Battery cell fault diagnosis method and system in battery cluster, and cloud server

Abstract

A battery cell fault diagnosis method and system in a battery cluster, and a cloud server. The method comprises: acquiring the temperatures, voltages, and initial characteristic parameters of a battery cluster as a whole and battery cells (S100); calculating a temperature fluctuation parameter and a voltage fluctuation parameter (S200); on the basis of a window time, extracting target characteristic values, and calculating correlation coefficients between the target characteristic values and the fluctuation parameters (S300); and finally normalizing the same types of correlation coefficients, and dividing same into fault types on the basis of a diagnosis coefficient interval (S400). The described method does not require a complex model, implements lightweight fault positioning by means of fluctuation parameter correlation analysis and normalization diagnosis, and reduces computing power requirements. The method is easy to implement in existing battery management systems, and is convenient for popularization and application.

Description

A battery cluster cell fault diagnosis method, system and cloud server TECHNICAL FIELD

[0001] The present application relates to the technical field of cell fault diagnosis, and in particular relates to a battery cluster cell fault diagnosis method, system and cloud server. BACKGROUND

[0002] Energy storage batteries are mainly used for storing and releasing electric energy to provide power when needed; they are widely used in many fields, such as renewable energy storage, electric vehicles, emergency power supply, power grid regulation, etc.

[0003] A battery cluster is usually composed of multiple cells, and multiple cells are connected in series or parallel to increase the voltage and capacity of the battery cluster to meet the needs of different devices; however, cell failure will affect the performance of the entire battery cluster, and timely diagnosis of cell failure is beneficial to maintaining the efficiency and life of the battery cluster, and can help maintenance personnel to take timely measures to avoid greater losses.

[0004] However, the existing cell fault diagnosis method usually needs to use a relatively complex model algorithm to label the original data, and then use deep learning, artificial intelligence algorithm, etc. to realize, which requires high computing power, large investment and high labor cost. SUMMARY

[0005] The present application provides a battery cluster cell fault diagnosis method, system and cloud server to solve the above technical problems.

[0006] Specifically, the present application provides a battery cluster cell fault diagnosis method, comprising the following steps:

[0007] Collecting parameters of the entire battery cluster and each single cell based on the BMS to obtain diagnosis parameters; wherein the diagnosis parameters at least include single cell temperature, single cell voltage and initial characteristic parameters.

[0008] Respectively based on the single cell temperature and single cell voltage to obtain temperature fluctuation parameters and voltage fluctuation parameters.

[0009] Based on the window time, a plurality of target characteristic values are extracted from the initial characteristic parameters, and the correlation coefficients of each target characteristic value and the voltage fluctuation parameters and temperature fluctuation parameters are calculated.

[0010] The same kind of correlation coefficient is normalized, the normalized correlation coefficient is judged to belong to which kind of cell fault, and the cell diagnosis result is obtained based on the judgment result.

[0011] In the technical solution, compared with the prior art, the fault diagnosis method does not depend on a complex model and high computing power, and can be implemented in a relatively simple environment; since the dependence on deep learning and artificial intelligence algorithms is reduced, the hardware and labor costs are reduced, and the fault diagnosis is more economical; real-time parameter acquisition and simple fluctuation analysis make the fault diagnosis process fast and efficient, and facilitate maintenance personnel to take timely measures; the method is easy to implement in an existing battery management system without the need for large-scale modification, and is convenient for popularization and application.

[0012] Further, after implementing the above technical solution, the method further comprises: data cleaning on the diagnosis parameters.

[0013] In the technical solution, data cleaning can remove noise and error data, improve the accuracy of the parameters, and make subsequent analysis more reliable.

[0014] Further, after completing the data cleaning, the method further comprises:

[0015] determining whether the single cell temperature and the single cell voltage correspond to each other, if yes, obtaining a temperature fluctuation parameter and a voltage fluctuation parameter based on the single cell temperature and the single cell voltage respectively; otherwise, performing temperature interpolation calculation on the single cell temperature, and then obtaining the temperature fluctuation parameter and the voltage fluctuation parameter based on the single cell temperature and the single cell voltage respectively.

