excessive temperature difference suddenly appears, the battery cannot be used normally. For example, if the same detection model is used to detect the faults of batteries in different application environments, only a rough judgment result can be obtained as to whether the battery is faulty, which leads to low detection accuracy of the detection results and a high false alarm rate. It is beneficial to improve the safety of battery application.

Based on the above considerations, in order to solve the problem of low detection accuracy and high false alarm rate of battery fault detection results. After intensive research, the inventor provides a battery detection method, device, equipment, storage medium and computer program product. During the battery detection process, for the first operating data generated by the first battery, the first detection result of the first battery is determined according to the fault detection model corresponding to the first battery and the first operating data, wherein the first detection result includes the first The first score of the target failure of a battery, so as to realize the preliminary detection of the first battery. Next, the preliminary detection result is adjusted according to the influence factor of the target failure time of the first battery, and the second detection result is obtained. Due to the time The impact factor is determined according to the time information of the target failure of the first battery within the first preset time period, therefore, the second detection result can be generated in combination with the occurrence of the target failure of the first battery itself within the first preset time period, In order to improve the reliability of the detection results.

The technical solutions described in the embodiments of the present application are applicable to batteries and electric devices using batteries. Electric devices can be vehicles, mobile phones, portable devices, notebook computers, ships, spacecraft, electric toys and electric tools, and so on. The embodiments of the present application do not impose special limitations on the above-mentioned electrical devices.

The battery detection method provided by the embodiment of the present application will be described in detail below through specific embodiments and application scenarios with reference to the accompanying drawings.

Please refer to FIG. 1 . FIG. 1 is a schematic flowchart of a battery testing method provided by an embodiment of the present application. As shown in FIG. 1 , the above method may include the following steps 110 to 130 .

Step 110, acquiring first operating data of the first battery.

Step 120: Determine a first detection result of the first battery according to the fault detection model corresponding to the first battery and the first operating data.

Wherein, the first detection result includes a first score of a target failure of the first battery;

Step 130: Determine a second detection result of the first battery according to the first score and the impact factor of the target failure time of the first battery.

Wherein, the time influence factor is determined according to the time information of the target failure of the first battery within the first preset time period.

In the above step 110, the first battery may refer to a single physical module including one or more battery cells to provide higher voltage and capacity. For example, the battery mentioned in this application may include a battery module or a battery pack, and the like. Batteries generally include a case for enclosing one or more battery cells. Wherein, the battery cells may include lithium-ion secondary battery cells, lithium-ion primary battery cells, lithium-sulfur battery cells, sodium-lithium-ion battery cells, sodium-ion battery cells, or magnesium-ion battery cells. The embodiment does not limit this.

The first operating data, for example, may include temperature, voltage, etc. of the first battery during application, and may also include temperature variation, voltage variation, etc., which are not listed here. Exemplarily, battery operation data such as temperature and voltage of the first battery may be collected according to a preset collection frequency. Taking temperature as an example, the temperature of the first battery can be collected according to the preset collection frequency according to the temperature sensor. Optionally, the temperature sensor can be a contact temperature sensor or a non-contact temperature sensor. Specific limits. For the temperature collected each time, the currently collected temperature may be compared with the temperature collected last time, so as to obtain the temperature change amount of the first battery.

After the first operating data of the first battery is acquired, step 120 of the embodiment of the present application may be performed.

In the above step 120, the fault detection model corresponding to the first battery is a trained model for fault detection of the battery. Optionally, the training samples of the fault detection model may include the operating data generated by the first battery during the application process or the test process, and may also include the third operating data generated during the application process or test of the second battery, so as to improve the performance of the training samples. The data volume of training data can improve the accuracy of fault detection. Optionally, the second battery can be the same type of battery as the first battery. For example, the application or test environment of the second battery may be the same as that of the first battery or may be different from the application or test environment of the first battery, which is not specifically limited herein.

According to the first operating data and in combination with the fault detection model corresponding to the first battery, a preliminary detection result of whether the first battery is faulty, that is, the first detection result can be obtained. The first detection result may include a first score for the target failure of the first battery.

Exemplarily, the target fault may include, for example, a battery overtemperature fault, and the first score output based on the fault detection model may be used to represent the risk of the first battery having an overtemperature fault. For example, when the first score is higher, the risk of the first battery having an overtemperature fault is greater.

