A method, device, and medium for determining a consistency screening result of a battery

Abstract

This invention discloses a method, apparatus, device, and medium for determining the consistency screening results of batteries. The method includes: for each battery to be inspected, performing multi-feature extraction to obtain a multi-feature set corresponding to the battery; for each feature in the multi-feature sets corresponding to all batteries to be inspected, using a descriptive statistical algorithm to calculate the feature value of the feature in the multi-feature sets corresponding to all batteries to be inspected, obtaining a candidate threshold for the feature; performing detection number screening and threshold segment screening on the candidate thresholds corresponding to the features to obtain a target threshold for the feature; and for each battery to be inspected, determining the consistency screening result of the battery to be inspected based on the feature values ​​in the multi-feature sets corresponding to the battery and the target thresholds corresponding to each feature. This method improves the screening accuracy of the consistency screening of batteries to be inspected, and can adaptively determine the target threshold for each feature before performing precise consistency screening of batteries.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of detection technology, and in particular to a method, apparatus, device and medium for determining the consistency screening results of batteries. Background Technology

[0002] In the large-scale application of lithium-ion batteries, battery consistency is a core factor determining the system's usable capacity, cycle life, and safety margins. Consistency screening is essentially outlier detection based on the battery's excitation response characteristics. This technology is mainly used to eliminate abnormal batteries, delay performance drops caused by the "bottleneck effect," and reduce the risk of thermal runaway.

[0003] Existing battery consistency screening methods either target a single feature or use a uniform threshold for screening multiple features. However, these methods can lead to batteries bypassing potential inconsistencies during the consistency screening process, resulting in an increased missed selection rate. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and medium for determining the consistency screening results of batteries, which improves the screening accuracy of batteries to be inspected and can also perform fast and accurate consistency screening of batteries based on quickly determining the target threshold corresponding to each feature.

[0005] In a first aspect, embodiments of the present invention provide a method for determining the consistency screening results of batteries, the method comprising: For each battery to be tested, multiple features are extracted to obtain the set of multiple features corresponding to the battery to be tested.

[0006] For each feature in the multi-feature set corresponding to all batteries to be tested, a descriptive statistical algorithm is used to calculate the feature value of the feature in the multi-feature set corresponding to all batteries to be tested, and the candidate threshold corresponding to the feature is obtained.

[0007] The candidate thresholds corresponding to the features are filtered by the number of detections and the threshold segments, respectively, to obtain the target thresholds corresponding to the features. For each battery to be tested, the consistency screening result of the battery to be tested is determined based on the feature values ​​in the multi-feature set corresponding to the battery to be tested and the target thresholds corresponding to each feature.

[0008] The battery consistency screening result determination method provided in this invention first extracts multiple consistency screening features from the batteries to be inspected, obtaining a multi-feature set that can reflect the condition of each battery from multiple perspectives. This provides a foundation for comprehensive multi-angle and multi-feature screening of the batteries to be inspected in subsequent consistency screening tests. Furthermore, for each consistency screening feature, a descriptive statistical algorithm is used to quantify the data trend of the extracted data of all batteries to be inspected under that feature, and an appropriate candidate threshold is selected based on the data trend. This provides a statistically accurate quantitative basis for determining appropriate dynamic thresholds for each feature in this consistency screening process. By using detection count screening and threshold segment screening methods to filter candidate thresholds for each feature to obtain the target threshold, a suitable dynamic threshold is accurately determined for each feature. Furthermore, candidate thresholds are screened from both the detection count and threshold segment perspectives. This not only removes abnormal thresholds from abnormal detection counts but also removes thresholds that are prone to being missed or misscreened based on the density of feature values ​​across all batteries. This solves the problems in existing battery consistency screening. By adaptively determining a more accurate target threshold (detection threshold) for each feature, it ensures that the target threshold corresponding to each feature will not cause batteries to bypass potential inconsistent features during consistency screening, thus improving the screening accuracy of batteries to be inspected. It also enables fast and accurate consistency screening of batteries based on the rapid determination of the target threshold corresponding to each feature.

[0009] Secondly, embodiments of the present invention also provide a battery consistency screening result determination device, the device comprising: The extraction module is used to extract multiple features from each battery to be tested, thereby obtaining a set of multiple features corresponding to the battery to be tested.

[0010] The calculation module is used to calculate the feature value of each feature in the multi-feature set corresponding to all batteries to be tested using descriptive statistical algorithms, and obtain the candidate threshold corresponding to the feature.

[0011] The determination module is used to perform detection number screening and threshold segment screening on the candidate thresholds corresponding to the features to obtain the target thresholds corresponding to the features. For each battery to be tested, the consistency screening result of the battery to be tested is determined based on the feature values ​​in the multi-feature set corresponding to the battery to be tested and the target thresholds corresponding to each feature.

[0012] Thirdly, embodiments of the present invention also provide an electronic device, the electronic device comprising: At least one processor; and A memory that is communicatively connected to at least one processor; wherein, The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the battery consistency screening result determination method according to any embodiment of the present invention.

[0013] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute the battery consistency screening result determination method of any embodiment of the present invention.

[0014] Fifthly, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the battery consistency screening result determination method of any embodiment of the present invention.

[0015] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the processor of the battery consistency screening result determination device, or it may be packaged separately from the processor of the battery consistency screening result determination device; this application does not impose any limitations on this.