[0016] In the technical solution, by determining the correspondence between the temperature and the voltage, the consistency between the data is ensured, and the possibility of misdiagnosis caused by mismatched data is reduced; if the non-corresponding condition is found, the temperature data is corrected through temperature interpolation calculation, which can more accurately reflect the actual working state of the cell, thereby improving the accuracy of fault diagnosis.

[0017] Further, the target feature values at least include single cell feature values and battery cluster feature values; a plurality of target feature values are extracted from the initial feature parameters based on a window time, including:

[0018] The first feature extraction and the second feature extraction are performed on the single cell and the battery cluster respectively based on the window time to obtain the single cell feature values and the battery cluster feature values.

[0019] In the technical solution, multi-level feature extraction makes the state analysis of the battery cluster as a whole and each single cell more in-depth, which is helpful to identify potential risks and fault modes.

[0020] Further, the first feature extraction specifically includes:

[0021] The first voltage value includes at least a maximum voltage value, a minimum voltage value, a voltage value before charging, and a voltage value after charging; and the second voltage value includes at least a voltage mean value, a voltage mode value, and a voltage median value.

[0022] In the above technical solution, the first voltage value covers multiple key parameters such as maximum, minimum, and voltage before and after charging, which helps to comprehensively reflect the working state and charging and discharging process of the battery cell; the second voltage value (such as mean value, mode value, and median value) provides a multi-dimensional perspective of voltage distribution, making the analysis more detailed and accurate; the limitation of the number of cycles focuses the analysis on a specific working period, which helps to find the trend of battery performance over time.

[0023] Further, the second feature extraction specifically includes:

[0024] The target current value includes at least an average non-zero current, an average charging current, and an average discharging current; the target SOC includes at least a pre-charging SOC, a post-charging SOC, a post-discharging SOC, a charging SOC change, a discharging SOC change, a window cycle number, and an accumulated cycle number; and the battery capacity includes at least a charging capacity and a discharging capacity.

[0025] In the above technical solution, by extracting the average current value (including non-zero current, charging current, and discharging current), the current behavior of the battery cluster under different operating conditions can be comprehensively understood, and the use of the battery can be comprehensively evaluated; including the pre-charging SOC, the post-charging SOC, and the post-discharging SOC, the state of charge of the battery cluster and its charging and discharging process can be accurately tracked, which helps to monitor the health status and efficiency of the battery; by obtaining the charging capacity and the discharging capacity, the actual capacity and the remaining capacity of the battery can be accurately calculated, providing a reliable basis for the evaluation of the battery performance.

[0026] Further, the acquisition of the window cycle number and the accumulated cycle number specifically includes:

[0027] Based on the pre-charging SOC, the post-charging SOC, or the post-discharging SOC, a data sample is selected, and the number of valid frames of the data sample and the time sequence number of the current window time are obtained; based on the data sample, the number of valid frames, and the time sequence number, the window cycle number is obtained; and based on multiple time sequence numbers, the window cycle numbers are summed to obtain the accumulated cycle number.

[0028] In the technical solution, the effective data samples are screened to ensure the accuracy of the cycle count and avoid incorrect count caused by invalid data; and the cumulative cycle numbers of the multiple time sequence numbers are summed to more scientifically evaluate the overall use state of the battery and support the development of a reasonable maintenance strategy.

[0029] Further, the cell failure types include at least a first failure type and a second failure type; and the cell diagnosis results include at least a first failure diagnosis result and a second failure diagnosis result, the normalized correlation coefficient is judged to belong to which cell failure type, and the cell diagnosis result is obtained based on the judgment result, specifically including:

[0030] The normalized correlation coefficient is used as a diagnosis coefficient; if the diagnosis coefficient is in a first interval, the single cell corresponding to the diagnosis coefficient is marked as paranoid; if the diagnosis coefficient is in a second interval, it is determined that the single cell corresponding to the diagnosis coefficient belongs to the first failure type, and the first failure diagnosis result corresponding to the first failure type is obtained; and if the diagnosis coefficient is in a third interval, it is determined that the single cell corresponding to the diagnosis coefficient belongs to the second failure type, and the second failure diagnosis result corresponding to the first failure type is obtained.

