Method, apparatus, electronic device, and storage medium for identifying an abnormal battery core

Abstract

The present application provides a method, device, electronic device and storage medium for identifying an abnormal battery core, the method includes determining whether a battery core is an abnormal battery core based on target characteristic data of the battery core, where the target characteristic data includes characteristic data generated in a chemical formation process that can distinguish an abnormal battery core from a normal battery core. In this way, on the one hand, since there is an obvious difference in the target characteristic data between an abnormal battery core and a normal battery core in the chemical formation process of the battery core, it is possible to realize an accurate determination of whether a battery core is an abnormal battery core based on this, and on the other hand, since in an industrial production flow, the chemical formation process of the battery core necessarily occurs before the process of mounting the battery core into a battery pack, it is possible to realize the identification of an abnormal battery core before mounting the battery core, thereby reducing the risk of performance degradation of a battery system and disposal of a battery pack caused by mounting an abnormal battery core.

Description

Technical Field

[0001] This application relates to the field of batteries, and more specifically to a method, apparatus, electronic device, and storage medium for identifying abnormal battery cores.

Background Art

[0002] The formation of lithium-ion batteries is an important step in battery production, and the results of formation directly affect the cycle life, rate performance, high and low temperature performance, etc. of the batteries. In the battery production process, if abnormalities occur (including but not limited to situations such as injection errors of electrolytes, mixed use of electrolytes, and exceeding the water content standard), these problems will cause problems such as lithium precipitation, low capacity, and deterioration of the quality of the SEI film in the battery, affecting the cycle performance and safety performance of the battery. The installation of these abnormal batteries affects the performance of the battery system. Moreover, as the integration degree of the battery system becomes higher and higher, it becomes extremely difficult to remove abnormal battery cores, and the installation of abnormal battery cores will lead to the abandonment of the entire battery pack. Therefore, it is necessary to identify abnormal battery cores before installing the battery cores.

Summary of the Invention

[0003] The objective of the embodiments of this application is to provide a method, apparatus, electronic device, and storage medium for identifying abnormal battery cores to achieve the identification of abnormal battery cores before installing the battery cores.

[0004] According to a first aspect, the embodiments of this application provide a method for identifying abnormal battery cores, the method including determining whether a battery core is an abnormal battery core based on target feature data of the battery core, where the target feature data includes feature data generated during the formation process that can distinguish abnormal battery cores from normal battery cores.

[0005] In the technical solution of the embodiment of the present application, based on the target characteristic data that can distinguish abnormal battery cores from normal battery cores generated during the formation process of the battery cores, an analysis is performed to determine whether the battery cores are abnormal battery cores. In this way, on the one hand, when comparing abnormal battery cores with normal battery cores without abnormalities, there are obvious differences in the target characteristic data during the formation process of the battery cores. Therefore, based on this, an accurate judgment on whether the battery cores are abnormal battery cores can be realized, and a reliable identification of abnormal battery cores can be realized. On the other hand, in the industrial production flow, since the formation process of the battery cores must occur before the process of mounting the battery cores into the battery pack, the technical solution of the embodiment of the present application can effectively achieve the purpose of identifying abnormal battery cores before mounting the battery cores, reduce the risk of performance degradation of the battery system caused by the mounting of abnormal battery cores, and reduce the risk of battery pack abandonment caused by the mounting of abnormal battery cores.

[0006] In some embodiments, the target characteristic data includes characteristic data affected by the electrolyte in the battery core that occurred during the formation process.

[0007] In the technical solution of the embodiment of the present application, based on the target characteristic data affected by the electrolyte in the battery core generated during the formation process of the battery core, an accurate judgment on whether electrolyte abnormalities have occurred in the battery core can be realized based on the target characteristic data, thereby achieving a reliable identification of abnormal battery cores with electrolyte abnormalities. Currently, there are mainly the following two methods for identifying abnormal battery cores with electrolyte abnormalities.

[0008] Method 1: Detect the resistivity of the electrolyte in the battery core and match the detected resistivity with the reference resistivity of this electrolyte. If the matching fails, it is determined that there is an abnormality in the electrolyte in the battery core. However, for electrolytes with similar components, the corresponding reference resistivities are also similar. This method has a poor detection effect for electrolytes with similar components, and may even be unable to detect them in some cases.

[0009] Method 2: Decompose the battery core, collect an electrolyte sample for component analysis, and identify whether there is an abnormality in the electrolyte within the battery core. However, this method has a long analysis time requirement, a slow analysis speed, and cannot meet production needs. Moreover, it is necessary to decompose the battery core for sampling, and it is impossible to analyze all the electrolytes within each battery core.

[0010] As can be seen from this, compared with Method 1, the technical solution of the embodiment of the present application is not affected by the components of the electrolyte itself. For electrolytes with similar components, reliable identification can be realized based on the target characteristic data generated during the formation process. Compared with Method 2, the detection method of the embodiment of the present application does not require decomposing the battery core, has a high analysis efficiency, a fast analysis speed that can meet production needs, can identify each battery core, and has higher reliability.

[0011] In some embodiments, the target characteristic data includes characteristic data affected by the water content in the battery core that occurs during the formation process.

[0012] In the technical solution of the embodiment of the present application, based on the target characteristic data affected by the water content in the battery core that occurs during the formation process of the battery core, an accurate judgment can be realized regarding whether an abnormal water content has occurred within the battery core, thereby achieving reliable identification of the abnormal battery core with an abnormal water content.

[0013] At present, the identification method for abnormal battery cores with abnormal water content is mainly as follows. In the actual production of batteries, after the battery cores are left standing at a high temperature for a long time, some battery cores are selected as sample battery cores, the electrode plates inside the pole windings of the sample battery cores are cut off, baked using a stepped heating method, and high-purity nitrogen gas is used as the carrier gas to introduce the volatile substances into the moisture test system for testing to determine the water content of the sample battery cores. This method belongs to a destructive test, and the sample battery cores are destroyed and cannot be used after the test, so it is impossible to test all battery cores. In addition, the test results of the sample battery cores cannot represent the actual water content of each battery core. For example, although the test results of the sample battery cores are qualified, due to the influence of the actual production situation of each battery core, there may still be some battery cores whose actual water content exceeds the standard. Therefore, the conventional method has the problem of low reliability of identification and does not meet the current requirements for monitoring and managing battery cores. By adopting the technical solution of the embodiment of the present application, it is possible to identify based on the target characteristic data affected by the water content in the battery core, which occurs in the formation process of each battery core, without destroying the battery core. Therefore, all battery cores can be tested and the corresponding identification results for each battery core can be obtained, the reliability of identification is higher, and the current requirements for monitoring and managing battery cores can be met.

[0014] In some embodiments, the target characteristic data includes a first target parameter value when the parameter change first reaches a first process change value and a second target parameter value when the parameter change first reaches a second process change value in the process of collecting parameters in the first stage of the formation process, where the first process change value and the second process change value are different.

[0015] In actual applications, as a result of conducting a large number of experiments, the inventor found that when comparing an abnormal battery core with electrolyte abnormalities or an abnormal battery core with abnormal water content with a normal battery core without abnormalities, there are relatively large differences in the parameter change process in the first stage of the formation process. As a result, it was discovered that the parameter values corresponding to when the abnormal battery core and the normal battery core first reach a certain process change value are different. Based on this, in the above technical solution, in the process of collecting parameters in the first stage, the first target parameter value when the parameter change first reaches the first process change value threshold and the second target parameter value when the parameter change first reaches the second process change value are used as the basis for determining whether there are electrolyte abnormalities or abnormal water content in the battery core. By comprehensively combining these two types of target parameter values, accurate identification of abnormal battery cores with electrolyte abnormalities or abnormal water content can be realized, and the reliability of the identification can be improved.

[0016] In some embodiments, determining whether a battery core is an abnormal battery core based on target feature data includes inputting the target feature data into a pre-set identification model to obtain an identification result as to whether the battery core is an abnormal battery core.

[0017] In the above technical solution, the pre-set identification model is used to process the target feature data, thereby utilizing the strong identification ability of the model to achieve rapid identification of abnormal battery cores.

[0018] In some embodiments, the identification model is a two-dimensional Gaussian model.

[0019] The two-dimensional Gaussian model is a model that can well reflect the distribution of various types of data. In the above technical solution, when using the two-dimensional Gaussian model for identification, rapid distinction between abnormal battery cores and normal battery cores can be realized.

[0020] In some embodiments, obtaining an identification result as to whether a battery core is an abnormal battery core by inputting target feature data into a preset identification model includes obtaining a probability density of the battery core calculated by a two-dimensional Gaussian model by inputting the target feature data into the two-dimensional Gaussian model, and determining that the battery core is an abnormal battery core when the probability density of the battery core is less than a preset probability density threshold value.

[0021] In the above technical solution, based on the probability density of the battery core calculated by the two-dimensional Gaussian model, it is possible to quickly determine whether the battery core is abnormal, thereby improving the identification efficiency of abnormal battery cores.

