Method and device for monitoring operation state of battery pack and storage medium

Abstract

The embodiment of the invention provides a method and device for monitoring the running state of a battery pack and a storage medium. The method comprises the following steps: acquiring real-time charging data of a to-be-tested battery pack, wherein the to-be-tested battery pack comprises a plurality of single batteries; based on the real-time charging data, static voltage consistency parameters of the multiple single batteries during initial charging and dynamic voltage consistency parameters of the multiple single batteries during the charging process are determined; based on the static voltage consistency parameter, the dynamic voltage consistency parameter and an estimation parameter, estimating an operation state index used for measuring the degree that the battery pack to be tested deviates from a normal working state, wherein the estimation parameter is predetermined based on voltage consistency data of a plurality of battery packs; and in response to the operation state index exceeding a predetermined threshold, determining that the operation state of the to-be-detected battery pack is abnormal, the predetermined threshold being predetermined based on the estimation parameter.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of power batteries, and more particularly to methods, devices, and computer-readable storage media for monitoring the operating status of a battery pack. Background Art

[0002] As the energy supply system of new energy vehicles, the monitoring, management and intervention of the system status of the power battery pack are crucial to ensure the range and safety. At present, the consistency between the single cells contained in the power battery pack is the main means of monitoring the battery operation status. Poor consistency not only affects the power output and endurance performance of the battery pack, but also affects the operating safety and service life of the battery pack. From different measurement angles, the consistency of the power battery pack can include multiple indicators, such as voltage consistency, capacity consistency, battery state of charge (SOC) consistency, internal resistance consistency and temperature consistency. The current battery consistency detection algorithm mainly starts from the above dimensions, pursuing a consistency detection algorithm with stronger adaptability, faster calculation speed, more accurate results and higher reliability. For the lithium iron phosphate power battery system, its voltage curve characteristics have a long platform voltage segment, that is, its voltage does not change much in a large SOC range (for example, the SOC range of 30% to 90%). This range is the most commonly used range for batteries. The platform voltage segment in this range will make it difficult to estimate the capacity consistency and SOC consistency, while the differences in internal resistance consistency and temperature consistency are not significant in themselves, which poses a great challenge to the construction of the consistency algorithm of the lithium iron phosphate power battery system. Summary of the invention

[0003] Embodiments of the present disclosure provide a method, an apparatus, and a computer-readable storage medium for monitoring an operating status of a battery pack.

[0004] In a first aspect of the present disclosure, a method for monitoring the operating status of a battery pack is provided, comprising: acquiring real-time charging data of a battery pack to be tested, the battery pack to be tested comprising a plurality of single cells; determining, based on the real-time charging data, static voltage consistency parameters of the plurality of single cells during initial charging and dynamic voltage consistency parameters during the charging process; estimating an operating status indicator for measuring the degree to which the battery pack to be tested deviates from a normal working state based on the static voltage consistency parameter, the dynamic voltage consistency parameter and an estimated parameter, wherein the estimated parameter is predetermined based on the voltage consistency data of the plurality of battery packs; and determining, in response to the operating status indicator exceeding a predetermined threshold, that the operating status of the battery pack to be tested is abnormal, wherein the predetermined threshold is predetermined based on the estimated parameter.

[0005] In a second aspect of the present disclosure, there is provided a device for monitoring the operating status of a battery pack, comprising: an acquisition module configured to acquire real-time charging data of a battery pack to be tested, wherein the battery pack to be tested comprises a plurality of single cells; a determination module configured to determine, based on the real-time charging data, static voltage consistency parameters of the plurality of single cells during initial charging and dynamic voltage consistency parameters during charging; an estimation module configured to estimate an operating status indicator for measuring the degree to which the battery pack to be tested deviates from a normal operating status based on the static voltage consistency parameter, the dynamic voltage consistency parameter and an estimated parameter, wherein the estimated parameter is predetermined based on voltage consistency data of a plurality of battery packs; and a judgment module configured to judge that the operating status of the battery pack to be tested is abnormal in response to the operating status indicator exceeding a predetermined threshold, wherein the predetermined threshold is predetermined based on the estimated parameter.

[0006] In a third aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] According to the embodiments of the present disclosure, it is possible to fully utilize the static voltage consistency parameters at the initial charging moment and the dynamic voltage consistency parameters that are representative during the charging process to form a two-dimensional feature, and to estimate the motion state index based on the two-dimensional feature and compare the motion state index with a predetermined threshold, so as to accurately monitor the abnormality of the voltage consistency of the battery pack and achieve the best effect in multiple dimensions such as the amount of feature data, algorithm coverage, algorithm accuracy and algorithm recall rate.

