Method and apparatus for extracting typical working condition of battery, device, chip, storage medium and product

Abstract

A method and apparatus for extracting a typical working condition of a battery, a device, a chip, a storage medium and a product. The method comprises: acquiring, from a battery data set, working condition data of a battery within a plurality of time periods, wherein the plurality of time periods comprise a first time period, and the type of the working condition data within the first time period is a first type; on the basis of a transition probability of change from the first type to any other type, determining, from the working condition data within the plurality of time periods, working condition data within a second time period, wherein the type of the working condition data within the second time period is a second type, and all the types comprise the second type; and splicing the working condition data within the first time period and within the second time period to obtain typical working condition data of the battery.

Description

Method, device, equipment, chip, storage medium and product for extracting typical battery operating conditions

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure is based on Chinese patent application number 202410363760.2, application date March 27, 2024, and invention name “Method, device, equipment, storage medium and product for extracting typical operating conditions of batteries”, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby introduced into the present disclosure as a reference. Technical Field

[0003] The present disclosure relates to, but is not limited to, the field of battery technology, and in particular to a method, apparatus, device, chip, storage medium, and product for extracting typical operating conditions of a battery. Background Art

[0004] With the rapid development of the new energy industry, batteries are widely used in different fields such as energy storage, automobiles, and ships. The working conditions of battery systems in different scenarios vary greatly.

[0005] Currently, specific operating conditions such as constant rate, constant current, and the China light-duty vehicle test cycle (CLTC) are commonly used to evaluate battery performance. However, the operating conditions in actual application scenarios are often complex and changeable, resulting in significant differences between the actual battery performance and the evaluation results under specific operating conditions. For example, the actual battery range may be lower than the battery range evaluated using the CLTC; for another example, the actual battery cell degradation rate may be higher than the battery cell degradation rate evaluated under specific operating conditions.

[0006] To more accurately evaluate battery performance, operating conditions that better reflect actual battery applications are required. Therefore, finding these operating conditions is a pressing issue.

[0007] Summary of the Invention

[0008] The present disclosure at least provides a method, device, equipment, chip, storage medium and product for extracting typical operating conditions of a battery.

[0009] The technical solution of the present disclosure is achieved as follows:

[0010] In a first aspect, an embodiment of the present disclosure provides a method for extracting typical operating conditions of a battery, the method comprising: obtaining operating condition data of the battery in multiple time periods from a battery data set, the multiple time periods including a first time period, and the type of the operating condition data in the first time period belonging to the first type; based on the transition probability from the first type to each type, determining the operating condition data in a second time period from the operating condition data in the multiple time periods; the type of the operating condition data in the second time period belongs to a second type, and the each type includes the second type; splicing the operating condition data in the first time period and the second time period to obtain the typical operating condition data of the battery.

[0011] According to the method of this embodiment, the operating condition data within the first time period and the second time period can be extracted from the operating condition data within multiple time periods for splicing, and in the process of determining the operating condition data within the second time period, the transition probability from the first type (the type of the operating condition data within the first time period) to each type is considered. In this way, the type change of the operating condition data in the typical operating condition data obtained by splicing can be more in line with the changing law of the actual scenario, or in other words, the typical operating condition data obtained can be more in line with the actual application scenario of the battery. Furthermore, when the typical operating condition data is used for battery performance evaluation, it is beneficial to improve the accuracy of the evaluation results.

[0012] In some embodiments, before obtaining the operating condition data of the battery in multiple time periods from the battery data set, the method also includes: determining the demand for the typical operating condition data of the battery, which demand is related to at least one of the capacity, duration, and state of charge SOC corresponding to the typical operating condition data of the battery; determining the termination condition based on the demand, and when the typical operating condition data of the battery meets the termination condition, the typical operating condition data of the battery meets the demand.

[0013] According to the method of this embodiment, the demand for typical operating condition data of the battery can be determined, and the corresponding end condition can be determined based on the demand. In this way, in the process of obtaining the typical operating condition data of the battery, typical operating condition data that meets the demand can be obtained based on the end condition.

[0014] In some embodiments, based on the transition probability of changing from the first type to each type, the operating condition data within the second time period is determined from the operating condition data within multiple time periods, including: based on the transition probability of changing from the first type to each type, determining that the type of the operating condition data within the second time period belongs to the second type; determining the operating condition data within N candidate time periods from the operating condition data within multiple time periods, the type of the operating condition data within the N candidate time periods belongs to the second type, and N is a positive integer; and determining the operating condition data within a candidate time period from the operating condition data within the N candidate time periods as the operating condition data within the second time period.

[0015] According to the method of this embodiment, based on the transition probabilities of changing from the first type to various types, it can be determined that the type of the operating condition data within the second time period belongs to the second type. Furthermore, operating condition data within N candidate time periods whose operating condition data belongs to the second type can be screened from the operating condition data within multiple time periods. The operating condition data within one candidate time period can then be determined from the N candidate time periods as the operating condition data within the second time period. Because the transition probabilities of changing from the first type (the type of the operating condition data within the first time period) to various types are taken into account during the process of determining the type of the operating condition data within the second time period, the type changes of the operating condition data within the spliced ​​typical operating condition data can be made more consistent with the changing patterns of actual scenarios.

[0016] In some embodiments, based on the transition probability from the first type to each type, determining that the type of the operating condition data in the second time period belongs to the second type includes: based on the transition probability from the first type to each type, determining the probability interval corresponding to each type; wherein the length of the probability interval corresponding to each type is equal to the transition probability from the first type to that type; when the random factor falls within the probability interval corresponding to the second type, determining that the type of the operating condition data in the second time period belongs to the second type.

[0017] According to the method of this embodiment, the longer the probability interval, the greater the likelihood that the random factor will fall within that probability interval; in other words, the greater the likelihood that the second type corresponds to the type corresponding to that probability interval. Thus, the determination of the type of the operating condition data within the second time period conforms to objective laws in real-world scenarios. Therefore, determining the second type as the type of the operating condition data within the second time period ensures that the type variations of the operating condition data in the final spliced ​​typical operating condition data are more consistent with the laws of variation in real-world scenarios.

[0018] In some embodiments, determining the operating condition data within a candidate time period from the operating condition data within N candidate time periods as the operating condition data within the second time period includes: determining the Mahalanobis distance between the operating condition data within the first time period and the operating condition data within each of the N candidate time periods; using the operating condition data within the first candidate time period among the N candidate time periods as the operating condition data within the second time period; and among the N candidate time periods, the Mahalanobis distance between the operating condition data within the first candidate time period and the operating condition data within the first time period is the smallest.

[0019] According to the method of this embodiment, in the process of determining the operating condition data within the second time period from the operating condition data within N candidate time periods, the operating condition data within a time period having the smallest Mahalanobis distance with the operating condition data within the first time period can be selected as the operating condition data within the second time period. In this way, after the operating condition data within the first time period and the second time period are spliced ​​together, it can be ensured that the spliced ​​operating condition data (typical operating condition data) will not undergo mutations. That is, the spliced ​​operating condition data can have better consistency and thus be more in line with the objective laws in actual scenarios.

[0020] In some embodiments, the method further includes: determining characteristic values ​​of the operating condition data in each of a plurality of time periods; clustering the operating condition data in a plurality of time periods based on the characteristic values ​​of the operating condition data in each of a plurality of time periods to obtain the type to which the operating condition data in each of a plurality of time periods belongs.

[0021] According to the method of this embodiment, by clustering the operating condition data in multiple time periods, the type of the operating condition data in each time period can be obtained. For example, it can be obtained that the type of the operating condition data in the first time period is the first type. Therefore, the operating condition data in the second time period can be determined based on the transition probability from the first type to each type, so that the operating condition data in the first time period and the second time period can be subsequently spliced ​​to obtain the typical operating condition data of the battery.

[0022] In some embodiments, before obtaining the operating condition data of the battery in multiple time periods from the battery data set, the method also includes: obtaining the operating condition data of the battery in multiple cycles from the battery data set; determining a first parameter of the operating condition data in multiple cycles, the first parameter being any one of the following: the mode, the mean, the value of the operating condition data corresponding to the maximum value of the probability density function; determining at least one target cycle from the multiple cycles, the difference between the value of the operating condition data in at least one target cycle and the first parameter being less than or equal to a first threshold; dividing the at least one target cycle to obtain multiple time periods.

[0023] According to the method of this embodiment, at least one target period can be determined from multiple periods, and the difference between the value of the operating condition data within the target period and the first parameter is less than or equal to the first threshold. In this way, the value of the operating condition data within the target period is within a range with a high probability of occurrence. It is understandable that if the probability of occurrence of the operating condition data value within a certain period is low, it means that the operating condition data within this period is not representative. However, through the above technical solution, this period can be eliminated, and only the target period is retained, thereby making the retained operating condition data within the target period more representative, and thus making the operating condition data within the multiple time periods obtained more representative.

[0024] In some embodiments, before obtaining the operating condition data of the battery in multiple time periods from the battery data set, the method also includes: obtaining the operating condition data of the battery in multiple cycles from the battery data set, where there are multiple types of operating condition data; determining a first parameter of each type of operating condition data in the multiple cycles, where the first parameter is any one of the following: the mode, the mean, and the value of the operating condition data corresponding to the maximum value of the probability density function; for each type of operating condition data in the multiple cycles, determining at least one target cycle from the multiple cycles, where the difference between the value of the operating condition data of the type in at least one target cycle and the corresponding first parameter is less than or equal to the first threshold corresponding to the type; determining the intersection of all target cycles to obtain M target cycles, where M is a positive integer; and dividing the M target cycles to obtain multiple time periods.

[0025] According to the method of this embodiment, M target periods can be determined from multiple periods, and the difference between the value of each type of operating condition data within the target period and the corresponding first parameter is less than or equal to the first threshold. This ensures that the value of each type of operating condition data within the target period falls within a range with a high probability of occurrence, making the operating condition data within the target period more representative, and further making the operating condition data within the multiple time periods more representative.