[0022] In some embodiments, obtaining an identification result as to whether a battery core is an abnormal battery core by inputting target feature data into a preset identification model includes obtaining a probability density of the battery core calculated by a two-dimensional Gaussian model by inputting the target feature data into the two-dimensional Gaussian model, and determining that the battery core is an abnormal battery core when the probability density of the battery core is less than a preset probability density threshold value and the target feature data is within a preset feature interval.

[0023] In the above technical solution, by combining the probability density of the battery core and whether the target feature data of the battery core is within a preset feature interval, it is possible to determine whether the battery core is abnormal from two aspects, thereby improving the reliability of the identification of abnormal battery cores.

[0024] In some embodiments, determining whether a battery core is an abnormal battery core based on the target feature data of the battery core includes determining whether the battery core is an abnormal battery core based on the target feature data of the battery core during the formation process of the battery core.

[0025] In the above technical solution, during the formation process of the battery core, based on the target characteristic data of the battery core, it is determined whether the battery core is an abnormal battery core, thereby realizing the identification and screening of abnormal battery cores at the formation stage of the battery core, and achieving the effect of early identification of abnormal battery cores, avoiding subsequent production processes for abnormal battery cores, and reducing resource waste.

[0026] According to a second aspect, the embodiments of the present application further provide an identification device for abnormal battery cores, which includes an identification module for determining whether a battery core is an abnormal battery core based on the target characteristic data of the battery core. Here, the target characteristic data includes characteristic data generated during the formation process that can distinguish abnormal battery cores from normal battery cores.

[0027] In some embodiments, the target characteristic data includes characteristic data of the battery core affected by the electrolyte during the formation process.

[0028] In some embodiments, the target characteristic data includes characteristic data of the battery core affected by the water content during the formation process.

[0029] In some embodiments, the target characteristic data includes a first target parameter value when the parameter change first reaches a first process change value and a second target parameter value when the parameter change first reaches a second process change value during the process of collecting parameters in the first stage of the formation process. Here, the first process change value and the second process change value are different.

[0030] In some embodiments, specifically, the identification module is used to input the target characteristic data into a preset identification model to obtain an identification result of whether the battery core is an abnormal battery core.

[0031] In some embodiments, the identification model is a two-dimensional Gaussian model.

[0032] In some embodiments, specifically, the identification module inputs target feature data into a two-dimensional Gaussian model to obtain the probability density of the battery core calculated by the two-dimensional Gaussian model, and is used to determine that the battery core is an abnormal battery core when the probability density of the battery core is smaller than a preset probability density threshold.

[0033] In some embodiments, specifically, the identification module inputs target feature data into a two-dimensional Gaussian model to obtain the probability density of the battery core calculated by the two-dimensional Gaussian model, and is used to determine that the battery core is an abnormal battery core when the probability density of the battery core is smaller than a preset probability density threshold and the target feature data is within a preset feature interval.

[0034] In some embodiments, specifically, during the formation process of the battery core, the identification module is used to determine whether the battery core is an abnormal battery core based on the target feature data of the battery core.

[0035] According to a third aspect, an embodiment of the present application further provides an electronic device, which includes a processor and a memory. The processor is used to implement any one of the above abnormal battery core identification methods by executing one or more instructions stored in the memory.

[0036] According to a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, in which one or more instructions are stored, and the one or more instructions can be executed by a processor to implement any one of the above abnormal battery core identification methods.

Brief Description of the Drawings

[0037] To more clearly illustrate the technical solutions of the embodiments of this application, the following briefly introduces the drawings that need to be used in the embodiments of this application. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation to the scope. For those skilled in the art, based on these drawings, other related drawings can be obtained without creative efforts.

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

DETAILED DESCRIPTION OF THE INVENTION

[0038] Hereinafter, embodiments of the technical solutions of this application will be described in detail with reference to the drawings. The following embodiments are only used to more clearly illustrate the technical solutions of this application and are merely examples, and the protection scope of this application is not limited thereby.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terms used herein are for the purpose of describing specific embodiments only and are not intended to limit this application. The terms "comprising" and "having" and any variations thereof in the description of the specification, claims, and drawings of this application are intended to cover non-exclusively "comprising".

[0040] In the description of the embodiments of this application, technical terms such as "first" and "second" are only for distinguishing different objects and cannot be understood as indicating, implying, or implicitly indicating the relative importance, the number of the indicated technical features, a specific order, or a primary-secondary relationship. In the description of the embodiments of this application, "a plurality" means two or more (including two) unless specifically and clearly limited otherwise.

[0041] As used herein, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of that phrase at each position in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art can explicitly or implicitly understand that the embodiments described herein can be combined with other embodiments.

[0042] In the description of the embodiments of this application, the term "and / or" is only a relationship describing related objects and represents that three relationships may exist. For example, A and / or B may represent three cases: A alone, a combination of A and B, and B alone. Also, the character " / " in this specification generally represents that the related objects before and after are in an "or" relationship.

[0043] In the description of the embodiments of the present application, unless otherwise specifically defined or limited, technical terms such as "attachment", "connection", "connection", "fixation", etc. should be understood in a broad sense. For example, it may be a fixed connection, a removable connection, or an integral one, a mechanical connection, an electrical connection, a direct connection, an indirect connection through an intermediate medium, or the internal communication between two elements or the interaction relationship between two elements. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of the present application according to specific situations.

[0044] Currently, from the perspective of the market development trend, the application of power batteries is becoming increasingly widespread. Power batteries are widely applied not only in energy storage power systems such as hydropower, thermal power, wind power, and solar power plants, but also in the field of electric transportation such as electric bicycles, electric motorcycles, and electric vehicles.

[0045] The most commonly used power batteries in these fields are lithium-ion batteries (i.e., batteries composed of lithium-ion battery cores). The inventor has noticed that in the production process of lithium-ion batteries, abnormalities may occur in the battery cores, including, but not limited to, electrolyte abnormalities (such as situations like electrolyte injection errors, mixed use of electrolytes, etc.), and abnormal water content (such as situations where the water content exceeds the standard). When such abnormalities occur, they may lead to problems in the battery, such as lithium precipitation, low capacity, and deterioration of the quality of the SEI film. When lithium precipitation occurs in the battery core, it may cause serious safety problems such as thermal runaway. The low capacity of the battery core has a profound impact on the usage effect and experience of the battery core, and the deterioration of the quality of the SEI film affects the cycle performance and safety performance of the battery. Therefore, the installation of abnormal battery cores affects the performance of the battery system. Furthermore, as the integration degree of the battery system increases, it becomes extremely difficult to remove the battery core. So, when an abnormal battery core is installed in the battery pack, even if the abnormal battery core is discovered by technical means later, it is difficult to remove the abnormal battery core, and the installation of the abnormal battery core may lead to the abandonment of the entire battery pack in which the abnormal battery core is installed. Therefore, it is necessary to identify abnormal battery cores on the production line before installing the battery cores.

[0046] The inventor has further noticed that the formation of lithium-ion batteries is an important step in battery production, and only when the battery core completes the formation can it enter subsequent steps (including the step of installing the battery core). The process data in the battery formation process (including, but not limited to, data such as the steps, time, current, voltage, temperature, and air pressure of battery formation) is saved in units of seconds and milliseconds. There may be differences in the values of some parameters during the formation process of battery cores with electrolyte abnormalities and those without electrolyte abnormalities.

[0047] Based on the above considerations, in order to meet the requirement of identifying abnormal battery cores before installing the battery cores, as a result of intensive research, the inventor has designed a method for identifying abnormal battery cores, and by obtaining target characteristic data that can distinguish abnormal battery cores from normal battery cores generated during the formation process of the battery cores, and further based on this target characteristic data, determining whether the battery core is an abnormal battery core. In this way, on the one hand, there are obvious differences in the target characteristic data between abnormal battery cores and normal battery cores during the formation process of the battery cores, so an accurate judgment on whether the battery core is an abnormal battery core can be realized based on this, and a reliable identification of abnormal battery cores can be realized. On the other hand, in the industrial production process, since the formation process of the battery cores will necessarily occur before the process of installing the battery cores into the battery pack, the purpose of identifying abnormal battery cores before installing the battery cores can be effectively achieved, reducing the risk of performance degradation of the battery system caused by the installation of abnormal battery cores, and reducing the risk of battery pack abandonment caused by the installation of abnormal battery cores.

[0048] To facilitate the understanding of the solutions of the embodiments of this application, several basic pieces of information related to the embodiments of this application will be introduced first as follows.

[0049] A battery pack consists of a plurality of battery cells. A battery cell is the smallest unit that makes up a battery pack. In one battery pack, there may be a plurality of battery cells. Among the plurality of battery cells, they may be connected in series, in parallel, or in series-parallel. Series-parallel connection means that there are both series connections and parallel connections among the plurality of battery cells. A plurality of battery cells can be directly connected in series, in parallel, or in series-parallel, and the whole composed of the plurality of battery cells can be further housed in a housing or other packaging so that the whole can be charged and discharged externally.

[0050] In actual applications, one battery pack may be provided as one battery. However, by connecting a plurality of battery packs in series, parallel, or series-parallel connection with each other to form a whole and accommodating them in a housing or other packaging, it may also be provided as one battery. That is, one battery may have one or a plurality of battery packs.

