Battery recession detection method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a battery recession detection method and device, electronic equipment and a storage medium, and relates to the field of industrial energy storage. The method comprises the following steps: acquiring first battery data including a battery cluster and second battery data of each battery in the battery cluster; splitting the first battery data into a plurality of sub-battery data according to charging and discharging states; for each piece of sub-battery data, if it is determined that the last moment in the sub-battery data meets the corresponding screening condition, the last moment serves as the target moment of the corresponding charging and discharging state; for each target moment, determining candidate abnormal batteries at the target moment from the batteries according to the dispersion degree of the voltage value of each piece of second battery data at the target moment; and for any one battery, the battery is determined to be a candidate abnormal battery in at least one charging state and a candidate abnormal battery in at least one discharging state, and is determined to be an abnormal battery. According to the invention, timely detection of the declined battery is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial energy storage, in particular, the present application relates to a battery degradation detection method and device, electronic equipment and storage medium. BACKGROUND

[0002] With the rapid development and popularization of industrial energy storage stations, the battery capacity degradation problem of energy storage warehouses of energy storage stations is increasingly concerned. Energy storage degradation can cause the capacity not to be fully charged during charging and not to be fully discharged during discharging, directly affecting the overall capacity utilization of the energy storage warehouse and the service life of the energy storage warehouse. Therefore, there is a problem that the degraded battery cannot be detected in time and effectively. SUMMARY

[0003] The present application provides a battery degradation detection method and device, electronic equipment and storage medium, which solves the technical problem that the degraded battery cannot be detected in time and effectively.

[0004] According to a first aspect of the present application, a battery degradation detection method is provided, which comprises: obtaining a data set, the data set comprising first battery data of a battery cluster and second battery data of each battery in the battery cluster, the first battery data comprising voltage values and charge-discharge states of the battery cluster at multiple time points; and the second battery data comprising voltage values of the corresponding battery at multiple time points. The first battery data is respectively split into multiple sub-battery data according to the charge-discharge state, and each sub-battery data comprises voltage values at consecutive charging time or discharging time. For each sub-battery data, if it is determined that the last time point in the sub-battery data meets the screening condition corresponding to the charge-discharge state in which the sub-battery data is located, the last time point is taken as the target time point of the corresponding charge-discharge state. For each target time point, according to the dispersion degree of the voltage values of each second battery data at the target time point, a candidate abnormal battery at the target time point is determined from each battery. For any one battery in the battery cluster, if the battery is determined to be a candidate abnormal battery in at least one charging state and a candidate abnormal battery in at least one discharging state, the battery is determined to be an abnormal battery.

[0005] According to a second aspect of the present application, a battery degradation detection device is provided, which comprises: An obtaining module is configured to obtain a data set, the data set comprising first battery data of a battery cluster and second battery data of each battery in the battery cluster, the first battery data comprising voltage values and charge-discharge states of the battery cluster at multiple time points; and the second battery data comprising voltage values of the corresponding battery at multiple time points. The splitting module is configured to split the first battery data into a plurality of sub-battery data according to charging and discharging states respectively, each of the sub-battery data including voltage values at continuous charging time or discharging time; The first determining module is configured to, for each of the sub-battery data, determine a last time in the sub-battery data as a target time of a corresponding charging and discharging state if the last time meets a screening condition corresponding to the charging and discharging state in which the sub-battery data is located. The second determining module is configured to, for each of the target times, determine a candidate abnormal battery at the target time from the batteries according to a dispersion degree of the voltage values of the second battery data at the target time. The third determining module is configured to, for any one of the batteries in the battery cluster, determine the battery as an abnormal battery if the battery is determined as a candidate abnormal battery in at least one charging state and a candidate abnormal battery in at least one discharging state.

[0006] According to a third aspect of the embodiments of the present application, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory, and the processor implements the steps of the method provided in the first aspect when executing the program.

[0007] According to a fourth aspect of the embodiments of the present application, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the method provided in the first aspect.

[0008] According to a fifth aspect of the embodiments of the present application, a computer program product is provided, which includes computer instructions stored in a computer readable storage medium, and when a processor of a computer device reads the computer instructions from the computer readable storage medium, the processor executes the computer instructions to cause the computer device to perform the steps of the method provided in the first aspect.

[0009] The technical scheme provided by the embodiments of the present application has the following beneficial effects: The battery degradation detection method provided by the embodiments of the present application includes obtaining a data set including first battery data of a battery cluster and second battery data of each battery, and splitting the first battery data into a plurality of sub-battery data according to charging and discharging states respectively, so as to obtain sub-battery data at continuous charging time and sub-battery data at continuous discharging time, thereby dividing the data of each charging process and each discharging process in the first battery data, facilitating subsequent detection of only the data of the charging and discharging states, improving detection efficiency, and reducing consumption of computing resources.

[0010] For each sub-battery data, if it is determined that the last time point in the sub-battery data meets the screening condition corresponding to the charge-discharge state in which the sub-battery data is located, the last time point is taken as the target time point of the corresponding charge-discharge state, the target time point close to the full charge state is screened out from the sub-battery data in the charge state, and the target time point close to the empty state is screened out from the sub-battery data in the discharge state, so that the candidate is screened out from the abnormal battery, only the data of the target time point is extracted for analysis, efficient extraction of available data is realized, and the subsequent operation burden is reduced.

[0011] For each target time point, the candidate abnormal battery at the target time point is determined from each battery according to the dispersion degree of the voltage value of each second battery data at the target time point, the dispersion degree of the voltage value of each battery close to the full charge state is counted, and the candidate abnormal battery that occurs voltage deviation at the target time point is determined, the dispersion degree of the voltage value of each battery close to the empty state is counted, and the candidate abnormal battery that occurs voltage deviation at the target time point is determined, and the accuracy and efficiency of abnormal screening are improved.

[0012] For any one battery in the battery cluster, the battery is determined as the candidate abnormal battery in at least one charge state and the candidate abnormal battery in at least one discharge state, which means that the battery has voltage deviation in the charge state and the discharge state, and therefore, the battery is taken as an abnormal battery, so that the screening of the abnormal battery that occurs battery degradation is realized. BRIEF DESCRIPTION OF DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the description of the embodiments of the present application will be briefly introduced.

[0014] Figure 1 The system architecture schematic diagram of the battery degradation detection method provided by the embodiments of the present application is shown. Figure 2 The flowchart of the battery degradation detection method provided by the embodiments of the present application is shown. Figure 3 The flowchart of the candidate abnormal battery determination method in the battery degradation detection method provided by the embodiments of the present application is shown. Figure 4 The flowchart of the first difference determination method in the battery degradation detection method provided by the embodiments of the present application is shown. Figure 5 The flowchart of the deviation degree determination method in the battery degradation detection method provided by the embodiments of the present application is shown. Figure 6A flowchart of a health evaluation method in a battery degradation detection method provided by an embodiment of the present application is shown in FIG. 1. Figure 7 A flowchart of a verification method in a battery degradation detection method provided by an embodiment of the present application is shown in FIG. 2. Figure 8 A structural diagram of a battery degradation detection device provided by an embodiment of the present application is shown in FIG. 3. Figure 9 A structural diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 4. DETAILED DESCRIPTION

[0015] Embodiments of the present application will be described below in conjunction with the accompanying drawings. It should be understood that the embodiments described below in conjunction with the accompanying drawings are exemplary descriptions of the technical solutions of the embodiments of the present application, and do not limit the technical solutions of the embodiments of the present application.