[0031] In the technical solution, the first failure type and the second failure type are defined to make the classification of cell failures more systematic and facilitate targeted diagnosis and processing; the normalized correlation coefficient is used as a diagnosis coefficient to effectively reduce the influence caused by different data scales and improve the accuracy of diagnosis; and this classification and judgment method can be applied to different types and scales of battery systems to enhance the flexibility and adaptability of the system.

[0032] Further, it should be noted that the diagnosis parameters are not limited to the single cell temperature, the single cell voltage and the initial characteristic parameters, and a person skilled in the art can also use corresponding sensors to measure, for example, the internal stress and the internal pressure of the single cell to derive the maximum pressure value, the minimum pressure value, the pressure before charging or after discharging, and the like. Through multi-dimensional data acquisition, the diagnosis result types can be more finely divided in the subsequent diagnosis, which is beneficial to more comprehensive clustering and maintenance.

[0033] More preferably, when the number of battery clusters is large, a hierarchical clustering, K-means+, or other clustering method can be used to cluster the diagnosis coefficients of abnormal batteries to facilitate batch diagnosis results.

[0034] Based on the same inventive concept, the application also provides a battery cluster cell fault diagnosis system, the domain controller at least includes a processor and a memory, the memory is used for storing computer instructions of a plurality of function modules of the capacity matching and grouping for realizing the battery ladder utilization; the processor communicates with the memory through a bus, and is used for executing each computer instruction of the function modules stored in the memory.

[0035] The plurality of function modules at least include: a dynamic parameter acquisition module: based on the BMS, parameters of the battery cluster as a whole and each single cell are acquired to obtain diagnostic parameters; wherein the diagnostic parameters at least include single cell temperature, single cell voltage and initial characteristic parameters; a fluctuation characteristic acquisition module: based on the single cell temperature and the single cell voltage, temperature fluctuation parameters and voltage fluctuation parameters are respectively acquired; a characteristic analysis module: based on a window time, a plurality of target characteristic values are extracted from the initial characteristic parameters, and correlation coefficients of each target characteristic value and the voltage fluctuation parameters and the temperature fluctuation parameters are calculated; a normalization diagnosis module: the same correlation coefficient is normalized, the normalized correlation coefficient is judged to belong to a cell fault category, and a cell diagnosis result is obtained based on the judgment result.

[0036] Based on the same concept, the application also provides a battery cluster cell fault diagnosis cloud server, the cloud server at least includes a battery cluster cell fault diagnosis system, the battery cluster cell fault diagnosis system uses the battery cluster cell fault diagnosis method to diagnose the fault of each single cell in the battery cluster to obtain the corresponding cell diagnosis result.

[0037] In the above technical solution, the cloud server can centrally manage the cells in multiple battery clusters, facilitate unified monitoring and fault diagnosis, and improve management efficiency; the cloud server has good scalability, and can increase computing resources according to needs to adapt to more battery cluster diagnosis needs; based on the cloud server, a friendly user interface can be provided, so that maintenance personnel can more easily access and understand the cell diagnosis result, and improve the operation experience.

[0038] Compared with the prior art, the application has the beneficial effects that:

[0039] The application further calculates the temperature fluctuation parameters and the voltage fluctuation parameters by acquiring parameters of the battery cluster as a whole and each single cell; then based on the temperature fluctuation parameters and the voltage fluctuation parameters and the extracted target characteristic values, corresponding correlation coefficients are obtained; and based on the normalized correlation coefficients, the cell diagnosis result is obtained.