[0051] Referring to FIG. 1, the battery cell 100 may be composed of a battery core 11, end caps 12, a case 13, and other functional members. Here, The end cap 12 refers to a member that covers the opening of the case 13 to isolate the internal environment of the battery cell 100 from the external environment. The shape of the end cap 12 may conform to the shape of the case 13 to fit the case 13, but is not limited thereto. Functional members such as electrode terminals 12a may be installed on the end cap 12. The electrode terminal 12a may be electrically connected to the battery core 11 to output or input the electrical energy of the battery cell 100.

[0052] The case 13 is an assembly for fitting with the end cap 12 to form the internal environment of the battery cell 100. Here, the formed internal environment may be used to accommodate the battery core 11, electrolyte, and other members.

[0053] The battery core 11 is a member in which an electrochemical reaction occurs in the battery cell 100. One or a plurality of battery cores 11 may be included in the case 13. The battery core 11 is mainly formed by winding or laminating a positive electrode plate and a negative electrode plate, and generally a separator is provided between the positive electrode plate and the negative electrode plate. The portions of the positive electrode plate and the negative electrode plate of the battery core 11 having the active material constitute the main body of the battery core assembly, and the portions of the positive electrode plate and the negative electrode plate having no active material constitute tabs 11a respectively. The positive tab and the negative tab may both be located at one end of the main body, or may be located at both ends of the main body respectively. In the charging and discharging process of the battery, the positive active material and the negative active material react with the electrolyte, and the tab 11a is connected to the electrode terminal to form a current circuit.

[0054] Here, each battery cell 100 may be a secondary battery or a primary battery. The battery cell 100 may have a cylindrical shape, a flat shape, a rectangular parallelepiped shape, or other shapes.

[0055] The formation of a lithium-ion battery is a process of activating the positive and negative electrode materials inside the battery core by charging multiple times after the battery manufacturing is completed, and improving the self-discharge, charge-discharge performance, and storage performance of the battery. In the embodiments of the present application, the first charging stage in the formation process is called the first stage.

[0056] In the embodiments of the present application, during formation, formation may be performed on each battery core that is not assembled into the battery cell 100, or formation may be performed on the battery core in the assembled battery cell 100.

[0057] It should be understood that the abnormal situations described in the embodiments of the present application include, but are not limited to, situations such as abnormal electrolyte and abnormal water content in the battery core. Here, abnormal electrolyte means that the electrolyte injected into the battery core cannot achieve the expected effect. The causes of abnormal electrolyte include injection errors of the electrolyte, contamination of the electrolyte during injection, etc. Abnormal water content means that the water content in the battery core does not meet the requirements of the preset specifications (for example, exceeding the water content standard or being less than the water content standard).

[0058] Based on the above description, according to some embodiments of the present application, referring to FIG. 2, FIG. 2 shows a basic flowchart of a method for identifying an abnormal battery core according to an embodiment of the present application, including the following.

[0059] S201: Based on the target characteristic data of the battery core, determine whether this battery core is an abnormal battery core.

[0060] It should be understood that in the embodiments of the present application, the target characteristic data is characteristic data that can distinguish an abnormal battery core from a normal battery core generated during the formation process.

[0061] For example, the target feature data may include feature data affected by the electrolyte in the battery core that occurred during the formation process, and based on the target feature data, it is possible to distinguish and identify between abnormal battery cores with electrolyte abnormalities and normal battery cores. Also, for example, the target feature data may include feature data affected by the water content in the battery core that occurred during the formation process, and based on the target feature data, it is possible to distinguish and identify between abnormal battery cores with abnormal water content and normal battery cores.

[0062] In the embodiments of the present application, the target feature data may be the values of parameters such as the film formation peak corresponding to a specific position that occurred during the formation process (dQ / dV, where dQ is the current flowing through the battery core per unit time, and dV is the voltage change per unit time in the battery core), the dynamic internal resistivity (V / I, where V is the voltage and I is the current), and dV / dQ.

[0063] In the embodiments of the present application, during the formation process or after the completion of the formation process, the formation process data (including but not limited to data such as the steps, time, current, voltage, temperature, and atmospheric pressure of battery formation) that occurred during the formation process of the battery core is introduced into an electronic device capable of executing the method for identifying polarized abnormal battery cores according to the embodiments of the present application, so that the electronic device can obtain the target feature data of the battery core from the formation process data.

[0064] In the embodiments of the present application, when the target feature data of the battery core is obtained during the formation process, it is possible to determine whether this battery core is an abnormal battery core based on the target feature data of the battery core at the formation stage of the battery core. Thereby, identification and screening of abnormal battery cores are realized at the formation stage of the battery core, abnormal battery cores are identified early, and the entry of abnormal battery cores into subsequent production flows is avoided, reducing resource waste.

[0065] It should be understood that in the formation process, the values of the parameters are constantly changing. In the formation process, since the parameter values of the abnormal battery core with an abnormality and the normal battery core without an abnormality may be close within some positions or intervals, differentiating based on the parameter values of these parameters within these positions or intervals will have a poor effect. However, there are obvious differences in the parameter values between the abnormal battery core and the normal battery core within some other positions or intervals, whereby the abnormal battery core and the normal battery core can be effectively distinguished. The parameter values within these specific positions or intervals can be used as the target feature data in the embodiments of the present application to realize the identification of whether the battery core is an abnormal battery core.

[0066] Exemplarily, as a result of a large number of experiments, the inventor found that for an abnormal battery core with an electrolyte abnormality, when comparing the abnormal battery core with an electrolyte abnormality with a normal battery core without an electrolyte abnormality, in the first stage of the formation process, there are relatively large differences in the change process of the parameters. As a result, it was discovered that the parameter values corresponding when the abnormal battery core with an electrolyte abnormality and the normal battery core without an electrolyte abnormality first reach a certain process change value are different. Similarly, as a result of a large number of experiments, the inventor found that for an abnormal battery core with a water content abnormality, when comparing the abnormal battery core with a water content abnormality with a normal battery core without a water content abnormality, similarly in the first stage of the formation process, relatively large differences occur in the change process of the parameters. As a result, it was further discovered that, similarly, the parameter values corresponding when the abnormal battery core with an electrolyte abnormality and the normal battery core without an electrolyte abnormality first reach a certain process change value are different. The difference between the two is only that the process change values that can reflect the difference between the abnormal battery core and the normal battery core are different.

[0067] Based on the above discovery, in one alternative embodiment of the examples of the present application, the target feature data may include the first target parameter value when the parameter change first reaches the first process change value preset in the process of collecting parameters in the first stage of the formation process. By using this first target parameter value when the parameter change first reaches the first process change value preset as the basis for determining whether an electrolyte abnormality has occurred in the battery core, it is possible to identify the abnormal battery core in which the electrolyte abnormality has occurred.

[0068] In one alternative embodiment of the examples of the present application, the target feature data may include the first target parameter value when the parameter change first reaches the first process change value and the second target parameter value when the parameter change first reaches the second process change value in the process of collecting parameters in the first stage of the formation process. Here, the first process change value and the second process change value are different. In this way, in the process of collecting parameters in the first stage, by using the first target parameter value when the parameter change first reaches the first process change value threshold and the second target parameter value when the parameter change first reaches the second process change value as the basis for determining whether an electrolyte abnormality has occurred in the battery core, it is possible to comprehensively use the two types of target parameter values to accurately identify the abnormal battery core in which the electrolyte abnormality has occurred.

[0069] It should be noted that in the examples of the present application, a sample battery core containing a large number of abnormal battery cores and normal battery cores is obtained in advance. Furthermore, based on the parameters collected in the first stage of the formation process of the sample battery core, the first process change value and the second process change value that can reflect the difference between the abnormal battery core and the normal battery core can be determined.

[0070] Exemplarily, when it is necessary to identify that the abnormal battery core is an abnormal battery core in which an electrolyte abnormality has occurred, the first process change value and the second process change value may be determined based on parameters collected at the first stage of the formation process for a sample battery core in which an electrolyte abnormality has occurred and a sample battery core in which no electrolyte abnormality has occurred. Similarly, when it is necessary to identify that the abnormal battery core is an abnormal battery core in which a water content abnormality has occurred, the first process change value and the second process change value may be determined based on parameters collected at the first stage of the formation process for a sample battery core in which a water content abnormality has occurred and a sample battery core in which no water content abnormality has occurred. The specific method for determining the first process change value and the second process change value will be described later.

[0071] It should be noted that in the embodiments of the present application, the target parameter may be a parameter that can reflect the changes in the formation process, such as the film formation peak, the dynamic internal resistivity, dV / dQ, etc., and is related to the cause of the abnormality of the battery core (for example, the electrolyte or the water content of the battery core). The target parameter value is the value of the target parameter.

[0072] Furthermore, it should be noted that the process change value described in the embodiments of the present application is the change value of the target parameter within a set collection time interval (for example, the collection time interval between two adjacent collection points). For example, assuming that the target parameter is the film formation peak, the process change value may be the gradient value of the film formation peak.

