Battery classification method and device, electronic equipment and computer readable storage medium

Abstract

The invention is suitable for the technical field of battery classification, and provides a battery classification method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining the detection data of a battery; determining mechanism data of the battery according to the detection data, wherein the mechanism data is used for reflecting an attribute association relationship among different data in the detection data; and classifying the batteries according to the mechanism data. Through the method, the accuracy of the obtained classification result can be improved.

Description

Technical Field

[0001] The present application belongs to the technical field of battery classification, and in particular, relates to a battery classification method, device, electronic device and computer-readable storage medium. Background Art

[0002] At present, there are more and more types of equipment that use batteries as power, and different types of equipment have different application requirements for batteries.

[0003] In order to improve battery utilization and reduce environmental pollution, batteries that meet the application requirements of device B (the application requirements of device B for batteries are lower than those of device A) are usually screened out from batteries that do not meet the application requirements of device A, and the screened batteries are applied to device B to achieve cascade utilization of batteries.

[0004] In the existing methods, a decision tree is usually used to screen batteries. This method determines the classification of batteries by analyzing the characteristics of the batteries, but the classification results obtained by this method are still not accurate enough. Summary of the invention

[0005] The embodiments of the present application provide a battery classification method, device, electronic device and computer-readable storage medium, which can solve the problem of low accuracy of classification results obtained when classifying batteries using existing methods.

[0006] In a first aspect, an embodiment of the present application provides a battery classification method, comprising:

[0007] Obtain battery test data;

[0008] Determining mechanism data of the battery according to the detection data, wherein the mechanism data is used to reflect the attribute association relationship between different data in the detection data;

[0009] The battery is classified according to the mechanistic data.

[0010] After obtaining the test data of the battery, the mechanism data of the battery is first determined based on the test data, and then the battery is classified based on the mechanism data. Since the mechanism data can reflect the attribute association relationship between different data in the test data, and the battery's cascade test index needs to be analyzed by combining the correlation of different data, therefore, when the above method is used to classify the battery, the accuracy of the classification result can be improved.

[0011] Optionally, the acquiring the detection data of the battery includes:

[0012] For each battery in the same battery pack, obtaining detection data of the battery;

[0013] Determining the mechanism data of the battery according to the detection data includes:

[0014] Determining mechanism data of the battery pack according to the detection data of each battery;

[0015] The classifying the battery according to the mechanism data comprises:

[0016] The battery packs are classified according to the mechanism data of the battery packs.

[0017] Optionally, the acquiring the detection data of the battery includes:

[0018] The historical detection data of the battery is obtained from the cloud.

[0019] Optionally, after acquiring the detection data of the battery, the method further includes:

[0020] Eliminating abnormal data in the detection data;

[0021] Determining the mechanism data of the battery according to the detection data includes:

[0022] The mechanism data of the battery is determined based on the detection data from which abnormal data is eliminated.

[0023] Optionally, determining the mechanism data of the battery according to the detection data includes:

[0024] According to the detection data, the mechanism data of the battery in at least one of the following categories is determined respectively: a fault category, a health category, and a usage condition information category.

[0025] Optionally, the mechanism data on the fault category includes at least one of the following: fault type, fault frequency, usage time of the battery when the fault occurs, and correlation between different faults;

[0026] The mechanism data in the health category includes at least one of the following: battery health assessment and health decay rate;

[0027] The mechanism data in the usage condition information category includes at least one of the following: data used to reflect the characteristics of the impact on the battery during charging, data used to reflect the characteristics of the impact on the battery during discharging, and data used to reflect the characteristics of the impact on the battery during standing.

[0028] Optionally, classifying the battery according to the mechanism data includes:

[0029] Performing standardization on the mechanism data;

[0030] The battery is classified according to the standardized mechanism data.

[0031] Optionally, classifying the battery according to the standardized mechanism data includes:

[0032] Clustering the standardized mechanism data, and obtaining the clustering result as the classification result of the battery;

[0033] or,

[0034] The mechanism data after standardization is identified using a preset classification model to obtain a classification result output by the classification model, and the classification result is used as the classification result of the battery, wherein the classification model is trained using the mechanism data with classification label results.