[0016] Those skilled in the art can understand that the singular forms "a", "an" and "the" used herein include plural forms unless specifically stated otherwise. It should be further understood that the terms "comprise" and "include" used in the embodiments of the present application mean that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements and / or components, but do not exclude other features, information, data, steps, operations, elements, components and / or combinations thereof supported by the present technology. It should be understood that when it is said that one element is "connected" or "coupled" to another element, the one element can be directly connected or coupled to the other element, or it can mean that the one element and the other element are connected through an intermediate element. In addition, "connected" or "coupled" used herein can include wireless connection or wireless coupling. The term "and / or" used herein means that at least one of the items defined by the term, for example, "A and / or B" can be implemented as "A", or as "B", or as "A and B".

[0017] In order to make the purposes, technical solutions and advantages of the present application clearer, the embodiments of the present application will be described in further detail below in conjunction with the accompanying drawings.

[0018] The technical solutions of the embodiments of the present application and the technical effects produced by the technical solutions of the present application will be described below through the description of several exemplary embodiments. It should be noted that the following embodiments can be mutually referenced, borrowed or combined, and the same terms, similar features and similar implementation steps in different embodiments will not be described repeatedly.

[0019] Figure 1A system architecture diagram for implementing the battery degradation detection method is provided in the embodiments of the present application, wherein the system architecture includes a terminal 120 and a server 140.

[0020] The terminal 120 is installed and runs an application program of the battery degradation detection method, and the terminal 120 is configured to obtain a data set and filter out an abnormal battery from a battery cluster according to the data set.

[0021] The terminal 120 is connected to the server 140 through a wireless network or a wired network.

[0022] The server 140 includes at least one of a single server, multiple servers, a cloud computing platform and a virtualization center. Illustratively, the server 140 includes a processor 144 and a memory 142, and the memory 142 includes a display module 1421, a control module 1422 and a receiving module 1423. The server 140 is configured to provide background services for the application program of the method. Optionally, the server 140 undertakes the main computing work, and the terminal 120 undertakes the secondary computing work; or the server 140 undertakes the secondary computing work, and the terminal 120 undertakes the main computing work; or the server 140 and the terminal 120 adopt a distributed computing architecture for collaborative computing.

[0023] Optionally, the device types of the terminal include at least one of a smart phone, a tablet computer, an electronic book reader, a Moving Picture Experts Group Audio Layer III (MP3) player, a Moving Picture Experts Group Audio Layer IV (MP4) player, a laptop computer and a desktop computer.

[0024] Those skilled in the art can know that the number of the terminals can be more or less. For example, the terminals can be only one, or the terminals can be dozens or hundreds, or more. The number and the device types of the terminals are not limited in the embodiments of the present application.

[0025] A battery degradation detection method is provided in the embodiments of the present application, as shown in the method includes: Figure 2 S101, obtaining a data set.

[0026] In the embodiments of the present application, the data set includes first battery data of a battery cluster and second battery data of each battery in the battery cluster, the first battery data includes voltage values and charge-discharge states of the battery cluster at multiple time points, and the second battery data includes voltage values of the corresponding batteries at multiple time points.

[0027] ​In the embodiment of the present application, the battery data of the battery cluster is collected by the sensor, the battery cluster is composed of multiple batteries, the first battery data of the battery cluster includes voltage values of the battery cluster at multiple time points and charging and discharging states, and the charging and discharging states include at least one of a charging state and a discharging state, that is, the first battery data includes voltage values of the battery cluster at multiple time points in the charging state and voltage values of the battery cluster at multiple time points in the discharging state.

[0028] In the embodiment of the present application, the first battery data and the second battery data obtained are data of the same period, and since the battery cluster is composed of multiple batteries, in order to detect the performance of each battery in the battery cluster, the second battery data of each battery also needs to be obtained, and the second battery data includes voltage values of the battery at multiple time points in the charging state and voltage values of the battery at multiple time points in the discharging state.

[0029] In the embodiment of the present application, after the first battery data and the second battery data are obtained, the first battery data and the second battery data are sorted in order from early to late according to time.

[0030] In one example, the first battery data of the battery cluster of a plurality of energy storage stations in a certain period is selected, and the data in the first battery data can further include information of multiple dimensions such as bin number, voltage, current, current power parameter, temperature, and time of the battery cluster, and the time interval of the multiple time points in the first battery data can be 20 seconds. The collected first battery data can be grouped according to the energy storage station, the bin number, and the cluster dimension.

[0031] S102, the first battery data is respectively split into multiple sub-battery data according to the charging and discharging states.

[0032] In the embodiment of the present application, each sub-battery data includes voltage values at consecutive charging time points or discharging time points, that is, for the sub-battery data in the charging state, the sub-battery data includes voltage values at consecutive charging time points in a charging process; and for the sub-battery data in the discharging state, the sub-battery data includes voltage values at consecutive discharging time points in a discharging process.

[0033] In the embodiment of the present application, since the first battery data obtained is battery data in a time period, the number of charging times and the number of discharging times in the time period can be multiple, and therefore, the obtained sub-battery data in the charging state is at least one, and the obtained sub-battery data in the discharging state is also at least one.

[0034] S103, for each sub-battery data, if it is determined that the last time point in the sub-battery data meets the screening condition corresponding to the charging and discharging state in which the sub-battery data is located, the last time point is taken as a target time point of the corresponding charging and discharging state.

[0035] In the embodiments of the present application, the charging state and the discharging state have corresponding screening conditions respectively, the screening condition corresponding to the charging state is used to screen the sub-battery data close to the full charging state, therefore, the data at the last moment in the sub-battery data is selected to determine whether the current sub-battery data is the sub-battery data close to the full charging state; the screening condition corresponding to the discharging state is used to screen the sub-battery data close to the full discharging state, therefore, the data at the last moment in the sub-battery data is selected to determine whether the current sub-battery data is the sub-battery data close to the full discharging state.

[0036] In the embodiments of the present application, for each sub-battery data in the charging state, the data (for example, the voltage value) at the last moment is obtained from the sub-battery data, because when the battery cluster is close to the full charging state, the voltage value will be higher than a certain value, therefore, by analyzing whether the voltage value at the last moment is higher than the certain value, the sub-battery data close to the full charging state can be screened out, and the last moment in the sub-battery data is taken as the target moment.

[0037] In the embodiments of the present application, for each sub-battery data in the discharging state, the data (for example, the voltage value) at the last moment is obtained from the sub-battery data, because when the battery cluster is close to the full discharging state, the voltage value will be lower than a certain value, therefore, by analyzing whether the voltage value at the last moment is lower than the certain value, the sub-battery data close to the full discharging state can be screened out, and the last moment in the sub-battery data is taken as the target moment.

[0038] In the embodiments of the present application, because when the battery cluster is close to the full charging state, the voltage of the degraded battery will quickly deviate upwards, the upward deviation refers to that the voltage of the battery is higher than the normal charging voltage range of the battery during the charging process, and quickly reaches the cut-off voltage of the charging process, so that other batteries cannot be fully charged, when the battery cluster is close to the full discharging state, the voltage of the degraded battery will quickly deviate downwards, the downward deviation refers to that the voltage of the battery is lower than the normal discharging voltage range of the battery during the discharging process, and quickly reaches the cut-off voltage of the discharging process, so that the power of other batteries cannot be effectively and completely released, therefore, after obtaining the corresponding sub-battery data in each state, the data at the last moment and the corresponding screening condition are obtained, the sub-battery data close to the full charging and the full discharging is screened out from the sub-battery data, and the last moment of the screened sub-battery data is taken as the target moment.