[0073] It should be understood that since there are obvious differences in the target characteristic data between the abnormal battery core and the normal battery core during the formation process of the battery core, based on the target characteristic data, an accurate judgment can be made as to whether the battery core is an abnormal battery core, and a reliable identification of the abnormal battery core can be realized.

[0074] In order to achieve an accurate determination as to whether a battery core is an abnormal battery core, in one alternative embodiment of the examples of the present application, based on the difference in the range of target characteristic data between the pre-collected abnormal battery cores and normal battery cores, a threshold range is set to determine whether the battery core is an abnormal battery core. (That is, it is determined whether the target characteristic data is within the preset threshold range or outside the preset threshold range, and further, based on the relationship between the target characteristic data and the threshold range between the collected abnormal battery cores and normal battery cores, it is determined whether the battery core is an abnormal battery core.)

[0075] For example, assuming that the abnormal battery core to be identified is an abnormal battery core with electrolyte abnormality, based on the target characteristic data of sample battery cores with a large amount of electrolyte abnormality and sample battery cores without electrolyte abnormality, a first threshold range corresponding to the abnormal battery core with electrolyte abnormality can be pre-collected. Then, it is determined whether the target characteristic data of the current battery core is within this preset first threshold range. If so, it is determined that this battery core is an abnormal battery core with electrolyte abnormality; if not, it is determined that this battery core does not have electrolyte abnormality.

[0076] Similarly, assuming that the abnormal battery core to be identified is an abnormal battery core with abnormal water content, based on the target characteristic data of sample battery cores with a large amount of abnormal water content and sample battery cores without abnormal water content, a second threshold range corresponding to the abnormal battery core with abnormal water content can be pre-collected. Then, it is determined whether the target characteristic data of the current battery core is within this preset second threshold range. If so, it is determined that this battery core is an abnormal battery core with abnormal water content; if not, it is determined that this battery core does not have abnormal water content.

[0077] Exemplarily, assuming that the target feature data in the embodiments of the present application only includes the first target parameter value when the parameter change first reaches the first process change value in the process of collecting parameters in the first stage of the formation process, one first target parameter threshold range is preset, the first target parameter value is compared with the first target parameter threshold range, and thereby when the first target parameter value is within the first target parameter threshold range, it may be determined that this battery core is an abnormal battery core.

[0078] Exemplarily, assuming that the target feature data in the embodiments of the present application includes the first target parameter value when the parameter change first reaches the first process change value and the second target parameter value when the parameter change first reaches the second process change value in the process of collecting parameters in the first stage of the formation process, one first target parameter threshold range and one second target parameter threshold range are preset, the first target parameter value is compared with the first target parameter threshold range, and the second target parameter value is compared with the second target parameter threshold range, and thereby when the first target parameter value is within the first target parameter threshold range and the second target parameter value is within the second target parameter threshold range, it may be determined that this battery core is an abnormal battery core.

[0079] It should be understood that the first target parameter threshold range and the second target parameter threshold range may be values set after pre-statistics of the first target parameter value and the second target parameter value in the first stage of the formation process for a large number of first sample battery cores with electrolyte abnormalities and second sample battery cores without electrolyte abnormalities. At this time, in the method described in the above paragraph, when it is determined that the battery core is an abnormal battery core, it can also be determined that electrolyte abnormalities have occurred in this battery core.

[0080] Furthermore, it should be understood that the first target parameter threshold range and the second target parameter threshold range may be values set after pre-statistics of the first target parameter values and the second target parameter values in the first stage of the formation process for a large number of first sample battery cores with abnormal water content and second sample battery cores without abnormal water content. At this time, in the method described in the above paragraph, when it is determined that the battery core is an abnormal battery core, it can also be determined that abnormal water content has occurred in this battery core.

[0081] To achieve an accurate determination of whether the battery core is an abnormal battery core, in another alternative embodiment of the embodiments of the present application, an identification model may be constructed, and by inputting target feature data into the pre-set identification model, an identification result of whether the battery core is an abnormal battery core may be obtained.

[0082] Here, the identification model may be a pre-constructed two-dimensional Gaussian model, but is not limited thereto. For example, the identification model may further be a classification model such as an SVM (Support Vector Machine) model or a CART (Classification And Regression Tree) model that takes target feature data as input.

[0083] It should be noted that when using classification models such as the SVM (Support Vector Machine) model and the CART (Classification And Regression Tree) model for identification, for each sample battery core required during model construction, it is necessary to pre-mark whether it belongs to the first sample battery core with abnormalities or the second sample battery core without abnormalities. Similarly, for the selective embodiment of identification based on the threshold range described above, it is also necessary to pre-mark whether the sample battery core for setting the threshold range belongs to the first sample battery core with abnormalities or the second sample battery core without abnormalities. However, when using the two-dimensional Gaussian model for identification, the distinction between the two types of sample battery cores can be realized by clustering through the two-dimensional Gaussian model itself without performing this marking. Therefore, when using the two-dimensional Gaussian model for identification, the workload of engineers can be reduced, and the difficulty of obtaining data corresponding to the sample battery core can be decreased.

[0084] Furthermore, it should be noted that in the embodiments of the present application, the SVM model, the CART model, and other classification models may be trained by using the first sample battery core with electrolyte abnormalities and the second sample battery core without electrolyte abnormalities, so that the classification model can output whether there are electrolyte abnormalities in the battery core. Similarly, the SVM model, the CART model, and other classification models may be trained by using the first sample battery core with abnormal water content and the second sample battery core without abnormal water content, so that the classification model can output whether there are abnormal water contents in the battery core.

[0085] It should be understood that in the embodiments of the present application, when it is necessary to specifically identify which abnormal type of abnormal battery core it is, by adopting a sample battery core with this abnormal type and a normal battery core without this abnormal type to perform model training or construction, or determination of a threshold range, identification of this abnormal type of abnormal battery core can be realized.

[0086] It should be further explained that when the identification model is a two-dimensional Gaussian model, in order to meet the data input requirements of the two-dimensional Gaussian model, there should be two types of target feature data. For example, the target feature data may be the first target parameter value when the parameter change first reaches the first process change value and the second target parameter value when the parameter change first reaches the second process change value in the process of collecting parameters in the first stage of the formation process.

[0087] Taking the case where the identification model is a two-dimensional Gaussian model as an example, the solutions of the embodiments of the present application will be further described below.

[0088] Based on the two-dimensional Gaussian model, in order to ensure that an accurate judgment can be made on whether the battery core is an abnormal battery core, first, two types of target feature data need to be selected, and further, a reasonable two-dimensional Gaussian model needs to be constructed based on these two types of target feature data.

[0089] Referring to FIG. 3, FIG. 3 shows a model construction method according to an embodiment of the present application, and this model construction method includes the following.

[0090] S301: Obtain two types of target feature data of each sample battery core in the formation process.

[0091] It should be noted that each sample battery core includes a first sample battery core with an abnormality and a second sample battery core without an abnormality. Exemplarily, the first sample battery core may be a sample battery core with an electrolyte abnormality, and the second sample battery core may be a normal battery core without any abnormality. The two types of target feature data may include feature data affected by the electrolyte in the battery core that occurred during the formation process. Also exemplarily, the first sample battery core may be a sample battery core with an abnormal water content, and the second sample battery core may be a normal battery core without any abnormality. The two types of target feature data may include feature data affected by the water content in the battery core that occurred during the formation process.

[0092] It should be noted that the two types of target feature data of the first sample battery core and the second sample battery core may be collected from the production line or other routes, and are not limited in the embodiments of the present application.

[0093] S302: Based on the two types of target feature data of each sample battery core, construct a two-dimensional Gaussian model.

[0094] In the embodiments of the present application, the average value and variance between the two types of target feature data may be calculated, and the correlation coefficient between the two types of target feature data may also be calculated. Based on the average value and variance of the two types of target feature data and the correlation coefficient between the features, the average value vector and covariance matrix required for the two-dimensional Gaussian model can be constructed. Then, based on the average value vector and covariance matrix, a two-dimensional Gaussian model can be obtained. relationship

[0095] ​There may be certain abnormal data in the two types of target feature data of the obtained sample battery cores, which may affect the reliability of the two-dimensional Gaussian model constructed thereby. Therefore, in one executable embodiment of the examples of the present application, first, a preliminary two-dimensional Gaussian model may be constructed based on the two types of target feature data of all the sample battery cores. Then, a final two-dimensional Gaussian model is constructed based on the two types of target feature data of each sample battery core belonging to the target cluster in this preliminary two-dimensional Gaussian model. Here, the target cluster is the cluster of the second sample battery cores indicating the absence of abnormalities in the preliminary two-dimensional Gaussian model.

[0096] It should be understood that the construction methods of the two-dimensional Gaussian model twice are as described in the above paragraph and will not be further explained here.

[0097] It should be understood that in the examples of the present application, after constructing a two-dimensional Gaussian model based on the two types of target feature data of the first sample battery core and the second sample battery core, in the two-dimensional Gaussian model, the probability density distribution belonging to the second sample battery core can be obtained, and based on this distribution, a probability density threshold can be set.