In order to improve the accuracy of detecting the first battery failure, step 130 in the embodiment of the present application may be performed next.

In the above step 130, the first preset time period may be a time period between the first battery generating the first operating data. Optionally, the length of the first preset time period may be from the time when the first battery is first used to the time when the first battery is running and generating the first running data. In the first preset time period, if it is determined that the target failure occurs in the first battery, the time when the target failure occurs in the first battery may be recorded, and the time information of the target failure occurs in the first battery may be generated. Optionally, the time information of the target failure of the first battery may be stored in a preset database, which is not specifically limited here.

According to the information on the time when the target failure occurs on the first battery within the first preset time period, the influence factor on the time when the target failure occurs on the first battery can be determined. Exemplarily, when the time span between the time information of the target failure of the first battery within the first preset time period and the time when the first battery operates to generate the first operating data is longer, the influence of the influencing factor is smaller; when the second The smaller the span between the time information of a target failure of a battery within the first preset time period and the time when the first battery operates to generate the first operating data, the greater the influence of the influencing factor.

Therefore, the first score can be adjusted through the time influence factor, so as to improve the accuracy of fault detection of the first battery. When generating the second detection result of the first battery, the second detection result of the first battery may be determined according to the adjusted first score.

According to the embodiment of the present application, for the first operating data generated by the first battery, the first detection result of the first battery is determined according to the fault detection model corresponding to the first battery and the first operating data, so as to realize the preliminary detection of the first battery. Next, adjust the preliminary detection result in combination with the target failure time impact factor of the first battery to obtain the second detection result. Since the time impact factor is based on the target failure of the first battery within the first preset time The time information is determined. Therefore, the second detection result can be generated in combination with the occurrence of the target failure of the first battery itself within the first preset time period, so as to improve the reliability of the detection result.

In some embodiments of the present application, the above step 130 may specifically include: according to the first score and the time impact factor of the target failure of the first battery, determining the second score of the target failure of the first battery; When the value is greater than the preset fault threshold, the second detection result includes early warning information that the target fault occurs in the first battery.

Exemplarily, when the influence of the time influence factor is greater, the reliability of the first detection result of the first battery is higher, thus, the first score can be increased through the time influence factor to obtain the second score; When the influence of the time influence factor is smaller, the reliability of the first test result of the first battery is lower. Therefore, the first score can be reduced by the time influence factor to obtain the second score.

The preset fault threshold can be set according to actual needs. Optionally, when the second score is greater than the preset fault threshold, it may be considered that the first battery has a high risk of a target fault, and an early warning message is issued. Therefore, in the second detection result, it may include that the first battery has a target fault warning information. When the second score is less than or equal to the preset fault threshold, it can be considered that the risk of the target fault of the first battery is small or no risk of fault, therefore, the second detection result may not include the warning information.

In some embodiments of the present application, the determination of the time impact factor may specifically be based on the following steps: First, obtain the first time information and the first operating data of the target failure of the first battery within the first preset time period The second time information; Next, determine the time impact factor according to the difference between the first time information and the second time information, wherein the size of the time impact factor is negatively correlated with the size of the difference.

In some embodiments, the first time information may be the time when the target failure occurred last before the first battery generates the first operating data, and the second time information may be the time information corresponding to the first battery generating the first operating data.

In this way, the size of the time impact factor can be determined according to the difference between the first time information and the second time information. Among them, the size of the time impact factor is negatively correlated with the size of the difference. That is, if the time when the last target failure occurred before the first battery generates the first operating data is longer than the second time information, the time influence factor is smaller; The shorter the distance from the second time information, the greater the time impact factor.

Optionally, when determining the time impact factor according to the difference between the first time information and the second time information, it may be determined according to a preset mapping relationship. For example, it can be a table look-up method, and multiple difference ranges are preset, and different difference ranges correspond to different time impact factors; another example, can be calculated according to a preset function, after inputting the difference into the preset function, through the calculation Get the time impact factor. The above examples are only examples, and no specific limitation is made here.

In some embodiments of the present application, the time impact factor may be determined, specifically, the time impact factor may be determined according to a preset time decay formula and a difference between the first time information and the second time information. Wherein, the preset time decay formula may be as shown in formula (1).