[0035] In a second aspect, an embodiment of the present application provides a battery classification device, comprising:

[0036] A detection data acquisition module, used to obtain battery detection data;

[0037] A mechanism data determination module, used to determine the mechanism data of the battery according to the detection data, wherein the mechanism data is used to reflect the attribute association relationship between different data in the detection data;

[0038] A battery classification module is used to classify the battery according to the mechanism data.

[0039] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the computer program.

[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0041] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes any one of the methods described in the first aspect.

[0042] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0044] Figure 1It is a flowchart of a battery classification method provided by an embodiment of the present application;

[0045] Figure 2 It is a structural schematic diagram of a battery classification device provided by an embodiment of the present application;

[0046] Figure 3 It is a structural schematic diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0047] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0048] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0049] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0050] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the phrases "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. appearing in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways.

[0051] As the battery usage time increases, the battery will gradually age, and the power provided by the aged battery will gradually fail to meet the application requirements of the device. In order to improve the utilization of batteries, batteries retired from devices with higher power requirements are usually used in devices with lower power requirements, that is, the utilization of batteries is improved through the cascade application of batteries.

[0052] Before reusing batteries, retired batteries need to be classified to select batteries that are suitable for use in other devices, thereby reducing the probability of failure of the selected batteries in subsequent applications of other devices.

[0053] When the decision tree method is used to classify and screen batteries, since the method classifies the batteries according to each data of the batteries respectively (for example, the batteries are classified once according to their appearance, or the batteries are classified at a first level according to their appearance, and then classified at a next level according to their capacity), that is, the method does not consider the correlation between the attributes of different data at each classification, and the battery's cascade detection indicators (such as battery life, battery capacity, etc.) need to be analyzed together by comprehensively analyzing the correlation of different data. Therefore, when the decision tree is used to screen batteries, the accuracy of the classification results obtained is low.

[0054] In order to improve the accuracy of battery classification results, an embodiment of the present application provides a battery classification method.

[0055] In this classification method, after obtaining the test data of the battery, the mechanism data that can reflect the attribute association relationship between different data in the test data is first determined based on the test data, and then the battery is classified based on the mechanism data.

[0056] The battery classification method provided in the embodiment of the present application is described below with reference to the accompanying drawings.

[0057] Figure 1 A schematic diagram of a battery classification method provided in an embodiment of the present application is shown, and the details are as follows:

[0058] S11, obtaining battery detection data.

[0059] The battery here is a battery that no longer meets the application requirements of a certain device, that is, the battery is a battery that may be used in a cascade application.

[0060] In the embodiment of the present application, the detection data of the battery includes at least one of the following: voltage, current, temperature, insulation resistance, battery charge state, and battery usage time.

[0061] It should be pointed out that the detection data here may be the historical detection data of the battery, that is, it is not the data of detecting the battery again after retirement. For example, it may be the detection data when the battery is used in a device with high application requirements for the battery.

[0062] Of course, the test data may also be data obtained by testing the battery again after retirement, which is not limited here.

[0063] Optionally, after obtaining the test data of the battery, the test data may be preprocessed, wherein the preprocessing includes but is not limited to: converting the format of the test data into a specified format, performing dimensionality reduction processing on the test data, performing statistics on the test data, etc.

[0064] S12, determining the mechanism data of the battery according to the detection data, wherein the mechanism data is used to reflect the attribute association relationship between different data in the detection data.

[0065] The mechanism data here includes one or more data. For example, assuming that the detection data includes the voltage of the battery during charging and the fully charged voltage, the mechanism data of the battery is determined in the following manner: if it is determined that the voltage of the battery during charging is greater than the fully charged voltage, it is determined that the battery has an overcharge fault, and at this time, the mechanism data of the battery includes: overcharge.

[0066] S13, classifying the battery according to the mechanism data.

[0067] Specifically, the mechanism standards corresponding to different classifications can be preset first. After the mechanism data of a battery is determined, the mechanism data is matched with different mechanism standards, and the battery is classified according to the matching results. Of course, classification can also be performed in other ways, which are not limited here. It only needs to be performed according to the mechanism data of the battery.

[0068] In the embodiment of the present application, after obtaining the test data of the battery, the mechanism data of the battery is first determined according to the test data, and then the battery is classified according to the mechanism data. Since the mechanism data can reflect the attribute association relationship between different data in the above test data, and the battery's cascade test index needs to be analyzed together by comprehensively analyzing the association of different data, therefore, when the above method is used to classify the battery, the accuracy of the classification result can be improved.