[0098] Then, when using the two-dimensional Gaussian model to determine whether the battery core is an abnormal battery core, after inputting the two types of target feature data of the battery core into the two-dimensional Gaussian model, the probability density corresponding to the battery core can be obtained, and thereby this probability density is compared with the set probability density threshold. If this probability density is smaller than the probability density threshold, it can be determined that an abnormality has occurred in the battery core. In the opposite case, it can be determined that no abnormality has occurred in the battery core.

[0099] It should be noted that when a two-dimensional Gaussian model is constructed, an effect schematic diagram as shown in FIG. 7 can be obtained, and there is a region range (for example, the region range within the left circle in FIG. 7) where some sample battery cores are clustered so as to belong to the abnormal battery core. Based on this, a characteristic interval corresponding to the abnormal battery core (for example, the horizontal coordinate range and the vertical coordinate range corresponding to the left circle in FIG. 7) can be obtained. Thereby, when using the two-dimensional Gaussian model to determine whether a battery core is an abnormal battery core, the target characteristic data of the battery core is input into the two-dimensional Gaussian model, and the probability density of the battery core obtained by calculation by the two-dimensional Gaussian model can be obtained. And when the probability density of the battery core is smaller than a preset probability density threshold value and the target characteristic data is within a preset characteristic interval, it is determined that the battery core is an abnormal battery core. Thereby, it is determined whether the battery core is abnormal from two aspects, and the reliability of identifying the abnormal battery core is improved.

[0100] It should be noted that the two types of target characteristic data adopted when constructing the two-dimensional Gaussian model should be consistent with the target characteristic data of the battery core collected in the subsequent identification process of the abnormal battery core. That is, if the two types of target characteristic data adopted when constructing the two-dimensional Gaussian model include the first target parameter value when the parameter change first reaches the first process change value and the second target parameter value when the parameter change first reaches the second process change value in the process of collecting parameters in the first stage of the formation process, when identifying the abnormal battery core, the target characteristic data of the collected battery core should also be the first target parameter value when the parameter change first reaches the first process change value and the second target parameter value when the parameter change first reaches the second process change value in the process of collecting parameters in the first stage of the formation process.

[0101] Furthermore, it should be further explained that when two types of target feature data include the first target parameter value when the parameter change first reaches the first process change value and the second target parameter value when the parameter change first reaches the second process change value in the process of collecting parameters in the first stage of the formation process, in order to ensure the discrimination effect of the target feature data on abnormal battery cores and normal battery cores, the selected first process change value and second process change value may be the two process change values with the maximum discrimination degree for the first sample battery core and the second sample battery core.

[0102] Therefore, in order to accurately find the two process change values with the maximum discrimination degree for the first sample battery core and the second sample battery core, in the embodiments of the present application, in the formation process, when each sample battery core first reaches each different preset process change value, the corresponding target parameter value is obtained, and based on the target parameter values corresponding to each different process change value, the first process change value and the second process change value may be identified.

[0103] Exemplarily, based on the target parameter values corresponding to two different process change values, the discrimination degree between the first sample battery core and the second sample battery core corresponding to these two different process change values is calculated, and further, the two different process change values corresponding to the maximum discrimination degree may be determined as the first process change value and the second process change value.

[0104] It should be understood that in the embodiments of the present application, the LDA (Linear Discriminant Analysis) algorithm may be adopted to calculate the discrimination degree (i.e., the inter-class distance calculated by the LDA algorithm) between the first sample battery core and the second sample battery core corresponding to each two different process change values among each different process change value.

[0105] Exemplarily, assuming there are three different process change values, which are A, B, and C respectively, based on the LDA algorithm, the discrimination degrees ab corresponding to between A and B, the discrimination degree ac corresponding to between A and C, and the discrimination degree bc corresponding to between B and C are calculated, and the maximum value may be determined from ab, ac, and bc. Assuming the maximum value is ac, it may be determined that the first process change value and the second process change value are A and C respectively.

[0106] In the embodiments of the present application, in order to ensure the discrimination effect on the first process change value and the second process change value, before adopting the LDA algorithm for calculation, by normalizing the target parameter value corresponding to each process change value, the target parameter value corresponding to each process change value may be converted into a standard normal distribution following N(0, 1), thereby facilitating the processing of the LDA algorithm.

[0107] It should be understood that for other types of discrimination models, after training the discrimination model based on the target feature data to obtain the trained discrimination model, it may be used. Since the training process is consistent with the normal training process of each type of discrimination model, it will not be described in detail here.

[0108] In the embodiments of the present application, when it is determined that the battery core is an abnormal battery core, this battery core may be marked, so that the engineer can perform the processing and analysis of the battery core based on this mark later.

[0109] For example, assuming that the determined battery core is an abnormal battery core with electrolyte abnormality, after identifying the abnormal battery cores for all of one or several lots of battery cores, based on the number of marked abnormal battery cores with electrolyte abnormality, if it is determined that the number of abnormal battery cores with electrolyte abnormality is greater than the preset threshold number, it can be determined that there is an injection error of the electrolyte, and thus operations such as an injection error alarm of the electrolyte can be performed according to the preset method.

[0110] In any case, in the embodiments of the present application, each time an abnormal battery core with electrolyte abnormality is determined without marking, the number of battery cores with electrolyte abnormality is updated, and based on the statistically determined number of battery cores with electrolyte abnormality that have already been determined, it may be determined whether the number of these battery cores is greater than a preset threshold number. If it is greater, it can be determined that there is an injection error of the electrolyte, and thereby operations such as an injection error alarm of the electrolyte can be performed according to a preset method.

[0111] Also, for example, assuming that the determined battery core is an abnormal battery core with abnormal water content, after identifying abnormal battery cores for all of one or several lots of battery cores, if it is determined based on the number of marked abnormal battery cores with abnormal water content that the number of abnormal battery cores with abnormal water content is greater than a preset threshold number, it can be determined that there is a problem in the water content control stage of the battery core production line, and thereby operations such as an alarm can be performed according to a preset method.

[0112] In the embodiments of the present application, the preset method may be, but is not limited to, notifying relevant engineers by short message or phone call, sounding an alarm, etc.

[0113] It should be noted that the above solution of the embodiments of the present application may be implemented by an electronic device having data processing capabilities, and may also be implemented by devices such as a PLC (Programmable Logic Controller), a computer, a smartphone, a server, etc.

[0114] It should be understood that in the embodiments of the present application, by connecting the electronic device to the industrial Internet, the marked battery cores can be notified to the industrial Internet and then notified to each engineer by the industrial Internet.

[0115] In the technical solution of the embodiment of the present application, by acquiring and analyzing the target characteristic data affected by the electrolyte in the battery core that occurs during the formation process of the battery core, it is determined whether the battery core is an abnormal battery core. In this way, on the one hand, there are obvious differences in the target characteristic data between the abnormal battery core and the normal battery core during the formation process of the battery core. Therefore, an accurate judgment can be realized based on this to determine whether the battery core is an abnormal battery core, and a reliable identification of the abnormal battery core can be realized. On the other hand, in the industrial production process, since the formation process of the battery core must occur before the process of mounting the battery core on the battery pack, the technical solution of the embodiment of the present application can effectively realize the purpose of identifying the abnormal battery core before mounting the battery core, reduce the risk of performance degradation of the battery system caused by the mounting of the abnormal battery core, and reduce the risk of battery pack abandonment caused by the mounting of the abnormal battery core.

[0116] To easily understand the solution according to the embodiment of the present application, the following takes the execution body as a PLC, and the target characteristic data is the change value of the film formation peak collected in the first stage of the formation process. When the change value of the film formation peak first reaches the first process change value (for example, the first film formation peak gradient value), the first film formation peak value, and the change value of the film formation peak first reaches the second process change value (for example, the second film formation peak gradient value) as an example of the specific implementation process of identifying whether electrolyte abnormality has occurred in the battery core by the two-dimensional Gaussian model, the present application is further illustrated. two Referring to FIG. 4, the implementation process includes the following.

[0117] Referring to FIG. 4, the implementation process includes the following.

[0118] S401: The PLC receives the formation process data of a certain lot or several lots of sample battery cores introduced.

[0119] Here, the formation process data may be introduced according to the formation lot, or the formation process data may be introduced according to the battery cores that have completed formation every day. According to the law of large numbers, the larger the number, the more the statistical parameters will conform to the data distribution rule of normal battery cores. Here, the lot battery cores may include a first sample battery core with electrolyte abnormality and a second sample battery core without electrolyte abnormality.

[0120] It should be noted that the formation process data is the process data stored during the formation process of the battery core (including but not limited to data such as the steps, time, current, voltage, temperature, and air pressure of battery formation).

[0121] S402: Pretreat the formation process data.

[0122] This step includes removing the formation process data corresponding to battery cores in which situations such as formation termination, sampling abnormality of formation equipment, no participation in formation, interruption in the first stage, and formation remeasurement occur, and obtaining data related to the film formation peak (including the value of the film formation peak and the film formation peak gradient value) from the remaining formation process data.