[0040] The fault diagnosis method of the application does not depend on complex models and high computing power, reduces the hardware and labor costs; and the fault diagnosis process is fast and efficient, facilitating maintenance personnel to take timely measures; the method is easy to implement in existing battery management systems without large-scale modification, facilitating popularization and application. BRIEF DESCRIPTION OF DRAWINGS

[0041] Fig. 1 is a flow chart of the battery cell fault diagnosis method in the battery cluster according to the application.

[0042] Fig. 2 is a normalized correlation coefficient diagram of the voltage fluctuation parameter and the temperature fluctuation parameter according to the embodiment.

[0043] Fig. 3 is a normalized correlation coefficient diagram of the voltage fluctuation parameter and the maximum voltage value according to the embodiment.

[0044] Fig. 4 is a normalized correlation coefficient diagram of the voltage fluctuation parameter and the minimum voltage value according to the embodiment.

[0045] Fig. 5 is a normalized correlation coefficient diagram of the voltage fluctuation parameter and the daily average discharge current according to the embodiment.

[0046] Fig. 6 is a normalized correlation coefficient diagram of the voltage fluctuation parameter and the window cycle number according to the embodiment.

[0047] Fig. 7 is a normalized correlation coefficient diagram of the voltage fluctuation parameter and the cumulative cycle number according to the embodiment.

[0048] Fig. 8 is a framework diagram of the battery cell fault diagnosis system in the battery cluster according to the embodiment of the application.

[0049] Fig. 9 is a framework diagram of the domain controller according to the embodiment of the application.

[0050] Fig. 10 is a framework diagram of the memory according to the embodiment of the application.

[0051] Fig. 11 is a framework diagram of the battery cell fault diagnosis cloud server in the battery cluster according to the embodiment of the application. DETAILED DESCRIPTION

[0052] The battery cell fault diagnosis method, system and cloud server according to the application will be further described in detail below in combination with specific embodiments and drawings.

[0053] Embodiment I:

[0054] Please refer to Fig. 1, the application provides a battery cell fault diagnosis method in the battery cluster, including the following steps:

[0055] S100: Collecting parameters of the battery cluster as a whole and each single battery cell based on the BMS to obtain diagnostic parameters; wherein the diagnostic parameters at least include single battery cell temperature, single battery cell voltage and initial characteristic parameters.

[0056] In some embodiments, the number of single battery cells in the battery cluster is 240 (there are 5 PACKs in the battery cluster, and each PACK has 48 single battery cells), and the window time is set to 24 hours.

[0057] Based on the BMS, the timing voltage, current, temperature and the like in the battery cluster are collected with high precision, and the SOC, cumulative discharge power and cumulative charging power are calculated or collected in real time at the BMS end and uploaded to the cloud server for data calculation.

[0058] In addition, it should be noted that the present application is not limited to 240 single battery cells, and those skilled in the art can apply the technical solutions of the present application to any battery cluster.

[0059] It should be noted that the diagnostic parameters are not limited to single battery cell temperature, single battery cell voltage and initial characteristic parameters, and those skilled in the art can also use corresponding sensors to measure, for example, single battery cell internal stress, internal pressure, etc., to derive maximum pressure value, minimum pressure value, pressure before charging or after discharging, etc. Through multi-dimensional data collection, the diagnostic result categories can be more finely divided in the subsequent, which is beneficial to more comprehensive clustering and maintenance.

[0060] Further, after the S100, it further includes: data cleaning on the diagnostic parameters.

[0061] In some embodiments, the diagnostic parameters obtained by high-precision collection or BMS preliminary calculation are subjected to data cleaning to remove incomplete data frames and obtain complete and valid data frames.

[0062] Further, after completing the data cleaning, it further includes:

[0063] Judging whether the single battery cell temperature and the single battery cell voltage correspond, if yes, turning to S200; otherwise, performing temperature interpolation calculation on the single battery cell temperature and then turning to S200.