[0016] The descriptions of the second, third, fourth, and fifth aspects in this application can be referred to the detailed description of the first aspect; and the beneficial effects of the descriptions of the second, third, fourth, and fifth aspects can be referred to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0017] In this application, the name of the device for determining the consistency screening results of the aforementioned batteries does not constitute a limitation on the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. As long as the function of each device or functional module is similar to that of this application, it falls within the scope of the claims of this application and its equivalents.

[0018] These or other aspects of this application will become more readily apparent in the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating a method for determining the consistency screening results of batteries, provided as an embodiment of the present invention; Figure 2A flowchart of another method for determining the consistency screening results of a battery provided in an embodiment of the present invention; Figure 3 Example diagrams of various features extracted from the battery under test provided in embodiments of the present invention; Figure 4 Example diagrams of intermediate thresholds corresponding to various features provided in embodiments of the present invention; Figure 5 A structural diagram of a battery consistency screening result determination device provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0021] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0022] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0023] The terms “initial” and “target” in the specification and drawings of this application are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a specific order of objects.

[0024] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0025] Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the figures. The process can correspond to a method, function, procedure, subroutine, subroutine, etc. Moreover, embodiments and features in the embodiments of the present invention can be combined with each other without conflict.

[0026] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0027] In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0028] Figure 1 This is a flowchart illustrating a method for determining the consistency screening results of batteries according to an embodiment of the present invention. This embodiment is applicable to the situation of performing consistency screening on batteries of the same model to be tested. This method can be executed by a battery consistency screening result determination device, which can be implemented in hardware and / or software and can be configured in an electronic device. (Continue to refer to...) Figure 1 This embodiment specifically includes: S101. For each battery to be tested, perform multi-feature extraction to obtain the multi-feature set corresponding to the battery to be tested.

[0029] The batteries to be tested are those from the same batch for which consistency screening is required. In this embodiment, the batteries to be tested are mainly of the same model. The batteries are not limited to ternary lithium batteries, but can also be lithium iron phosphate batteries, sodium-ion batteries, lead-acid batteries, and lithium-sulfur batteries, etc. The screening features are multiple consistency screening features used for battery consistency screening. The multi-feature set contains the feature value corresponding to each consistency screening feature.

[0030] Specifically, in a battery consistency screening process, multiple batteries of the same model are selected as screening targets, i.e., batteries to be inspected. Furthermore, in one implementation, all features that can be used for battery consistency screening are selected as the features to be extracted for the batteries to be inspected. In another implementation, multiple highly demanded features are selected as the features to be extracted for the batteries to be inspected, based on the screening requirements and battery usage needs for this one-time battery screening. After determining the features to be extracted, these features are extracted for each battery to be inspected, and the extracted data (feature values) corresponding to all features after feature extraction are used as the multi-feature set for the battery to be inspected.

[0031] S102. For each feature in the multi-feature set corresponding to all batteries to be tested, use a descriptive statistical algorithm to calculate the feature value of the feature in the multi-feature set corresponding to all batteries to be tested, and obtain the candidate threshold corresponding to the feature.

[0032] Descriptive statistical algorithms are used to process the acquired sample data to obtain statistics that characterize the trend and dispersion of the sample data. In this embodiment, descriptive statistical algorithms include, but are not limited to, calculating the mean, variance, standard deviation, and range. The feature values ​​are the feature values ​​obtained after extracting the features of the battery under test.

[0033] Specifically, to quantify the extraction status of all batteries under inspection under a single feature, the feature values ​​extracted for each battery under inspection corresponding to the same feature can be statistically calculated from the multi-feature set corresponding to all batteries under inspection. This is achieved using descriptive statistical algorithms to obtain the statistical data for each feature. Therefore, in practical implementation, for each consistency screening feature, the feature value of that feature can be determined from the multi-feature set corresponding to each battery under inspection, and descriptive statistical algorithms, such as those for calculating the mean and standard deviation, can be used to calculate the feature value of that feature for all batteries under inspection, obtaining the corresponding statistical parameters. Furthermore, since these statistical parameters quantify the distribution of batteries under inspection under that feature from different perspectives, multiple candidate thresholds can be derived based on these statistical parameters. For example, using the mean as a benchmark, one candidate threshold for that feature can be obtained; alternatively, using the standard deviation, quantiles, etc., as benchmarks, other candidate thresholds for that feature can be obtained.

[0034] In this embodiment, multiple consistency screening features are first extracted from the batteries under test to obtain a multi-feature set that can reflect the condition of each battery from multiple perspectives. This provides a foundation for comprehensive multi-angle and multi-feature screening of the batteries under test in subsequent consistency screening detection. Furthermore, for each consistency screening feature, descriptive statistical algorithms are used to quantify the data trend of the extracted data of all batteries under test under that feature, and appropriate candidate thresholds are selected based on the data trends. This provides a statistically accurate quantitative basis for determining appropriate dynamic thresholds for each feature in this consistency screening process.

[0035] S103. Detection count screening and threshold segment screening are performed on the candidate thresholds corresponding to the features to obtain the target thresholds corresponding to the features. For each battery to be tested, the consistency screening result of the battery to be tested is determined based on the feature values ​​in the multi-feature set corresponding to the battery to be tested and the target thresholds corresponding to each feature.

[0036] The detection count refers to the number of inconsistent batteries detected that do not meet the threshold requirements when screening batteries using candidate thresholds. Detection count screening is a method of filtering candidate thresholds using the detection count as a screening criterion. Threshold segment screening is a method of filtering candidate thresholds based on segment conditions (such as segment density, segment density ratio, etc.) that the threshold segments must meet, which are composed of multiple candidate thresholds. The consistency screening result is used to characterize which feature detected inconsistency for each battery under inspection in this consistency screening.