[0008] It should be understood that the contents described in this content section are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0011] Figure 2 A flowchart showing a process for monitoring the operating status of a battery pack according to some embodiments of the present disclosure is shown;

[0012] Figure 3A flowchart showing a process of determining an estimation parameter and a predetermined threshold according to some embodiments of the present disclosure is shown;

[0013] Figure 4 A schematic structural block diagram of an apparatus for monitoring the operating status of a battery pack according to some embodiments of the present disclosure is shown; and

[0014] Figure 5 A block diagram of a device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0015] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0016] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0017] As briefly mentioned above, for lithium iron phosphate power battery systems, there is a long platform voltage segment in its voltage curve characteristics, that is, its voltage does not change much in a large SOC range. This range is the most commonly used range for batteries. The platform voltage segment in this range will make it difficult to estimate capacity consistency and SOC consistency, while the differences in internal resistance consistency and temperature consistency are not significant. This poses a great challenge to the consistency algorithm for building lithium iron phosphate power battery systems.

[0018] A conventional power battery pack consistency evaluation scheme can calculate the capacity dispersion, equivalent DC internal resistance dispersion and voltage platform dispersion of the power battery pack according to the characteristic parameters of the power battery pack; using the preset evaluation weights, the weighted average calculation of each dispersion is performed to obtain the comprehensive evaluation coefficient of the power battery pack. With this scheme, the consistency of the power battery pack can be comprehensively evaluated, so that accurate evaluation results can be obtained. As a systematic and comprehensive battery pack consistency evaluation method, this scheme is currently widely used on cloud platforms to monitor the reliability of power batteries.

[0019] The above evaluation scheme relies on accurate capacity estimation and internal resistance estimation on the one hand, and discrete quantitative evaluation of the voltage of all single cells on the other hand. For ternary system or lithium manganese oxide system batteries, since the voltage characteristic curve of the battery has a relatively obvious slope, that is, the remaining power of the battery has a relatively strong one-to-one correspondence with the voltage value, better results can be obtained. However, for the lithium iron phosphate system, this evaluation scheme has the following disadvantages.

[0020] It is difficult to estimate the capacity and internal resistance of lithium iron phosphate batteries, especially for two-wheeled motorcycles or some low-speed vehicles. The hardware reliability of the power battery system is poor, and it is impossible to obtain reliable capacity and internal resistance estimates. If the threshold is relaxed, it will lead to more false alarms. If the threshold is tightened, there will be too few scenarios that meet the judgment, resulting in a monitoring blind spot.

[0021] In addition, according to the characteristics of the charge and discharge curve of lithium iron phosphate batteries, the voltage rise at the charging end leads to a large voltage dispersion, which makes it difficult to set the threshold value for voltage consistency.

[0022] For lithium iron phosphate power battery systems, a conventional consistency detection method includes obtaining vehicle battery system data, which includes the highest and lowest voltages, as well as the battery system SOC, and obtaining the voltage difference based on the highest and lowest voltages; judging whether it is the charge and discharge plateau data based on the SOC, and screening the vehicle battery system data in the charge and discharge plateau period; calculating the cumulative proportion of voltage differences greater than the set voltage difference after screening, and calculating the ΔSOC based on the relationship between the cumulative proportion and ΔSOC; judging whether the ΔSOC is greater than the warning critical value, if it is greater than or equal to the warning critical value, the battery consistency is poor. Based on this detection method, it can solve the problem that the SOC deviation is difficult to calculate during the dynamic operation of the battery system, resulting in misjudgment of battery consistency. This detection scheme overcomes the difficulties faced by the comprehensive evaluation scheme mentioned above. It uses the voltage difference between the highest and lowest voltages of the battery system to obtain the cumulative proportion greater than the set voltage difference, and obtains △SOC based on the cumulative proportion. In this case, it avoids the problem that the SOC corresponding to the highest and lowest voltages cannot be accurately obtained by the table lookup method when the vehicle battery system data obtained is in the charging and discharging platform period with little voltage change, which makes the calculated △SOC inaccurate, thereby improving the accuracy of battery consistency judgment. However, this detection scheme also has the following disadvantages.

[0023] This detection scheme relies on the calibration of previous data, has a low fault coverage and poor adaptability, and only performs abnormal diagnosis on specific voltage discrete modes in the power battery pack, and cannot cover voltage fault types such as sampling abnormalities and cell disconnection. In addition, this detection scheme cannot cover low temperature conditions, and is ineffective for winter operation scenarios. In addition, this detection scheme requires processing and judgment of long-term data, which takes up a lot of storage space and computing resources.

[0024] To this end, an embodiment of the present disclosure proposes a scheme for monitoring the operating state of a battery pack. According to various embodiments of the present disclosure, a two-dimensional feature is formed using a static voltage consistency parameter at the initial charging moment and a representative dynamic voltage consistency parameter during the charging process, and a motion state index is estimated based on the two-dimensional feature and the estimated parameter and compared with a predetermined threshold, thereby accurately monitoring the abnormality of the voltage consistency of the battery pack.

[0025] It will be understood from the following description that according to the embodiments of the present disclosure, by using the static voltage consistency parameter and the dynamic voltage consistency parameter as two-dimensional input data and judging the operating state of the battery pack based on this, the abnormal threshold of battery voltage consistency can be set adaptively, while effectively reducing the required amount of data, algorithm processing time and complexity. In addition, the embodiments of the present disclosure take into account the influence of ambient temperature factors on battery voltage consistency, and make adaptive adjustments to the abnormal judgment threshold through the temperature characteristics of the battery to be tested to avoid interference caused by temperature on the judgment.