[0039] In one example, by obtaining the data of the last time in the sub-battery data and the screening condition of the corresponding charge and discharge state, the sub-battery data representing the battery cluster power from 40% charge to 60% is removed, the sub-battery data representing the battery cluster power from 70% discharge to 50% is removed, and only the sub-battery data representing the battery cluster charge to 90% and the sub-battery data representing the battery cluster discharge to 10% are retained.

[0040] It should be noted that the above specific values are for further explanation of the scheme of the present application, and do not specifically limit the specific removal and retention of the charge and discharge power. The specific power to be removed and retained is determined according to the actual situation.

[0041] S104, for each target time, determining a candidate abnormal battery at the target time from each battery according to the dispersion degree of the voltage value of each second battery data at the target time.

[0042] In the embodiment of the present application, each target time is a time close to the full charge state or a time close to the discharge completion state. The voltage value of each battery constituting the battery cluster at the target time can be further obtained.

[0043] In the embodiment of the present application, since the voltage of the battery appearing the degradation condition deviates to a certain extent when close to full charge and close to discharge completion, according to the dispersion degree of the voltage value of each battery at the target time of the charge state, the battery whose voltage deviates at the time close to full charge is screened as the abnormal candidate battery of the charge state, and according to the dispersion degree of the voltage value of each battery at the target time of the discharge state, the battery whose voltage deviates at the time close to discharge completion is screened as the abnormal candidate battery of the discharge state.

[0044] S105, for any one battery in the battery cluster, if the battery is determined as a candidate abnormal battery in at least one charge state and a candidate abnormal battery in at least one discharge state, the battery is determined as an abnormal battery.

[0045] In the embodiment of the present application, for any one battery in the battery cluster, if the battery is determined as a candidate abnormal battery in at least one charge state, it means that the battery has at least one problem of voltage upward deviation when close to full charge, and if the battery is determined as a candidate abnormal battery in at least one discharge state, it means that the battery has at least one problem of voltage downward deviation when close to discharge completion. Since the voltage deviates upward when the battery appears close to full charge, and the voltage deviates downward when the battery appears close to discharge completion, it is determined that the battery has a degradation condition. Therefore, when the battery is determined as a candidate abnormal battery in at least one charge state and a candidate abnormal battery in at least one discharge state, it is determined that the battery has degradation, and the battery is taken as an abnormal battery.

[0046] The battery degradation detection method provided by the embodiments of the present application comprises the following steps: obtaining a first battery data set comprising a battery cluster and a second battery data set comprising each battery; and splitting the first battery data into a plurality of sub-battery data according to the charging and discharging states, so as to obtain sub-battery data in a continuous charging time period and sub-battery data in a continuous discharging time period. In this way, the data of each charging process and each discharging process in the first battery data is divided out, which facilitates subsequent detection of only the data of the charging and discharging states, improves the detection efficiency, and reduces the consumption of computing resources.

[0047] For each sub-battery data, if it is determined that the last time in the sub-battery data meets the screening condition corresponding to the charging and discharging state in which the sub-battery data is located, the last time is taken as a target time of the corresponding charging and discharging state. In this way, the target time close to the full-charge state is screened out from the sub-battery data in the charging state, and the target time close to the discharged state is screened out from the sub-battery data in the discharging state, so that only the data of the target time is extracted for analysis when the abnormal battery is screened out, which realizes efficient extraction of available data and reduces the subsequent computational burden.

[0048] For each target time, the candidate abnormal battery at the target time is determined from each battery according to the dispersion degree of the voltage values of each second battery data at the target time. In this way, the dispersion degree of the voltage values of each battery close to the full-charge state is counted, so that the candidate abnormal battery that deviates in voltage at the target time is determined, and the dispersion degree of the voltage values of each battery close to the discharged state is counted, so that the candidate abnormal battery that deviates in voltage at the target time is determined, which improves the accuracy and efficiency of abnormal screening.

[0049] For any battery in the battery cluster, if the battery is determined to be a candidate abnormal battery in at least one charging state and a candidate abnormal battery in at least one discharging state, it means that the battery deviates in voltage in both the charging state and the discharging state. Therefore, the battery is taken as an abnormal battery, so that the screening of the abnormal battery that degrades is realized.

[0050] On the basis of the above embodiments, as an optional embodiment, a method for determining a candidate abnormal battery is provided, as shown in Figure 3 The specific content is as follows: S201, for each target time, obtaining the voltage value of each battery at the target time from each second battery data as the first voltage value corresponding to the target time, and averaging each first voltage value to obtain the first voltage mean value corresponding to the target time; S202, for each target moment, according to the difference between each first voltage value and the first voltage average, statistics the dispersion degree of the first voltage value; S203, for each target moment, obtaining the first difference between the preset voltage average and the first voltage average, determining the first difference value according to the first difference and the dispersion degree; S204, for each first voltage value corresponding to each target moment, if the difference between the first voltage value and the corresponding first voltage average is greater than the first difference value, the battery corresponding to the first voltage value is regarded as the candidate abnormal battery of the target moment.

[0051] In S201 of the embodiment of the present application, after the target moment close to full charge or close to discharge is determined, for each target moment, the voltage value of each battery at the target moment is obtained from the second battery data as the first voltage value, that is, the voltage value of each battery close to full charge or close to discharge is obtained, and the first voltage average of the current target moment is obtained by averaging the first voltage value of the current target moment.

[0052] In S202 of the embodiment of the present application, for each target moment, the dispersion degree of the first voltage value is calculated according to the difference between the first voltage value corresponding to the current target moment and the first voltage average, and the dispersion degree of the first voltage value can be represented by the standard deviation, for example, first calculate the difference between each first voltage value and the first voltage average, square each difference to obtain the squared difference, average all squared differences to obtain the average of the squared difference, and finally square root the average of the squared difference to obtain the standard deviation.

[0053] In the embodiment of the present application, when the target moment corresponds to the charging state, the preset voltage average is the voltage average of the qualified battery corresponding to the charging state; when the target moment corresponds to the discharging state, the preset voltage average is the voltage average of the qualified battery corresponding to the discharging state.

[0054] In the embodiment of the present application, the first difference value is used to represent the fault tolerance range of the battery voltage deviation, when the difference between the battery voltage and the set standard voltage is not greater than the first difference value, it is determined that the current battery is within the reasonable deviation range, and when the difference between the battery voltage and the set standard voltage is greater than the first difference value, it is determined that the current battery is within the unreasonable deviation range.

[0055] In S203 of the embodiment of the present application, since the voltage of the battery cluster may deviate from the normal voltage as a whole, the difference needs to be adjusted, therefore, at the target time corresponding to the charging state, the first difference between the voltage mean value of the qualified battery corresponding to the charging state and the first voltage mean value corresponding to the current target time is obtained, and the adjusted first difference value is determined according to the first difference and the dispersion degree; at the target time corresponding to the discharging state, the first difference between the voltage mean value of the qualified battery corresponding to the discharging state and the first voltage mean value corresponding to the current target time is obtained, and the adjusted first difference value is determined according to the first difference and the dispersion degree, that is, each target time has a corresponding first difference value.

[0056] In S204 of the embodiment of the present application, for each first voltage value corresponding to each target time, whether the first battery corresponding to the first voltage value exists voltage deviation is determined by judging the difference between the first voltage value and the corresponding first voltage mean value, when the difference between the first voltage value and the corresponding first voltage mean value is greater than the first difference value, it means that the voltage deviation degree of the current battery is not within the reasonable range, and the battery corresponding to the current first voltage value is taken as the candidate abnormal battery of the target time.