T=C×e ^-Δt (1)

As a specific example, it is recorded that the first operating data is obtained at time t1, and the first operating data includes the temperature difference corresponding to t1. According to the temperature difference and the fault detection model corresponding to the first battery, scoring is performed to obtain the target failure rate of the first battery. The first score S1. Next, combined with the first time information of the last target failure of the first battery, wherein the first time information includes the time t2 of the last target failure of the first battery, thus the difference Δt between t1 and t2 can be obtained; Combined with the preset time decay formula, the time impact factor T can be calculated. Optionally, the product of the time impact factor and the first score may be used as the second score.

In some embodiments of the present application, in order to improve the accuracy of the first detection result, before determining the first detection result of the first battery, the embodiment of the present application may further include the following steps:

Step 201, acquiring a plurality of second operating data generated by the first battery within a second preset time period, and a second detection result corresponding to each second operating data;

Step 202 , update and train the initial fault detection model according to the plurality of second operating data and the second detection result corresponding to each second operating data, to obtain a fault detection model corresponding to the first battery.

Specifically, the second preset time period may be a time period between the first battery generating the first operating data. Wherein, the first preset time period may be the same or different, which is not specifically limited here.

The second operating data, for example, may include temperature, voltage, etc. of the first battery during application, and may also include temperature variation, voltage variation, etc., which are not listed here. Exemplarily, battery operation data such as temperature and voltage of the first battery may be collected according to a preset collection frequency. Taking temperature as an example, the temperature of the first battery can be collected according to the preset collection frequency by the temperature sensor. For each collected temperature, the current collected temperature can be compared with the last collected temperature to obtain the second battery temperature. A battery temperature variation.

The second detection result is a detection result obtained after fault detection is performed on the first battery, for example, the second detection result may include whether a target fault occurs on the first battery.

The initial fault detection model can be a detection model that has been trained. In order to improve the accuracy of the fault detection results, the initial fault detection model is performed through a plurality of second operating data and the second detection results corresponding to each second operating data. After updating the training, the fault detection model corresponding to the first battery can be used.

In some embodiments of the present application, the second detection result includes early warning information that the target failure occurs in the first battery or the target failure does not occur in the first battery; step 202 may specifically be based on the following steps:

Specifically, the first training sample of the initial failure may include the third operating data generated during the application process or test of the second battery. For example, the application or test environment of the second battery may be the same as that of the first battery, or may be the Applications or test environments are different, and are not specifically limited here. The first training samples also include detection information of battery faults corresponding to each third running data.

Updating the first training samples according to the plurality of first operating data and the second detection results corresponding to each second operating data can effectively expand the sample size of the first training samples.

Exemplarily, the second training samples may include a plurality of second operating data corresponding to the first battery and a second detection result corresponding to each second operating data, as well as a plurality of third operating data and a plurality of third operating data generated by the second battery. The detection information of the battery failure corresponding to each third running data.

In some embodiments of the present application, the second training samples include a plurality of second operating data of the first battery and a plurality of third operating data of the second battery, each second operating data corresponds to a second detection result, and each The third detection result corresponding to the third operating data; Exemplarily, update and train the initial fault detection model, which may specifically be: according to multiple second operating data of the first battery and multiple third operating data of the second battery data, the second detection result corresponding to each second operating data, and the third detection result corresponding to each third operating data, to determine the first score of the target failure of the first battery, wherein the first score is used to represent A first probability of a target fault occurring on the first battery when the first operating data satisfies a preset fault judgment condition.

Specifically, the second battery may generate a plurality of third operating data during operation or testing, and each third operating data corresponds to second battery operating information, for example, when the second battery generates the third operating data, Whether the second battery is faulty, etc.

The preset fault judgment conditions can be set according to the characteristic variables included in the first operating data, such as: temperature, voltage, temperature variation, voltage variation, frequency of the temperature exceeding the preset temperature advance, etc. Not specifically limited.