[0026] Some example embodiments of the present disclosure will be described below with reference to the accompanying drawings. Please note that in some descriptions of the embodiments, certain specific values ​​may be involved in order to better help readers understand. These values ​​are exemplary and may vary according to specific application scenarios, and do not limit the scope of the present disclosure in any way.

[0027] Figure 1 1 is a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. Figure 1 As shown, the environment 100 includes a power battery pack 110 , a charging device 120 , and a battery management system 130 .

[0028] The power battery pack 100 includes a plurality of single cells, which may also be referred to as cells in this article. The consistency of each single cell of the power battery pack 100 during operation is crucial to ensuring the driving range and safety. Poor consistency not only affects the power output and driving range performance of the power battery pack 110, but also affects the operating safety and service life of the power battery pack 110. From different measurement angles, the consistency of the power battery pack 110 may include multiple operating status indicators, such as voltage consistency, capacity consistency, SOC consistency, internal resistance consistency, and temperature consistency.

[0029] The charging device 120 is used to charge the power battery pack 110, and can record the charging data of the power battery pack 110 during the charging process, such as the voltage, temperature, capacity and SOC of each single battery during the charging process. The charging device 120 may include any known or future available type, such as a charging pile or a charging cabinet, and the embodiments of the present disclosure are not limited to this. The charging device 120 may communicate with the battery management system 130 to send the charging data to the battery management system 130. The battery management system 130 may determine the operating state of the power battery pack 110 based on the received charging data. The battery management system 130 may include any known or future available type, such as a BMS battery system or a cloud platform, and the embodiments of the present disclosure are not limited to this. In the embodiments of the present disclosure, the battery management system 130 is mainly used to determine the voltage consistency state between each single battery of the power battery pack 110 based on the charging data, especially the voltage consistency state of a battery with a voltage platform segment such as a lithium iron phosphate battery. It should be understood that the embodiments of the present disclosure can also be applied to other types of batteries, such as ternary systems or lithium manganese oxide systems.

[0030] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and does not imply any limitation on the scope of the present disclosure.

[0031] Since lithium iron phosphate batteries have a platform voltage segment within a larger SOC range, it is difficult to estimate the capacity consistency and SOC consistency within this range, while the differences in internal resistance consistency and temperature consistency are not significant in themselves, which poses a great challenge to the consistency algorithm for building a lithium iron phosphate power battery system. Conventional detection schemes for lithium iron phosphate batteries have problems such as low fault coverage, poor adaptability, inability to cover low temperature conditions, large data processing volume, and waste of storage space and computing resources. In view of this, in various embodiments of the present disclosure, a two-dimensional feature is formed using a static voltage consistency parameter at the initial charging moment and a representative dynamic voltage consistency parameter during the charging process, and based on the two-dimensional feature, a motion state index is estimated and the motion state index is compared with a predetermined threshold, so as to accurately monitor the abnormality of the voltage consistency of the battery pack. The voltage consistency monitoring principle according to an embodiment of the present disclosure will be described in detail below.

[0032] Reference below Figure 2 A flowchart of a process 200 for monitoring the operating status of a battery pack is described. The process 200 may be performed by the battery management system 130. The operating status of the battery pack may be monitored during the charging phase of the power battery pack 110.

[0033] In block 210, real-time charging data of the power battery pack 110 is obtained, such as the voltage of each single cell during the charging process and the ambient temperature, etc. For example, the voltage data may include the voltage of each single cell of the power battery pack 110 during initial charging and the voltage of each single cell when charged to different power percentages (i.e., different SOCs).

[0034] In block 220, based on the real-time charging data, the static voltage consistency parameters of the plurality of cells during initial charging and the dynamic voltage consistency parameters during the charging process are determined. The static voltage consistency parameters are used to characterize the voltage consistency of each cell during initial charging of the power battery pack 110. The static voltage consistency parameters are used to characterize the voltage consistency of each cell during the charging process of the power battery pack 110.

[0035] In one embodiment, the initial variance δ of the voltage of each single battery in the power battery pack 110 during initial charging can be determined based on the real-time charging data. 0 As the static voltage consistency parameter δ s .

[0036] In one embodiment, a first variance δ of the voltages of the plurality of battery cells when charged to a first predetermined power percentage SOC1 may be determined based on the real-time charging data. SOC1 and a second variance δ of the voltage when charged to a second predetermined power percentage SOC2 SOC2 , and determine the first variance δSOC1 and the second variance δ SOC2 The average value (δ SOC1 +δ SOC2 ) / 2 as the dynamic voltage consistency parameter δ d The first predetermined power percentage SOC1 is less than the second predetermined power percentage SOC2.

[0037] In one embodiment, the first predetermined power percentage SOC1 is greater than 30% and less than 55%, and the second predetermined power percentage SOC2 is greater than 55% and less than 85%. As an example, the first predetermined power percentage SOC1 can be 50%, and the second predetermined power percentage SOC2 can be 70%.