[0037] Specifically, after using descriptive statistical algorithms to statistically calculate the feature values ​​of each feature of the battery under test, each feature can have multiple candidate thresholds. Then, detection count filtering and threshold segment filtering methods can be used to filter the candidate thresholds for each feature. The final candidate thresholds remaining after filtering can be used as the target threshold for that feature. Furthermore, for each battery under test, it can be determined whether the feature value of each feature in the multi-feature set meets the target threshold corresponding to that feature, thereby determining the consistency screening result for that battery under test.

[0038] In this embodiment, candidate thresholds for each feature are selected using both detection count screening and threshold segment screening to obtain the target threshold. This achieves accurate determination of a suitable dynamic threshold for each feature. Furthermore, candidate thresholds are screened from both the detection count and threshold segment perspectives. This not only removes abnormal thresholds from abnormal detection counts but also removes thresholds that are prone to being missed or mis-screened based on the density of feature values ​​across all batteries. This solves the problems in existing battery consistency screening. By adaptively determining a more accurate target threshold (detection threshold) for each feature, it ensures that the target threshold for each feature will not cause the battery to bypass potential inconsistent features during consistency screening. This improves the screening accuracy of the batteries to be inspected and enables fast and accurate consistency screening of batteries based on the rapid determination of the target threshold for each feature.

[0039] The battery consistency screening result determination method provided in this invention first extracts multiple consistency screening features from the batteries to be inspected, obtaining a multi-feature set that can reflect the condition of each battery from multiple perspectives. This provides a foundation for comprehensive multi-angle and multi-feature screening of the batteries to be inspected in subsequent consistency screening tests. Furthermore, for each consistency screening feature, a descriptive statistical algorithm is used to quantify the data trend of the extracted data of all batteries to be inspected under that feature, and an appropriate candidate threshold is selected based on the data trend. This provides a statistically accurate quantitative basis for determining appropriate dynamic thresholds for each feature in this consistency screening process. By using detection count screening and threshold segment screening methods to filter candidate thresholds for each feature to obtain the target threshold, a suitable dynamic threshold is accurately determined for each feature. Furthermore, candidate thresholds are screened from both the detection count and threshold segment perspectives. This not only removes abnormal thresholds from abnormal detection counts but also removes thresholds that are prone to being missed or misscreened based on the density of feature values ​​across all batteries. This solves the problems in existing battery consistency screening. By adaptively determining a more accurate target threshold (detection threshold) for each feature, it ensures that the target threshold corresponding to each feature will not cause batteries to bypass potential inconsistent features during consistency screening, thus improving the screening accuracy of batteries to be inspected. It also enables fast and accurate consistency screening of batteries based on the rapid determination of the target threshold corresponding to each feature.

[0040] Figure 2 This is a flowchart of another method for determining the consistency screening result of a battery according to an embodiment of the present invention. This embodiment is based on the above embodiment and specifies the steps and optional embodiments of obtaining the multi-feature set corresponding to the battery to be tested, obtaining the candidate threshold corresponding to the feature, obtaining the target threshold corresponding to the feature, and determining the consistency screening result of the battery to be tested. Furthermore, since existing screening methods usually rely on only a single type of feature, it is difficult to comprehensively measure the consistency of the battery from multiple scale dimensions, and potentially inconsistent batteries may be missed. At the same time, screening strategies based on multiple types of features face the key challenge of threshold setting: if a uniform judgment threshold is used for all features, inconsistent batteries may be missed on some feature dimensions, while excessive rejection may occur on other dimensions, misjudging batteries that are actually consistent as inconsistent. To solve the above problems, in this embodiment, the method may specifically include: S201. Determine dynamic screening features based on the consistency screening requirements and usage requirements of all batteries to be tested.

[0041] Among these, the consistency screening requirement refers to the user's key requirement for the consistency screening of the batteries to be inspected. The usage requirement refers to the battery requirements of the process when the screened consistent batteries are applied to subsequent processes.

[0042] Specifically, since the purpose of each consistency screening of the batteries to be inspected is to remove abnormal inconsistent batteries and to group batteries with similar performance into the same battery pack as much as possible, in practice, in addition to using all available features as dynamic screening features, the dynamic screening features for this screening can also be determined based on the consistency screening requirements of this screening and the battery usage requirements for the subsequent process of using the screened batteries.

[0043] For example, if the purpose of the consistency screening of the batteries under test is to eliminate abnormally inconsistent batteries, then features such as open-circuit voltage, internal resistance, capacity, self-discharge rate, charge-discharge curve characteristics, impedance spectrum, and incremental capacity can be selected as dynamic screening features. If the purpose of the consistency screening of the batteries under test is to group batteries with similar performance into the same battery pack as much as possible, then the usage requirements can be determined based on the performance parameters of the batteries required for the battery pack to be constructed later, and thus the corresponding dynamic screening features can be obtained.

[0044] Optionally, in this embodiment, common consistency screening features include: open-circuit voltage, capacity, internal resistance, self-discharge rate, coulombic efficiency, charge-discharge curve, constant current-constant voltage time ratio, hysteresis, pulse excitation time constant, incremental capacity, battery model parameters, impedance spectrum, and power spectral density, etc.

[0045] S202. For each battery to be tested, each feature in the dynamic screening features is used as the current feature to be extracted. The features of the battery to be tested are extracted sequentially to obtain the multi-feature set corresponding to the battery to be tested.

[0046] Among them, the features to be extracted are the features currently waiting to be extracted.