[0026] In some embodiments, the method also includes: when the typical operating condition data of the battery does not meet the termination conditions, the typical operating condition data of the battery is updated by executing the following steps: based on the transition probability of changing from the second type to each type, the operating condition data in the next time period is determined from the operating condition data in multiple time periods; the type of the operating condition data in the next time period is included in the various types; the operating condition data in the next time period is spliced ​​after the operating condition data in the previous time period to obtain the updated typical operating condition data of the battery, and the previous time period is the second time period.

[0027] According to the method of this embodiment, if the typical operating condition data of the battery does not meet the termination condition, the type of the operating condition data (such as the second type) in the previous time period (such as the second time period) can be changed to the transition probability of each type. The operating condition data in the next time period can be determined from the operating condition data in these multiple time periods. The operating condition data in the next time period can then be spliced ​​after the operating condition data in the previous time period to obtain the updated typical operating condition data of the battery. This method can ensure that the type change of the operating condition data in the updated typical operating condition data of the battery can better conform to the changing laws of actual scenarios.

[0028] In some embodiments, the typical operating condition data of the battery includes: operating condition data within L time periods, where L is a positive integer; the termination condition includes at least one of the following: the cumulative capacity of the battery within the L time periods reaches a second threshold; the cumulative duration corresponding to the L time periods reaches a third threshold; the cumulative SOC corresponding to the L time periods reaches a fourth threshold, wherein the SOC corresponding to each time period is: the difference between the maximum SOC and the minimum SOC of the battery within the time period.

[0029] According to the method of this embodiment, the data amount of the typical operating condition data of the battery can be flexibly controlled through the end condition, thereby obtaining typical operating condition data that meets the requirements.

[0030] In a second aspect, an embodiment of the present disclosure provides a device for extracting typical operating conditions of a battery, the device comprising: a first acquisition unit, for acquiring operating condition data of the battery in multiple time periods from a battery data set, the multiple time periods including a first time period, and the type of the operating condition data in the first time period belonging to the first type; a first determination unit, for determining the operating condition data in a second time period from the operating condition data in the multiple time periods based on a transition probability from the first type to each type; the type of the operating condition data in the second time period belongs to a second type, and the each type includes the second type; a splicing unit, for splicing the operating condition data in the first time period and the second time period to obtain typical operating condition data of the battery.

[0031] In a third aspect, an embodiment of the present disclosure provides a device for extracting typical operating conditions of a battery, the device comprising a memory and a processor; wherein the memory is used to store computer-executable instructions; the processor is connected to the memory and is used to implement the method of the first aspect by executing the computer-executable instructions.

[0032] In a fourth aspect, an embodiment of the present disclosure provides a chip, comprising: a processor for calling and running a computer program from a memory, so that a device equipped with the chip executes the method of the first aspect.

[0033] In a fifth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by at least one processor, the method of the first aspect is implemented.

[0034] In a sixth aspect, an embodiment of the present disclosure provides a computer program product, comprising a computer program or instructions, which, when executed by a processor, implements the method of the first aspect.

[0035] In an embodiment of the present disclosure, operating condition data of a battery in multiple time periods can be obtained from a battery data set, the multiple time periods including a first time period, the type of the operating condition data in the first time period belonging to the first type; further, based on the transition probability of changing from the first type to each type, the operating condition data in the second time period can be determined from the operating condition data in the multiple time periods, the type of the operating condition data in the second time period belonging to the second type (the above-mentioned each type includes the second type); by splicing the operating condition data in the first time period and the second time period, typical operating condition data of the battery can be obtained. According to the method of the embodiment of the present disclosure, the operating condition data in the first time period and the second time period can be extracted from the operating condition data in the multiple time periods for splicing, and in the process of determining the operating condition data in the second time period, the transition probability of changing from the first type (the type of the operating condition data in the first time period) to each type is considered. In this way, the type change of the operating condition data in the spliced ​​typical operating condition data can be more consistent with the change law of the actual scenario, or in other words, the obtained typical operating condition data can be more consistent with the actual application scenario of the battery, and further, when the typical operating condition data is used for battery performance evaluation, it is beneficial to improve the accuracy of the evaluation result.

[0036] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to explain the technical solutions of the present disclosure.

[0038] FIG1 is a schematic flow chart of a method for extracting typical operating conditions of a battery provided by an embodiment of the present disclosure;

[0039] FIG2 is a schematic diagram of a possible implementation flow of a method for extracting typical operating conditions of a battery provided in an embodiment of the present disclosure;

[0040] FIG3 is a schematic diagram of probability density obtained by statistically analyzing average discharge rates in an embodiment of the present disclosure;

[0041] FIG4 is a schematic diagram of splicing currents in various operating condition segments in an embodiment of the present disclosure;

[0042] FIG5 is a schematic diagram of splicing temperatures in various operating condition segments in an embodiment of the present disclosure;

[0043] FIG6 is a schematic diagram of the structure of a device for extracting typical battery operating conditions provided by an embodiment of the present disclosure;

[0044] FIG7 is a schematic diagram of a hardware entity of a device for extracting typical battery operating conditions in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0045] In order to enable a more detailed understanding of the features and technical contents of the embodiments of the present disclosure, the implementation of the embodiments of the present disclosure is described in detail below with reference to the accompanying drawings. The accompanying drawings are for reference only and are not intended to limit the embodiments of the present disclosure.

[0046] Unless otherwise defined, all technical and scientific terms used in the embodiments of the present disclosure have the same meaning as those commonly understood by those skilled in the art. The terms used in the embodiments of the present disclosure are only for the purpose of describing the embodiments of the present disclosure and are not intended to limit the present disclosure.

[0047] In the following description, references to "some embodiments" describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. It should also be noted that the terms "first, second, and third" in the embodiments of the present disclosure are only used to distinguish similar objects and do not represent a specific ordering of the objects. It is understood that the specific order or sequence of "first, second, and third" can be interchanged where permitted, so that the embodiments of the present disclosure described herein can be implemented in an order other than that illustrated or described herein.

[0048] It should be understood that the term "and / or" in the embodiments of the present disclosure is merely a description of the association relationship between associated objects, indicating that three possible relationships exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0049] With the rapid development of the new energy industry, batteries are widely used in different fields such as energy storage, automobiles, and ships. The operating conditions of battery systems in different scenarios vary greatly, and different operating conditions also place different demands on battery cells and battery management systems (BMS).

[0050] In the embodiments of the present disclosure, the battery may be a battery cell (sometimes also referred to as a battery cell), or a battery module or battery pack comprising a plurality of battery cells. A battery cell refers to a basic unit that can realize the mutual conversion of chemical energy and electrical energy, and can be used to make a battery module or battery pack, thereby being used to supply power to electrical devices. A battery cell may be a secondary battery, which refers to a battery cell that can be activated by charging the active material after the battery cell is discharged and can continue to be used. The battery cell may be a lithium-ion battery, a sodium-ion battery, a sodium-lithium-ion battery, a lithium metal battery, a sodium metal battery, a lithium-sulfur battery, a magnesium-ion battery, a nickel-hydrogen battery, a nickel-cadmium battery, a lead-acid battery, etc., and the embodiments of the present disclosure are not limited thereto.

[0051] At present, when evaluating battery performance (the performance of functional modules such as battery cells and battery management systems (BMS) in battery systems), specific operating conditions such as constant rate, constant current, and CLTC are usually used. However, the operating conditions in actual application scenarios are often complex and changeable, which leads to large differences between the actual performance of the battery and the evaluation results under specific operating conditions. For example, the actual battery life is lower than the battery life obtained by CLTC evaluation; for example, the actual cell decay rate is higher than the cell decay rate obtained by evaluation under specific operating conditions; for example, under specific operating conditions, the evaluation results obtained by evaluating the state of charge (SOC) / state of health (SOH) in the battery BMS are significantly different from the SOC / SOH in actual application scenarios, and so on.

[0052] To more accurately evaluate battery performance, operating conditions that better reflect actual battery applications are required. Therefore, finding these operating conditions is a pressing issue.

[0053] In view of this, embodiments of the present disclosure provide a method, apparatus, device, chip, storage medium, and product for extracting typical battery operating conditions. In this method, operating condition data of a battery over multiple time periods can be obtained from a battery data set, where the multiple time periods include a first time period, and the type of the operating condition data in the first time period belongs to the first type. Furthermore, based on the transition probability from the first type to each type, operating condition data for a second time period can be determined from the operating condition data in the multiple time periods, where the type of the operating condition data in the second time period belongs to a second type (where the aforementioned types include the second type). By concatenating the operating condition data for the first and second time periods, typical battery operating condition data can be obtained.

[0054] According to the method of the embodiment of the present disclosure, the operating condition data within the first time period and the second time period can be extracted from the operating condition data within multiple time periods for splicing, and in the process of determining the operating condition data within the second time period, the transition probability from the first type (the type of the operating condition data within the first time period) to each type is considered. In this way, the type change of the operating condition data in the typical operating condition data obtained by splicing can be more in line with the changing law of the actual scenario, or in other words, the typical operating condition data obtained can be more in line with the actual application scenario of the battery. Furthermore, when the typical operating condition data is used for battery performance evaluation, it is beneficial to improve the accuracy of the evaluation results.

[0055] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0056] The present disclosure provides a method for extracting typical battery operating conditions. As shown in FIG1 , the method may include:

[0057] S101 , obtaining operating condition data of a battery in multiple time periods from a battery data set, where the multiple time periods include a first time period, and the operating condition data in the first time period is of a first type.

[0058] S102 , based on the transition probability from the first type to each type, determine the operating condition data within a second time period from the operating condition data within the multiple time periods; the type of the operating condition data within the second time period belongs to the second type, and the various types include the second type.

[0059] S103 , combining the operating condition data in the first time period and the second time period to obtain typical operating condition data of the battery.

[0060] The above steps S101 to S103 are respectively described in detail below.

[0061] S101 , obtaining operating condition data of a battery in multiple time periods from a battery data set, where the multiple time periods include a first time period, and the operating condition data in the first time period is of a first type.