[0069] In some embodiments, the above S11 includes:

[0070] For each battery in the same battery pack, the detection data of the battery is obtained.

[0071] Correspondingly, the above S12 includes:

[0072] The mechanism data of the battery pack is determined based on the detection data of each battery.

[0073] Correspondingly, the above S13 includes:

[0074] The battery packs are classified according to the mechanism data of the battery packs.

[0075] In the embodiment of the present application, the battery pack can be an original battery pack that has not been reorganized (i.e., a battery pack obtained from a manufacturer), or a new battery pack that has been reorganized (i.e., a new battery pack that is obtained by reorganizing the single cells in a battery pack that has been retired from a device). However, whether it is a battery pack obtained before reorganization or a battery pack obtained after reorganization, it is necessary to obtain the test data of these battery packs to determine the mechanism data of the battery pack based on the obtained test data.

[0076] For example, assuming that battery pack A used in device A no longer meets the application requirements of device A, it is necessary to analyze whether battery pack A can be used in a cascade manner. At this time, the detection data of each battery in battery pack A can be obtained separately, and then the mechanism data of battery pack A can be determined based on these detection data. Finally, battery pack A can be classified according to the mechanism data of battery pack A.

[0077] For another example, assume that battery pack A used in device A no longer meets the application requirements of device A, and battery pack B used in device B no longer meets the application requirements of device B. After disassembling battery pack A, two single cells, battery A1 and battery A2, are obtained. After disassembling battery pack B, two single cells, battery B1 and battery B2, are obtained. If it is desired to combine battery A1 and battery B1 into a new battery pack (assuming it is battery pack C), the test data of battery A1 and battery B1 in battery pack C are obtained respectively, and then the mechanism data of battery pack C is determined based on these test data, and finally the battery pack C is classified based on the mechanism data of battery pack C.

[0078] In the embodiments of the present application, considering that some scenarios directly use battery packs instead of single batteries to provide power to the application equipment, the battery packs are directly classified instead of independently classifying each battery in the battery pack. This can ensure the accuracy of the classification results, thereby ensuring that new devices that are more compatible with the battery pack can be found later based on the obtained classification results.

[0079] In some embodiments, considering that the battery management system (BMS) collects relevant data of the batteries in the system during use, such as voltage, current, temperature, insulation resistance, battery state of charge, and battery usage time, and each BMS uploads the collected data to the cloud, therefore, the detection data of the battery during historical use (i.e., before the last device was retired) can be obtained from the cloud. At this time, the above S11 includes:

[0080] The above battery history detection data is obtained from the cloud.

[0081] Specifically, the detection data of the battery collected by the corresponding BMS can be found from the cloud according to the unique identifier of the battery.

[0082] In the embodiment of the present application, since the detection data is historical detection data obtained from the cloud, that is, there is no need to re-perform various tests on each battery to obtain the corresponding detection data, the workload required for battery classification can be greatly reduced, thereby improving the battery classification speed and reducing the cost required for classification.

[0083] In some embodiments, after considering the above S11, it also includes:

[0084] Eliminate abnormal data from the above detection data.

[0085] Correspondingly, the above S12 includes:

[0086] The mechanism data of the battery is determined based on the detection data after excluding abnormal data.

[0087] The above-mentioned abnormal data includes: data whose value is not within the corresponding preset range, such as excluding abnormal data in the detection data obtained from the cloud.

[0088] In the embodiment of the present application, it is considered that different types of detection data usually need to meet the corresponding value ranges, for example, the current detection data needs to meet the value range of the current of the battery, and the voltage detection data needs to meet the value range of the voltage of the battery. Therefore, when it is determined that a certain type of data does not meet the value range of that type, it is indicated that the data is abnormal data and is eliminated. After the abnormal data in the detection data is eliminated, the mechanism data of the battery is determined based on the remaining detection data, so the accuracy of the detection data involved in the calculation of the mechanism data is guaranteed, thereby ensuring the accuracy of the classification results determined based on the mechanism data.