[0047] Specifically, after obtaining the dynamic screening features, each feature can be numbered for convenient recording later. Then, for each battery to be tested, the various dynamic screening features (i.e., the features to be extracted) of the battery to be tested can be extracted based on existing methods for extracting different features of the battery, obtaining the feature value corresponding to each feature. Finally, all features and their corresponding feature values ​​are used as a multi-feature set corresponding to the battery to be tested.

[0048] In this embodiment, not only can all features of the battery under test be extracted as the basis for subsequent battery consistency screening, but dynamic screening features can also be determined according to actual consistency screening requirements and usage needs. Feature extraction is performed on the dynamic screening features of the battery under test, realizing the extraction of multiple features of the battery under test based on actual needs. This not only determines the feature values ​​of the battery under test in a comprehensive manner based on battery screening needs, but also saves time and effort in feature extraction, achieving accurate feature extraction of the battery under test.

[0049] S203. For each feature in the multi-feature set corresponding to all batteries to be tested, calculate the mean, standard deviation and range of the feature values ​​corresponding to the feature in the multi-feature set corresponding to all batteries to be tested in sequence, and obtain the standard deviation multiple of the feature based on the standard deviation and range.

[0050] Here, the mean is the arithmetic average of a set of sample data, representing the central tendency of the sample data. The standard deviation represents the dispersion of each sample data relative to the mean. The range is the maximum value minus the minimum value in a set of samples, representing the overall numerical fluctuation range of the samples. Furthermore, in this embodiment, a set of sample data corresponds to the feature values ​​of all the batteries to be tested under a single feature.

[0051] Specifically, for each feature in the multi-feature set corresponding to all batteries under test, first determine the feature value corresponding to that feature for each battery under test. Then, calculate the mean, standard deviation, and range of all feature values ​​respectively. Finally, the standard deviation multiple of the feature can be calculated based on the standard deviation and range.

[0052] For example, the standard deviation multiple of a feature is obtained based on the standard deviation and the range, including: Calculate the ratio of the range to the standard deviation, and round the range up to obtain the standard deviation multiple of the feature.

[0053] The rounding up option is used to find the smallest integer greater than or equal to the real number.

[0054] Specifically, you can first calculate the ratio of the range to the standard deviation, that is, divide the range by the standard deviation, and then round up the resulting ratio to obtain the standard deviation multiple K of the feature.

[0055] S204. Determine the candidate threshold corresponding to the feature based on the standard deviation multiple, mean, and standard deviation.

[0056] Specifically, in practice, candidate screening thresholds can be generated based on the 3-sigma (3σ) algorithm, standard deviation multiples, mean, and standard deviation logic. Alternatively, they can be generated as follows: For example, determining the candidate threshold corresponding to a feature based on the standard deviation multiple, mean, and standard deviation includes: (a) Using the multiple of the standard deviation as the maximum value, we obtain an integer sequence that ends at the maximum value.

[0057] Specifically, the standard deviation multiple St can be used as the maximum value of the interval, and 1 can be used as the minimum value of the interval to obtain the interval [1, St]. Then, an integer sequence is generated from 1 to St with a preset number as the interval. In practice, an integer sequence containing St values ​​can be generated from 1 to St with 1 as the preset number. For example, if St is 3, the integer sequence is 1, 2, 3.

[0058] (ii) For each number in the integer sequence, calculate the boundary threshold corresponding to the number using the number, mean and standard deviation, and use the boundary thresholds corresponding to all numbers as candidate thresholds for the features.

[0059] In this embodiment, the boundary threshold is divided into an upper boundary threshold and a lower boundary threshold.

[0060] Specifically, for each number K in the integer sequence (such as 1, 2, and 3 in the example above, which can all replace K), the lower boundary threshold can be obtained by subtracting K from the standard deviation, and the upper boundary threshold can be obtained by adding K to the standard deviation. Therefore, we can finally obtain 2×St candidate thresholds consisting of St upper boundary thresholds and St lower boundary thresholds.

[0061] In this embodiment, the feature numbers corresponding to all batteries under each feature are calculated sequentially. This allows for the quantification of the feature values ​​of the batteries under each feature, considering their concentration level, overall dispersion, and maximum fluctuation range. This provides a basis for selecting appropriate thresholds for the feature from multiple perspectives. Furthermore, the calculated standard deviation multiple measures the degree of extreme value range relative to the overall dispersion. Based on this, an integer sequence is obtained, which serves as the basis for quantifying the distribution of batteries under each feature. Finally, each number in the integer sequence is used as a benchmark to sequentially determine the upper and lower boundary thresholds, resulting in candidate thresholds. This allows for the reasonable division of different upper and lower boundary thresholds based on the adaptively generated dynamic candidate thresholds, combined with the overall situation and dispersion of the feature values ​​extracted from the batteries under each feature. This provides an adaptive threshold for reducing missed and incorrect screenings.

[0062] S205. Determine the maximum number of detections based on the total number of batteries to be tested and the detection ratio, and determine the actual number of detections corresponding to each candidate threshold based on the candidate threshold corresponding to the feature and the feature value corresponding to the feature in the multi-feature set corresponding to all batteries to be tested.

[0063] In this embodiment, the number of detected samples mainly refers to those samples that are greater than the upper boundary threshold or less than the lower boundary threshold (i.e., the feature values ​​corresponding to the batteries under test). The total number of batteries under test is the total number of batteries under test. The detection ratio is set by the user based on experience; in this embodiment, it can be 0.09%. The maximum number of detected samples is the maximum limit for the number of samples corresponding to the candidate thresholds.