[0062] In this step, the battery's operating condition data (i.e., historical operating condition data) over multiple time periods can be obtained from the battery data set. The durations of different time periods can be the same or different, and a time period can be, for example, 1 minute (min) or 2 minutes. In some embodiments, the battery states within the same time period should be the same to avoid including multiple battery states within the same time period. Battery states can be categorized into, for example, a charging state, a discharging state, and a resting state.

[0063] As an example, the operating condition data of the battery within a certain time period may include, but is not limited to, at least one of the following: the battery's current, temperature, SOC, and discharge rate.

[0064] For example, the multiple time periods may include a first time period, and the type of the operating condition data in the first time period belongs to the first type.

[0065] S102 , based on the transition probability from the first type to each type, determine the operating condition data within a second time period from the operating condition data within the multiple time periods; the type of the operating condition data within the second time period belongs to the second type, and the various types include the second type.

[0066] Since the operating condition data in the first time period is of the first type, the operating condition data in the second time period can be determined from the operating condition data in the multiple time periods based on the transition probabilities from the first type to various types, wherein the operating condition data in the second time period is of the second type, and the various types include the second type. Furthermore, in S103, the operating condition data in the second time period can be concatenated with the operating condition data in the first time period to obtain typical operating condition data of the battery.

[0067] For example, assuming that the operating condition data within the multiple time periods can be divided into three types (or, in other words, each of the above types includes three types), namely Type #1, Type #2, and Type #3. Assuming that the first type is Type #1, then the transition probabilities of changing from the first type to each type may include: the transition probability of changing from the first type to Type #1 (the first type), the transition probability of changing from Type #1 to Type #2, and the transition probability of changing from Type #1 to Type #3. The second type can be any one of Type #1, Type #2, and Type #3. In other words, the second type and the first type can be the same type or different types.

[0068] As an implementation method, the transition probability of changing from type #1 (first type) to the target type (such as type #1, type #2 or type #3) can be calculated, for example, by dividing the number of changes from type #1 to the target type by the total number of occurrences of type #1 operating condition data.

[0069] For example, for two adjacent time periods in the multiple time periods, if the operating condition data in the first time period is of type #1 and the operating condition data in the second time period is of the target type, then it can be considered that a "change from type #1 to the target type" has occurred. If, among the multiple time periods, there are K time periods with operating condition data of type #1, then the total number of occurrences of type #1 operating condition data can be considered to be K.

[0070] For example, assume that the multiple time periods include four time periods arranged in chronological order: Time Period #1, Time Period #2, Time Period #3, and Time Period #4. The operating condition data in Time Period #1 is of Type #1, the operating condition data in Time Period #2 is of Type #2, the operating condition data in Time Period #3 is of Type #3, and the operating condition data in Time Period #4 is of Type #1. Assuming the target type is Type #2, since a change from Type #1 to Type #2 occurred once between Time Period #1 and Time Period #2, the number of changes from Type #1 to Type #2 is 1. Since the operating condition data in Time Period #1 and Time Period #4 is of Type #1, the total number of occurrences of Type #1 operating condition data is 2. In this case, the transition probability from Type #1 to the target type (Type #2) is 1 / 2.

[0071] According to the method of this embodiment, in the process of determining the operating condition data within the second time period, the transition probability from the first type (the type of the operating condition data within the first time period) to each type is taken into consideration. In this way, after splicing the operating condition data within the first time period and the second time period, the type change of the operating condition data in the typical spliced ​​data can be made more consistent with the change law of the actual scenario.

[0072] In some embodiments, before obtaining the operating condition data of the battery in multiple time periods from the battery data set, the method may also include: determining the demand for the typical operating condition data of the battery, which demand is related to at least one of the capacity, duration, and SOC corresponding to the typical operating condition data of the battery; determining the termination condition based on the demand, and when the typical operating condition data of the battery meets the termination condition, the typical operating condition data of the battery meets the demand.

[0073] That is, before obtaining typical battery operating condition data, the requirements for the battery's typical operating condition data can be determined based on the actual scenario. As an example, this requirement can be: at least one of the capacity, duration, or SOC corresponding to the typical operating condition data reaches a certain threshold. Furthermore, a corresponding termination condition can be determined based on this requirement, which serves as the basis for obtaining the typical operating condition data. In this way, when obtaining the battery's typical operating condition data, when the acquired typical operating condition data meets the termination condition, the typical operating condition data that meets the requirements can be obtained.

[0074] Among them, further introduction to the end conditions will be given below and will not be detailed here.

[0075] In some embodiments, based on the transition probabilities from the first type to each type, determining the operating condition data within the second time period from the operating condition data within the multiple time periods can be achieved by following the steps 11) to 13):

[0076] 11) Based on the transition probabilities from the first type to various types, determine whether the type of the operating condition data in the second time period belongs to the second type.

[0077] As an implementation method, first, based on the transition probability from the first type to each type, the probability interval corresponding to each type can be determined; wherein the length of the probability interval corresponding to each type is equal to the transition probability from the first type to that type.

[0078] For example, assuming that the operating condition data within the multiple time periods can be divided into three types, namely type #1 (assuming the first type is type #1), type #2 and type #3, where the transition probability from type #1 to type #1 is P1, the transition probability from type #1 to type #2 is P2, and the transition probability from type #1 to type #3 is P3. Then, the length of the probability interval corresponding to type #1 is P1, the length of the probability interval corresponding to type #2 is P2, and the length of the probability interval corresponding to type #3 is P3.

[0079] As an example, assuming that the values ​​of P1, P2 and P3 are 0.5, 0.3 and 0.2 respectively, then the probability interval corresponding to type #1 can be, for example, [0-0.5], the probability interval corresponding to type #2 can be, for example, [0.5-0.8], and the probability interval corresponding to type #3 can be, for example, [0.8-1.0].

[0080] Furthermore, a random factor may be generated, and when the random factor falls within a probability interval corresponding to the second type, it may be determined that the type of the operating condition data within the second time period belongs to the second type.

[0081] For example, assuming the second type is type #2, a random factor can be randomly generated (e.g., a random factor between 0 and 1 can be randomly generated). If the random factor falls within the probability interval corresponding to type #2, type #2 can be determined as the type of the operating condition data in the second time period. As an example, assuming the generated random factor is 0.6, since 0.6 falls within the probability interval [0.5-0.8] corresponding to type #2, type #2 can be determined as the type of the operating condition data in the second time period.

[0082] It should be understood that in some other examples, the second type may also be type #1 or type #3. For example, the second type may be type #1. In this case, if the random factor falls within the probability interval corresponding to type #1, type #1 may be determined as the type of the operating condition data in the second time period. For another example, the second type may be type #3. In this case, if the random factor falls within the probability interval corresponding to type #3, type #3 may be determined as the type of the operating condition data in the second time period.

[0083] According to the above technical solution, since the length of the probability interval corresponding to type #1 is the longest (length is 0.5) and the length of the probability interval corresponding to type #3 is the shortest (length is 0.2), the probability of the random factor falling within the probability interval corresponding to type #1 is the greatest, and the probability of falling within the probability interval corresponding to type #3 is the least. In other words, the type of the working condition data determined in the second time period (the second type) is most likely to be type #1, and the probability of being type #3 is the least. On the other hand, according to the above calculation results, in the actual scenario, the transition probability P1 of changing from type #1 to type #1 is greater than the transition probability P2 of changing from type #1 to type #2, and the transition probability P3 of changing from type #1 to type #3 is greater than the transition probability P3. Therefore, it can be seen that the determination of the type of the working condition data in the second time period conforms to the objective laws in the actual scenario. Therefore, determining the second type as the type of the working condition data in the second time period, or in other words, determining the second type as the type of the working condition data in the next time period of the first time period, can make the type change of the working condition data in the typical working condition data finally spliced ​​together more consistent with the change law of the actual scenario.

[0084] 12) Determine operating condition data within N candidate time periods from the operating condition data within the multiple time periods, where the operating condition data within the N candidate time periods are of the second type, and N is a positive integer.

[0085] 13) Determine the operating condition data within a candidate time period from the operating condition data within the N candidate time periods as the operating condition data within the second time period.

[0086] In step 11), it has been determined that the type of the operating condition data within the second time period should belong to the second type. Therefore, the operating condition data within N candidate time periods whose type of operating condition data belongs to the second type can be screened out from the operating condition data within the multiple time periods. Furthermore, the operating condition data within a candidate time period can be determined from the operating condition data within the N candidate time periods as the operating condition data within the second time period.

[0087] According to the method of this embodiment, based on the transition probabilities of changing from the first type to various types, it can be determined that the type of the operating condition data within the second time period belongs to the second type. Furthermore, operating condition data within N candidate time periods whose operating condition data belongs to the second type can be screened from the operating condition data within multiple time periods. The operating condition data within one candidate time period can then be determined from the N candidate time periods as the operating condition data within the second time period. Because the transition probabilities of changing from the first type (the type of the operating condition data within the first time period) to various types are taken into account during the process of determining the type of the operating condition data within the second time period, the type changes of the operating condition data within the spliced ​​typical operating condition data can be made more consistent with the changing patterns of actual scenarios.

[0088] In one possible manner, for example, the operating condition data within a candidate time period may be randomly determined from the operating condition data within the N candidate time periods as the operating condition data within the second time period.

[0089] In another possible embodiment, determining the operating condition data within a candidate time period from the operating condition data within the N candidate time periods as the operating condition data within the second time period can be achieved through the following steps: determining the Mahalanobis distance between the operating condition data within the first time period and the operating condition data within each candidate time period in the N candidate time periods; using the operating condition data within the first candidate time period among the N candidate time periods as the operating condition data within the second time period; and among the N candidate time periods, the Mahalanobis distance between the operating condition data within the first candidate time period and the operating condition data within the first time period is the smallest.