[0123] Here, in the formation process data of a certain sample battery core, if the number of formation steps is smaller than the required number of set formation steps, it is determined that there is a situation of formation termination for this sample battery core; if data corruption occurs in the formation process data of a certain sample battery core, it is determined that there is a situation of sampling abnormality of formation equipment for this sample battery core; if there is no current value and the voltage value does not increase in the formation process data of a certain sample battery core, it is determined that this sample battery core has not participated in formation; if a situation of charging termination and restart occurs in the first stage in the formation process data of a certain sample battery core, it is determined that there is a situation of interruption in the first stage for this sample battery core; if the number of formation steps in the formation process data of a certain sample battery core is larger than the required number of set formation steps, it is determined that there is a situation of formation remeasurement for this sample battery core.

[0124] It should be noted that the value of the film formation peak may be obtained by calculation based on data such as current and voltage in the formation process data. The film formation peak gradient value may be obtained by calculating the difference based on the values of two adjacent film formation peaks obtained twice.

[0125] And, an initial film formation peak gradient value and a gradient change value may be preset, and based on the initial film formation peak gradient value and this gradient change value, each preset film formation peak gradient value is obtained. And, the value of the film formation peak corresponding to the time when each film formation peak gradient value is reached for the first time is obtained.

[0126] It should be noted that the value of the film formation peak corresponding to each film formation peak gradient value may be the average value of the values of two film formation peaks of this film formation peak gradient value obtained by calculation when each film formation peak gradient value is reached for the first time. Here, the film formation peak gradient value is equal to the difference between the film formation peaks between two adjacent sampling points. For example, assuming that the values of the film formation peaks between two adjacent sampling points when the first film formation peak gradient value is reached for the first time are A and B respectively, the value of the film formation peak corresponding to the first film formation peak gradient value may be equal to (A + B) / 2. Of course, the value of the film formation peak corresponding to each film formation peak gradient value may be the value of any one of the two film formation peaks corresponding to this film formation peak gradient value, but it is not limited.

[0127] Then, based on the values of the film formation peaks corresponding to each film formation peak gradient value, the LDA algorithm is adopted to calculate the discrimination degree (i.e., the inter-class distance calculated by the LDA algorithm) between the corresponding first sample cell core and the second sample cell core for each of the two different film formation peak gradient values, and determine the two different film formation peak gradient values corresponding to the maximum discrimination degree, which may be the first film formation peak gradient value and the second film formation peak gradient value respectively. At the same time, obtain the first film formation peak value (i.e., the value of the film formation peak corresponding to the first film formation peak gradient value) and the second film formation peak value (i.e., the value of the film formation peak corresponding to the second film formation peak gradient value) corresponding to each sample cell core.

[0128] In the embodiments of the present application, in order to ensure the discrimination effect of the first film formation peak gradient value and the second film formation peak gradient value, before adopting the LDA algorithm for calculation, the values of the film formation peaks corresponding to each film formation peak gradient value may be further standardized, so that the values of the film formation peaks corresponding to each film formation peak gradient value are converted into a standard normal distribution following N(0,1), thereby facilitating the processing of the LDA algorithm.

[0129] S403: Calculate the mean and variance of the first film formation peak value, and the mean and variance of the second film formation peak value respectively, and calculate the correlation coefficient between the first film formation peak value and the second film formation peak value. relationship Calculate the correlation coefficient.

[0130] S404: Based on the mean and variance of the first film formation peak value and the second film formation peak value, and the correlation coefficient between the first film formation peak value and the second film formation peak value, construct the mean vector and covariance matrix required for the two-dimensional Gaussian model, and obtain a preliminary two-dimensional Gaussian model.

[0131] S405: Based on the first film formation peak value and the second film formation peak value of each sample battery core belonging to the target cluster in this preliminary two-dimensional Gaussian model, calculate the mean value and variance of the first film formation peak value, and the mean value and variance of the second film formation peak value respectively, and calculate the correlation coefficient between the first film formation peak value and the second film formation peak value. relationship Calculate the number.

[0132] It should be understood that the target cluster is a cluster of second sample battery cores indicating the absence of electrolyte abnormalities in the preliminary two-dimensional Gaussian model.

[0133] S406: Based on the mean value and variance of the latest first film formation peak value and the second film formation peak value, and the correlation coefficient between the first film formation peak value and the second film formation peak value, construct the mean value vector and covariance matrix required for the two-dimensional Gaussian model, and obtain the final two-dimensional Gaussian model.

[0134] S407: Determine the target probability density range based on the probability density region where there is a target cluster in the final two-dimensional Gaussian model.

[0135] For example, as shown in Figure 5, the region defined by two circles in Figure 5 is the region where there is a target cluster, and the engineer may use the probability density range corresponding to each sample battery core within the range defined by any one of the circles as the target probability density range. For example, the probability density range corresponding to the sample battery core within the region defined by the outermost circle may be used as the target probability density range. It should be understood that the abscissa in Figure 5 is the first film formation peak value, and the ordinate is the second film formation peak value.

[0136] S408: The PLC receives the formation process data of the battery core to be detected that has been introduced.

[0137] S409: Obtain the first film formation peak value and the second film formation peak value in the first stage of the battery core to be detected from the formation process data.

[0138] S410: Calculate the first film formation peak value and the second film formation peak value in the first stage of the battery core to be detected using the final two-dimensional Gaussian model, and obtain the probability density of the battery core to be detected.

[0139] S411: Determine whether the probability density of the battery core to be detected is within the target probability density range. If so, proceed to step S412; if not, proceed to step S413.

[0140] Exemplarily, the target probability density range may be a range starting from 0. At this time, by setting only one probability density threshold, it may be determined whether the probability density of the battery core to be detected is smaller than this probability density threshold. If it is smaller, it indicates that the probability density of the battery core to be detected is within the target probability density range, and proceed to step S412; if not, proceed to step S413.

[0141] S412: Determine that there is no electrolyte abnormality in the battery core to be detected.

[0142] S413: Mark the battery core to be detected and report the mark result to the industrial Internet.

[0143] It should be understood that in the embodiments of the present application, instead of making a judgment based on probability density, the first film formation peak value and the second film formation peak value in the first stage of the battery core to be detected are used as the two coordinate values of a coordinate point, and the battery core to be detected is converted into a coordinate point in the coordinate system shown in FIG. 5, and it may be determined whether this coordinate point is located within the set circle (for example, the outermost circle in FIG. 5). If so, determine that there is no electrolyte abnormality in the battery core to be detected; if not, determine that there is an electrolyte abnormality in the battery core to be detected. At this time, the battery core to be detected may be marked and the mark result reported to the industrial Internet.

[0144] It should be further understood that the process shown in FIG. 4 essentially consists of two stages. Here, steps S401 to S407 are in the model construction stage, and steps S408 to S413 are in the battery core identification stage. After the final two-dimensional Gaussian model is constructed by steps S401 to S407, this final two-dimensional Gaussian model may be repeatedly applied, that is, steps S408 to S413 may be repeatedly executed for different battery cores to be detected.

[0145] By the above method, the purpose of identifying a battery core with electrolyte abnormality before the battery core is installed can be realized. At the same time, as a result of detection by experiments, this method has high robustness, few errors, and can have good effects in actual applications.

[0146] To easily understand the solution according to the embodiment of the present application, hereinafter, taking the execution body as a PLC, the target feature data is the first film formation peak value when the change value of the film formation peak first reaches the first process change value (for example, the first film formation peak gradient value) in the first stage of the formation process, and the change value of the film formation peak first reaches the second process change value (for example, the second film formation peak gradient value). two And the second film formation peak value when it reaches, and taking the specific implementation process of identifying whether there is an abnormal water content in the battery core by the two-dimensional Gaussian model as an example, the present application will be further illustrated by examples.

[0147] Referring to FIG. 6, the implementation process includes the following.

[0148] S601: The PLC receives the formation process data of a certain lot or several lots of sample battery cores introduced.

[0149] Similarly, the formation process data may be introduced according to the formation lot, or the formation process data may be introduced according to the battery cores that have completed formation every day. Here, the battery cores may include a first sample battery core with abnormal water content and a second sample battery core without abnormal water content.

[0150] Similarly, the formation process data is the process data (including but not limited to data such as the steps, time, current, voltage, temperature, and atmospheric pressure of battery formation) stored during the formation process of the battery core.

[0151] S602: Preprocess the formation process data.

[0152] This step includes removing the formation process data corresponding to battery cores in which situations such as formation termination, sampling abnormality of formation equipment, non-involvement in formation, interruption in the first stage, and formation remeasurement have occurred, and obtaining data related to the film formation peak (including the value of the film formation peak and the film formation peak gradient value) from the remaining formation process data.