Exemplarily, taking the second operating data and the third operating data both include temperature variation as an example, the preset fault judgment condition is whether the temperature variation exceeds a preset temperature threshold, and when the temperature variation exceeds a preset temperature threshold , indicating that an event of excessive temperature difference has occurred in the battery. Based on all the operating data of the second training sample, statistical analysis can be performed to obtain the data volume of the operating data when the temperature variation in the entire training sample exceeds the preset temperature threshold, and also obtain the data volume of the operating data corresponding to the target failure of the battery. , and, when the temperature variation exceeds the preset temperature threshold and the battery has a target failure, the data volume of the corresponding operating data. In this way, the probability of occurrence of excessive temperature difference P (excessive temperature difference), the probability of target failure P (target failure), and the probability of occurrence of target failure with excessive temperature difference P (temperature difference | target failure ).

Next, according to the preset Bayesian probability model, the first probability P (target failure|excessive temperature difference) of the target failure of the first battery can be calculated when the temperature difference is too large. Exemplarily, the first probability can be obtained according to the following calculation method: P(target fault|excessive temperature difference)=[P(excessive temperature difference|target fault)×P(target fault)]/P(excessive temperature difference).

After the first probability is obtained, the first score can be determined according to the first probability. In order to simplify the calculation process, the first probability can be directly assigned to the first score.

According to the embodiment of the present application, by combining multiple second operating data of the first battery to update the initial fault detection model, the reliability of the first score output by the fault detection model can be improved, thereby reducing the false alarm rate of faults.

In order to better understand the battery detection method provided in the embodiment of the present application, an example of the practical application of the above battery detection method is provided here for description.

Step 301, obtaining an initial fault detection model.

Specifically, according to the first training samples, the constructed battery fault detection model is trained to obtain the trained initial fault detection model, wherein the third operating data of the second battery corresponds to each third operating data Secondary battery operating information. Specifically, the second battery operating information. For example, if the secondary battery has a target failure. Target failure, for example, an overtemperature failure of the second battery due to an excessive temperature difference of the second battery. The constructed battery fault detection model can be a Bayesian probability model.

Step 302, acquiring a plurality of second operating data of the first battery and operating information of the first battery corresponding to each second operating data.

Specifically, the second operating data is the battery operating data generated by the first battery during application or testing. After obtaining the second operating data, it is also necessary to obtain the operating data of the first battery when the first battery generates the second operating data. information, specifically, operating information of the first battery. For example, whether the first battery has an overtemperature fault due to an excessive temperature difference of the first battery.

Step 303: Update the first training samples according to the plurality of second operating data of the first battery and the operating information of the first battery corresponding to each second operating data to obtain second training samples.

Step 304 , update and train the initial fault detection model according to the second training sample to obtain a fault detection model corresponding to the first battery.

After obtaining the fault detection model corresponding to the first battery, fault detection may be performed based on the fault detection model corresponding to the first battery for the operating data generated by the first battery.

When updating and training the initial fault detection model, it is possible to calculate the first probability P of the target fault occurring on the first battery when the temperature difference is too large (target fault|excessive temperature difference), so as to obtain the fault detection model corresponding to the first battery , that is, a Bayesian probability model. Exemplarily, the first probability can be obtained according to the following calculation method: P(target fault|excessive temperature difference)=[P(excessive temperature difference|target fault)×P(target fault)]/P(excessive temperature difference).

Step 305, acquiring first operating data of the first battery.

Step 306: Determine a first detection result of the first battery according to the fault detection model corresponding to the first battery and the first operating data.

The first operating data may include, for example, the amount of temperature change of the first battery during operation, and according to the amount of temperature change and the fault detection model, the first score of the target failure of the first battery may be determined. Can be used to indicate the risk of overtemperature failure of the first battery. For example, when the first score is higher, the risk of the first battery having an overtemperature fault is greater.

Step 307, acquiring the time-influencing factor of the target failure of the first battery.

Specifically, the first time information can be obtained first, including the time t2 when the target failure occurred last time on the first battery, and the time t1 when the first operating data was obtained, and then, according to the preset time decay formula and the first time information and The difference of the second time information determines the time impact factor. Wherein, the preset time decay formula may be as shown in formula (1).

Step 308: Determine the second detection result of the first battery according to the time influence factor.

Specifically, according to the first score and the impact factor of the target failure time of the first battery, the second score of the target failure of the first battery can be determined; when the second score is greater than the preset failure threshold, the second detection result Including early warning information of target failure of the first battery.