[0057] In the embodiment of the present application, for the first voltage value corresponding to the target time of the charging state, the first difference value corresponding to the target time is obtained, if it is determined that the difference between the first voltage value and the voltage mean value is greater than the corresponding first difference value, the battery corresponding to the first voltage value is taken as the candidate abnormal battery of the target time of the charging state; for the first voltage value corresponding to the target time of the discharging state, the first difference value corresponding to the target time is obtained, if it is determined that the difference between the first voltage value and the voltage mean value is greater than the corresponding first difference value, the battery corresponding to the first voltage value is taken as the candidate abnormal battery of the target time of the discharging state.

[0058] In the above scheme, for each target time close to the full charging state and close to the empty discharging state, the first voltage value of each battery of the target time is obtained to obtain the first voltage mean value and the dispersion degree, for each target time of the charging and discharging state, the deviation of the voltage mean value compared with the qualified voltage is determined based on the first difference between the first voltage mean value and the voltage mean value corresponding to the qualified battery under the corresponding charging and discharging state, thereby the fault tolerance range of the battery voltage deviation is determined in combination with the standard deviation of the first voltage value, the error range of the abnormal battery is adjusted based on the actual situation, for each first voltage value of each target time, the difference between the first voltage value and the corresponding first voltage mean value is compared with the first difference value, and whether the battery corresponding to the first voltage value is the candidate abnormal battery of the target time is determined according to the comparison result, the screening of the candidate abnormal battery of each target time is realized, and the accuracy and comprehensiveness of the abnormal detection are improved.

[0059] On the basis of the above embodiments, as an optional embodiment, a first difference determination method is provided, as shown in the following formula: Figure 4 The specific content is as follows: S301, the first difference is normalized, and the normalized first difference is corrected to a preset first coefficient to obtain a second coefficient; S302, the second coefficient is used to enhance the dispersion degree as the first difference.

[0060] In S301 of the embodiment of the present application, the first difference is normalized, so that the normalized first difference can correct the preset first coefficient, the preset first coefficient is greater than 1, and the preset first coefficient can be 3. By adding the normalized first difference to the preset first coefficient, the corrected second coefficient is obtained.

[0061] In S302 of the embodiment of the present application, the range of the difference value is enhanced by multiplying the second coefficient and the dispersion degree to obtain the first difference.

[0062] In the embodiment of the present application, the second coefficient is determined by the following formula:

[0063] When the first voltage value corresponding to the target moment of the charging state is determined, is the voltage mean value of the qualified battery in the charging state, k is is the approximate value of the left shift of the decimal point by two bits, when the first voltage value corresponding to the target moment of the discharging state is determined, is the voltage mean value of the qualified battery in the discharging state, k is is the approximate value of the left shift of the decimal point by two bits, 3 is the first coefficient, is the first voltage mean value.

[0064] In the embodiment of the present application, the first difference is determined by the following formula:

[0065] Wherein, is the first difference, is the second coefficient, is the dispersion degree represented by the standard deviation.

[0066] In the above scheme, the first difference is normalized, so that the output value can correct the preset first coefficient with the same standard, thereby obtaining the second coefficient. By using the second coefficient to enhance the dispersion degree, the error size (first difference) of the voltage value based on the mean value can be determined, so that the candidate abnormal battery outside the error can be accurately detected.

[0067] On the basis of the above embodiments, as an optional embodiment, a determination method of deviation degree is provided, as shown in the following table: Figure 5 The specific content is as follows: S401, for each target time, if there is a candidate abnormal battery at the target time, the second voltage value of each candidate abnormal battery existing at the target time at the target time is obtained from each second battery data; S402, average the second voltage values corresponding to all target times of the same charge and discharge state to obtain the second voltage average of the same charge and discharge state; S403, for each second voltage value corresponding to each target time, the deviation degree of the second voltage value is determined according to the difference between the second voltage value and the second voltage average of the corresponding charge and discharge state; S404, for each second voltage value, determine the number of times the battery corresponding to the second voltage value has performed the corresponding charge and discharge process; S405, establish a corresponding relationship between the deviation degree of each second voltage value and the number of times the corresponding battery has performed the corresponding charge and discharge process, and determine the correlation between the deviation degree of the second voltage and the number of times the corresponding charge and discharge process has been performed.

[0068] In S401 of the embodiment of the present application, for each target time with a candidate abnormal battery, the second voltage value of the candidate abnormal battery at the target time at the target time is obtained from the second battery data, that is, the voltage value of the deviated battery corresponding to each time of voltage up deviation or down deviation is obtained, that is, the second voltage value of the battery at each time of deviation in the charging state is obtained, and the second voltage value of the battery at each time of deviation in the discharging state is obtained.

[0069] In S402 of the embodiment of the present application, the average of the second voltage values corresponding to all target times of the charging state means that the second voltage values of the battery at each time of up deviation in the charging state are averaged to obtain the second voltage average corresponding to the charging state, and the second voltage values of the battery at each time of down deviation in the discharging state are averaged to obtain the second voltage average corresponding to the discharging state.

[0070] In S403 of the embodiment of the present application, the second voltage value corresponding to the target time refers to the second voltage value of the candidate abnormal battery existing at the target time, for each second voltage value of each target time of each charging state, the deviation degree of the second voltage value is determined according to the difference between the second voltage value and the second voltage average of the charging state, for each second voltage value of each target time of each discharging state, the deviation degree of the second voltage value is determined according to the difference between the second voltage value and the second voltage average of the discharging state.

[0071] In the embodiment of the present application, the deviation degree of the second voltage value can be determined in the following manner:

[0072] wherein, is the second voltage value, when the second voltage value is the voltage value corresponding to the charging state, is the second voltage mean value corresponding to the charging state, when the second voltage value is the voltage value corresponding to the discharging state, is the second voltage mean value corresponding to the discharging state.

[0073] In S404 of the embodiment of the present application, for each second voltage value, if the second voltage value is the second voltage value corresponding to the target moment of the charging state, the number of charging procedures that the battery has performed before the present deviation is determined, that is, the number of times that the battery has been charged is determined, if the second voltage value is the second voltage value corresponding to the target moment of the discharging state, the number of discharging procedures that the battery has performed before the present deviation is determined, that is, the number of times that the battery has been discharged is determined.

[0074] In S405 of the embodiment of the present application, the deviation degree of each second voltage value and the corresponding number of times of charging or discharging are established, if the result shows that the number of times of charging or discharging is positively correlated with the deviation degree, it indicates that there is a high correlation between the deviation degree of the second voltage value and the corresponding number of times of charging and discharging.

[0075] In the above scheme, for the target moment of the abnormal candidate battery, the second voltage value corresponding to each candidate abnormal battery existing at the target moment is obtained, the second voltage values corresponding to all target moments of the same charging and discharging state are averaged, that is, the second voltage mean value corresponding to the charging state and the second voltage mean value corresponding to the discharging state are obtained, after the above second voltage mean values are obtained, each second voltage value corresponding to each target moment of the corresponding charging and discharging state can be determined by using each second voltage mean value to determine the corresponding deviation degree, thereby realizing the quantification of the deviation degree of each charging state and providing strong data support for the subsequent analysis of the voltage deviation of each charging state.