[0064] In some embodiments, the temperature interpolation calculation on the single battery cell temperature includes:

[0065] The arrangement order of the single battery cells in the battery cluster is determined according to the actual current flow direction in the battery cluster where the single battery cell is located; then the temperature measuring points are marked as known temperature measuring points and unknown temperature measuring points respectively, the actual flow path distance between any known temperature measuring point and unknown temperature measuring point is obtained, and a weight coefficient is calculated according to the distance; when it is determined that the distance between the known temperature measuring point and the unknown temperature measuring point meets a preset interpolation distance threshold, a preset rule interpolation operation is performed according to the temperature of the known temperature measuring point and the weight coefficient, and the temperature value of the unknown temperature measuring point is calculated. The temperature value is the temperature of the single battery cell after temperature interpolation calculation.

[0066] It should be noted that the skilled person in the art can also use other temperature interpolation methods, and it is not limited to the above method.

[0067] S200: Obtain temperature fluctuation parameters and voltage fluctuation parameters based on the single battery cell temperature and the single battery cell voltage respectively.

[0068] In some embodiments, multiple frames of voltage parameters and temperature parameters of all single battery cells are collected based on the window time, then the range or standard deviation corresponding to the multiple frames of voltage parameters and temperature parameters of the multiple single battery cells within the window time is obtained, the fluctuation parameters are further normalized by normal distribution, and multiple standard fluctuation parameters are obtained; finally, the obtained standard fluctuation parameters are checked for eligibility, and when the detection passes, the final temperature fluctuation parameters and voltage fluctuation parameters are obtained based on the standard fluctuation parameters.

[0069] It should be noted that the skilled person in the art can also use other fluctuation parameter calculation methods, and it is not limited to the above method.

[0070] S300: Extract multiple target feature values from the initial feature parameters based on the window time, and calculate the correlation coefficients of the target feature values and the voltage fluctuation parameters and temperature fluctuation parameters.

[0071] Further, the target feature values at least include single battery cell feature values and battery cluster feature values; the S300 of extracting multiple target feature values from the initial feature parameters based on the window time includes:

[0072] The first feature extraction and the second feature extraction are performed on the single battery cells and the battery cluster respectively based on the window time to obtain the single battery cell feature values and the battery cluster feature values.

[0073] Further, the first feature extraction specifically includes:

[0074] The first voltage value is obtained based on the window time, and the second voltage value is obtained based on the window time; wherein the first voltage value at least includes a maximum voltage value, a minimum voltage value, a voltage value before charging and a voltage value after charging; and the second voltage value at least includes a voltage mean value, a voltage mode value and a voltage median value.

[0075] In some embodiments, the cycle number is preferably 1, and a person skilled in the art can also select a suitable cycle number according to actual application requirements, and is not limited thereto; wherein the cycle number 1 includes that the number of charging and discharging processes cannot be greater than 2 at the same time.

[0076] The above first voltage value and second voltage value can be obtained based on the time sequence voltage initially collected by the BMS, and the above voltage values are corresponding to a single battery cell.

[0077] Further, the second feature extraction specifically includes:

[0078] The target current value, target SOC and battery capacity are obtained based on the window time; wherein the target current value at least includes an average non-zero current, an average charging current and an average discharging current; the target SOC at least includes a pre-charging SOC, a post-charging SOC, a post-discharging SOC, a charging SOC change, a discharging SOC change, a window cycle number and a cumulative cycle number; and the battery capacity at least includes a charging capacity and a discharging capacity.

[0079] In some embodiments, the above target current value can be obtained based on the current collected by the BMS, and part of the above target SOC and battery capacity can be obtained based on the calculated or collected SOC, cumulative discharging cycle amount and cumulative charging cycle amount; and the above target current value, target SOC and battery capacity are corresponding to the whole battery cluster.