[0038] Initial variance δ 0 , the first variance δ SOC1 and the second variance δ SOC2 The calculation method is:

[0039]

[0040] Wherein, i is 0 indicating the initial charging time, i is SOC1 indicating the time when the battery is charged to the first predetermined power percentage SOC1, and i is SOC2 indicating the time when the battery is charged to the second predetermined power percentage SOC2; n is the number of single cells; V i，j is the voltage value of the jth single cell at time i, u i is the average voltage of all single cells at time i. 0 , δ SOC1 and δ SOC2 , the static voltage consistency parameter δ can be constructed s =δ 0 and the dynamic voltage consistency parameter δ d =(δ SOC1 +δ SOC2 ) / 2.

[0041] In other embodiments, other types of static voltage consistency parameters and dynamic voltage consistency parameters may be constructed, and these implementations all fall within the scope of the present disclosure. For example, the voltage variance when charging to a single predetermined percentage of power during the charging process may be used as the dynamic voltage consistency parameter, or the voltage variance when charging to more than three predetermined percentages of power during the charging process may be used as the dynamic voltage consistency parameter.

[0042] In addition, it should be noted that the numbers, values, etc. mentioned above and elsewhere in the present disclosure are exemplary and are not intended to limit the scope of the present disclosure in any way. Any other appropriate numbers and values ​​are possible.

[0043] In block 230 , based on the static voltage consistency parameter δ of the power battery pack 110 s , dynamic voltage consistency parameter δ d And estimation parameters are used to estimate the operating state index used to measure the degree to which the power battery pack 110 deviates from the normal working state, wherein the estimation parameters are predetermined based on the voltage consistency data of multiple battery packs. The voltage consistency data of each battery pack also includes a static voltage consistency parameter δ s,i and the dynamic voltage consistency parameter δ d，i The voltage consistency data of multiple battery packs may include normal data and abnormal data mixed in the normal data. If the estimated parameters are determined directly based on all the voltage consistency data of multiple battery packs, it may lead to inaccurate parameters and misjudgment of outliers. In order to obtain more robust estimated parameters, it is necessary to first find the normal data from the voltage consistency data of multiple battery packs, and then calculate the estimated parameters. The specific determination process of the estimated parameters will be combined with Figure 3 Describe in detail.

[0044] In one embodiment, the estimated parameters include the static voltage consistency parameter δ of the normal data s，i The mean value u1 of the normal data and the dynamic voltage consistency parameter δ d，i The mean u2 of the normal data and the covariance matrix ∑ of the normal data are predetermined based on the voltage consistency data of the plurality of battery packs and stored in the storage unit.

[0045] In one embodiment, the operating status indicator includes a Mahalanobis distance d. The calculation method of the Mahalanobis distance d is as follows.

[0046]

[0047] Among them, δ s is the static voltage consistency parameter of the power battery pack 110 to be tested, δ d is the dynamic voltage consistency parameter of the power battery pack 110 to be tested, and u1 is the static voltage consistency parameter δ of normal data. s，i The mean value of u2 is the dynamic voltage consistency parameter δ of normal data. d，i The mean u2 of , ∑ is the covariance matrix of normal data.

[0048] It should be understood that the Mahalanobis distance d is only an example of the operating status indicator of the battery pack. In other embodiments, the operating status indicator can adopt any appropriate indicator, which all falls within the scope of the present disclosure.

[0049] In block 240, in response to the operating status indicator exceeding a predetermined threshold, it is determined that the operating status of the power battery pack 110 is abnormal, such as abnormal internal resistance of the battery. Accordingly, in response to the operating status indicator not exceeding the predetermined threshold, it is considered that the operating status of the power battery pack 110 is normal. The predetermined threshold is predetermined based on the estimated parameter and stored in the storage unit.

[0050] In one embodiment, in response to determining that the operating state of the power battery pack 110 is abnormal, an alarm signal is generated, and the alarm signal can be sent to the charging device 120 to remind the user or the operation and maintenance personnel.

[0051] In one embodiment, the ambient temperature of the power battery pack 110 can be obtained, and a corresponding predetermined threshold is selected from a plurality of predetermined thresholds based on the ambient temperature, wherein the plurality of predetermined thresholds are predetermined based on the estimated parameters and different temperatures. In other words, different predetermined thresholds can be set for different ambient temperatures, and the influence of the ambient temperature factor on the voltage consistency of the battery pack is considered, and the abnormal determination threshold is adaptively adjusted according to the temperature characteristics of the battery pack to be tested, so as to avoid the interference of the temperature on the determination.

[0052] As described above, the estimated parameter is predetermined based on the voltage consistency data of the plurality of battery packs and stored in the storage unit, and the predetermined threshold is predetermined based on the estimated parameter and stored in the storage unit. Figure 3 The process 300 of determining the estimated parameters and the predetermined threshold is described. The process 300 can form a tolerance ellipse based on a two-dimensional normal battery determination area obtained from a large amount of battery consistency data. The battery consistency data located within the tolerance ellipse is considered to be a normal battery, and the battery consistency data located outside the tolerance ellipse is considered to be an abnormal battery.