[0153] Similarly, in the formation process data of a certain sample battery core, if the number of formation steps is smaller than the required number of set formation steps, it is determined that there is a situation of formation termination in this sample battery core. If data corruption occurs in the formation process data of a certain sample battery core, it is determined that there is a situation of sampling abnormality of formation equipment in this sample battery core. If there is no current value and the voltage value does not increase in the formation process data of a certain sample battery core, it is determined that this sample battery core is not involved in formation. If a situation of charging termination and restart occurs in the first stage in the formation process data of a certain sample battery core, it is determined that there is a situation of interruption in the first stage in this sample battery core. If the number of formation steps in the formation process data of a certain sample battery core is larger than the required number of set formation steps, it is determined that there is a situation of formation remeasurement in this sample battery core.

[0154] And an initial film formation peak gradient value and a gradient change value may be preset, and based on the initial film formation peak gradient value and this gradient change value, each preset film formation peak gradient value is obtained. And when each film formation peak gradient value is reached for the first time, the value of the film formation peak corresponding thereto is obtained.

[0155] Similarly, the value of the film formation peak corresponding to each film formation peak gradient value may be the average value of the values of the two film formation peaks of this film formation peak gradient value calculated when each film formation peak gradient value is reached for the first time. Here, the film formation peak gradient value is equal to the difference between the film formation peaks between two adjacent sampling points. Of course, the value of the film formation peak corresponding to each film formation peak gradient value may be the value of any one of the two film formation peaks corresponding to this film formation peak gradient value, but it is not limited thereto.

[0156] And based on the value of the film formation peak corresponding to each film formation peak gradient value, the LDA algorithm is adopted to calculate the discrimination degree (that is, the inter-class distance calculated by the LDA algorithm) between the corresponding first sample battery core and the second sample battery core for every two different film formation peak gradient values, and two different film formation peak gradient values corresponding to the maximum discrimination degree are determined, which may be the first film formation peak gradient value and the second film formation peak gradient value respectively. At the same time, the first film formation peak value (that is, the value of the film formation peak corresponding to the first film formation peak gradient value) and the second film formation peak value (that is, the value of the film formation peak corresponding to the second film formation peak gradient value) corresponding to each sample battery core are obtained.

[0157] Optionally, in order to ensure the discrimination effect of the first film formation peak gradient value and the second film formation peak gradient value, before calculating by adopting the LDA algorithm, the value of the film formation peak corresponding to each film formation peak gradient value may be further standardized, so that the value of the film formation peak corresponding to each film formation peak gradient value is converted into a standard normal distribution following N(0,1), thereby facilitating the processing of the LDA algorithm.

[0158] S603: Calculate the average value and variance of the first film formation peak value, and the average value and variance of the second film formation peak value respectively, and calculate the correlation coefficient between the first film formation peak value and the second film formation peak value. relationship

[0159] S604: Based on the average value and variance of the first film formation peak value and the second film formation peak value, and the correlation coefficient between the first film formation peak value and the second film formation peak value, construct the average value vector and covariance matrix required for the two-dimensional Gaussian model to obtain a preliminary two-dimensional Gaussian model.

[0160] S605: Based on the first film formation peak value and the second film formation peak value of each sample battery core belonging to the target cluster in this preliminary two-dimensional Gaussian model, calculate the average value and variance of the first film formation peak value, and the average value and variance of the second film formation peak value respectively, and calculate the correlation coefficient between the first film formation peak value and the second film formation peak value. relationship

[0161] It should be understood that the target cluster is a cluster of second sample battery cores indicating the absence of abnormal water content in the preliminary two-dimensional Gaussian model.

[0162] S606: Based on the average value and variance of the latest first film formation peak value and the second film formation peak value, and the correlation coefficient between the first film formation peak value and the second film formation peak value, construct the average value vector and covariance matrix required for the two-dimensional Gaussian model to obtain the final two-dimensional Gaussian model.

[0163] S607: Based on the probability density region where the target cluster exists in the final two-dimensional Gaussian model, determine the target probability density range, and based on the region where the abnormal battery core cluster exists in the final two-dimensional Gaussian model, determine the abnormal range of the first film formation peak value and the abnormal range of the second film formation peak value.

[0164] ​​For example, as shown in FIG. 7 (the horizontal coordinate in FIG. 7 is the first film formation peak value, and the vertical coordinate is the second film formation peak value), in FIG. 7, the region defined by the three circles on the right side is the region where the target cluster is located, and the region defined by the circle on the left side is the region where the abnormal battery core cluster is located. The probability density range corresponding to each sample battery core within the range defined by any one of the three circles on the right side may be used as the target probability density range. For example, the probability density range corresponding to the sample battery core within the region defined by the outermost circle may be used as the target probability density range. The horizontal coordinate range of the circle on the left side may be used as the abnormal range of the first film formation peak value, and the vertical coordinate range of the circle on the left side may be used as the abnormal range of the second film formation peak value.

[0165] S608: The PLC receives the formation process data of the battery core to be detected that has been introduced.

[0166] S609: Obtain the first film formation peak value and the second film formation peak value of the battery core to be detected in the first stage from the formation process data.

[0167] S610: Use the final two-dimensional Gaussian model to calculate the first film formation peak value and the second film formation peak value of the battery core to be detected in the first stage, and obtain the probability density of the battery core to be detected.

[0168] S611: Determine whether the probability density of the battery core to be detected is within the target probability density range. If so, proceed to step S612; if not, proceed to step S613.

[0169] Exemplarily, the target probability density range may be a range starting from 0. At this time, by setting only one probability density threshold, it may be determined whether the probability density of the battery core to be detected is smaller than this probability density threshold. If it is smaller, it indicates that the probability density of the battery core to be detected is within the target probability density range, and proceed to step S612; if not, proceed to step S613.

[0170] S612: Determine that there is no abnormal water content in the battery core to be detected.

[0171] S613: Determine whether the first film formation peak value of the battery core to be detected is within the abnormal range of the first film formation peak value, and whether the second film formation peak value is within the abnormal range of the second film formation peak value. If both are within the range (that is, the first film formation peak value is within the abnormal range of the first film formation peak value, and the second film formation peak value is within the abnormal range of the second film formation peak value), go to step S6 14 ; otherwise, go to step S612.

[0172] S614: Mark the battery core to be detected and report the marking result to the industrial Internet.

[0173] It should be understood that in the embodiments of the present application, instead of making a judgment based on probability density, the first film formation peak value and the second film formation peak value in the first stage of the battery core to be directly detected are used as the two coordinate values of a coordinate point, and the battery core to be detected is converted into a coordinate point in the coordinate system shown in FIG. 7, and it may be determined whether this coordinate point is located within the circle on the left side of FIG. 7 (that is, instead of making a judgment on probability density, directly make the judgment in step S613). If it is not located, determine that there is no abnormal water content in the battery core to be detected; if it is located, determine that there is an abnormal water content in the battery core to be detected. At this time, the battery core to be detected may be marked and the marking result reported to the industrial Internet.

[0174] It should be further understood that the process shown in FIG. 6 substantially has two stages. Here, steps S601 to S607 are in the model construction stage, and steps S608 to S614 are in the battery core identification stage. After the final two-dimensional Gaussian model is constructed by steps S601 to S607, this final two-dimensional Gaussian model may be repeatedly applied, that is, steps S608 to S614 may be repeatedly executed for different battery cores to be detected.

[0175] According to the above method, it is possible to achieve the purpose of identifying a battery core with abnormal water content before mounting the battery core. At the same time, as a result of detection by experiments, this method has high robustness, few errors, and can have good effects in actual applications. The above solution does not require destroying the battery core, can realize the detection of abnormal water content for each battery core, and has high detection reliability.

[0176] Based on the same inventive concept, in the embodiments of the present application, an identification device 800 for abnormal battery cores and a model building device 900 are further provided. As shown in FIGS. 8 and 9, FIG. 8 shows an identification device for abnormal battery cores adopting the method shown in FIG. 2, and FIG. 9 shows a model building device adopting the method shown in FIG. 3. It should be understood that the specific functions of device 800 and device 900 may refer to the above description. To avoid repetition of the description, the detailed description is appropriately omitted here. Device 800 and device 900 include at least one software functional module that can be stored in a memory in the form of software or firmware or fixed in the operating systems of device 800 and device 900. Specifically, it is as follows.

[0177] Referring to FIG. 8, device 800 includes an identification module 801 for determining whether a battery core is an abnormal battery core based on target characteristic data of the battery core, where the target characteristic data includes characteristic data generated during the formation process that can distinguish an abnormal battery core from a normal battery core.

[0178] In one alternative embodiment of the embodiments of the present application, the target characteristic data includes characteristic data of the battery core affected by the electrolyte during the formation process.

[0179] In another alternative embodiment of the embodiments of the present application, the target characteristic data includes characteristic data of the battery core affected by the water content during the formation process.

[0180] In the above two alternative embodiments, the target feature data includes a first target parameter value when the parameter change first reaches a first process change value and a second target parameter value when the parameter change first reaches a second process change value in the process of collecting parameters in the first stage of the formation process, where the first process change value is different from the second process change value.

[0181] In the embodiments of the present application, the identification module 801 is specifically used to input the target feature data into a preset identification model to obtain an identification result as to whether the battery core is an abnormal battery core.