[0089] After obtaining the detection data, it is necessary to determine the corresponding mechanism data based on the detection data. In some embodiments, considering that the cascade utilization of batteries requires a comprehensive analysis of various indicators, and the mechanism data of different categories may have different effects on the classification of batteries, therefore, determining the corresponding mechanism data according to the category is conducive to improving the accuracy of the subsequent classification results. At this time, the above S12 includes:

[0090] According to the detection data, the mechanism data of the battery in at least one of the following categories are determined respectively: fault category, health category and usage condition information category.

[0091] Among them, all categories of mechanism data of a battery can reflect the portrait of the battery, and these mechanism data can be called the portrait data of the battery.

[0092] In the embodiment of the present application, the mechanism data of the fault category refers to the category related to the battery fault, such as the mechanism data of different battery faults, the association between faults, etc.

[0093] Optionally, the mechanism data on the above-mentioned fault category includes at least one of the following: fault type, fault frequency, usage time of the above-mentioned battery when the fault occurs, and correlation between different faults.

[0094] Among them, the fault types include overcharge, over discharge, overheat, short circuit, etc. Optionally, each fault type is distinguished by fault level, and the fault level includes minor and major, etc. Of course, in actual situations, multiple levels of distinction can also be made, which is not limited here.

[0095] The fault frequency refers to the number of times each battery has different fault types. For example, if there are two types of faults in a battery: fault A and fault B, the number of times the battery has fault A is counted, and the number of times the battery has fault B is counted.

[0096] The battery usage time when the fault occurs refers to the time the battery has been used when the fault occurs, which is tracked and recorded for each type of fault. It should be noted that since the same type of fault may occur multiple times, the usage time when the fault occurs each time is recorded. Furthermore, the usage time corresponding to the same type can be recorded in the form of a list for easy query.

[0097] The correlation between different faults refers to the correlation between faults of different fault types. For example, two faults of different types occurring within a preset interval are determined to be related faults. The preset interval can be set to 5 to 10 minutes. Of course, the preset interval can also be set according to actual conditions, which will not be described here.

[0098] In the embodiment of the present application, the mechanism data of the health category refers to the mechanism data used to indicate the health of the battery. Optionally, the mechanism data of the health category includes at least one of the following: the health assessment degree and health decay rate of the battery.

[0099] The battery health assessment refers to the health assessment obtained by evaluating the battery health based on the detection data before the current moment. The health assessment can be pre-assessed by the cloud, such as determining the battery health assessment according to the following two methods:

[0100] (1) Obtain data such as the voltage and power of the battery during the charging process, generate an IC curve (i.e., a curve of current changing over time) of the battery based on the acquired data, determine the parameters of the corresponding characteristic peak (such as peak width, peak position, and peak height) from the IC curve, and then estimate the health assessment of the battery based on the parameters of the characteristic peak.

[0101] (2) Sample data with state of health (SOH) labels are used to train a health assessment prediction model, and the trained health assessment prediction model is then used to process the characteristics of the battery (the characteristics correspond to the type of sample data) to obtain the health assessment of the battery.

[0102] In the embodiment of the present application, the mechanism data of the use condition information category refers to the mechanism data corresponding to the battery in the working conditions of charging, discharging, and resting. Optionally, the mechanism data in the above-mentioned use condition information category includes at least one of the following: data used to reflect the characteristics of the battery during the charging process, data used to reflect the characteristics of the battery during the discharging process, and data used to reflect the characteristics of the battery during the resting process.

[0103] Among them, the data used to reflect the characteristics of the battery during the charging process include: fast charging ratio (i.e. the ratio of the charging amount charged by fast charging to the charging amount charged by all charging methods), fast charging frequency, etc. These data can be expressed in the form of a characteristic sequence. Of course, in actual situations, other data of the battery during the charging process can also be obtained, as long as the data has an impact on the battery.

[0104] The data used to reflect the characteristics of the impact on the battery during the discharge process include: the number of large current discharges, the depth of discharge (DoD), etc. These data can be expressed in the form of a characteristic sequence.

[0105] The data used to reflect the characteristics of the impact on the battery during the static process include: high state of charge (SOC) static.

[0106] In the embodiment of the present application, since different categories of mechanism data reflect different information about the battery, determining more categories of mechanism data is equivalent to determining a larger amount of information. Therefore, when the battery is classified according to the mechanism data with a larger amount of information, it is beneficial to improve the accuracy of the battery classification results.