[0053] Process 300 obtains the threshold for judging normal batteries by determining the mean and covariance of the static voltage consistency parameters and dynamic voltage consistency parameters of normal data in a large amount of data. Since abnormal data are mixed in the normal data set, directly calculating the two estimated parameters of the mean and covariance is susceptible to the influence of outliers and offset, resulting in inaccurate parameters, and then misjudgment of outliers. In order to obtain more robust estimated parameters and more reasonable thresholds, the embodiment of the present disclosure searches for the data subset with the smallest covariance matrix as normal data under the premise of known prior abnormal probability, and then calculates its parameters.

[0054] In block 301 , training data of n battery packs are obtained, the training data including charging data of the n battery packs, where n is a positive integer greater than 1. The charging data of each battery pack includes the voltage and ambient temperature of each single battery during the charging process.

[0055] In blocks 302 and 303, based on the acquired training data, voltage consistency data of n battery packs are calculated, including static voltage consistency parameters δ s，i and the dynamic voltage consistency parameter δ d，i , where i is the serial number of each battery pack. Static voltage consistency parameter δ s，i and the dynamic voltage consistency parameter δ d，i The calculation process of is similar to the static voltage consistency parameter δ of the power battery pack 110 described above. s and the dynamic voltage consistency parameter δ d The calculation process will not be described in detail here.

[0056] In block 304 , based on a priori abnormality probability ρ, voltage consistency data of n*(1-ρ) battery packs among the n battery packs are randomly selected to form an initial data subset S. The priori abnormality probability ρ is used to characterize the probability that the n battery packs may have operational abnormalities, and its value is between 0 and 1.

[0057] At block 305, determine the static voltage consistency parameter δ in the initial data subset S. s，i The first initial average value u1, the dynamic voltage consistency parameter δ in the initial data subset S d，i The second initial mean u2 of and the initial covariance matrix ∑ of the initial data subset S.

[0058]

[0059] Considering the influence of temperature on battery voltage consistency, the initial covariance matrix ∑ can be adjusted based on the temperature. To this end, in box 306, the ambient temperature T is obtained, and in box 307, the initial covariance matrix ∑ is adjusted according to the ambient temperature to obtain the intermediate covariance matrix ∑ by the following formula: T :

[0060]

[0061] Among them, T s is the set temperature reference value, and c is the weight coefficient. This formula can adjust the diagonal value of the initial covariance matrix according to the ambient temperature, thereby changing the algorithm's tolerance for static consistency and dynamic consistency, that is, changing the shape of the tolerance ellipse. Specifically, the embodiments of the present disclosure make the algorithm more tolerant to dynamic consistency at low temperatures to cope with the impact of temperature.

[0062] At block 308, based on the voltage consistency data of the n battery packs (static voltage consistency parameter δ s，i and the dynamic voltage consistency parameter δ d,i ), the first initial mean value u1, the second initial mean value u2 and the intermediate covariance matrix ∑T Determine the operating status indicator of each of the n battery groups, such as the Mahalanobis distance d i :

[0063]

[0064] Among them, δ s，i , δ d，i is the first dimension feature of the input (static voltage consistency parameter δ s，i ) and the second dimension feature (dynamic voltage consistency parameter δ d，i ), * T Transpose the matrix.

[0065] In block 309, according to the Mahalanobis distance d i Sort the original data (voltage consistency data of n battery packs) and extract d i The smallest first n*(1-ρ) samples.

[0066] In block 310, the first n*(1-ρ) samples taken are used as a new data subset S, thereby updating the data subset S to form normal data.

[0067] In block 311, the static voltage consistency parameter δ in the normal data is determined s，i The mean value u1 of is taken as the first target average value to determine the dynamic voltage consistency parameter δ in the normal data. d,i The mean u2 of is taken as the second target mean value, and the target covariance matrix ∑ of the normal data is determined to form the estimated parameters. The determination process of the target covariance matrix ∑ is similar to the determination process of the initial covariance matrix ∑ described above, and will not be repeated here.

[0068] After recalculating the two-dimensional mean u1, u2 and covariance matrix ∑ of the updated data subset S, we have:

[0069] det(∑ new )≤det(∑ old )

[0070] That is, the new covariance matrix ∑ new The value of is less than or equal to the old covariance matrix ∑ old In other words, the covariance of the updated data subset S is the smallest covariance among all subsets of the entire data set, which indicates that the selected n*(1-ρ) samples have the highest degree of aggregation in the data set and can be considered as normal samples.

[0071] In box 311, the operating status indicator of each battery pack in the n*(1-ρ) battery packs, such as the Mahalanobis distance di, is also determined based on the normal data (i.e., the updated data subset S), the first target average value u1, the second target average value u2, and the target covariance matrix ∑; and the Mahalanobis distance di corresponding to the outermost data in the normal data is selected as the predetermined threshold On this basis, the threshold is calculated according to the target covariance matrix ∑ The distance between the axes in both directions gives the tolerance ellipse:

[0072]

[0073] Then, store the estimated parameters u 1 、u 2 and ∑ and a predetermined threshold and a predetermined threshold Used to perform online detection in process 200.