[0076] On the basis of each of the above embodiments, as an optional embodiment, a health assessment method is provided, as shown in Figure 6 The specific content is as follows: S501, for any one battery in the battery cluster, the number of times that the battery is determined as a candidate abnormal battery in the corresponding charging and discharging state is counted, and the number of times that the voltage of the battery deviates in the corresponding charging and discharging state is determined according to the counting result; S502, for each candidate abnormal battery, the deviation degree of the second voltage value of the candidate abnormal battery in the corresponding charge and discharge state is counted, and the deviation degree of the voltage of the candidate abnormal battery in the corresponding charge and discharge state is determined. S503, for each candidate abnormal battery, the health of the candidate abnormal battery is evaluated according to the number of directional deviations and the deviation degree of the corresponding deviation.

[0077] In S501 of the embodiment of the application, the directional deviation refers to upward deviation or downward deviation. For any battery in the battery cluster, if the battery is determined as a candidate abnormal battery once, it means that the voltage of the battery deviates once. Since the deviation of the voltage of the battery is divided into upward deviation and downward deviation, for any battery in the battery cluster, the number of times that the battery is determined as a candidate abnormal battery in the charging state is counted, so as to determine the number of times that the voltage of the battery deviates upward, and the number of times that the battery is determined as a candidate abnormal battery in the discharging state is counted, so as to determine the number of times that the voltage of the battery deviates downward.

[0078] In S502 of the embodiment of the application, for each candidate abnormal battery, the deviation degree of the second voltage value of the candidate abnormal battery in the charging state is counted, that is, the deviation degree of the voltage of the candidate abnormal battery in the charging state is counted, for example, the deviation degree of each deviation is averaged, or the intermediate value, the maximum value is determined. The deviation degree of the candidate abnormal battery in the charging state deviates upward; for each candidate abnormal battery, the deviation degree of the second voltage value of the candidate abnormal battery in the discharging state is counted, that is, the deviation degree of the voltage of the candidate abnormal battery in the discharging state is counted, for example, the deviation degree of each deviation is averaged, or the intermediate value, the maximum value is determined. The deviation degree of the candidate abnormal battery in the discharging state deviates downward.

[0079] In S503 of the embodiment of the application, for each candidate abnormal battery, the health of the battery is evaluated according to the number of directional deviations and the corresponding deviation degree. For the candidate abnormal battery, the weights of the number of deviations and the deviation degree can be determined according to the actual situation of the battery, for example, the weights are adjusted according to the use environment, type and performance of the battery, and then a health score value is obtained by weighted summation, and then according to the pre-set health score value range and the corresponding relationship of the evaluation result, the specific health state of the battery is determined.

[0080] In the above scheme, since each time a candidate abnormal battery is determined, it means that the battery deviates once, and therefore the number of deviations can be determined based on the number of times the candidate abnormal battery is determined, and according to the deviation degree of each battery each time it deviates, the overall deviation degree of the battery can be determined, and the health of the battery can be evaluated based on the overall deviation degree and the number of deviations of each battery, which provides reference data for further analysis of the degraded battery.

[0081] Based on the above embodiments, as an optional embodiment, as shown in Figure 7 The verification method is specifically as follows: S601, obtaining a voltage graph of a battery cluster; S602, according to the voltage graph, statistics the difference between the voltage values of each battery at the same time under the corresponding charging and discharging state, and determines the problem battery in the battery cluster according to the statistics result; S603, if the abnormal battery is consistent with the problem battery, outputting alarm information representing that the abnormal battery is a degraded battery.

[0082] The voltage graph is used to represent the information of the voltage of each battery in the battery cluster changing with time at multiple times; In S601 of the embodiment of the present application, the voltage graph of the battery cluster in the same time period as the first battery data is obtained; the voltage graph can display the voltage of each battery in the battery cluster, and the voltage value of each battery in the voltage graph is presented by a separate curve, and each curve represents the change of the voltage of a battery with time.

[0083] In S602 of the embodiment of the present application, through the voltage graph, it can be identified which battery has abnormal voltage fluctuation or deviation, and therefore, according to the voltage graph, the difference between the voltage values of each battery at the same time under the charging state is counted, that is, the difference between the voltage values of each battery when close to full charge is counted, and the difference between the voltage values of each battery at the same time under the discharging state is counted, that is, the difference between the voltage values of each battery when close to empty is counted, if the difference between the voltage value of a certain battery and the voltage value of other battery is large, it means that the battery has a degradation condition, and the battery is taken as a problem battery.

[0084] In S603 of the embodiment of the present application, after determining all the problem batteries according to the voltage graph, the problem battery and the determined abnormal battery are compared, if the abnormal battery is consistent with the problem battery, it means that the detection of the abnormal battery this time is correct, and alarm information representing that the abnormal battery is a degraded battery is outputted, so that the abnormal battery can be processed in time.

[0085] In the above scheme, since the voltage diagram can clearly know whether the voltage value of each battery in the battery cluster deviates greatly compared with the voltage values of other batteries, the problem battery in the battery cluster can be directly determined based on the voltage diagram, and the accuracy of the scheme is detected by judging whether the problem battery is consistent with the abnormal battery.

[0086] On the basis of the above embodiments, as an optional embodiment, the screening condition corresponding to the charging state is that the voltage value is greater than a first threshold value; and the screening condition corresponding to the discharging state is that the voltage value is less than a second threshold value.

[0087] In the embodiments of the present application, since the function of the screening condition corresponding to the charging state is to screen out the sub-battery data representing the proximity to full charge, and the voltage value of the battery will rise to the first threshold value when the battery is close to full charge, the screening condition corresponding to the charging state is that the voltage value is greater than the first threshold value; since the function of the screening condition corresponding to the discharging state is to screen out the sub-battery data representing the proximity to full discharge, and the voltage value of the battery will decrease to the second threshold value when the battery is close to full discharge, the screening condition corresponding to the discharging state is that the voltage value is less than the second threshold value.

[0088] In the embodiments of the present application, for each sub-battery data of the charging state, if the voltage value of the last time of the sub-battery data is greater than the first threshold value, the last time is taken as the target time of the charging state.

[0089] In the embodiments of the present application, the voltage value of the last time of the sub-battery data of the charging state is the highest value in the voltage values of the sub-battery data, therefore, the voltage value of the last time is compared with the first threshold value, if the voltage value of the last time is greater than the first threshold value, it indicates that the current sub-battery data is the sub-battery data representing the proximity to full charge, therefore, the last time is taken as the target time of the charging state, i.e. the time close to full charge.

[0090] In the embodiments of the present application, for each sub-battery data of the discharging state, if the voltage value of the last time of the sub-battery data is less than the second threshold value, the last time is taken as the target time of the discharging state.

[0091] In the embodiments of the present application, the voltage value of the last time of the sub-battery data of the discharging state is the lowest value in the voltage values of the sub-battery data, therefore, the voltage value of the last time is compared with the second threshold value, if the voltage value of the last time is less than the second threshold value, it indicates that the current sub-battery data is the sub-battery data representing the proximity to full discharge, therefore, the last time is taken as the target time of the discharging state, i.e. the time close to full discharge.

[0092] In the above scheme, since the sub-battery data is the data in the charging state or the data in the discharging state, and the voltage of the battery that is in decline deviates only when the battery is close to full charge or close to empty, the first threshold value is set to filter out the target time close to the full charge state from all the sub-battery data corresponding to the charging state, and the second threshold value is set to filter out the target time close to the empty state from all the sub-battery data corresponding to the discharging state, that is, only the time when the voltage deviation phenomenon can be detected is filtered out, avoiding analyzing the voltage value at the time when the deviation phenomenon cannot occur, improving the filtering efficiency of the abnormal battery, and reducing the consumption of computing resources.