[0107] After the mechanism data is determined, the battery is classified according to the mechanism data. In some embodiments, considering that the processing of standardized data is more efficient and accurate than that of unstandardized data, the mechanism data may be standardized before the battery is classified. In this case, the above S13 includes:

[0108] A1. Standardize the above mechanism data.

[0109] The standardization processing here includes: setting the format of the mechanism data to conform to a preset format, and / or setting the structure of each mechanism data to conform to a preset structure, etc.

[0110] For example, assume that the battery includes three categories of mechanism data: fault category, health category, and usage condition information category. M The data of each sub-category include the following: fault type (represented by f_i), fault frequency (represented by cn_i), the battery usage time when the fault occurs (represented by ft_lst), and the correlation of different faults (represented by corr_f); the mechanism data of the health category (represented by life M The data of the battery health assessment (represented by soh_i) and health decay rate (represented by soh_v_i); the mechanism data of the operating condition information category (represented by status M The three categories of mechanism data are standardized by generating matrices corresponding to the mechanism data of each category respectively, and then generating matrices corresponding to all the mechanism data of the battery according to the matrices corresponding to the three categories of mechanism data (also called profile matrix using profile). M express):

[0111] The matrix corresponding to the mechanism data of the fault category:

[0112] fault M =[f_i cn_i ft_lst corr_f].

[0113] The matrix corresponding to the mechanism data of the health category: life M =[soh_i soh_v_i].

[0114] The matrix corresponding to the mechanism data of the operating condition information category is:

[0115] status M =[chg_fet dhg_fet std_fet].

[0116] The final generated image matrix:

[0117] A2. Classify the above batteries according to the above mechanism data after standardization.

[0118] In the embodiment of the present application, since the mechanism data is standardized before the batteries are classified, it is beneficial to improve the accuracy and efficiency of the classification.

[0119] In some embodiments, the battery classification may be performed by clustering or by model processing. In this case, the standardized mechanism data is clustered, and the obtained clustering result is used as the classification result of the battery.

[0120] When clustering batteries, you can choose unsupervised methods such as K-Means or density-based spatial clustering of applications with noise (DBSCAN) for clustering. If you use K-Means for clustering, you can first determine the number of categories (assuming it is K) and the cluster centers of different categories, then calculate the distance between the battery mechanism data and the K cluster centers, and finally classify the battery into the class corresponding to the cluster center with the smallest distance. The formula used for distance calculation is as follows:

[0121]

[0122] In the above formula, i is the battery to be calculated, j is the initial cluster center (or initial battery state) of a preset category, and p is a variable. When p is 2, the above formula is the calculation formula for the Euclidean distance. Calculate the distance L from each battery to the initial battery state of each category p , repeat the calculation until the iteration termination condition is met. Among them, the total distance minimization is usually used as the iteration termination condition, and the category with the shortest distance is the category of battery i.

[0123] Optionally, the number of categories corresponding to K-Means can be set based on experience. For example, considering that the scenarios of battery cascade applications are usually: passenger cars (such as cars) → commercial vehicles (such as trucks) → two-wheeled or three-wheeled vehicles → energy storage (such as power banks, charging cabinets, etc.), the number of categories can be set to 4.

[0124] Optionally, the number of categories k corresponding to K-Means can also be determined by the elbow method or the Gap statistic method: Set Gap(K) = E(log D x )-log D k .

[0125] Among them, K is the number of categories, D k is the loss function (or the sum of squared deviations), E(log D k ) refers to logD k The expectation of E(log D k ) can be generated through Monte Carlo simulation. Specifically, first, in the area where the original sample (i.e., the mechanism data of the battery to be classified) is located, random samples as many as the number of original samples are randomly generated according to uniform distribution, and K-Means is performed on this random sample, and the corresponding D is calculated. k This is repeated many times. For example, after 20 calculations, 20 logD values ​​can be obtained. k For these 20 log D k Taking the average value, we get E(log D k ). According to log D k and E(log D k ) can calculate Gap(K), and the K corresponding to the maximum value of Gap(K) is the optimal K.

[0126] In the embodiment of the present application, when the batteries are classified by clustering, since the clustering algorithm is simple and converges quickly, the classification of the batteries can be quickly achieved by the above method.