[0074] In some embodiments, the estimated parameter u 1 、u 2 and ∑ and a predetermined threshold It can be predetermined before the power battery pack 110 is put into operation. In some embodiments, the estimated parameter u 1 、u 2 and ∑ and a predetermined threshold The power battery pack 110 may be updated after running for a period of time.

[0075] In some embodiments, normal data is also selected in the following manner: based on the prior abnormal probability ρ, randomly selecting voltage consistency data of n*(1-ρ) battery packs out of n battery packs to form an initial data subset; determining a first initial average value of the static voltage consistency parameter in the initial data subset, a second initial average value of the dynamic voltage consistency parameter in the initial data subset, and an initial covariance matrix of the initial data subset; determining an operating status indicator of each of the n battery packs based on the voltage consistency data of the n battery packs, the first initial average value, the second initial average value, and the initial covariance matrix; and selecting the static voltage consistency parameters and dynamic voltage consistency parameters of n*(1-ρ) battery packs with smaller operating status indicators out of the n battery packs to form normal data.

[0076] like Figure 3 As shown, based on the parameter u 1 、u 2 and ∑ and a predetermined threshold Process 200 can monitor the operating status of the battery pack. Blocks 210, 220, 230 and 240 and the specific process and combination of selecting the predetermined threshold value based on the ambient temperature Figure 2The contents described are similar and will not be repeated here. In process 200, the temperature change rate and the voltage jump value can also be calculated based on the acquired charging data, and the operating state of the battery pack can be monitored accordingly.

[0077] Figure 4 FIG. 4 is a schematic structural block diagram of an apparatus 400 for monitoring the operating status of a battery pack according to some embodiments of the present disclosure. In some embodiments, the apparatus 400 may be implemented as or included in a battery management system 130 .

[0078] like Figure 4 As shown, the device 400 includes an acquisition module 410 configured to acquire real-time charging data of a battery pack to be tested, wherein the battery pack to be tested includes a plurality of single cells. For example, the acquisition module 410 can acquire real-time charging data of the power battery pack 110 from the charging device 120 .

[0079] The device 400 also includes a processing module 420, which is connected to the acquisition module 410 to receive real-time charging data and monitor the operating state of the battery pack based on the real-time charging data. The processing module 420 may include a determination module, an estimation module, and a judgment module. The determination module is configured to determine the static voltage consistency parameters of multiple single cells during initial charging and the dynamic voltage consistency parameters during the charging process based on the real-time charging data. The estimation module is configured to estimate the operating state index used to measure the degree to which the battery pack to be tested deviates from the normal working state based on the static voltage consistency parameter, the dynamic voltage consistency parameter, and the estimation parameter, wherein the estimation parameter is predetermined based on the voltage consistency data of multiple battery packs and stored in the storage unit. The judgment module is configured to determine that the operating state of the battery pack to be tested is abnormal in response to the operating state index exceeding a predetermined threshold, wherein the predetermined threshold is predetermined based on the estimation parameter and stored in the storage unit. In some embodiments, the processing module 420 may be an MCU.

[0080] In some embodiments, the determination module determines the static voltage consistency parameter and the dynamic voltage consistency parameter in the following manner: determining an initial variance of the voltages of a plurality of single cells during initial charging as a static voltage consistency parameter; determining a first variance of the voltages of the plurality of single cells when charged to a first predetermined percentage of power and a second variance of the voltages when charged to a second predetermined percentage of power, wherein the first predetermined percentage of power is less than the second predetermined percentage of power; and determining an average value of the first variance and the second variance as a dynamic voltage consistency parameter.

[0081] In some embodiments, the first predetermined power percentage is greater than 30% and less than 55%, and the second predetermined power percentage is greater than 55% and less than 85%.

[0082] In some embodiments, the estimated parameters are predetermined in the following manner: determining voltage consistency data of n battery packs, where n is a positive integer greater than 1; selecting voltage consistency data of n*(1-ρ) battery packs with the highest degree of aggregation from the voltage consistency data of the n battery packs as normal data based on the prior abnormality probability ρ of the n battery packs; and determining a first target average value of the static voltage consistency parameters in the normal data, a second target average value of the dynamic voltage consistency parameters in the normal data, and a covariance matrix of the normal data as estimated parameters.

[0083] In some embodiments, normal data is selected in the following manner: based on a prior abnormal probability ρ, randomly selecting voltage consistency data of n*(1-ρ) battery packs out of n battery packs to form an initial data subset; determining a first initial average value of a static voltage consistency parameter in the initial data subset, a second initial average value of a dynamic voltage consistency parameter in the initial data subset, and an initial covariance matrix of the initial data subset; determining an operating status indicator of each of the n battery packs based on the voltage consistency data of the n battery packs, the first initial average value, the second initial average value, and the initial covariance matrix; and selecting the static voltage consistency parameters and dynamic voltage consistency parameters of n*(1-ρ) battery packs with smaller operating status indicators out of the n battery packs to form normal data.