[0093] On the basis of the above embodiments, as an optional embodiment, the first battery data further includes current values of the battery cluster at multiple time points in a preset period, and when the current value is negative, it indicates that the battery cluster is in a charging state, and when the current value is positive, it indicates that the battery cluster is in a discharging state.

[0094] In the embodiments of the present application, since the first battery data further includes current values of the battery cluster at multiple time points in a preset period, it can be determined which time point data in the sub-battery data is in a charging state and which time point data is in a discharging state according to the positive and negative conditions of the current value.

[0095] In the embodiments of the present application, when the current value is negative, it indicates that the current battery cluster is in a charging state, and when the current value is positive, it indicates that the current battery cluster is in a discharging state. By changing the positive and negative values of the current value, the first battery data can be divided into at least one sub-battery data in a charging state and at least one sub-battery data in a discharging state.

[0096] In the above scheme, based on the current values at multiple time points in the obtained first battery data, the sub-battery data corresponding to the charging state and the sub-battery data in the discharging state are split from the first battery data, that is, the data that can be used for abnormal battery screening is extracted, avoiding subsequent processing of useless data, improving the efficiency of decline battery detection, and saving computing resources.

[0097] In the embodiments of the present application, the process of the present application further includes: the sensor collects the first battery data and the second battery data, decodes and converts the first battery data and the second battery data to the cache, cleans the data, and falls the data to the data warehouse. The offline analysis algorithm is used to determine the battery that is in decline, generate an OLTP table, and finally verify the result data.

[0098] In the embodiment of the present application, when screening the candidate abnormal battery, the 3 sigma principle of normal distribution can also be used to identify the candidate abnormal battery, that is, the average voltage of the battery cluster is calculated, and the standard deviation of the voltage is calculated. Since the cluster voltage deviates from the normal average voltage as a whole, the coefficient 3 needs to be modified. By combining the calculated cluster average voltage with the average voltage of the lithium iron phosphate voltage at different charging periods, a modified coefficient is obtained.

[0099] In the embodiment of the present application, when the first battery data is divided based on the charging and discharging state, the sub-battery data in the static state, that is, the state of not charging and not discharging, is also divided.

[0100] In the embodiment of the present application, when the target time is screened, the sub-battery data in the middle period, that is, the sub-battery data not belonging to the charging state close to the full charge state and the sub-battery data not belonging to the discharging state close to the discharged state, is also screened. After determining that there is a corresponding candidate abnormal battery, the sub-battery data in the middle period is also saved together for subsequent analysis of the battery for extraction.

[0101] In the embodiment of the present application, first, the first battery data of a fixed period is read by a big data spark-hive calculation engine, dimension index calculation is performed, sub-battery content based on the charging state and the discharging state is generated, and then secondary processing is performed to generate voltage deviation information in different state periods of the charging and discharging start or end.

[0102] Then, based on the modified normal distribution and the designed deviation degree model, the monomer voltage that meets the deviation on the charging high platform period and the deviation on the discharging low platform period and does not meet the deviation on the charging start low platform period is calculated, and the final monomer capacity degradation information is obtained. The statistical information includes the frequency, time span, and degradation degree. Combined with the specific voltage UI diagram, secondary verification is performed. The related information of the energy storage station with degradation or signs of degradation is fed back to the maintenance department for subsequent processing to eliminate potential hidden dangers.

[0103] In the embodiment of the present application, the present application designs a new energy industrial energy storage technology field, specifically a method for analyzing energy storage battery business data based on a big data platform. By extracting the voltage deviation characteristics of the batteries in the battery cluster in the energy storage warehouse, the batteries with degraded capacity are separated and filtered out. Finally, whether there is degradation and the degree of degradation are concluded by further cross verification of the voltage diagram of the battery cluster, so as to feed back to the relevant maintenance department for maintenance, thereby prolonging the service life and efficiency of the energy storage warehouse.

[0104] The embodiment of the present application provides a battery degradation detection device, as shown in Figure 8As shown, the battery degradation detection device 80 can include an obtaining module 801, a splitting module 802, a first determining module 803, a second determining module 804, and a third determining module 805.

[0105] Specifically, the obtaining module 801 is configured to obtain a data set including first battery data of a battery cluster and second battery data of each battery in the battery cluster, the first battery data including voltage values and charge-discharge states of the battery cluster at multiple time points, and the second battery data including voltage values of the corresponding battery at multiple time points. The splitting module 802 is configured to split the first battery data into multiple sub-battery data according to the charge-discharge states respectively, each sub-battery data including voltage values at consecutive charge time points or discharge time points. The first determining module 803 is configured to, for each sub-battery data, if it is determined that the last time point in the sub-battery data meets a screening condition corresponding to the charge-discharge state in which the sub-battery data is located, take the last time point as a target time point of the corresponding charge-discharge state. The second determining module 804 is configured to, for each target time point, determine a candidate abnormal battery at the target time point from the batteries according to the dispersion degree of the voltage values of the second battery data at the target time point. The third determining module 805 is configured to, for any one battery in the battery cluster, if the battery is determined to be a candidate abnormal battery in at least one charge state and a candidate abnormal battery in at least one discharge state, determine the battery as an abnormal battery.

[0106] The battery degradation detection device provided by the embodiments of the present application can obtain a data set including first battery data of a battery cluster and second battery data of each battery, and split the first battery data into multiple sub-battery data according to the charge-discharge states, so as to obtain sub-battery data at consecutive charge time points and sub-battery data at consecutive discharge time points, thereby dividing the data of each charge process and each discharge process in the first battery data, facilitating subsequent detection of only the data of the charge-discharge states, improving the detection efficiency, and reducing the consumption of computing resources.

[0107] For each sub-battery data, if it is determined that the last time point in the sub-battery data meets a screening condition corresponding to the charge-discharge state in which the sub-battery data is located, the last time point is taken as a target time point of the corresponding charge-discharge state, which realizes screening of a target time point close to a full charge state from the sub-battery data in the charge state and screening of a target time point close to a discharged state from the sub-battery data in the discharge state, so that only the data of the target time point is extracted for analysis when screening the abnormal battery, which realizes efficient extraction of available data and reduces the subsequent computational burden.

[0108] For each target moment, the candidate abnormal battery at the target moment is determined from each battery according to the dispersion degree of the voltage value of each second battery data at the target moment, the dispersion degree of the voltage value of each battery close to the full charge state is counted, and the candidate abnormal battery with voltage deviation at the target moment is determined, the dispersion degree of the voltage value of each battery close to the discharged state is counted, and the candidate abnormal battery with voltage deviation at the target moment is determined, and the accuracy and efficiency of abnormal screening are improved.

[0109] For any one battery in the battery cluster, if the battery is determined as a candidate abnormal battery in at least one charging state and a candidate abnormal battery in at least one discharging state, it indicates that the battery has voltage deviation in the charging state and the discharging state, and therefore the battery is taken as an abnormal battery, thereby realizing the screening of abnormal batteries with battery degradation.

[0110] The device provided in the embodiments of the present application can execute the method provided in the embodiments of the present application, and the implementation principles are similar. The actions performed by each module in the device of the embodiments of the present application are corresponding to the steps in the method of the embodiments of the present application. The detailed function description of each module of the device can be referred to the description of the corresponding method in the foregoing description, and will not be repeated here.