[0127] In some embodiments, the above-mentioned A2 includes: using a preset classification model to identify the above-mentioned mechanism data after standardization processing, and obtaining the classification result output by the above-mentioned classification model, and the above-mentioned classification result is used as the classification result of the above-mentioned battery, wherein the above-mentioned classification model is trained using the mechanism data with classification label results.

[0128] Specifically, the classification model to be trained is trained in advance using the mechanism data with classification label results until the classification results output by the trained classification model meet the conditions for stopping training. The classification label results here are used to indicate the category to which the corresponding mechanism data belongs.

[0129] After a classification model is trained, the mechanism data of the battery to be classified is input into the classification model, and the classification result output by the classification model is obtained.

[0130] In the embodiment of the present application, since the generalization ability of the model is relatively strong when performing classification, classifying the batteries in the above manner can improve the accuracy of the obtained classification results.

[0131] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0132] Corresponding to the battery classification method described in the above embodiment, Figure 2 A structural block diagram of a battery classification device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0133] Reference Figure 2 The battery classification device 2 includes: a detection data acquisition module 21, a mechanism data determination module 22, and a battery classification module 23. Among them:

[0134] The detection data acquisition module 21 is used to acquire the detection data of the battery.

[0135] The mechanism data determination module 22 is used to determine the mechanism data of the battery according to the detection data. The mechanism data is used to reflect the attribute association relationship between different data in the detection data.

[0136] The battery classification module 23 is used to classify the above-mentioned battery according to the above-mentioned mechanism data.

[0137] In the embodiment of the present application, after obtaining the test data of the battery, the mechanism data of the battery is first determined according to the test data, and then the battery is classified according to the mechanism data. Since the mechanism data can reflect the attribute association relationship between different data in the above test data, and the battery's cascade test index needs to be analyzed together by comprehensively analyzing the association of different data, therefore, when the above method is used to classify the battery, the accuracy of the classification result can be improved.

[0138] In some embodiments, when acquiring the detection data of the battery, the detection data acquisition module 21 is specifically used to:

[0139] For each battery in the same battery pack, the detection data of the battery is obtained.

[0140] Correspondingly, when the mechanism data determination module 22 determines the mechanism data of the battery according to the detection data, it is specifically used to:

[0141] The mechanism data of the battery pack is determined based on the detection data of each battery.

[0142] Correspondingly, when the battery classification module 23 classifies the battery according to the mechanism data, it is specifically used to:

[0143] The battery packs are classified according to the mechanism data of the battery packs.

[0144] In some embodiments, when acquiring the detection data of the battery, the detection data acquisition module 21 is specifically used to:

[0145] The above battery history detection data is obtained from the cloud.

[0146] In some embodiments, the battery classification device 2 provided in the embodiment of the present application further includes:

[0147] Also includes:

[0148] The abnormal data elimination module is used to eliminate abnormal data in the detection data after obtaining the detection data of the battery.

[0149] Correspondingly, when the mechanism data determination module 22 determines the mechanism data of the battery according to the detection data, it is specifically used to:

[0150] The mechanism data of the battery is determined based on the detection data after excluding abnormal data.

[0151] In some embodiments, when the mechanism data determination module 22 determines the mechanism data of the battery according to the detection data, it is specifically used to:

[0152] According to the detection data, the mechanism data of the battery in at least one of the following categories are determined respectively: fault category, health category and usage condition information category.

[0153] In some embodiments,

[0154] The mechanism data on the above-mentioned fault category includes at least one of the following: fault type, fault frequency, usage time of the above-mentioned battery when the fault occurs, and correlation between different faults;

[0155] The mechanism data in the above health category includes at least one of the following: battery health assessment and health decay rate;

[0156] The mechanism data in the above-mentioned usage condition information category includes at least one of the following: data used to reflect the characteristics of the impact on the battery during the charging process, data used to reflect the characteristics of the impact on the battery during the discharging process, and data used to reflect the characteristics of the impact on the battery during the static process.

[0157] In some embodiments, the battery classification module 23 includes:

[0158] The standard processing unit is used to perform standard processing on the above mechanism data.

[0159] A classification unit is used to classify the above-mentioned battery according to the above-mentioned mechanism data after standardization.