[0080] Further, the window cycle number and cumulative cycle number are obtained, specifically including:

[0081] The data sample is selected based on the pre-charging SOC, post-charging SOC or post-discharging SOC, and the effective frame number of the data sample and the time sequence number of the current window time are obtained; the window cycle number is obtained based on the data sample, effective frame number and time sequence number; and the cumulative cycle number is obtained by adding and summing each window cycle number based on a plurality of time sequence numbers.

[0082] In some embodiments, the window cycle number can be obtained based on the change value of the SOC within the selected window time, and when the SOC is in percentage, the window cycle number of the current selected data sample or data sample group can be calculated by using the following formula:

[0083]

[0084] wherein, N represents the number of valid frames in the selected window time, and m is the time sequence number of the current window.

[0085] The "cumulative cycle number" is the sum of all "window cycle numbers" at the time node and before.

[0086]

[0087] Further, the correlation coefficient of each of the target characteristic values and the voltage fluctuation parameter and the temperature fluctuation parameter is calculated.

[0088]

[0089] wherein, , represents the correlation coefficient of two parameters, represents the sample mean of parameter , represents the sample mean of parameter , represents , the correlation coefficient of represents the sample mean of parameter , represents the sample mean of parameter .

[0090] wherein, for example, the correlation coefficient of the voltage fluctuation parameter and the temperature fluctuation parameter of the single battery cell is calculated as follows: .

[0091] The correlation coefficient of the voltage fluctuation parameter of the single battery cell and the maximum voltage value of the single battery cell: .

[0092] The correlation coefficient of the voltage fluctuation parameter of the single battery cell and the minimum voltage value of the single battery cell: .

[0093] The correlation coefficient of the voltage fluctuation parameter of the single battery cell and the average discharge current of the battery cluster as a whole: .

[0094] The correlation coefficient of the voltage fluctuation parameter of the single battery cell and the window cycle number of the battery cluster as a whole: .

[0095] The correlation coefficient of the voltage fluctuation parameter of the single battery cell and the cumulative cycle number of the battery cluster as a whole: .

[0096] Each single cell gets 6 correlation coefficients, and 240 single cells get 1440 correlation coefficients.

[0097] S400: Normalize the same kind of correlation coefficient, judge the normalized correlation coefficient belonging to the cell fault category, and obtain the cell diagnosis result based on the judgment result.

[0098] In some embodiments, the same kind of correlation coefficient of each single cell is normalized:

[0099]

[0100] For example, the battery cluster has 240 (i.e. Q in the formula) single cells, and the fluctuation parameters and minimum values of 240 cells are calculated by steps S200 and S300, respectively, and are recorded as , 240 groups of data are obtained, and the corresponding correlation coefficient is calculated for each group of data using the above correlation coefficient formula, and , for The normalization is performed according to the following formula:

[0101]

[0102] At this time, the normalized correlation coefficient of the voltage fluctuation parameter and the temperature fluctuation parameter of each single cell is obtained: , and similarly, , , , , .

[0103] Further, the cell fault category includes at least a first fault category (i.e. D category) and a second fault category (i.e. U category); the cell diagnosis result includes at least a first fault diagnosis result (corresponding to the diagnosis result of D category) and a second fault diagnosis result (corresponding to the diagnosis result of U category); the judgment of the normalized correlation coefficient belonging to the cell fault category in S400 is based on the judgment result to obtain the cell diagnosis result, which specifically includes:

[0104] The normalized correlation coefficient is used as a diagnosis coefficient; if the diagnosis coefficient is in the first interval, the single cell corresponding to the diagnosis coefficient is marked as paranoid; if the diagnosis coefficient is in the second interval, it is determined that the single cell corresponding to the diagnosis coefficient belongs to the first fault category, and the first fault diagnosis result corresponding to the first fault category is obtained; if the diagnosis coefficient is in the third interval, it is determined that the single cell corresponding to the diagnosis coefficient belongs to the second fault category, and the second fault diagnosis result corresponding to the first fault category is obtained.