[0090] For example, assuming that the N candidate time periods include candidate time period #1, candidate time period #2, and candidate time period #3, the Mahalanobis distance (denoted as D1) between the operating condition data in the first time period and the operating condition data in candidate time period #1, the Mahalanobis distance (denoted as D2) between the operating condition data in the first time period and the operating condition data in candidate time period #2, and the Mahalanobis distance (denoted as D3) between the operating condition data in the first time period and the operating condition data in candidate time period #3 can be determined respectively. Assuming D2>D1>D3, the operating condition data in candidate time period #3 can be used as the operating condition data in the second time period.

[0091] According to the method of this embodiment, in the process of determining the operating condition data within the second time period from the operating condition data within N candidate time periods, the operating condition data within a time period having the smallest Mahalanobis distance with the operating condition data within the first time period can be selected as the operating condition data within the second time period. In this way, after the operating condition data within the first time period and the second time period are spliced ​​together, it can be ensured that the spliced ​​operating condition data (typical operating condition data) will not undergo mutations. That is, the spliced ​​operating condition data can have better consistency and thus be more in line with the objective laws in actual scenarios.

[0092] In some embodiments, the method may further include: determining the characteristic value of the operating condition data in each of the multiple time periods; clustering the operating condition data in the multiple time periods based on the characteristic value of the operating condition data in each of the multiple time periods to obtain the type of the operating condition data in each of the multiple time periods.

[0093] For example, assuming the operating condition data for each time period includes the battery's current, temperature, and SOC, the following operations can be performed for each time period: Integrate the battery's current in ampere-hours to obtain the battery capacity (referred to as capacity) corresponding to that time period; calculate the average battery temperature for that time period to obtain the average temperature corresponding to that time period; and calculate the average battery SOC for that time period to obtain the average SOC corresponding to that time period. The capacity, average temperature, and average SOC corresponding to that time period can then be used as the characteristic values ​​of the operating condition data for that time period.

[0094] Furthermore, the operating condition data for the multiple time periods can be clustered based on the capacity, average temperature, and average SOC corresponding to each time period, thereby determining the type of the operating condition data for each time period. For example, through clustering, the capacity, average temperature, and average SOC corresponding to the first time period can be aggregated into the first type, and thus the type of the operating condition data for the first time period can be determined to be the first type.

[0095] It should be understood that the embodiments of the present disclosure do not limit the clustering algorithm used for clustering. As an example, the clustering algorithm may be a K-means clustering algorithm, a mean shift clustering algorithm, a density-based clustering algorithm, etc.

[0096] According to the method of this embodiment, by clustering the operating condition data in multiple time periods, the type of the operating condition data in each time period can be obtained. For example, it can be obtained that the type of the operating condition data in the first time period is the first type. Therefore, the operating condition data in the second time period can be determined based on the transition probability from the first type to each type, so that the operating condition data in the first time period and the second time period can be subsequently spliced ​​to obtain the typical operating condition data of the battery.

[0097] In some embodiments, before obtaining the operating condition data of the battery in multiple time periods from the battery data set, the method may further include the following steps 21) to 24):

[0098] 21) Obtaining battery operating condition data over multiple cycles from a battery data set.

[0099] A period may be, for example, one hour, one day, one week, one month, one quarter, etc.

[0100] For example, if a cycle is one day, the battery's operating condition data for multiple days can be obtained. For example, the battery's operating condition data generated every day over a period of time can be counted.

[0101] For example, the operating condition data of the battery in a cycle may include, for example, the average temperature, average discharge rate, maximum SOC, or minimum SOC of the battery in the cycle.

[0102] 22) Determine a first parameter of the operating condition data within the multiple cycles. The first parameter may be, for example, any one of the following: mode, mean, or the value of the operating condition data corresponding to the maximum value of the probability density function.

[0103] In one example, the first parameter is a mode. In this case, the mode of the operating condition data within the multiple cycles can be determined. For example, assuming the operating condition data is the average discharge rate, the mode of the average discharge rate within the multiple cycles can be calculated. This mode is the first parameter of the operating condition data within the multiple cycles.

[0104] In another example, the first parameter is an average. In this case, the average of the operating condition data over the multiple cycles can be determined. For example, assuming the operating condition data is an average discharge rate, the average of the average discharge rates over the multiple cycles can be calculated, and this average is the first parameter of the operating condition data over the multiple cycles.

[0105] In another example, the first parameter is the value of the operating condition data corresponding to the maximum value of the probability density function. In this case, the probability density function of the operating condition data over the multiple cycles can be first determined, and then the value of the operating condition data corresponding to the maximum value of the probability density function can be determined. Taking the operating condition data as the average discharge rate as an example, the probability density function of the average discharge rate over the multiple cycles can be first determined, and then the value of the average discharge rate corresponding to the maximum value of the probability density function can be determined. This value is the first parameter of the operating condition data over the multiple cycles.

[0106] 23) Determine at least one target cycle from the multiple cycles, and the difference between the value of the operating condition data in the at least one target cycle and the first parameter is less than or equal to a first threshold.

[0107] Assuming the value of the first parameter is a, then at least one target cycle can be determined from the multiple cycles, and the difference between the operating condition data value within the at least one target cycle and a is less than or equal to a first threshold. In other words, the operating condition data value within the at least one target cycle can be within the range [ab, a+c], where b and c can be equal or unequal. If b and c are unequal, the larger of b and c must be less than or equal to the first threshold.

[0108] For example, if the operating condition data is an average discharge rate, then the difference between the value of the average discharge rate in the at least one target cycle and the first parameter a should be less than or equal to the first threshold.

[0109] 24) Divide the at least one target period to obtain the aforementioned multiple time periods.

[0110] After determining the at least one target period, the at least one target period may be divided into shorter time periods, thereby obtaining the aforementioned multiple time periods.

[0111] According to the method of this embodiment, at least one target period can be determined from multiple periods, and the difference between the value of the operating condition data within the target period and the first parameter is less than or equal to the first threshold. In this way, the value of the operating condition data within the target period is within a range with a high probability of occurrence. It is understandable that if the probability of occurrence of the operating condition data value within a certain period is low, it means that the operating condition data within this period is not representative. However, through the above technical solution, this period can be eliminated, and only the target period is retained, thereby making the retained operating condition data within the target period more representative, and thus making the operating condition data within the multiple time periods obtained more representative.

[0112] In some embodiments, before obtaining the operating condition data of the battery in multiple time periods from the battery data set, the method may further include the following steps 31) to 35):

[0113] 31) Obtaining operating condition data of the battery over multiple cycles from the battery data set, where the operating condition data are of various types.

[0114] For example, the operating condition data of the battery in a cycle may include, but is not limited to, at least two of the following: the average temperature of the battery in the cycle, the average discharge rate, the maximum SOC, and the minimum SOC.

[0115] Taking one day as an example, assuming that the battery's operating data for one day includes average temperature and average discharge rate, then the average temperature and average discharge rate generated by the battery every day over a period of time can be calculated.

[0116] 32) Determine a first parameter of each type of operating condition data within the multiple cycles. The first parameter may be, for example, any one of the following: mode, mean, or the value of the operating condition data corresponding to the maximum value of the probability density function.

[0117] For example, assuming that the operating condition data of the battery over a cycle includes average temperature and average discharge rate, a first parameter of the average temperature over the multiple cycles can be determined, and a first parameter of the average discharge rate over the multiple cycles can be determined. The method for determining the first parameter can be referred to in step 22 above and will not be repeated here.

[0118] 33) For each type of operating condition data within the multiple cycles, at least one target cycle is determined from the multiple cycles, and the difference between the value of the type of operating condition data within the at least one target cycle and the corresponding first parameter is less than or equal to the first threshold corresponding to the type.

[0119] For example, assuming that the operating condition data of the battery in a cycle includes average temperature and average discharge rate, then, for the average temperature in multiple cycles, at least one target cycle can be determined from the multiple cycles, and the difference between the average temperature in the at least one target cycle and the corresponding first parameter (i.e., the first parameter of the average temperature in the multiple cycles) is less than or equal to a first threshold.

[0120] Similarly, for the average discharge rate within the multiple cycles, at least one target cycle can be determined from the multiple cycles, and the difference between the value of the average discharge rate within the at least one target cycle and the corresponding first parameter (that is, the first parameter of the average discharge rate within the multiple cycles) is less than or equal to the first threshold.

[0121] 34) Determine the intersection of all target periods to obtain M target periods, where M is a positive integer.

[0122] For example, assuming that at least one target cycle determined for the average temperature includes P target cycles, and at least one target cycle determined for the average discharge rate includes Q target cycles, then the intersection of the P target cycles and the Q target cycles can be determined to obtain M target cycles.

[0123] 35) Divide the M target periods to obtain the above-mentioned multiple time periods.

[0124] After determining the M target periods, the M target periods may be divided into shorter time periods, thereby obtaining the aforementioned multiple time periods.

[0125] According to the method of this embodiment, M target periods can be determined from multiple periods, and the difference between the value of each type of operating condition data within the target period and the corresponding first parameter is less than or equal to the first threshold. This ensures that the value of each type of operating condition data within the target period falls within a range with a high probability of occurrence, making the operating condition data within the target period more representative, and further making the operating condition data within the multiple time periods more representative.

[0126] S103 , combining the operating condition data in the first time period and the second time period to obtain typical operating condition data of the battery.

[0127] The operation data in the first time period and the second time period are spliced ​​together, which can also be understood as splicing the operation data in the second time period after the operation data in the first time period. In some embodiments, the first time period can be a time period randomly determined from the multiple time periods.

[0128] It should be noted that if there are multiple types of operating condition data, each type of operating condition data can be spliced ​​separately. For example, if the operating condition data for the first and second time periods include battery current and temperature, the battery current for the second time period can be spliced ​​after the battery current for the first time period, and the battery temperature for the second time period can be spliced ​​after the battery temperature for the first time period, thereby obtaining the typical operating condition data of the battery.

[0129] In some embodiments, the method may further include: if the typical operating condition data of the battery does not meet the termination condition, updating the typical operating condition data of the battery by performing the following steps 41) and 42):

[0130] 41) Based on the transition probability of changing from the second type to each type, determine the operating condition data in the next time period from the operating condition data in multiple time periods; the type of the operating condition data in the next time period is included in the above types.