[0064] Specifically, in practice, determining the maximum detection count can be achieved in two ways. One approach is to directly set the maximum detection count based on user experience. Another approach is to determine the maximum detection count based on the total number of batteries to be tested and the detection ratio. For example, the total number of batteries to be tested can be directly multiplied by the detection ratio to obtain the maximum detection count. Simultaneously, for each candidate threshold corresponding to a feature, it can be determined whether the feature values ​​corresponding to all batteries to be tested are detected at the candidate threshold, thus obtaining the actual detection count corresponding to the candidate threshold.

[0065] For example, in this embodiment, feature values ​​greater than the upper boundary threshold or less than the lower boundary threshold are detected. Therefore, for each upper boundary threshold in the candidate thresholds, feature values ​​greater than the upper boundary threshold are determined to obtain the actual number of detections corresponding to the upper boundary threshold. Similarly, for each lower boundary threshold in the candidate thresholds, feature values ​​less than the lower boundary threshold are determined to obtain the actual number of detections corresponding to the lower boundary threshold.

[0066] S206. Candidate thresholds with actual detection counts equal to zero or greater than the maximum detection count are removed to obtain intermediate thresholds. Then, intermediate thresholds are filtered a second time based on the number of feature values ​​in the segments formed by adjacent intermediate thresholds, the minimum density of the segments, and the density ratio interval, to obtain the filtered intermediate thresholds.

[0067] Specifically, after obtaining the actual detection count corresponding to each candidate threshold, candidate thresholds with an actual detection count of zero can be eliminated, as can candidate thresholds with an actual detection count greater than the maximum detection count, thus obtaining intermediate thresholds. Furthermore, based on the number of feature values ​​in the segments formed by adjacent intermediate thresholds, and the minimum density and density ratio interval of the segments, a secondary screening of the intermediate thresholds is performed to obtain the screened intermediate thresholds, which can be: For all intermediate upper boundary thresholds, the intermediate upper boundary thresholds are filtered based on the number of feature values ​​in the segment formed between two adjacent intermediate upper boundary thresholds, the minimum density of the segment, and the density ratio interval, to obtain the filtered intermediate upper boundary thresholds; and for all intermediate lower boundary thresholds, the intermediate lower boundary thresholds are filtered based on the number of feature values ​​in the segment formed between two adjacent intermediate lower boundary thresholds, the minimum density of the segment, and the density ratio interval, to obtain the filtered intermediate lower boundary thresholds.

[0068] The minimum fragment density is the minimum fragment density limit that a fragment composed of two adjacent intermediate boundary thresholds must satisfy. In this embodiment, the minimum fragment density can be half of the maximum detection count. The actual density ratio is the ratio of the upper fragment density (the number of feature values ​​of a fragment composed of the reference boundary threshold and adjacent boundary thresholds far from the mean) to the lower fragment density (the number of feature values ​​of a fragment composed of the reference boundary threshold and adjacent boundary thresholds close to the mean) to a boundary threshold with upper and lower boundary thresholds as a reference. The density ratio interval is the interval that limits the value of the actual density ratio. In this embodiment, the density ratio interval is generally set to an interval near 1, optionally [0.7, 1].

[0069] Specifically, both the upper and lower boundary thresholds use the same filtering method: A certain middle boundary threshold (which must have adjacent middle boundary thresholds above and below it) is used as a benchmark. Another adjacent middle boundary threshold is selected, and the area between them is considered a segment (if the other middle boundary threshold is far from the mean, the area between them is considered the upper segment; if the other middle boundary threshold is close to the mean, the area between them is considered the lower segment). The number of feature values ​​falling within this segment (i.e., the feature value interval corresponding to the segment formed by the benchmark middle boundary threshold and the other middle boundary threshold) is determined. This number of feature values ​​can be used as the (upper / lower) segment density. Furthermore, it is determined whether both the upper and lower segment densities are greater than the minimum segment density. If so, it is necessary to further determine whether the benchmark threshold needs to be removed based on the density ratio described below; otherwise, the middle boundary threshold is directly retained. Furthermore, for each retained intermediate boundary threshold, the actual density ratio corresponding to the intermediate boundary threshold is obtained by dividing the density of the upper segment by the density of the lower segment, and it is determined whether the actual density ratio corresponding to the intermediate boundary threshold is within the density ratio range; if it is, the intermediate boundary threshold is used as the intermediate threshold; if it is not, the intermediate boundary threshold is removed.

[0070] Optionally, for intermediate boundary thresholds where there are no other adjacent intermediate boundary thresholds on at least one side above or below, the following steps can be taken to determine them: For the intermediate boundary threshold closest to the mean, if there are no other intermediate boundary thresholds above / below it, the fragment density below it is set to -1; for the intermediate boundary threshold furthest from the mean, if there are no other intermediate boundary thresholds above / below it, the fragment density above it is the number of detections for that intermediate boundary threshold. In this way, the above-mentioned screening based on fragment density and fragment density ratio can be continued for these intermediate boundary thresholds.

[0071] S207. For the intermediate thresholds after filtering, determine the target threshold corresponding to the feature based on the number of intermediate thresholds and the mean value corresponding to the feature.

[0072] Specifically, after filtering all thresholds to obtain the intermediate thresholds, the final target thresholds are determined for the upper / lower regions of the mean (the regions where the upper / lower boundary thresholds are located). If the number of intermediate thresholds is greater than 1, the intermediate threshold closest to the mean corresponding to the feature can be directly selected as the target threshold for that feature; if it is equal to 1, the intermediate threshold is directly used as the target threshold for that feature; if it is less than 1, i.e., zero, the target threshold for the upper / lower regions is determined to be empty.