[0111] In the embodiments of the present application, an electronic device (computer device / system) is provided, which includes a memory, a processor and a computer program stored in the memory. The processor executes the above computer program to realize the steps of the battery degradation detection method. Compared with related technologies, the data set containing the first battery data of the battery cluster and the second battery data of each battery is obtained, and the first battery data is split into multiple sub-battery data according to the charging and discharging states, thereby obtaining sub-battery data in continuous charging moments and sub-battery data in continuous discharging moments. The data of each charging process and each discharging process in the first battery data is divided out, which facilitates subsequent detection of only the charging and discharging state data, improves the detection efficiency, and reduces the consumption of computing resources.

[0112] For each sub-battery data, if it is determined that the last moment in the sub-battery data meets the screening condition corresponding to the charging and discharging state where the sub-battery data is located, the last moment is taken as the target moment of the corresponding charging and discharging state. The target moment close to the full charge state is screened from the sub-battery data in the charging state, and the target moment close to the discharged state is screened from the sub-battery data in the discharging state, so that only the data of the target moment is extracted for analysis when screening the abnormal battery, thereby realizing efficient extraction of available data and reducing the subsequent computational burden.

[0113] For each target time, the candidate abnormal battery at the target time is determined from each battery according to the dispersion degree of the voltage value of each second battery data at the target time, the dispersion degree of the voltage value of each battery close to the full charge state is counted, and the candidate abnormal battery with voltage deviation at the target time is determined, the dispersion degree of the voltage value of each battery close to the empty charge state is counted, and the candidate abnormal battery with voltage deviation at the target time is determined, and the accuracy and efficiency of abnormal screening are improved.

[0114] For any one battery in the battery cluster, if the battery is determined as a candidate abnormal battery in at least one charge state and a candidate abnormal battery in at least one discharge state, it means that the battery has voltage deviation in both charge state and discharge state, and therefore the battery is taken as an abnormal battery, so that the screening of abnormal batteries with battery degradation is realized.

[0115] In an optional embodiment, an electronic device is provided, such as Figure 9 As shown in the figure, Figure 9 The electronic device 4000 shown in the figure includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 can also include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception, etc. It should be noted that in actual application, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present application.

[0116] The processor 4001 can be a CPU (Central Processing Unit, central processor), a general-purpose processor, a DSP (Digital Signal Processor, data signal processor), an ASIC (Application Specific Integrated Circuit, application specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can realize or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure content of the present application. The processor 4001 can also be a combination of computing functions, such as one or more microprocessor combinations, combinations of DSP and microprocessor, etc.

[0117] The bus 4002 can include a path that transmits information between the above-described components. The bus 4002 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 4002 can be divided into an address bus, a data bus, a control bus, or the like. For convenience of representation, Figure 9 In the drawing, only one thick line is shown, but this does not mean that there is only one bus or only one type of bus.

[0118] The memory 4003 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, a magnetic disk storage medium, other magnetic storage device, or any other medium that can be used to carry or store computer programs and that can be read by a computer, without limitation.

[0119] The memory 4003 is used to store a computer program for implementing the embodiments of the present application, and is controlled by the processor 4001 to perform. The processor 4001 is used to execute the computer program stored in the memory 4003 to realize the steps shown in the foregoing method embodiments.

[0120] The electronic device package can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet PCs), PMPs (Portable Multimedia Players), vehicle terminals (for example, car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. Figure 9 The electronic device shown is only an example and should not limit the functions and use range of the embodiments of the present disclosure.

[0121] The embodiments of the present application provide a computer readable storage medium, and the computer readable storage medium stores a computer program. When the computer program is executed by a processor, the steps and corresponding contents of the foregoing method embodiments can be realized. Compared with the prior art, the following can be realized: By acquiring a first battery data set containing a battery cluster and a second battery data set containing individual batteries, and splitting the first battery data into multiple sub-battery data according to the charge and discharge states respectively, sub-battery data in continuous charging time and sub-battery data in continuous discharging time are obtained, which realizes the division of data of each charging process and each discharging process in the first battery data, facilitates subsequent detection of only the charge and discharge state data, improves detection efficiency, and reduces the consumption of computing resources.

[0122] For each sub-battery data, if it is determined that the last time in the sub-battery data meets the screening condition corresponding to the charge and discharge state of the sub-battery data, the last time is taken as the target time of the corresponding charge and discharge state, which realizes the screening of the target time close to the full charge state from the sub-battery data in the charging state, and the screening of the target time close to the discharged state from the sub-battery data in the discharging state, so that only the data of the target time is extracted for analysis when screening the abnormal battery, which realizes efficient extraction of available data and reduces the subsequent computational burden.

[0123] For each target time, the candidate abnormal battery at the target time is determined from each battery according to the dispersion degree of the voltage value of each second battery data at the target time, which realizes the statistics of the dispersion degree of the voltage value of each battery close to the full charge state, thereby determining the candidate abnormal battery that occurs voltage deviation at the target time, and realizes the statistics of the dispersion degree of the voltage value of each battery close to the discharged state, thereby determining the candidate abnormal battery that occurs voltage deviation at the target time, which improves the accuracy and efficiency of abnormal screening.

[0124] For any one battery in the battery cluster, if the battery is determined to be a candidate abnormal battery in at least one charging state and a candidate abnormal battery in at least one discharging state, it means that the battery has voltage deviation in both charging and discharging states, so the battery is taken as an abnormal battery, thereby realizing the screening of the abnormal battery that occurs battery degradation.

[0125] It should be noted that the computer readable medium of the present disclosure described above can be a computer readable signal medium or a computer readable medium or any combination of the above two. The computer readable storage medium may, for example, be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of computer readable storage media can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to a wire, a cable, an RF (radio frequency) or the like, or any suitable combination of the above.

[0126] The embodiment of the present application also provides a computer program product comprising a computer program, which, when executed by a processor, can implement the steps and corresponding contents of the foregoing method embodiments. Compared with the prior art, the following can be achieved: By obtaining the data set containing the first battery data of the battery cluster and the second battery data of each battery, and splitting the first battery data into a plurality of sub battery data according to the charge and discharge state respectively, the sub battery data in the continuous charging time and the sub battery data in the continuous discharging time are obtained, so that the data of each charging process and each discharging process in the first battery data is divided out, which is convenient for subsequent detection of the charge and discharge state data, improves the detection efficiency and reduces the consumption of operation resources.

[0127] For each sub-battery data, if it is determined that the last time in the sub-battery data meets the screening condition corresponding to the charge-discharge state in which the sub-battery data is located, the last time is taken as the target time of the corresponding charge-discharge state, the target time close to the full charge state is screened out from the sub-battery data in the charge state, and the target time close to the discharge state is screened out from the sub-battery data in the discharge state, so that the candidate is screened out from the abnormal battery, only the data of the target time is extracted for analysis, efficient extraction of available data is realized, and the subsequent operation burden is reduced.

[0128] For each target time, the candidate abnormal battery at the target time is determined from each battery according to the dispersion degree of the voltage value of each second battery data at the target time, the dispersion degree of the voltage value of each battery close to the full charge state is counted, and the candidate abnormal battery that deviates in voltage at the target time is determined, the dispersion degree of the voltage value of each battery close to the discharge state is counted, and the candidate abnormal battery that deviates in voltage at the target time is determined, and the accuracy and efficiency of abnormal screening are improved.

[0129] For any one battery in the battery cluster, if the battery is determined to be a candidate abnormal battery in at least one charge state and a candidate abnormal battery in at least one discharge state, it indicates that the battery deviates in voltage in the charge state and the discharge state, and therefore the battery is taken as an abnormal battery, so that the screening of the abnormal battery that occurs battery degradation is realized.