[0131] If the type of the operating condition data in the previous time period belongs to the second type, the operating condition data in the next time period may be determined from the operating condition data in multiple time periods based on the transition probabilities from the second type to various types. The previous time period may be the second time period.

[0132] In this embodiment, based on the transition probability of changing from the second type to each type, the implementation method of the operating condition data in the next time period is determined from the operating condition data in multiple time periods. Please refer to S102 for determining the implementation method of the operating condition data in the second time period from the operating condition data in the multiple time periods based on the transition probability of changing from the first type to each type, which will not be repeated here.

[0133] 42) The operating condition data in the next time period is spliced ​​onto the operating condition data in the previous time period to obtain updated typical operating condition data of the battery, where the previous time period is the second time period.

[0134] After determining the operating condition data in the next time period, the operating condition data in the next time period may be spliced ​​onto the operating condition data in the previous time period to obtain updated typical operating condition data of the battery.

[0135] According to the method of this embodiment, if the typical operating condition data of the battery does not meet the termination condition, the type of the operating condition data (such as the second type) in the previous time period (such as the second time period) can be changed to the transition probability of each type. The operating condition data in the next time period can be determined from the operating condition data in these multiple time periods. The operating condition data in the next time period can then be spliced ​​after the operating condition data in the previous time period to obtain the updated typical operating condition data of the battery. This method can ensure that the type change of the operating condition data in the updated typical operating condition data of the battery can better conform to the changing laws of actual scenarios.

[0136] In some embodiments, the typical operating condition data of the battery includes operating condition data within L time periods, where L is a positive integer. In this case, the termination condition may include, for example, at least one of the following: the cumulative capacity of the battery within the L time periods reaches a second threshold; the cumulative duration corresponding to the L time periods reaches a third threshold; or the cumulative SOC corresponding to the L time periods reaches a fourth threshold, where the SOC corresponding to each time period is the difference between the maximum SOC and the minimum SOC of the battery within that time period.

[0137] For example, assuming that the requirement for typical battery operating condition data includes: the capacity corresponding to the typical operating condition data reaches a certain threshold (such as a second threshold), the termination condition may include: the cumulative capacity of the battery within the L time periods reaches the second threshold. In this case, if the cumulative capacity of the battery within the L time periods reaches the second threshold, updating the battery's typical operating condition data can be stopped, that is, new operating condition data is stopped from being appended to the end of the typical operating condition data.

[0138] As another example, assuming that the requirement for typical battery operating condition data includes: the duration corresponding to the typical operating condition data reaches a certain threshold (such as a third threshold), the termination condition may include: the cumulative duration corresponding to the L time periods reaches the third threshold. In this case, if the cumulative duration corresponding to the L time periods reaches the third threshold, updating the typical battery operating condition data may be stopped.

[0139] As another example, assuming that the requirement for typical operating condition data of a battery includes: the SOC corresponding to the typical operating condition data reaches a certain threshold (such as a fourth threshold), then the termination condition may include: the cumulative SOC corresponding to the L time periods reaches the fourth threshold, wherein the SOC corresponding to each time period is: the difference between the maximum SOC and the minimum SOC of the battery during that time period. For example, assuming that the L time periods include a first time period, a second time period, and a third time period, wherein the difference between the maximum SOC and the minimum SOC during the first time period is 2, the difference between the maximum SOC and the minimum SOC during the second time period is 3, and the difference between the maximum SOC and the minimum SOC during the third time period is 1, then the SOC corresponding to the first time period, the second time period, and the third time period are 2, 3, and 1, respectively. In this case, the cumulative value of the SOC corresponding to the L time periods is 2+3+1=6. According to the termination condition, if the cumulative value 6 reaches the fourth threshold, then updating the typical operating condition data of the battery can be stopped.

[0140] According to the method of this embodiment, the data amount of the typical operating condition data of the battery can be flexibly controlled through the end condition, thereby obtaining typical operating condition data that meets the requirements.

[0141] To facilitate understanding of the embodiments of the present disclosure, the following describes a possible implementation process of the method for extracting typical battery operating conditions provided by the embodiments of the present disclosure. As shown in FIG2 , the implementation process may include:

[0142] S201, obtaining the operating condition data of the battery throughout its entire life cycle and performing data cleaning.

[0143] For example, the operating condition data of the battery from its launch to its retirement can be obtained from the battery data recorded and stored by the BMS, that is, the operating condition data of the battery throughout its entire life cycle (historical operating condition data). The obtained operating condition data can then be cleaned.

[0144] As an implementation method, invalid data in the operating condition data may be replaced by the previous frame of data.

[0145] Taking temperature data as an example, Table 1 shows the pre-cleaning and post-cleaning temperature data from time #1 to time #5. As shown in Table 1, the pre-cleaning temperature data of "-40" corresponding to time #3 is obviously invalid data. Therefore, "-40" can be replaced with the previous frame of data (i.e., "25"), so that the post-cleaning temperature data corresponding to time #3 is "25".

[0146] Table 1

[0147] As another implementation, invalid data in the operating condition data can be replaced with the average of the two frames of data before and after. Taking Table 1 as an example, the data before and after the frame of "-40" is both "25", so the average of the two frames of data before and after "-40" is "25". Therefore, after data cleaning of "-40", "-40" can be changed to "25".

[0148] S202: Count key operating condition data in the operating condition data according to the period.

[0149] For example, assuming that a cycle is one day, the key operating condition data include average temperature, average discharge rate, maximum SOC and minimum SOC, then the average temperature, average discharge rate, maximum SOC and minimum SOC of each day can be counted according to the number of days.

[0150] Table 2 shows the key operating data from May 20 to May 24.

[0151] Table 2

[0152] In some embodiments, the data efficiency within each cycle can be calculated and cycles with an efficiency below a threshold can be eliminated. The data efficiency within a cycle = the number of cleaned operating condition data within that cycle / the total number of operating condition data within that cycle. Taking Table 2 as an example, assuming a threshold of 0.95, since the data efficiency for May 22nd is 0.7, which is below the threshold of 0.95, the operating condition data for May 22nd can be eliminated. This makes the remaining operating condition data more valuable for reference.

[0153] S203: Select representative typical cycles based on the key operating condition data.

[0154] In this step, for each key operating condition data, the probability density of the statistical data distribution can be calculated separately.

[0155] As an example, for the average discharge magnification, the probability density obtained by statistics is shown in Figure 3. Among them, when the average magnification is a, the probability density is the largest.

[0156] In one possible approach, we can use the value a as the center and take 35% to the left and right (i.e., 1σ to the left and right) to obtain the interval [a-σ, a+σ] (i.e., the interval with a probability of 70%). Furthermore, we can take all periods (e.g., dates) whose average magnification falls within the interval [a-σ, a+σ] as a set to obtain a typical set of periods corresponding to the average magnification.

[0157] Taking a cycle of one day as an example, assuming that the average discharge rate of 10 days falls within the interval [a-σ, a+σ]. In other words, the average discharge rate of each day in the 10 days falls within the interval [a-σ, a+σ]. Then, the 10 dates corresponding to the 10 days can be regarded as a set, which is the typical cycle set corresponding to the average discharge rate.

[0158] By performing the above operations on each key operating condition data, a typical cycle set corresponding to each key operating condition data can be obtained. For example, in this embodiment, corresponding typical cycle sets can be obtained for average temperature, average discharge rate, maximum SOC, and minimum SOC, resulting in four typical cycle sets. Furthermore, the intersection of these four typical cycle sets can be taken to obtain the final typical cycle set.

[0159] According to the method of this embodiment, the values ​​of each key operating condition data within the typical cycle set are ultimately obtained to fall within a range with a high probability of occurrence. It is understood that if the probability of occurrence of the key operating condition data within a certain cycle is low, it indicates that the key operating condition data within that cycle is not representative. However, the above technical solution can eliminate this cycle (outlier cycle) and retain only the cycles within the typical cycle set, thereby making the operating condition data within the retained cycles more representative.

[0160] In some embodiments, a typical cycle set can also be obtained based on statistical values ​​such as mode and mean. For example, for the average discharge rate, the mode / mean of the average discharge rate in all cycles can be counted. Assuming that the value of the mode / mean is b, then the value b can be used as the center and a certain range can be taken to the left and right to obtain the interval [bc, b+d], where c and d can be the same or different. Furthermore, all cycles (such as dates) whose average discharge rate falls within the interval [bc, b+d] can be taken as a set to obtain a typical cycle set corresponding to the average discharge rate.

[0161] In some embodiments, after obtaining the typical cycle set, a portion of the cycles in the typical cycle set may be randomly deleted to further reduce the amount of data.

[0162] S204 , dividing the operating condition data in the typical cycle set to obtain multiple operating condition segments.

[0163] In this step, the cycles within the typical cycle set may be split / divided into shorter time periods, for example, every 2 minutes.

[0164] In some embodiments, when dividing time periods, it is necessary to ensure that the battery status within the same time period is the same to avoid including multiple battery statuses (battery status may include charging state, discharging state, and static state) within the same time period. For example, the battery status in time period #1 is all charging state, the battery status in time period #2 is all discharging state, and the battery status in time period #3 is all static state.

[0165] For each time period, the operating condition characteristic value corresponding to that time period can be obtained based on the operating condition data (raw operating condition data) within that time period. For example, the following operations can be performed for each time period: the current within that time period is read and the ampere-hour integration of the current within that time period is performed (i.e., the current is multiplied by time and then accumulated) to obtain the capacity corresponding to that time period; the battery temperature (which can be simply referred to as temperature) within that time period is read and the average battery temperature within that time period is calculated to obtain the average temperature corresponding to that time period; the SOC within that time period is read and the average SOC within that time period is calculated to obtain the average SOC corresponding to that time period. The capacity, average temperature, and average SOC corresponding to that time period are the operating condition characteristic values ​​corresponding to that time period.