[0073] After the above filtering, the remaining thresholds for each feature have three possibilities: 0, 1, and 2. 0 indicates that both the upper and lower boundary thresholds for the feature are removed, suggesting that the feature is relatively concentrated and may not have inconsistent cells. 1 indicates that among the remaining thresholds for the feature, either the upper or lower boundary threshold is 1, suggesting that inconsistent cells may exist at the upper or lower boundary of the feature. 2 indicates that the feature has one threshold at both the upper and lower boundaries (i.e., one upper boundary threshold and one lower boundary threshold), suggesting that inconsistent cells may exist at both the upper and lower boundaries of the feature.

[0074] In this embodiment, candidate thresholds are first screened based on the maximum number of detections for each candidate threshold. This removes thresholds with excessive detections, reducing the risk of false screening and ensuring that thresholds closer to most consistent cells are removed, thus avoiding excessive false screening. Furthermore, for the thresholds adjacent to the baseline threshold, screening is performed sequentially based on the minimum density and density ratio range. Screening the minimum density of the intermediate thresholds identifies thresholds that may be located within inconsistent cells (outliers), avoiding significant missed screening. Limiting the density ratio range of the intermediate thresholds preserves thresholds close to the boundary between consistent and inconsistent cells (outlier segmentation points).

[0075] S208. Each feature whose corresponding target threshold is not empty is taken as a valid feature. For each battery to be tested, the consistency screening result corresponding to the battery to be tested is determined according to the feature value of the valid feature in the multi-feature set corresponding to the battery to be tested and the target threshold corresponding to the valid feature.

[0076] Specifically, the target threshold corresponding to each feature determined according to the above steps may be either empty or not empty. In this embodiment, if the target threshold corresponding to a feature is empty, then the feature is invalid; if the target threshold corresponding to a feature is not empty, then the feature is valid. At this time, for each battery to be tested, whether the battery to be tested is an inconsistent battery can be determined based on the feature value of each valid feature in the multi-feature set corresponding to the battery and the target threshold corresponding to that valid feature. That is, samples with values ​​greater than the upper boundary threshold or less than the lower boundary threshold are detected inconsistent batteries. Furthermore, the valid features that detect inconsistent batteries for the battery to be tested are used as detection features, and the number of times inconsistent batteries are detected is recorded. Finally, the detection features and the number of detections are used as the consistency screening result corresponding to the battery to be tested.

[0077] Optionally, in this embodiment, the consistency screening result output this time may include, in addition to the consistency screening result for each battery to be tested, the effective features determined above and the target threshold value corresponding to the effective features.

[0078] Optionally, a practical example is provided to simply illustrate the consistency screening process of the batteries under test in this embodiment: Using 6000 lithium iron phosphate batteries (actually 60000, but reduced for clarity in illustrations) with a rated capacity of 40 Ah as the batteries to be tested, 81 selectable features were extracted for each battery, including open-circuit voltage, capacity, internal resistance, self-discharge rate, coulombic efficiency, charge-discharge curve, constant current / constant voltage time ratio, hysteresis, pulse excitation time constant, incremental capacity, battery model parameters, impedance spectrum, and power spectral density. In practice, multiple features can be selected for extraction as needed. Based on the total number of 6000 batteries tested, the maximum detection count Fn was determined to be 60, the minimum density Dm to be 30, and the density ratio range Dr to be [0.7, 1]. Each feature was then numbered, and subsequently referred to as Feature 1, Feature 2, etc. Figure 3 As shown, Figure 3 These are example diagrams illustrating the features extracted from the battery under test according to embodiments of the present invention. Figure 3The example shown only includes features 1 through 12. The horizontal axis of the graph for each feature represents the number of each battery under test, totaling 6000. The vertical axis represents the extracted feature values ​​(feature values) for each battery under test. The black dots represent the feature values ​​extracted for each battery under that feature. For each feature, taking feature 1 as an example, the mean, standard deviation, and range of the feature values ​​extracted for feature 1 from all batteries under test are calculated: 2519.7, 420.8, and 2921.9. Following the formula for calculating the standard deviation multiple, the standard deviation multiple is St = 11. Eleven K values ​​are generated at equal intervals based on the interval [1, St] = [1, 11]: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]. Each K value is then substituted into the lower boundary threshold calculation formula to obtain 22 candidate thresholds. For these 22 candidate thresholds, the effective features can be selected as features 3, 4, 5, 6, 8, 9, 10, and 12 using the screening method described above; and the target thresholds for the effective features are: {Feature 3: [-124.1], Feature 4: [135.7], ..., Feature 12: [3229.4, 3214.3]}. Finally, based on the effective features and their corresponding target thresholds, consistency screening detection can be performed on each battery to be inspected, resulting in consistency screening results such as {Sample 1 ID: [Number of detections: 3, Detected features: [Feature 3, Feature 5, Feature 10]], ...}.