In the technical solution of the embodiment of the present application, for the first operating data generated by the first battery, the first detection result of the first battery is determined according to the fault detection model corresponding to the first battery and the first operating data, wherein the first detection The result includes the first score of the target failure of the first battery, so as to realize the preliminary detection of the first battery. Next, the preliminary detection result is adjusted according to the influence factor of the target failure time of the first battery to obtain the second detection result , since the time impact factor is determined according to the time information of the target failure of the first battery within the first preset time period, the second In order to improve the reliability of the detection results; in addition, the first score is adjusted by the time influence factor, and after the second score is obtained, the detection result is determined based on the second score and the preset fault threshold, which can make The difference between the detection results of whether the target fault occurs is more obvious, which is convenient for issuing accurate early warning information.

FIG. 2 is a schematic structural diagram of a battery testing device provided by an embodiment of the present application. As shown in FIG. 3 , the battery testing device 200 may include: an acquisition module 210 and a processing module 220 .

An acquisition module 210, configured to acquire first operating data of the first battery;

The processing module 220 is configured to determine a first detection result of the first battery according to the fault detection model corresponding to the first battery and the first operating data, wherein the first detection result includes a first score of a target failure of the first battery;

The processing module 220 is further configured to determine the second detection result of the first battery according to the first score and the time impact factor of the target failure of the first battery, wherein the time impact factor is based on the time impact factor of the first battery in the first preset time period The time information of the occurrence of the target fault in the target is determined.

In some embodiments, the processing module 220 is further configured to determine a second score for the target failure of the first battery according to the first score and the impact factor of the time when the target failure occurs for the first battery; when the second score is greater than the preset When the fault threshold is set, the second detection result includes early warning information that the target fault occurs in the first battery.

In some embodiments, the acquiring module 210 is further configured to acquire the first time information when the target failure occurs in the first battery within the first preset time period and the second time information when the first operating data is collected;

The processing module 220 is further configured to determine a time impact factor according to the difference between the first time information and the second time information, wherein the magnitude of the time influence factor is negatively correlated with the magnitude of the difference.

In some embodiments, the processing module 220 is further configured to determine the time impact factor according to the preset time decay formula and the difference between the first time information and the second time information, wherein the preset time decay formula is:

T=C×e ^-Δt

In some embodiments, the acquisition module 210 is further configured to acquire a plurality of second operating data generated by the first battery within a second preset time period, and a second detection result corresponding to each second operating data;

The processing module 220 is further configured to update and train the initial fault detection model according to the plurality of second operating data and the second detection results corresponding to each second operating data, so as to obtain a fault detection model corresponding to the first battery.

In some embodiments, the second detection result includes early warning information that the target failure occurs in the first battery or the target failure does not occur in the first battery;

The processing module 220 is further configured to update the first training samples of the initial fault detection model according to the plurality of first operating data and the second detection results corresponding to each second operating data to obtain second training samples;

The processing module 220 is further configured to update and train the initial fault detection model according to the second training samples to obtain a fault detection model corresponding to the first battery.

The processing module 220 is further configured to, according to the plurality of second operating data of the first battery and the plurality of third operating data of the second battery, the second detection result corresponding to each second operating data, and each third operating data corresponding to The third detection result determines the first score of the target failure of the first battery, wherein the first score is used to represent the first probability of the target failure of the first battery when the first operating data meets the preset failure judgment condition.

It can be understood that the battery detection device 200 in the embodiment of the present application may correspond to the execution body of the battery detection method provided in the embodiment of the present application, and the specific details of the operation and/or function of each module/unit of the battery detection device 200 Reference may be made to the description of the corresponding part of the battery detection method provided in the above embodiments of the present application, and for the sake of brevity, details are not repeated here.

Fig. 3 shows a schematic structural diagram of a battery testing device provided by an embodiment of the present application. As shown in Figure 3, the device may include a processor 301 and a memory 302 storing computer program instructions.

Specifically, the above-mentioned processor 301 may include a central processing unit (Central Processing Unit, CPU), or a specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application .