[0160] In some embodiments, when the classification unit classifies the battery according to the standardized mechanism data, the classification unit specifically includes:

[0161] Clustering the standardized mechanism data, and obtaining the clustering result as the classification result of the battery;

[0162] or,

[0163] The mechanism data after standardization is identified using a preset classification model to obtain a classification result output by the classification model, and the classification result is used as the classification result of the battery, wherein the classification model is trained using the mechanism data with classification label results.

[0164] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0165] Figure 3 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3 As shown, the electronic device 3 of this embodiment includes: at least one processor 30 ( Figure 3 Only one processor is shown in the figure), a memory 31, and a computer program 32 stored in the above-mentioned memory 31 and executable on at least one of the above-mentioned processors 30, wherein the above-mentioned processor 30 implements the steps in any of the above-mentioned method embodiments when executing the above-mentioned computer program 32.

[0166] The electronic device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will appreciate that Figure 3 It is only an example of the electronic device 3 and does not constitute a limitation on the electronic device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0167] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0168] In some embodiments, the memory 31 may be an internal storage unit of the electronic device 3, such as a hard disk or memory of the electronic device 3. In other embodiments, the memory 31 may also be an external storage device of the electronic device 3, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 3. Further, the memory 31 may also include both an internal storage unit of the electronic device 3 and an external storage device. The memory 31 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0169] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0170] An embodiment of the present application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps in any of the above-mentioned method embodiments when executing the computer program.

[0171] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0172] An embodiment of the present application provides a computer program product. When the computer program product runs on an electronic device, the electronic device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0173] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera / electronic device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0174] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0175] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0176] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0177] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0178] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A battery classification method, characterized in that: include: Obtain battery test data; Determining mechanism data of the battery according to the detection data, wherein the mechanism data is used to reflect the attribute association relationship between different data in the detection data; The battery is classified according to the mechanistic data.

2. The battery classification method according to claim 1, characterized in that: The obtaining of the battery detection data includes: For each battery in the same battery pack, obtaining detection data of the battery; Determining the mechanism data of the battery according to the detection data includes: Determining mechanism data of the battery pack according to the detection data of each battery; The classifying the battery according to the mechanism data comprises: The battery packs are classified according to the mechanism data of the battery packs.

3. The battery classification method according to claim 1 or 2, characterized in that: The obtaining of the battery detection data includes: The historical detection data of the battery is obtained from the cloud.

4. The battery classification method according to claim 1 or 2, characterized in that: After obtaining the detection data of the battery, the method further includes: Eliminating abnormal data in the detection data; Determining the mechanism data of the battery according to the detection data includes: The mechanism data of the battery is determined based on the detection data from which abnormal data is eliminated.

5. The battery classification method according to claim 1, characterized in that: Determining the mechanism data of the battery according to the detection data includes: According to the detection data, the mechanism data of the battery in at least one of the following categories is determined respectively: a fault category, a health category, and a usage condition information category.

6. The battery classification method according to claim 5, characterized in that: The mechanism data on the fault category includes at least one of the following: fault type, fault frequency, usage time of the battery when the fault occurs, and correlation between different faults; The mechanism data in the health category includes at least one of the following: battery health assessment and health decay rate; The mechanism data in the usage condition information category includes at least one of the following: data used to reflect the characteristics of the impact on the battery during charging, data used to reflect the characteristics of the impact on the battery during discharging, and data used to reflect the characteristics of the impact on the battery during standing.

7. The battery classification method according to any one of claims 1 to 6, characterized in that: The classifying the battery according to the mechanism data comprises: Standardizing the mechanism data; The battery is classified according to the standardized mechanism data.

8. The battery classification method according to claim 7, characterized in that: The classifying of the battery according to the standardized mechanism data comprises: Clustering the standardized mechanism data, and obtaining the clustering result as the classification result of the battery; or, A preset classification model is used to identify the standardized mechanism data to obtain a classification result output by the classification model, and the classification result is used as the classification result of the battery, wherein the classification model is trained using the mechanism data with classification label results.

9. A battery sorting device, characterized in that: include: A detection data acquisition module, used to obtain battery detection data; A mechanism data determination module, used to determine the mechanism data of the battery according to the detection data, wherein the mechanism data is used to reflect the attribute association relationship between different data in the detection data; A battery classification module is used to classify the battery according to the mechanism data.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images