[0079] And, such as Figure 4 As shown, Figure 4 Example diagrams of intermediate thresholds corresponding to various features provided in embodiments of the present invention. Figure 4 The example still only shows examples from features 1 to 12. Taking feature 1 as an example, in addition to black dots, multiple horizontal lines (partial candidate thresholds) have been added to the figure, each line representing a candidate threshold. Further, the line above the mean in the figure is the upper boundary threshold, and the line below the mean is the lower boundary threshold. If the middle line of the upper boundary threshold (the dashed line in the upper boundary threshold) is used as the baseline threshold, the segment between the baseline threshold and the lower line (the dashed line in the upper boundary threshold) is the lower segment, and the segment between the baseline threshold and the upper line (the dotted line in the upper boundary threshold) is the upper segment; similarly, if the middle line of the lower boundary threshold (the dashed line in the lower boundary threshold) is used as the baseline threshold, the segment between the baseline threshold and the lower line (the dotted line in the upper boundary threshold) is the upper segment, and the segment between the baseline threshold and the upper line (the dashed line in the upper boundary threshold) is the lower segment. The segment density is the number of black dots falling into the upper / lower segment. And, in Figure 4 In the data, some features contain solid black lines, which represent the target threshold (adaptive detection threshold) obtained after filtering.

[0080] Figure 5 A structural diagram of a battery consistency screening result determination device provided in an embodiment of the present invention is shown below. Figure 5 As shown, the device includes: The extraction module 501 is used to perform multi-feature extraction on each battery to be tested, and obtain the multi-feature set corresponding to the battery to be tested. The calculation module 502 is used to calculate the feature value of each feature in the multi-feature set corresponding to all batteries to be tested using a descriptive statistical algorithm, so as to obtain the candidate threshold corresponding to the feature. The determination module 503 is used to perform detection number screening and threshold segment screening on the candidate thresholds corresponding to the features to obtain the target thresholds corresponding to the features. For each battery to be tested, the consistency screening result of the battery to be tested is determined according to the feature values ​​in the multi-feature set corresponding to the battery to be tested and the target thresholds corresponding to each feature.

[0081] Based on the above embodiments, the extraction module 501 is specifically used for: Based on the consistency screening requirements and usage requirements of all batteries to be inspected, dynamic screening features are determined; for each battery to be inspected, each feature in the dynamic screening features is used as the current feature to be extracted, and features are extracted sequentially for the battery to be inspected to obtain a multi-feature set corresponding to the battery to be inspected.

[0082] Based on the above embodiments, the calculation module 502 is specifically used for: For all batteries to be tested, the mean, standard deviation and range of the feature values ​​corresponding to the features in the multi-feature set are calculated in sequence, and the standard deviation multiple of the feature is obtained based on the standard deviation and range; the candidate threshold corresponding to the feature is determined based on the standard deviation multiple, mean and standard deviation.

[0083] Based on the above embodiments, the standard deviation multiple of the feature is obtained according to the standard deviation and range. The calculation module 502 is specifically used for: Calculate the ratio of the range to the standard deviation, and round the range up to obtain the standard deviation multiple of the feature.

[0084] Based on the above embodiments, the candidate threshold corresponding to the feature is determined according to the standard deviation multiple, mean, and standard deviation. The calculation module 502 is specifically used for: The maximum value is obtained by taking the multiple of the standard deviation as the maximum value. For each number in the integer sequence, the boundary threshold corresponding to the number is calculated using the number, mean and standard deviation. The boundary thresholds corresponding to all numbers are used as candidate thresholds for the feature.

[0085] Based on the above embodiments, the candidate thresholds corresponding to the features are screened by the number of detections and by threshold fragments to obtain the target thresholds corresponding to the features. The determination module 503 is specifically used for: The maximum detection count is determined based on the total number of batteries to be tested and the detection ratio. The actual detection count for each candidate threshold is determined based on the candidate threshold corresponding to the feature and the feature value corresponding to the feature in the multi-feature set corresponding to all batteries to be tested. Candidate thresholds with an actual detection count equal to zero or greater than the maximum detection count are removed to obtain intermediate thresholds. The intermediate thresholds are then further filtered based on the number of feature values ​​in the segments formed by adjacent intermediate thresholds, the minimum density of the segments, and the density ratio interval to obtain the filtered intermediate thresholds. For the filtered intermediate thresholds, the target threshold corresponding to the feature is determined based on the number of intermediate thresholds and the mean value corresponding to the feature.

[0086] Based on the above embodiments, for each battery to be tested, the consistency screening result of the battery to be tested is determined according to the feature values ​​in the multi-feature set corresponding to the battery and the target threshold corresponding to each feature. The determination module 503 is specifically used for: Each feature whose corresponding target threshold is not empty is taken as a valid feature. For each battery to be tested, the consistency screening result corresponding to the battery to be tested is determined based on the feature value of the valid feature in the multi-feature set corresponding to the battery to be tested and the target threshold corresponding to the valid feature.

[0087] The battery consistency screening result determination device provided in the embodiments of the present invention can execute the battery consistency screening result determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0088] It is worth noting that in the embodiments of the battery consistency screening result determination device described above, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0089] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 6 A block diagram is shown of an exemplary electronic device 11 suitable for implementing embodiments of the present invention. Figure 6 The electronic device 11 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0090] like Figure 6As shown, the electronic device 11 is represented in the form of a general-purpose computing electronic device. The components of the electronic device 11 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0091] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0092] Electronic device 11 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 11, including volatile and non-volatile media, removable and non-removable media.