Memory 302 may include mass storage for information or instructions. By way of example and not limitation, memory 302 may include a hard disk drive (Hard Disk Drive, HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a Universal Serial Bus (Universal Serial Bus, USB) drive or two or more Combinations of multiple of the above. In one example, memory 302 may include removable or non-removable (or fixed) media, or memory 302 may be a non-volatile solid-state memory. The memory 302 may be internal or external to the battery testing device.

Memory may include read only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical/tangible memory storage devices. Thus, in general, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions, and when the software is executed (e.g., by one or multiple processors) operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

The processor 301 reads and executes the computer program instructions stored in the memory 302 to implement the method described in the embodiment of the present application, and achieve the corresponding technical effect achieved by executing the method in the embodiment of the present application, which is not described here for brevity. repeat.

In an example, the battery detection device may further include a communication interface 303 and a bus 310 . Wherein, as shown in FIG. 3 , the processor 301 , the memory 302 , and the communication interface 303 are connected through a bus 310 to complete mutual communication.

The communication interface 303 is mainly used to realize the communication between various modules, devices, units and/or devices in the embodiments of the present application.

The bus 310 includes hardware, software or both, and couples the components of the online traffic charging device to each other. By way of example and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Super Transmission (Hyper Transport, HT) interconnect, Industry Standard Architecture (Industry Standard Architecture, ISA) bus, InfiniBand interconnect, Low Pin Count (LPC) bus, memory bus, Micro Channel Architecture (MCA) bus, peripheral component interconnect PCI bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus, or other suitable bus or a combination of two or more of these combination. Bus 310 may comprise one or more buses, where appropriate. Although the embodiments of this application describe and illustrate a particular bus, this application contemplates any suitable bus or interconnect.

The battery detection device can execute the battery detection method of the embodiment of the present application, so as to realize the corresponding technical effect of the battery detection method described in the embodiment of the present application.

In addition, in combination with the battery detection method of the foregoing embodiments, the embodiments of the present application may provide a readable storage medium for implementation. Computer program instructions are stored on the readable storage medium; when the computer program instructions are executed by a processor, any one of the battery detection methods in the above-mentioned embodiments is implemented. Examples of readable storage media may be non-transitory machine readable media such as electronic circuits, semiconductor memory devices, Read-Only Memory (ROM), floppy disks, Compact Disc Read-Only Memory (CD- ROM), CD-ROM, hard disk, etc.

It is to be understood that the application is not limited to the specific configurations and processes described above and shown in the figures. For conciseness, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application .

The functional blocks shown in the structural block diagrams described above may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), appropriate firmware, a plug-in, a function card, and the like. When implemented in software, the elements of the present application are the programs or code segments employed to perform the required tasks. Programs or code segments can be stored in machine-readable media, or transmitted over transmission media or communication links by data signals carried in carrier waves. "Machine-readable medium" may include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, Read-Only Memory (ROM), flash memory, Erasable Read Only Memory (EROM), floppy disks, compact discs (Compact Disc Read-Only Memory, CD-ROM), optical disc, hard disk, fiber optic media, radio frequency (Radio Frequency, RF) link, etc. Code segments may be downloaded via a computer network such as the Internet, an Intranet, or the like.

It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps may be performed in the order mentioned in the embodiment, or may be different from the order in the embodiment, or several steps may be performed simultaneously.

In addition, in combination with the battery detection method, device, and readable storage medium in the foregoing embodiments, embodiments of the present application may provide a computer program product for implementation. When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device is made to execute any battery detection method in the foregoing embodiments.

Aspects of the present disclosure are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present disclosure. It will be understood that each block of the flowchart and/or block diagrams, and combinations of blocks in the flowchart and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine such that execution of these instructions via the processor of the computer or other programmable data processing apparatus enables Implementation of the functions/actions specified in one or more blocks of the flowchart and/or block diagrams. Such processors may be, but are not limited to, general purpose processors, special purpose processors, application specific processors, or field programmable logic circuits. It can also be understood that each block in the block diagrams and/or flowcharts and combinations of blocks in the block diagrams and/or flowcharts can also be realized by dedicated hardware for performing specified functions or actions, or can be implemented by dedicated hardware and Combination of computer instructions to achieve.

The above is only a specific implementation of the present application, and those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described systems, modules and units can refer to the foregoing method embodiments The corresponding process in , will not be repeated here. It should be understood that the protection scope of the present application is not limited thereto, and any person familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the application, and these modifications or replacements should cover all Within the protection scope of this application.