[0166] For ease of description, each time period and the data it contains (operating condition data) are referred to as an operating condition segment below. Table 3 shows an example of 5 operating condition segments. Among them, the three numerical values ​​in the operating condition characteristic value represent the capacity, average temperature and average SOC respectively. In the example of Table 3, the time period is divided every 2 minutes (min). For example, the time period [1min, 2min] corresponds to the operating condition segment #1, the time period [5min, 6min] corresponds to the operating condition segment #4, and the time period [7min, 8min] corresponds to the operating condition segment #5. It should be noted that in order to ensure that the battery status is the same in the same time period, the 3rd minute can correspond to the operating condition segment #2 alone, and the 4th minute can correspond to the operating condition segment #3 alone.

[0167] Table 3

[0168] S205: Clustering the obtained operating condition segments.

[0169] In this step, each operating condition segment can be clustered based on its operating condition feature value. The number of clustering categories can be determined based on actual business needs. For example, the operating condition segments can be divided into 9 categories through clustering.

[0170] It should be understood that the embodiments of the present disclosure do not limit the clustering algorithm used for clustering. As an example, the clustering algorithm may be a K-means clustering algorithm, a mean shift clustering algorithm, a density-based clustering algorithm, etc.

[0171] In some embodiments, before clustering the various operating condition segments, the operating condition characteristic values ​​may also be standardized, and the adopted normalization algorithm may be, for example, the minimum-maximum (min-max) normalization method, the z-score normalization method, the proportion method, etc.

[0172] S206 , based on the transition probability between different types of operating condition segments and the Mahalanobis distance between the operating condition segments, the operating condition segments are spliced ​​to obtain a typical operating condition.

[0173] Assuming that the operating condition segments are divided into 9 categories in S205 , the transition probability matrices of the 9 categories of operating condition segments can be calculated.

[0174] To facilitate understanding, the following introduces the transition probability matrix using three types of operating condition segments as an example.

[0175] Table 4 shows an example of a transition probability matrix for three types of operating condition segments. The first row of data represents the probability of a segment transitioning from type #1 to type #1 (i.e., 0.5), the probability of a segment transitioning from type #1 to type #2 (i.e., 0.3), and the probability of a segment transitioning from type #1 to type #3 (i.e., 0.2). The second row of data represents the probability of a segment transitioning from type #2 to type #1 (i.e., 0.4), the probability of a segment transitioning from type #2 to type #2 (i.e., 0.4), and the probability of a segment transitioning from type #2 to type #3 (i.e., 0.2). The third row of data represents the probability of a segment transitioning from type #3 to type #1 (i.e., 0.1), the probability of a segment transitioning from type #3 to type #2 (i.e., 0.3), and the probability of a segment transitioning from type #3 to type #3 (i.e., 0.6).

[0176] The transition from type #A (A is 1, 2, or 3) to type #B (B is 1, 2, or 3) can also be understood as the transition from type A to type B. For example, in Table 3, from the 1st to the 3rd minute, the operating condition segment transitions from type #1 to type #2; from the 3rd to the 4th minute, the operating condition segment transitions from type 2 to type #1; and from the 4th to the 6th minute, the operating condition segment transitions from type #1 to type #1.

[0177] Table 4

[0178] Below, we'll use the example of a condition segment transitioning from type #1 to type #2 to explain how to calculate the probability of a condition segment transitioning from type #1 to type #2. For example, the probability of a condition segment transitioning from type #1 to type #2 is calculated as follows: the number of times a condition segment transitions from type #1 to type #2 (i.e., the number of times a type 1 condition segment changes to a type 2 condition segment after it occurs) / the total number of times type #1 condition segments occur. For example, in Table 3, the number of times a condition segment transitions from type #1 to type #2 is 1, and the total number of times type #1 condition segments occur is 3. The remaining probabilities are calculated similarly.

[0179] Furthermore, the transition probability matrix can be modified to obtain probability intervals for subsequent calculations. The probability intervals obtained by modifying the transition probability matrix shown in Table 4 are shown in Table 5. The interval length of each probability interval is the size of the probability of the corresponding position in Table 4. For example, the probability interval of the first row and first column in Table 5 is [0-0.5], and the interval length of this probability interval is 0.5, which is the size of the probability of the first row and first column in Table 4; for another example, the probability interval of the first row and second column in Table 5 is [0.5-0.8], and the interval length of this probability interval is 0.3, which is the size of the probability of the first row and second column in Table 4.

[0180] Table 5

[0181] To obtain typical operating conditions, perform steps 1 to 3 below.

[0182] Step 1: Randomly determine the initial type of the operating condition segment, and randomly obtain a operating condition segment of the initial type.

[0183] Assuming that the randomly determined initial type is type #1, then a condition segment can be randomly selected from all type #1 condition segments as the initial condition segment. Assuming that the initial condition segment is condition segment 1_5,

[0184] In this embodiment, the operating condition segment i_j indicates that the operating condition segment is the j-th operating condition segment of type i.

[0185] Step 2: Randomly generate a random number between 0 and 1 (corresponding to the random factor in the above embodiment), and determine the next operating condition segment based on the random number.

[0186] Assuming that the generated random number is 0.6, according to Table 5, 0.6 is within the probability interval [0.5-0.8], which corresponds to type #2. Therefore, it can be determined that the type of the next operating condition segment is type #2.

[0187] Step 3: Calculate the Mahalanobis distance between the operating condition segment 1_5 and each operating condition segment in type #2, and use the operating condition segment in type #2 that has the closest Mahalanobis distance to the operating condition segment 1_5 as the next operating condition segment.

[0188] Assuming that the operating condition segment of type #2 that has the closest Mahalanobis distance to the operating condition segment 1_5 is the operating condition segment 2_8, the operating condition segment 2_8 can be used as the next operating condition segment of the operating condition segment 1_5.

[0189] Repeat the above process to obtain a list of operating condition segments. Table 6 shows an example of an operating condition segment list. Among them, operating condition segments 1-5 can be determined by random selection, and other operating condition segments can be calculated based on the previous operating condition segment.

[0190] Table 6

[0191] In some embodiments, if the cumulative capacity of the operating condition segments in the operating condition segment list reaches a certain threshold (such as the second threshold in the aforementioned embodiment), or the cumulative duration corresponding to the operating condition segments in the operating condition segment list reaches a certain threshold (such as the third threshold in the aforementioned embodiment), or the cumulative SOC corresponding to the operating condition segments in the operating condition segment list reaches a certain threshold (such as the fourth threshold in the aforementioned embodiment), then adding new operating condition segments to the operating condition segment list can be stopped.

[0192] As an example, assuming the rated capacity of the battery cell is 100Ah, the second threshold value can be determined to be 100Ah, which is 1 times the rated capacity. Alternatively, the second threshold value can be determined to be other values ​​according to actual business needs, which is not limited in the embodiments of the present disclosure.

[0193] After obtaining the operating condition segment list, the operating condition data in each operating condition segment can be spliced ​​in the order of the operating condition segments in the operating condition segment list to obtain the final typical operating condition. If the operating condition segment contains multiple operating condition data, each operating condition data can be spliced ​​separately.

[0194] For example, if the operating condition data contained in the operating condition fragments include current and temperature, the current in each operating condition fragment can be spliced ​​according to the order of the operating condition fragments in the operating condition fragment list (the splicing result is shown in Figure 4), and the temperature in each operating condition fragment can be spliced ​​(the splicing result is shown in Figure 5), so as to obtain the final typical operating condition.

[0195] S207, establishing a typical operating condition library for different types of battery products to evaluate the performance of the battery system.

[0196] For different types of battery products, at least one typical operating condition of each type of battery product can be obtained according to the methods in S201 to S206 above, so that a typical operating condition library can be established for each type of battery product. Furthermore, the operating conditions (such as current and temperature) of the battery can be controlled in the laboratory according to the typical operating conditions in the typical operating condition library, and the performance of the battery cell and BMS algorithm under different operating conditions can be tested. According to the method of this embodiment, representative typical operating conditions of the battery can be extracted from a large amount of battery historical data, thereby providing a reference for the development and testing of functions such as battery cells and BMS. By extracting the typical operating conditions of the battery, a more comprehensive battery performance evaluation can be achieved to reduce the error between the battery performance evaluation results in the laboratory simulation scenario and the battery performance in the actual scenario.

[0197] The method of the embodiment of the present disclosure can solve the following technical problems:

[0198] 1) Difficulty in applying real historical data: As battery applications expand, a vast amount of historical data has accumulated across various battery products. Assuming a battery generates one frame of data per second, this translates to 86,400 pieces of data per day. Over several years, this massive amount of data will accumulate, resulting in an excessively large data volume.

[0199] 2) Poor data quality: For example, during data acquisition, the following situations may occur: the battery device is not working or is overloaded for special reasons, or the uploaded data is invalid due to a communication failure, or data is missing due to a transmission interruption. If these situations occur, the acquired data may not be directly usable, or the acquired data may not accurately reproduce the battery's usage cycle and operating conditions in real-world scenarios during testing.

[0200] 3) The problem of difficulty in obtaining representative working conditions: The performance of battery cells and BMS in the battery system will be affected by the working conditions of the battery, such as temperature, current, SOC, etc. The working conditions in the application environment of different products vary greatly, and the battery performance will also vary under different working conditions. In addition, the battery performance test in the laboratory is usually a short-cycle test (such as one charge / discharge cycle of the battery, one day, etc.), so the selection of short-cycle working conditions is very important for the objective evaluation of battery performance. The working conditions of the battery will also change during use, so it is necessary to adjust the relevant parameters based on the working conditions. For example, the parameters of the battery algorithm can be adjusted based on the historical working condition change characteristics of the battery.

[0201] In response to the above technical issues 1) and 2), in this embodiment, in order to reduce the amount of data, some interfering data can be eliminated, and preliminary screening logic can be designed based on the characteristics of the battery cells. In addition, the use of batteries often has certain periodic patterns, so the key characteristics of the battery (such as: total charge / discharge capacity, average charge / discharge power, average charge / discharge rate, maximum / minimum SOC, maximum / minimum / average temperature, data efficiency, etc.) can be counted according to the cycle (such as by hour, day, week, month, quarter, etc.), and then typical cycles can be screened out.