[0130] The terms "first", "second", "third", "fourth", "1", "2", and the like (if any) in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described.

[0131] It should be understood that, although the flowcharts of the embodiments of the present application indicate the implementation order of each operation step by arrows, the implementation order of these steps is not limited to the order indicated by the arrows. Unless otherwise specified herein, in some implementation scenarios of the embodiments of the present application, the implementation steps in each flowchart can be executed in other orders as required. In addition, part or all of the steps in each flowchart can include multiple sub-steps or multiple stages based on the actual implementation scenario. Part or all of these sub-steps or stages can be executed at the same time, and each of these sub-steps or stages can also be executed at different times. In the scenario where the execution times are different, the execution order of these sub-steps or stages can be flexibly configured according to requirements, and the embodiments of the present application do not limit this.

[0132] The above are only optional implementations of some implementation scenarios of the present application. It should be noted that, for those skilled in the art, other similar implementation manners based on the technical concept of the present application without departing from the technical concept of the present application also belong to the protection scope of the embodiments of the present application.

Claims

1. A method for detecting battery degradation, characterized in that, include: Obtain a dataset, which includes first battery data of a battery cluster and second battery data of each battery in the battery cluster. The first battery data includes the voltage value and charge / discharge state of the battery cluster at multiple times. The second battery data includes the voltage value of the corresponding battery at the multiple times. The first battery data is divided into multiple sub-battery data according to the charging and discharging state. Each sub-battery data includes the voltage value during a continuous charging or discharging period. For each sub-battery data, if it is determined that the last moment in the sub-battery data meets the screening condition corresponding to the charge / discharge state of the sub-battery data, then the last moment is taken as the target moment of the corresponding charge / discharge state. For each target time, based on the degree of dispersion of the voltage values ​​of each second battery data at the target time, candidate abnormal batteries are determined from each battery at the target time. If any battery in the battery cluster is identified as a candidate abnormal battery with at least one charging state and at least one discharging state, then the battery is determined to be an abnormal battery.

2. The method according to claim 1, characterized in that, For each target time, determining candidate abnormal batteries from among the batteries at that target time based on the dispersion of the voltage values ​​of each second battery data at that target time includes: For each target time, the voltage value of each battery at the target time is obtained from the data of each second battery as the first voltage value corresponding to the target time. The average value of each first voltage value is calculated to obtain the first voltage mean value corresponding to the target time. For each target time, the dispersion of the first voltage value is statistically analyzed based on the difference between each first voltage value and the average first voltage value. For each target time, a first difference is obtained between a preset average voltage and the first average voltage, and a first difference is determined based on the first difference and the degree of dispersion; when the target time corresponds to a charging state, the preset average voltage is the average voltage of a qualified battery in the charging state; when the target time corresponds to a discharging state, the preset average voltage is the average voltage of a qualified battery in the discharging state. For each first voltage value corresponding to each target time, if the difference between the first voltage value and the corresponding first voltage mean is greater than the first difference, then the battery corresponding to the first voltage value is regarded as a candidate abnormal battery at the target time.

3. The method according to claim 2, characterized in that, Determining the first difference based on the first difference and the degree of dispersion includes: The first difference is normalized, and the normalized first difference is used to correct the preset first coefficient to obtain the second coefficient. The dispersion is enhanced based on the second coefficient, which serves as the first difference.

4. The method according to claim 1, characterized in that, The process of identifying candidate anomalous batteries from among the individual batteries at the target time further includes: For each target time, if there are candidate abnormal batteries at the target time, then the second voltage value of each candidate abnormal battery at the target time is obtained from each second battery data at the target time. The average value of the second voltage at all target moments in the same charge-discharge state is obtained by averaging the second voltage values ​​in the same charge-discharge state. For each second voltage value corresponding to each target time, the degree of deviation of the second voltage value is determined based on the difference between the second voltage value and the average second voltage value of the corresponding charge and discharge state; For each second voltage value, determine the number of times the battery corresponding to the second voltage value has performed the corresponding charge and discharge cycle; A correlation is established between the degree of deviation of each second voltage value and the number of times the corresponding charge and discharge process has been performed on the corresponding battery, and the correlation between the degree of deviation of the second voltage value and the number of times the corresponding charge and discharge process has been performed is determined.

5. The method according to claim 4, characterized in that, After determining the degree of deviation of the second voltage value, the method further includes: For any battery in the battery cluster, the number of times the battery is identified as a candidate abnormal battery in the corresponding charge / discharge state is counted, and the number of times the battery voltage deviates directionally in the corresponding charge / discharge state is determined based on the statistical results. For each candidate abnormal battery, the deviation of the second voltage value under the corresponding charge and discharge state of the candidate abnormal battery is statistically analyzed to determine the degree of deviation of the voltage of the candidate abnormal battery under the corresponding charge and discharge state. For each candidate abnormal battery, a health assessment is performed based on the number of directional deviations and the degree of deviation.

6. The method according to claim 1, characterized in that, The step of designating the battery corresponding to the second voltage value as an abnormal battery in a discharge state further includes: Obtain a voltage map of the battery cluster; the voltage map is used to characterize the voltage of each battery in the battery cluster as a function of time at multiple points in time; Based on the voltage diagram, the differences in voltage values ​​between each battery at the same moment under the corresponding charge and discharge states are statistically analyzed, and the battery cluster with degradation problems is identified based on the statistical results. If the abnormal battery is the same as the problematic battery, then an alarm message indicating that the abnormal battery is a battery with degradation is output.

7. The method according to claim 1, characterized in that, The filtering condition corresponding to the charging state is that the voltage value is greater than the first threshold; the filtering condition corresponding to the discharging state is that the voltage value is less than the second threshold. If it is determined that the last moment in the sub-battery data meets the filtering criteria corresponding to the charge / discharge state of the sub-battery data, then the last moment is taken as the target moment for the corresponding charge / discharge state, including: For each sub-cell data point in the charging state, if the voltage value of the last moment of the sub-cell data point is greater than a first threshold, then the last moment is taken as the target moment of the charging state. For each sub-cell data point in the discharge state, if the voltage value at the last moment of the sub-cell data point is less than the second threshold, then the last moment is taken as the target moment of the discharge state.

8. The method according to claim 1, characterized in that, The first battery data also includes the current value of the battery cluster at multiple times within a preset period. When the current value is negative, it indicates that the battery cluster is in a charging state, and when the current value is positive, it indicates that the battery cluster is in a discharging state.

9. A battery degradation detection device, characterized in that, include: The acquisition module is used to acquire a dataset, which includes first battery data of a battery cluster and second battery data of each battery in the battery cluster. The first battery data includes the voltage value and charge / discharge state of the battery cluster at multiple times; the second battery data includes the voltage value of the corresponding battery at the multiple times. The splitting module is used to split the first battery data into multiple sub-battery data according to the charging and discharging state. Each sub-battery data includes the voltage value during a continuous charging or discharging period. The first determining module is used to determine, for each sub-battery data, if the last moment in the sub-battery data meets the filtering conditions corresponding to the charging and discharging state of the sub-battery data, then the last moment is taken as the target moment of the corresponding charging and discharging state. The second determining module is used to determine, for each target time, candidate abnormal batteries from the batteries at the target time based on the degree of dispersion of the voltage values ​​of each second battery data at the target time. The third determining module is used to determine that any one of the batteries in the battery cluster is an abnormal battery if it is determined to be a candidate abnormal battery with at least one charging state and at least one discharge state.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the method according to any one of claims 1-8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-8.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-8.

Images