Claims

A battery detection method, characterized in that, comprising:

acquiring first operating data of the first battery;

According to the fault detection model corresponding to the first battery and the first operating data, determine a first detection result of the first battery, wherein the first detection result includes the first detection result of a target fault of the first battery. one point value;

Determine the second detection result of the first battery according to the first score and the time impact factor of the target failure of the first battery, wherein the time impact factor is based on the time impact factor of the first battery at The time information when the target fault occurs within a preset time period is determined.
The method according to claim 1, wherein the second detection result of the first battery is determined according to the first score and the influence factor of the target failure time of the first battery, include:

determining a second score for the target failure of the first battery according to the first score and the impact factor of the time for the target failure of the first battery to occur;

When the second score is greater than a preset fault threshold, the second detection result includes early warning information that the target fault occurs in the first battery.
The method according to claim 1, characterized in that, before said first score and said first battery occurrence time influencing factor of said target failure, said method further comprises:

Obtaining first time information when the target failure occurs on the first battery within a first preset time period and second time information when the first operating data is collected;

The time impact factor is determined according to a difference between the first time information and the second time information, where the magnitude of the time influence factor is negatively correlated with the magnitude of the difference.
The method according to claim 3, wherein the determining the time impact factor according to the difference between the first time information and the second time information includes:

Determine the time impact factor according to a preset time decay formula and the difference between the first time information and the second time information, wherein the preset time decay formula is:

T=C×e -Δt

Wherein, T is the time influencing factor, Δt is a difference between the first time information and the second time information, and C is a preset constant.
The method according to claim 1, characterized in that before determining the first detection result of the first battery according to the fault detection model corresponding to the first battery and the first operating data, the Methods also include:

Acquire a plurality of second operating data generated by the first battery within a second preset time period, and a second detection result corresponding to each second operating data;

According to the plurality of second operating data and the second detection result corresponding to each second operating data, the initial fault detection model is updated and trained to obtain the fault detection model corresponding to the first battery.
The method according to claim 5, wherein the second detection result includes early warning information that the target failure occurs in the first battery or the target failure does not occur in the first battery; The plurality of second operating data and the second detection results corresponding to each of the second operating data, update and train the initial fault detection model, and obtain the fault detection model corresponding to the first battery, including:

updating the first training samples of the initial fault detection model according to the plurality of first operating data and the second detection results corresponding to each of the second operating data to obtain second training samples;

The initial fault detection model is updated and trained according to the second training samples to obtain the fault detection model corresponding to the first battery.
The method according to claim 6, wherein the second training samples include a plurality of second operating data of the first battery and a plurality of third operating data of the second battery, each of the second a second detection result corresponding to the operating data, and a third detection result corresponding to each of the third operating data;

The updating and training the initial fault detection model according to the second training sample to obtain the fault detection model corresponding to the first battery includes:

According to the plurality of second operating data of the first battery and the plurality of third operating data of the second battery, each second detection result corresponding to the second operating data, each corresponding to the third operating data The third detection result is to determine the first score of the target failure of the first battery, wherein the first score is used to indicate that the first A first probability of the battery experiencing the target failure.
A battery detection device, characterized in that it comprises:

an acquisition module, configured to acquire the first operating data of the first battery;

A processing module, configured to determine a first detection result of the first battery according to the fault detection model corresponding to the first battery and the first operating data, wherein the first detection result includes the first battery The first score for a target failure;

The processing module is further configured to determine a second detection result of the first battery according to the first score and the time influencing factor of the target failure of the first battery, wherein the time influencing factor Determined according to the time information when the target failure occurs on the first battery within a first preset time period.
A battery testing device, characterized in that the device includes: a processor and a memory storing computer program instructions;

When the processor executes the computer program instructions, the battery detection method according to any one of claims 1-7 is implemented.
A computer-readable storage medium, characterized in that computer program instructions are stored on the computer-readable storage medium, and when the computer program instructions are executed by a processor, the battery according to any one of claims 1-7 is realized. Detection method.
A computer program product, characterized in that when the instructions in the computer program product are executed by the processor of the electronic device, the electronic device is made to execute the battery detection method according to any one of claims 1-7.