[0093] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Electronic device 11 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 6 Not shown; usually referred to as a "hard drive"). Although Figure 6 As not shown, disk drives for reading and writing to removable non-volatile disks (e.g., "floppy disks") and optical disc drives for reading and writing to removable non-volatile optical discs (e.g., CD-ROMs, DVD-ROMs, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0094] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0095] Electronic device 11 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with electronic device 11, and / or with any device that enables electronic device 11 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, electronic device 11 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. Figure 6 As shown, network adapter 20 communicates with other modules of electronic device 11 via bus 18. It should be understood that, although... Figure 6 As not shown, other hardware and / or software modules may be used in conjunction with electronic device 11, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0096] The processing unit 16 executes various functional applications and page displays by running programs stored in the system memory 28, such as implementing the battery consistency screening result determination method provided in this embodiment. Of course, those skilled in the art will understand that the processor can also implement the technical solutions of the battery consistency screening result determination method provided in any embodiment of the present invention.

[0097] This invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements, for example, the battery consistency screening result determination method provided in this invention.

[0098] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0099] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0100] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0101] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the method provided in any embodiment of this invention.

[0102] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0103] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0104] Furthermore, the acquisition, storage, use, and processing of data in the technical solution of this invention all comply with the relevant provisions of national laws and regulations.

[0105] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for determining the consistency screening results of batteries, characterized in that, The method includes: For each battery to be tested, multiple features are extracted to obtain a set of multiple features corresponding to the battery to be tested. For each feature in the multi-feature set corresponding to all batteries to be tested, a descriptive statistical algorithm is used to calculate the feature value of the feature in the multi-feature set corresponding to all batteries to be tested, and the candidate threshold corresponding to the feature is obtained. The candidate thresholds corresponding to the features are filtered by the number of detections and the threshold segments, respectively, to obtain the target thresholds corresponding to the features. For each battery to be tested, the consistency screening result of the battery to be tested is determined according to the feature values ​​in the multi-feature set corresponding to the battery to be tested and the target thresholds corresponding to each feature.

2. The method according to claim 1, characterized in that, For each battery to be tested, a multi-feature extraction process is performed to obtain a multi-feature set corresponding to the battery to be tested, including: Dynamic screening features are determined based on the consistency screening requirements and usage requirements of all batteries to be tested. For each battery to be tested, features are extracted sequentially using each feature in the dynamic screening features as the current feature to be extracted, to obtain a multi-feature set corresponding to the battery to be tested.

3. The method according to claim 1, characterized in that, The step of using descriptive statistical algorithms to calculate the feature values ​​of the feature in the multi-feature set corresponding to all batteries to be tested, and obtaining the candidate threshold corresponding to the feature, includes: For all batteries under test, the mean, standard deviation and range of the feature values ​​corresponding to the features in the multi-feature set are calculated sequentially, and the standard deviation multiple of the feature is obtained based on the standard deviation and the range. The candidate threshold corresponding to the feature is determined based on the standard deviation multiple, the mean, and the standard deviation.

4. The method according to claim 3, characterized in that, The step of obtaining the standard deviation multiple of the feature based on the standard deviation and the range includes: Calculate the ratio of the range to the standard deviation, and round the ratio up to obtain the standard deviation multiple of the feature.

5. The method according to claim 3, characterized in that, Determining the candidate threshold corresponding to the feature based on the standard deviation multiple, the mean, and the standard deviation includes: Using the standard deviation multiple as the maximum value, an integer sequence ending at the maximum value is obtained; For each number in the integer sequence, a boundary threshold corresponding to the number is calculated using the number, the mean, and the standard deviation, and the boundary thresholds corresponding to all numbers are used as candidate thresholds corresponding to the feature.

6. The method according to claim 1, characterized in that, The step of performing detection count filtering and threshold segment filtering on the candidate thresholds corresponding to the feature to obtain the target threshold corresponding to the feature includes: The maximum number of detections is determined based on the total number of batteries to be tested and the detection ratio, and the actual number of detections corresponding to each candidate threshold is determined based on the candidate threshold corresponding to the feature and the feature value corresponding to the feature in the multi-feature set corresponding to all batteries to be tested. Candidate thresholds whose actual detection count is equal to zero or greater than the maximum detection count are eliminated to obtain intermediate thresholds. Then, intermediate thresholds are further filtered based on the number of feature values ​​in the segments formed by adjacent intermediate thresholds, the minimum density of the segments, and the density ratio range to obtain filtered intermediate thresholds. For the intermediate thresholds after filtering, the target threshold corresponding to the feature is determined based on the number of intermediate thresholds and the mean value corresponding to the feature.

7. The method according to claim 1, characterized in that, For each battery to be tested, the consistency screening result of the battery to be tested is determined based on the feature values ​​in the multi-feature set corresponding to the battery and the target threshold corresponding to each feature, including: Each feature whose corresponding target threshold is not empty is taken as a valid feature. For each battery to be tested, the consistency screening result corresponding to the battery to be tested is determined according to the feature value of the valid feature in the multi-feature set corresponding to the battery to be tested and the target threshold corresponding to the valid feature.

8. A device for determining the consistency screening results of batteries, characterized in that, The device includes: The extraction module is used to perform multi-feature extraction on each battery to be tested, and obtain the multi-feature set corresponding to the battery to be tested. The calculation module is used to calculate the feature value of each feature in the multi-feature set corresponding to all batteries under test using a descriptive statistical algorithm, so as to obtain the candidate threshold corresponding to the feature. The determination module is used to perform detection number screening and threshold segment screening on the candidate thresholds corresponding to the features to obtain the target thresholds corresponding to the features, and for each battery to be tested, determine the consistency screening result of the battery to be tested based on the feature values ​​in the multi-feature set corresponding to the battery to be tested and the target thresholds corresponding to each feature.

9. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the battery consistency screening result determination method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method for determining the consistency screening results of batteries as described in any one of claims 1 to 7.

Images