[0084] In some embodiments, normal data is selected in the following manner: based on a prior abnormal probability ρ, randomly selecting voltage consistency data of n*(1-ρ) battery packs out of n battery packs to form an initial data subset; determining a first initial average value of a static voltage consistency parameter in the initial data subset, a second initial average value of a dynamic voltage consistency parameter in the initial data subset, and an initial covariance matrix of the initial data subset; adjusting the initial covariance matrix based on the ambient temperature to obtain an intermediate covariance matrix; determining an operating status indicator of each of the n battery packs based on the voltage consistency data of the n battery packs, the first initial average value, the second initial average value, and the intermediate covariance matrix; and selecting the static voltage consistency parameters and dynamic voltage consistency parameters of n*(1-ρ) battery packs with smaller operating status indicators out of the n battery packs to form normal data.

[0085] In some embodiments, the predetermined threshold is predetermined by: determining an operating status indicator of each of the n*(1-ρ) battery packs based on normal data, a first target average value, a second target average value, and a target covariance matrix; and selecting an operating status indicator corresponding to the outermost data in the normal data as the predetermined threshold.

[0086] In some embodiments, the apparatus 400 further includes an intervention module 430 configured to generate an alarm signal in response to determining that the operating state of the battery pack to be tested is abnormal.

[0087] In some embodiments, the acquisition module 410 is further configured to acquire the ambient temperature of the battery pack to be tested. Accordingly, the processing module 420 further includes a selection module, which is configured to select a corresponding predetermined threshold from a plurality of predetermined thresholds based on the ambient temperature, wherein the plurality of predetermined thresholds are predetermined based on the estimated parameters and different temperatures and stored in the storage unit.

[0088] In some embodiments, the operating status indicator includes the Mahalanobis distance.

[0089] According to the embodiments of the present disclosure, it is possible to fully utilize the static voltage consistency parameters at the initial charging moment and the dynamic voltage consistency parameters that are representative during the charging process to form a two-dimensional feature, and to estimate the motion state index based on the two-dimensional feature and compare the motion state index with a predetermined threshold, so as to accurately monitor the abnormality of the voltage consistency of the battery pack and achieve the best effect in multiple dimensions such as the amount of feature data, algorithm coverage, algorithm accuracy and algorithm recall rate.

[0090] The embodiment of the present disclosure proposes a method for determining a battery internal resistance abnormality threshold based on a minimum covariance matrix. The threshold is learned from a large amount of battery charging data, and its input data is multidimensional and may be a voltage jump value, a temperature change rate, etc.

[0091] The embodiment of the present disclosure utilizes the Mahalanobis distance calculated from the multi-dimensional features of the battery to be tested in combination with the learned threshold value to determine whether the internal resistance of the battery is abnormal. The introduction of multi-dimensional features increases the fault tolerance and robustness of the algorithm.

[0092] The embodiments of the present disclosure propose an adaptive power battery voltage consistency anomaly detection method based on dynamic and static characteristics and using minimum covariance. The method uses static voltage consistency (voltage variance at the time of initial battery charging) and dynamic voltage consistency (the mean of the voltage variance when the battery is charged to the battery SOC of SOC1 and SOC2) as two-dimensional input data, and can adaptively set the battery voltage consistency anomaly threshold, while effectively reducing the required data quantity, algorithm processing time and complexity. In addition, the embodiments of the present disclosure take into account the impact of ambient temperature factors on battery voltage consistency, and adaptively adjust the abnormal judgment threshold through the temperature characteristics of the battery to be tested to avoid interference caused by temperature on the judgment.

[0093] Figure 5 A block diagram of an electronic device 500 is shown in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 5The electronic device 500 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 5 The electronic device 500 shown can be used to implement Figure 1 The battery management system 130 or Figure 4 at least a portion of the device 400.

[0094] like Figure 5 As shown, the electronic device 500 is in the form of a general electronic device. The components of the electronic device 500 may include, but are not limited to, one or more processors or processing units 510, a memory 520, a storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processing unit 510 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 520. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 500.

[0095] The electronic device 500 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 520 may be a volatile memory (e.g., a register, a cache, a random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 530 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data (e.g., training data for training) and may be accessed within the electronic device 500.

[0096] The electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 5 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 520 may include a computer program product 525 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0097] The communication unit 540 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 500 can be implemented in a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 500 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0098] The input device 550 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 560 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 500 may also communicate with one or more external devices (not shown) through the communication unit 540 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 500, or communicate with any device that allows the electronic device 500 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0099] According to an exemplary implementation of the present disclosure, a device for monitoring the operating state of a battery pack is provided. The device includes at least one processing unit and at least one memory. The at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, and when the instructions are executed by the at least one processing unit, the device executes the method described above.