[0202] In the process of screening typical cycles, statistics can be combined with key operating condition data to ensure that the values ​​of each key operating condition data in the screened typical cycles are within a range with a high probability of occurrence (for example, within ±1σ of the mean value, or within a certain range near the mode, etc.). In some embodiments, cycles with data efficiency below a threshold can also be eliminated to make the operating condition data in the retained typical cycles more valuable for reference. Furthermore, by taking the intersection of the typical cycle sets corresponding to each key operating condition data, a representative typical cycle set can be obtained.

[0203] In response to the above technical problem 3), in this embodiment, the data in the typical cycle set can be divided into smaller data segments / operating condition segments (for example, division is performed every 1 minute or every 2 minutes), and then the operating condition segments are aggregated using the K-means clustering algorithm based on the operating condition feature values ​​of the operating condition segments (such as capacity, average temperature, and average SOC). The aggregation is into n operating condition types containing multiple operating condition segments, which are recorded as type #1, type #2, type #3, ..., type #n, etc. After that, the transition probability (transition probability) between different types can be calculated, and a sequence of possible operating condition types can be spliced ​​out based on the transition probability. Then, based on the Mahalanobis distance between the operating condition segments, the operating condition segment closest to the previous operating condition segment under this type is obtained. After splicing these operating condition segments, a typical operating condition can be obtained. The typical operating condition can better simulate the actual operating condition of the battery.

[0204] The method of the embodiment of the present disclosure has the following advantages:

[0205] 1) More representative working conditions can be obtained from big data (for example, a few thousand rows of representative working condition data can be extracted from tens of millions of rows of working condition data).

[0206] 2) The extracted operating conditions (typical operating conditions) are more representative of the actual operating conditions of the battery. Therefore, using typical operating conditions for testing the SOC and SOH performance of battery cells and evaluating the performance of the BMS algorithm can reduce the error between the test / evaluation results and the actual results (for example, the error in the actual battery range, the error in the SOC calculation accuracy, etc.).

[0207] 3) Different parameters can be designed for different operating conditions. For example, the battery's operating conditions over a period of time can be obtained and dynamically updated based on the characteristics of these conditions. For example, if the battery has been operating at a high temperature over the past week, the battery thermal management parameters related to cooling can be adjusted. For example, the cooling water circulation rate can be increased to improve cooling efficiency.

[0208] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, the technical solutions of the present disclosure can be subjected to various simple modifications, and these simple modifications all fall within the scope of protection of the present disclosure. For example, the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe the various possible combinations. For another example, the various different embodiments of the present disclosure can also be arbitrarily combined, and as long as they do not violate the ideas of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure. For another example, under the premise of no conflict, the various embodiments and / or the technical features in each embodiment described in the present disclosure can be arbitrarily combined with the prior art, and the technical solutions obtained after the combination should also fall within the scope of protection of the present disclosure.

[0209] Based on the aforementioned embodiments, the present disclosure provides a corresponding device for extracting typical battery operating conditions. The device includes various modules and submodules included in each module, and can be implemented by a processor in a computer device with information processing capabilities; of course, it can also be implemented by a specific logic circuit. During implementation, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA).

[0210] An embodiment of the present disclosure provides a device for extracting typical battery operating conditions. As shown in FIG6 , the device 600 for extracting typical battery operating conditions (hereinafter referred to as the device 600 ) may include:

[0211] The first acquisition unit 601 is used to obtain the operating condition data of the battery in multiple time periods from the battery data set, the multiple time periods include the first time period, and the type of the operating condition data in the first time period belongs to the first type; the first determination unit 602 is used to determine the operating condition data in the second time period from the operating condition data in the multiple time periods based on the transition probability from the first type to each type; the type of the operating condition data in the second time period belongs to the second type, and the each type includes the second type; the splicing unit 603 is used to splice the operating condition data in the first time period and the second time period to obtain typical operating condition data of the battery.

[0212] In some embodiments, the device 600 also includes a second determination unit for determining a requirement for typical operating condition data of the battery before obtaining the operating condition data of the battery in multiple time periods from the battery data set, where the requirement is related to at least one of the capacity, duration, and state of charge SOC corresponding to the typical operating condition data of the battery; and a third determination unit for determining an end condition based on the requirement, where the typical operating condition data of the battery meets the end condition, and the typical operating condition data of the battery meets the requirement.

[0213] In some embodiments, the first determination unit 602 includes: a first determination subunit, used to determine that the type of the operating condition data within the second time period belongs to the second type based on the transition probability from the first type to each type; a second determination subunit, used to determine the operating condition data within N candidate time periods from the operating condition data within multiple time periods, the type of the operating condition data within the N candidate time periods belongs to the second type, and N is a positive integer; a third determination subunit, used to determine the operating condition data within a candidate time period from the operating condition data within the N candidate time periods as the operating condition data within the second time period.

[0214] In some embodiments, the first determination subunit is specifically used to: determine the probability interval corresponding to each type in each type based on the transition probability from the first type to each type; wherein the length of the probability interval corresponding to each type is equal to the transition probability from the first type to the type; when the random factor falls within the probability interval corresponding to the second type, determine that the type of the operating condition data in the second time period belongs to the second type.

[0215] In some embodiments, the third determination subunit is specifically used to: determine the Mahalanobis distance between the operating condition data in the first time period and the operating condition data in each of the N candidate time periods; use the operating condition data in the first candidate time period among the N candidate time periods as the operating condition data in the second time period; among the N candidate time periods, the Mahalanobis distance between the operating condition data in the first candidate time period and the operating condition data in the first time period is the smallest.

[0216] In some embodiments, the device 600 also includes: a fourth determination unit, used to determine the characteristic value of the operating condition data in each of the multiple time periods; a clustering unit, used to cluster the operating condition data in the multiple time periods based on the characteristic value of the operating condition data in each of the multiple time periods, and obtain the type of the operating condition data in each of the multiple time periods.

[0217] In some embodiments, the device 600 also includes: a second acquisition unit, used to obtain the operating condition data of the battery in multiple cycles from the battery data set before obtaining the operating condition data of the battery in multiple time periods from the battery data set; a fifth determination unit, used to determine a first parameter of the operating condition data in multiple cycles, the first parameter being any one of the following: the mode, the mean, the value of the operating condition data corresponding to the maximum value of the probability density function; a sixth determination unit, used to determine at least one target cycle from multiple cycles, the difference between the value of the operating condition data in at least one target cycle and the first parameter being less than or equal to a first threshold; a first division unit, used to divide at least one target cycle to obtain multiple time periods.

[0218] In some embodiments, the device 600 also includes: a third acquisition unit, used to obtain the operating condition data of the battery in multiple cycles from the battery data set before obtaining the operating condition data of the battery in multiple time periods from the battery data set, and there are multiple types of operating condition data; a seventh determination unit, used to determine the first parameter of each type of operating condition data in multiple cycles, the first parameter being any one of the following: the mode, the mean, and the value of the operating condition data corresponding to the maximum value of the probability density function; an eighth determination unit, used to determine at least one target cycle from the multiple cycles for each type of operating condition data in the multiple cycles, the difference between the value of the operating condition data of the type in at least one target cycle and the corresponding first parameter is less than or equal to the first threshold corresponding to the type; a ninth determination unit, used to determine the intersection of all target cycles to obtain M target cycles, where M is a positive integer; a second division unit, used to divide the M target cycles to obtain multiple time periods.

[0219] In some embodiments, the device 600 also includes: an updating unit, which is used to update the typical operating condition data of the battery by executing the following steps when the typical operating condition data of the battery does not meet the termination conditions: based on the transition probability of changing from the second type to each type, determining the operating condition data in the next time period from the operating condition data in multiple time periods; the type of the operating condition data in the next time period is included in the various types; splicing the operating condition data in the next time period after the operating condition data in the previous time period to obtain the updated typical operating condition data of the battery, and the previous time period is the second time period.

[0220] In some embodiments, the typical operating condition data of the battery includes: operating condition data within L time periods, where L is a positive integer; the termination condition includes at least one of the following: the cumulative capacity of the battery within the L time periods reaches a second threshold; the cumulative duration corresponding to the L time periods reaches a third threshold; the cumulative state of charge (SOC) corresponding to the L time periods reaches a fourth threshold, wherein the SOC corresponding to each time period is: the difference between the maximum SOC and the minimum SOC of the battery within the time period.

[0221] The description of the above device embodiment is similar to the description of the above method embodiment and has similar beneficial effects as the method embodiment. In some embodiments, the functions or modules / units included in the device provided by the embodiment of the present disclosure can be used to perform the method described in the above method embodiment. For technical details not disclosed in the device embodiment of the present disclosure, please refer to the description of the method embodiment of the present disclosure for understanding.

[0222] It should be noted that, in the embodiments of the present disclosure, if the above method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present disclosure is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk. In this way, the embodiments of the present disclosure are not limited to any specific hardware, software or firmware, or any combination of hardware, software and firmware.

[0223] An embodiment of the present disclosure also provides a device for extracting typical operating conditions of a battery, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, some or all of the steps in the above method are implemented.

[0224] The present disclosure also provides a chip, which includes a processor configured to call and execute a computer program from a memory, so that a device equipped with the chip executes some or all of the steps in the above method.

[0225] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements some or all of the steps in the above method. The computer-readable storage medium may be transient or non-transient.

[0226] The embodiment of the present disclosure further provides a computer program, comprising computer-readable codes. When the computer-readable codes are executed in a device, a processor in the device executes some or all of the steps in the above method.

[0227] The present disclosure also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, implements some or all of the steps in the above method. The computer program product can be implemented specifically through hardware, software, or a combination thereof. In some embodiments, the computer program product is specifically embodied as a computer storage medium. In other embodiments, the computer program product is specifically embodied as a software product, such as a software development kit (SDK), etc.