[0182] In the embodiments of the present application, the identification model is a two-dimensional Gaussian model.

[0183] In the embodiments of the present application, the identification module 801 is specifically used to input the target feature data into a two-dimensional Gaussian model to obtain the probability density of the battery core calculated by the two-dimensional Gaussian model, and when the probability density of the battery core is smaller than a preset probability density threshold, it is used to determine that the battery core is an abnormal battery core.

[0184] In the embodiments of the present application, the identification module 801 is specifically used to input the target feature data into a two-dimensional Gaussian model to obtain the probability density of the battery core calculated by the two-dimensional Gaussian model, and when the probability density of the battery core is smaller than a preset probability density threshold and the target feature data is within a preset feature interval, it is used to determine that the battery core is an abnormal battery core.

[0185] In the embodiments of the present application, the identification module 801 is specifically used to determine whether the battery core is an abnormal battery core based on the target feature data of the battery core in the formation process of the battery core.

[0186] In an embodiment of the present application, the apparatus 800 further includes a marking module for marking a battery core when the battery core is an abnormal battery core.

[0187] Referring to FIG. 9, the apparatus 900 includes a second acquisition module 901 for acquiring two types of target feature data of each sample battery core in the formation process, where the target feature data includes feature data that can distinguish an abnormal battery core from a normal battery core generated in the formation process, and each sample battery core includes a first sample battery core with an abnormality and a second sample battery core without an abnormality; and a construction module 902 for constructing a two-dimensional Gaussian model based on the two types of target feature data of each sample battery core.

[0188] In an alternative embodiment of the embodiment of the present application, the first sample battery core is a sample battery core with an abnormal electrolyte, and the target feature data includes feature data affected by the electrolyte in the battery core generated in the formation process.

[0189] In another alternative embodiment of the embodiment of the present application, the first sample battery core is a sample battery core with an abnormal water content, and the target feature data includes feature data affected by the water content in the battery core generated in the formation process.

[0190] In the above two alternative embodiments, the two types of target feature data include a first target parameter value when the parameter change first reaches a first process change value and a second target parameter value when the parameter change first reaches a second process change value in the process of collecting parameters in the first stage of the formation process, where the first process change value and the second process change value are different.

[0191] In the embodiments of the present application, the construction module 902 is specifically used to construct a preliminary two-dimensional Gaussian model based on two types of target feature data of all sample battery cores, and to construct a final two-dimensional Gaussian model based on the two types of target feature data of each sample battery core belonging to the target cluster in the preliminary two-dimensional Gaussian model, where the target cluster is a cluster of second sample battery cores indicating the absence of electrolyte abnormality in the preliminary two-dimensional Gaussian model.

[0192] In the above optional embodiment, the second acquisition module 901 is specifically used to acquire the target parameter value corresponding to the time when each sample battery core first reaches each preset different process change value during the formation process, identify the first process change value and the second process change value based on the target parameter values corresponding to the different process change values, and use the target parameter value corresponding to the first process change value and the target parameter value corresponding to the second process change value as two types of target feature data of each sample battery core, where the first process change value and the second process change value are the two process change values with the largest discrimination degree for the first sample battery core and the second sample battery core among the preset different process change values.

[0193] In the above optional embodiment, the second acquisition module 901 is specifically used to calculate the discrimination degree between the first sample battery core and the second sample battery core corresponding to the two different process change values based on the target parameter values corresponding to the two different process change values, and use the two different process change values corresponding to the maximum discrimination degree as the first process change value and the second process change value.

[0194] It should be understood that for the sake of brief description, some of the content described in the method part above will not be further described in the device part.

[0195] In an embodiment of the present application, an electronic device is further provided. Referring to FIG. 10, it includes a processor 1001 and a memory 1002. Here, The processor 1001 is used to execute one or more instructions stored in the memory 1002 to implement the method for identifying the abnormal battery core or to implement the model building method.

[0196] It should be noted that the processor 1001 and the memory 1002 may be connected via an internal communication bus, but are not limited thereto.

[0197] As can be understood, the structure shown in FIG. 10 is only schematic. The electronic device may further include more or fewer assemblies than those shown in FIG. 10, or may have a configuration different from that shown in FIG. 10. For example, the electronic device may further have devices such as a data input interface and a data output interface.

[0198] In an embodiment of the present application, the electronic device may be a device with data processing capabilities such as a PLC, a computer, a smartphone, a server, etc., and is not limited in the embodiments of the present application.

[0199] It should be noted that the PLC is a digital arithmetic controller for automation control having a microprocessor, and can load control instructions into and store them in the internal memory in real time and execute them. The PLC consists of functional units such as a microprocessor, an internal memory, an input / output interface, and a power supply. When the electronic device is a PLC, the processor 1001 is the microprocessor of the PLC, and the memory 1002 is the internal memory of the PLC.

[0200] Embodiments of the present application further provide a computer-readable storage medium, such as a flexible disk, an optical disk, a hard disk, a flash memory, a USB disk, an SD (Secure Digital Memory Card) card, an MMC (Multimedia Card) card, etc. One or more instructions for implementing the above steps are stored in this computer-readable storage medium, and these one or more instructions are executed by one or more processors to implement the above method for identifying an abnormal battery core or implement the above model construction method. This will not be further explained here.

[0201] Finally, it should be noted that the above embodiments are only for explaining the technical solutions of the present application and do not limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments or equivalently replace some or all of their technical features. These modifications or replacements do not depart from the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should be included in the scope of the claims and the specification of the present application. In particular, as long as there is no conflict in structure or steps, the technical features mentioned in each embodiment may be combined in any manner. The present application is not limited to the specific embodiments disclosed in the specification, but includes all technical solutions within the scope of the claims.

Claims

1. A method for identifying an abnormal battery core, comprising: determining whether the battery core is an abnormal battery core based on target characteristic data of the battery core, wherein: the target characteristic data includes characteristic data generated during the formation process and capable of distinguishing an abnormal battery core from a normal battery core; the determining whether the battery core is an abnormal battery core based on the target characteristic data of the battery core includes: inputting the target characteristic data into a preset identification model to obtain an identification result as to whether the battery core is an abnormal battery core. The method for identifying an abnormal battery core is characterized by the above.

2. The method for identifying an abnormal battery core according to claim 1, wherein the target characteristic data includes characteristic data affected by the electrolyte in the battery core generated during the formation process.

3. The method for identifying an abnormal battery core according to claim 1, wherein the target characteristic data includes characteristic data affected by the water content in the battery core generated during the formation process.

4. The target characteristic data includes: in the process of collecting parameters in the first stage of the formation process, a first target parameter value when the parameter change first reaches a first process change value, and a second target parameter value when the parameter change first reaches a second process change value, where the first process change value and the second process change value are different. The method for identifying an abnormal battery core according to claim 1 is characterized by the above.

5. The identification model is a two-dimensional Gaussian model. The method for identifying an abnormal battery core according to any one of claims 1 to 3 is characterized by the above.

6. Inputting the target feature data into a pre-set identification model to obtain an identification result as to whether the battery core is an abnormal battery core is inputting the target feature data into the two-dimensional Gaussian model to obtain the probability density of the battery core calculated by the two-dimensional Gaussian model, and when the probability density of the battery core is smaller than a pre-set probability density threshold value, determining that the battery core is an abnormal battery core. The method for identifying an abnormal battery core according to claim 5 is characterized by including the above steps.

7. Inputting the target feature data into a pre-set identification model to obtain an identification result as to whether the battery core is an abnormal battery core is inputting the target feature data into the two-dimensional Gaussian model to obtain the probability density of the battery core calculated by the two-dimensional Gaussian model, and when the probability density of the battery core is smaller than a pre-set probability density threshold value and the target feature data is within a pre-set feature interval, determining that the battery core is an abnormal battery core. The method for identifying an abnormal battery core according to claim 5 is characterized by including the above steps.

8. Determining whether the battery core is an abnormal battery core based on the target feature data of the battery core is including, in the formation process of the battery core, determining whether the battery core is an abnormal battery core based on the target feature data of the battery core. The method for identifying an abnormal battery core according to any one of claims 1 to 3 is characterized by including the above steps.

9. An identification device for an abnormal battery core with abnormal electrolyte, comprising an identification module for determining whether the battery core is an abnormal battery core based on the target feature data of the battery core, where the target feature data includes feature data generated in the formation process that can distinguish an abnormal battery core from a normal battery core. Determining whether the battery core is an abnormal battery core based on the target characteristic data of the battery core, includes inputting the target characteristic data into a preset identification model to obtain an identification result as to whether the battery core is an abnormal battery core, and an identification device for an abnormal battery core with an abnormal electrolyte, characterized in that.

10. An electronic device including a processor and a memory, wherein the processor is used to execute one or more instructions stored in the memory to implement the method for identifying an abnormal battery core according to any one of claims 1 to 4, and an electronic device characterized in that.

11. A computer-readable storage medium, in which one or more instructions are stored, and the instructions can be executed by a processor to implement the method for identifying an abnormal battery core according to any one of claims 1 to 4, and a computer-readable storage medium characterized in that.

Images