[0100] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0101] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0102] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0103] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0104] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0105] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for monitoring the operating status of a battery pack, comprising: Acquiring real-time charging data of a battery pack to be tested, wherein the battery pack to be tested includes a plurality of single cells; Determining, based on the real-time charging data, static voltage consistency parameters of the plurality of single cells during initial charging and dynamic voltage consistency parameters during the charging process; estimating an operating status indicator for measuring the degree to which the battery pack to be tested deviates from a normal operating state based on the static voltage consistency parameter, the dynamic voltage consistency parameter, and an estimated parameter, wherein the estimated parameter is predetermined based on voltage consistency data of a plurality of battery packs; as well as In response to the operating status indicator exceeding a predetermined threshold, it is determined that the operating status of the battery pack to be tested is abnormal, wherein the predetermined threshold is predetermined based on the estimated parameter.

2. The method according to claim 1, wherein determining the static voltage consistency parameter and the dynamic voltage consistency parameter comprises: Determining an initial variance of the voltages of the plurality of single cells during initial charging as the static voltage consistency parameter; Determining a first variance of voltages of the plurality of battery cells when charged to a first predetermined percentage of power and a second variance of voltages of the plurality of battery cells when charged to a second predetermined percentage of power, wherein the first predetermined percentage of power is less than the second predetermined percentage of power; as well as An average value of the first variance and the second variance is determined as the dynamic voltage consistency parameter. 3 . The method according to claim 2 , wherein the first predetermined power percentage is greater than 30% and less than 55%, and the second predetermined power percentage is greater than 55% and less than 85%.

4. The method according to claim 1, wherein the estimation parameters are predetermined by: Determining the voltage consistency data of n battery packs, where n is a positive integer greater than 1; Based on the priori abnormal probability ρ of the n battery packs, selecting the voltage consistency data of n*(1-ρ) battery packs with the highest degree of aggregation from the voltage consistency data of the n battery packs as normal data; and A first target average value of the static voltage consistency parameter in the normal data, a second target average value of the dynamic voltage consistency parameter in the normal data, and a covariance matrix of the normal data are determined as the estimation parameters.

5. The method according to claim 4, wherein the normal data is selected by: Based on the prior abnormal probability ρ, randomly selecting the voltage consistency data of n*(1-ρ) battery packs among the n battery packs to form an initial data subset; Determining a first initial average value of the static voltage consistency parameter in the initial data subset, a second initial average value of the dynamic voltage consistency parameter in the initial data subset, and an initial covariance matrix of the initial data subset; determining the operating status indicator of each of the n battery packs based on the voltage consistency data of the n battery packs, the first initial average value, the second initial average value, and the initial covariance matrix; and The static voltage consistency parameters and the dynamic voltage consistency parameters of n*(1-ρ) battery groups with smaller operating status indicators among the n battery groups are selected to form the normal data.

6. The method according to claim 4, wherein the normal data is selected by: Based on the prior abnormal probability ρ, randomly selecting the voltage consistency data of n*(1-ρ) battery packs among the n battery packs to form an initial data subset; Determining a first initial average value of the static voltage consistency parameter in the initial data subset, a second initial average value of the dynamic voltage consistency parameter in the initial data subset, and an initial covariance matrix of the initial data subset; Adjusting the initial covariance matrix based on the ambient temperature to obtain an intermediate covariance matrix; determining the operating status indicator of each of the n battery packs based on the voltage consistency data of the n battery packs, the first initial average value, the second initial average value, and the intermediate covariance matrix; and The static voltage consistency parameters and the dynamic voltage consistency parameters of n*(1-ρ) battery groups with smaller operating status indicators among the n battery groups are selected to form the normal data.

7. The method according to claim 4, wherein the predetermined threshold is predetermined by: Determine the operating status indicator of each of the n*(1-ρ) battery packs based on the normal data, the first target average value, the second target average value, and the target covariance matrix; and The operating status indicator corresponding to the outermost data in the normal data is selected as the predetermined threshold.

8. The method according to claim 1, further comprising: In response to determining that the operating state of the battery pack to be tested is abnormal, an alarm signal is generated.

9. The method according to claim 1, further comprising: Obtaining the ambient temperature of the battery pack to be tested; as well as A corresponding predetermined threshold is selected from a plurality of predetermined thresholds based on the ambient temperature, wherein the plurality of predetermined thresholds are predetermined based on the estimated parameters and different temperatures.

10. The method according to any one of claims 1 to 9, wherein the operating status indicator comprises a Mahalanobis distance.

11. A device for monitoring the operating status of a battery pack, comprising: An acquisition module is configured to acquire real-time charging data of a battery pack to be tested, wherein the battery pack to be tested includes a plurality of single cells; A determination module configured to determine static voltage consistency parameters of the plurality of single cells during initial charging and dynamic voltage consistency parameters during charging based on the real-time charging data; an estimation module configured to estimate an operating state indicator for measuring the degree to which the battery pack to be tested deviates from a normal operating state based on the static voltage consistency parameter, the dynamic voltage consistency parameter and an estimation parameter, wherein the estimation parameter is predetermined based on voltage consistency data of a plurality of battery packs; as well as The determination module is configured to determine that the operating state of the battery pack to be tested is abnormal in response to the operating state indicator exceeding a predetermined threshold, wherein the predetermined threshold is predetermined based on the estimated parameter.

12. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 10.

Images