[0228] It should be noted that the descriptions of the various embodiments above tend to emphasize the differences between the various embodiments, and their similarities or similarities can be referenced to each other. The descriptions of the above device, chip, storage medium, computer program, and computer program product embodiments are similar to the descriptions of the above method embodiments and have similar beneficial effects as the method embodiments. For technical details not disclosed in the embodiments of the device, chip, storage medium, computer program, and computer program product disclosed herein, please refer to the description of the method embodiments disclosed herein for understanding.

[0229] An embodiment of the present disclosure provides a device for extracting typical operating conditions of a battery. As shown in FIG7 , the device 700 for extracting typical operating conditions of a battery (hereinafter referred to as the device 700 ) includes a processor 710 . The processor 710 can call and run a computer program from a memory to implement the method in the embodiment of the present disclosure.

[0230] In some embodiments, as shown in FIG7 , the device 700 may further include a memory 720. The processor 710 may call and execute computer programs from the memory 720 to implement the methods in the embodiments of the present disclosure. The memory 720 may be a separate device independent of the processor 710 or integrated into the processor 710.

[0231] In some embodiments, as shown in FIG7 , the device 700 may further include a transceiver 730. The processor 710 may control the transceiver 730 to communicate with other devices. Specifically, the transceiver 730 may send information or data to other devices or receive information or data sent by other devices. The transceiver 730 may include a transmitter and a receiver. The transceiver 730 may further include an antenna, which may be one or more.

[0232] It should be understood that “one embodiment”, “an embodiment” or “some embodiments” mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present disclosure. Therefore, “in one embodiment”, “in an embodiment” or “in some embodiments” appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in the various embodiments of the present disclosure, the size of the serial numbers of the above-mentioned steps / processes does not mean the order of execution. The execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure. The serial numbers of the embodiments of the present disclosure are for description only and do not represent the advantages and disadvantages of the embodiments.

[0233] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0234] In the several embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units or modules is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0235] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0236] In addition, all functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0237] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, and other media that can store program codes.

[0238] Alternatively, if the above-mentioned integrated unit of the present disclosure is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the relevant technology, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0239] The above are only implementation methods of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this disclosure, and they should all be covered by the protection scope of the present disclosure.

Claims

1. A method for extracting typical operating conditions of a battery, the method comprising: Acquire operating condition data of the battery in multiple time periods from the battery data set, where the multiple time periods include a first time period, and the type of the operating condition data in the first time period belongs to a first type; determining, based on the transition probabilities from the first type to each type, operating condition data within a second time period from the operating condition data within the plurality of time periods; the type of the operating condition data within the second time period belongs to a second type, and the various types include the second type; The operating condition data in the first time period and the second time period are combined to obtain typical operating condition data of the battery.

2. The method according to claim 1, wherein Before acquiring the operating condition data of the battery in multiple time periods from the battery data set, the method further includes: Determining a requirement for typical operating condition data of the battery, where the requirement is related to at least one of capacity, duration, and state of charge (SOC) corresponding to the typical operating condition data of the battery; An end condition is determined based on the requirement. When the typical operating condition data of the battery meets the end condition, the typical operating condition data of the battery meets the requirement.

3. The method according to claim 2, wherein: The requirements include at least one of the following: The capacity corresponding to the typical operating condition data of the battery reaches a second threshold; The duration corresponding to the typical operating condition data of the battery reaches a third threshold; The SOC corresponding to the typical operating condition data of the battery reaches a fourth threshold.

4. The method according to any one of claims 1 to 3, wherein The determining, based on the transition probabilities from the first type to each type, the operating condition data within the second time period from the operating condition data within the multiple time periods includes: determining, based on transition probabilities from the first type to various types, that the type of the operating condition data within the second time period belongs to the second type; Determining operating condition data within N candidate time periods from the operating condition data within the multiple time periods, where the type of the operating condition data within the N candidate time periods belongs to the second type, and N is a positive integer; The operating condition data within a candidate time period is determined from the operating condition data within the N candidate time periods as the operating condition data within the second time period.

5. The method according to claim 4, wherein The determining, based on the transition probabilities from the first type to each type, that the type of the operating condition data within the second time period belongs to the second type includes: Determining a probability interval corresponding to each of the types based on the transition probability of changing from the first type to each type; wherein the length of the probability interval corresponding to each type is equal to the transition probability of changing from the first type to the type; When the random factor falls within the probability interval corresponding to the second type, it is determined that the type of the operating condition data within the second time period belongs to the second type.

6. The method according to claim 4 or 5, wherein: The determining, from the operating condition data in the N candidate time periods, the operating condition data in a candidate time period as the operating condition data in the second time period includes: determining a Mahalanobis distance between the operating condition data in the first time period and the operating condition data in each of the N candidate time periods; The operating condition data in a first candidate time period among the N candidate time periods is used as the operating condition data in the second time period; among the N candidate time periods, the Mahalanobis distance between the operating condition data in the first candidate time period and the operating condition data in the first time period is the smallest.

7. The method according to claim 4 or 5, wherein: The determining, from the operating condition data in the N candidate time periods, the operating condition data in a candidate time period as the operating condition data in the second time period includes: The operating condition data within a candidate time period is randomly determined from the operating condition data within the N candidate time periods as the operating condition data within the second time period.

8. The method according to any one of claims 1 to 7, wherein The method further comprises: determining a characteristic value of the operating condition data in each of the plurality of time periods; Based on the characteristic value of the operating condition data in each of the multiple time periods, the operating condition data in the multiple time periods are clustered to obtain the type to which the operating condition data in each of the multiple time periods belongs.

9. The method according to claim 8, wherein The operating condition data in each of the multiple time periods includes: battery current, battery temperature and battery SOC; Determining the characteristic value of the operating condition data in each of the multiple time periods includes: For each of the multiple time periods, perform the following operations: Integrating the battery current in the time period in ampere hours to obtain the battery capacity corresponding to the time period; Calculating an average value of the temperature of the battery within the time period to obtain an average temperature corresponding to the time period; Calculating an average SOC value of the battery within the time period to obtain an average SOC value corresponding to the time period; The battery capacity, average temperature, and average SOC corresponding to the time period are used as characteristic values ​​of the operating condition data within the time period.

10. The method according to claim 8 or 9, wherein: The clustering of the operating condition data within the multiple time periods includes: Clustering the operating condition data within the multiple time periods is performed using any of the following clustering algorithms: K-means clustering algorithm, mean shift clustering algorithm, density-based clustering algorithm.

11. The method according to any one of claims 1 to 10, wherein Before acquiring the operating condition data of the battery in multiple time periods from the battery data set, the method further includes: Acquiring operating condition data of the battery over a plurality of cycles from a battery data set; Determining a first parameter of the operating condition data within the multiple cycles, the first parameter being any one of the following: a mode, a mean, or a value of the operating condition data corresponding to a maximum value of a probability density function; Determine at least one target cycle from the multiple cycles, wherein a difference between a value of the operating condition data in the at least one target cycle and the first parameter is less than or equal to a first threshold; The at least one target period is divided to obtain the multiple time periods.

12. The method according to any one of claims 1 to 10, wherein Before acquiring the operating condition data of the battery in multiple time periods from the battery data set, the method further includes: Acquire operating condition data of the battery over multiple cycles from a battery data set, where the operating condition data is of multiple types; Determining a first parameter of each type of operating condition data within the multiple cycles, the first parameter being any one of the following: a mode, a mean, or a value of the operating condition data corresponding to a maximum value of a probability density function; For each type of operating condition data within the multiple cycles, determine at least one target cycle from the multiple cycles, wherein a difference between a value of the type of operating condition data within the at least one target cycle and a corresponding first parameter is less than or equal to a first threshold corresponding to the type; Determine the intersection of all the target periods to obtain M target periods, where M is a positive integer; The M target periods are divided to obtain the multiple time periods.

13. The method according to claim 2, wherein: The method further comprises: When the typical operating condition data of the battery does not meet the termination condition, the typical operating condition data of the battery is updated by performing the following steps: determining operating condition data for a next time period from the operating condition data for the multiple time periods based on the transition probability of changing from the second type to each type; wherein the type of the operating condition data for the next time period is included in the each type; The operating condition data in the next time period is spliced ​​onto the operating condition data in the previous time period to obtain updated typical operating condition data of the battery, where the previous time period is the second time period.

14. The method according to claim 2 or 13, wherein: The typical operating condition data of the battery includes: operating condition data within L time periods, where L is a positive integer; and the termination condition includes at least one of the following: The accumulated capacity of the battery in the L time periods reaches a second threshold; The cumulative duration corresponding to the L time periods reaches a third threshold; The SOC corresponding to the L time periods accumulates to a fourth threshold, wherein the SOC corresponding to each time period is: the difference between the maximum SOC and the minimum SOC of the battery in the time period.

15. The method according to any one of claims 1 to 14, wherein In the multiple time periods, the battery states in the same time period are the same; the battery states include a charging state, a discharging state, and a static state.

16. A device for extracting typical operating conditions of a battery, the device comprising: a first acquiring unit, configured to acquire, from a battery data set, operating condition data of the battery within a plurality of time periods, wherein the plurality of time periods include a first time period, and the type of the operating condition data within the first time period is a first type; a first determining unit configured to determine, from the operating condition data within the plurality of time periods, operating condition data within a second time period based on transition probabilities of changing from the first type to various types; the type of the operating condition data within the second time period being of a second type, the various types including the second type; The splicing unit is used to splice the operating condition data in the first time period and the second time period to obtain the typical operating condition of the battery. Status data.

17. A device for extracting typical operating conditions of a battery, the device comprising: a memory for storing computer-executable instructions; A processor, connected to the memory, configured to implement the method according to any one of claims 1 to 15 by executing the computer-executable instructions.

18. A chip, comprising: A processor, configured to call and run a computer program from a memory, so that a device equipped with the chip executes the method according to any one of claims 1 to 15.

19. A computer-readable storage medium storing a computer program, wherein the computer program implements the method according to any one of claims 1 to 15 when executed by at least one processor.

20. A computer program product comprising a computer program or instructions, wherein when the computer program or instructions are executed by a processor, the method according to any one of claims 1 to 15 is implemented.

Images