[0105] In some embodiments, when the normalized correlation coefficient of each single cell is obtained, the single cell with the coefficient outside the interval is marked as paranoid, where the interval is marked as , the interval is marked as , and where represents the correlation coefficient, represents significantly less than the average level, represents significantly greater than the average level.

[0106] Although according to the definition of correlation coefficient, when the absolute value of the correlation coefficient is less than 0.2 or 0.1, there is no significant correlation or weak correlation, but due to the increase of data volume, it tends to be stable, for example, the maximum value of voltage often appears at the end of charging, which often shows transient characteristics and disappears soon, but the voltage fluctuation also has a positive correlation with it, so after the above normalization, one with significant correlation paranoia in the cluster sample can still be obtained in the small correlation coefficient.

[0107] At this time, according to the definition of correlation, the reason for the excessive fluctuation of part of the cells can be analyzed, for example:

[0108] When the normalized voltage fluctuation of a single cell and the average discharge current correlation coefficient belong to , the fluctuation of the cell and the average discharge current correlation is at a high level within the cluster, or in other words, the voltage fluctuation of the cell and the average discharge current relationship is greater, and the size of the discharge current will significantly affect its fluctuation characteristics.

[0109] When the normalized voltage fluctuation of a single cell and the average discharge current correlation coefficient belong to , the fluctuation of the cell and the average discharge current correlation is at a low level within the cluster, or in other words, the voltage fluctuation of the cell and the average discharge current relationship is smaller, and the size of the average discharge current will not significantly affect its fluctuation characteristics. When the number of class cells exceeds a certain proportion (for example, 3%), the discharge current of the cluster should be reduced.

[0110] Similarly, when the normalized voltage fluctuation of a single cell and the cumulative cycle number correlation coefficient belongs to , the aging level of the cell is significantly at a high level within the cluster, and vice versa.

[0111] When the normalized temperature fluctuation of a single cell and the cumulative cycle number correlation coefficient belongs to If the cell belongs to the cluster, then the temperature difference level of the location where the cell is located is obviously at a higher level over time, otherwise at a lower level.

[0112] When the normalized voltage fluctuation of a single cell is related to the temperature fluctuation coefficient If the cell belongs to the cluster, then the temperature control and heat dissipation of the location where the cell is located are at a poor level within the cluster, otherwise at a better level.

[0113] And so on, not to mention.

[0114] Among them, R is preferably 3, and the rest of the values can also be selected by those skilled in the art according to the actual application requirements, and are not limited to this.

[0115] When diagnosing single cells, the problematic cells often show abnormalities in multiple parameters. The data calculated from the "raw data after example cleaning" and the normalized correlation coefficient calculated therefrom are used to make a diagnosis.

[0116] As shown in FIG. 2, the results show that the voltage fluctuation parameter and the temperature fluctuation parameter in the battery cluster are regularly distributed, except that the temperature control of PACK1 is poor, and the rest of the PACKs are regularly distributed. The results obviously cannot give a diagnosis for the single cell, but have great significance for optimizing the heat dissipation system. The heat management of PACK1 is optimized.

[0117] As shown in FIG. 3, considering that the voltage fluctuation parameter and the maximum voltage value have less correlation, other coefficients need to be considered comprehensively, but from this coefficient, the voltage fluctuation of the cell No. 204 has less correlation with the maximum voltage value, and the maximum value of the cells No. 204, 171 and 174 is more obvious in the maximum value transient characteristic cluster.

[0118] As shown in FIG. 4, the coefficient of the cells No. 1, 79 and 204 is obviously larger in the cluster, the coefficient is biased without PACK rule, showing discrete characteristics, and the proportion is more than 4%. The cluster battery needs to adjust the lower limit threshold of the voltage to prolong the service life.

[0119] As shown in FIG. 5, the coefficient shows that the impedance of the cells No. 17, 174 and 204 is smaller.

[0120] As shown in FIG. 6, it shows that the voltage fluctuation of the cells No. 4, 69 and 204 has a higher correlation with the cycle number in the window time. By comparing the correlation of voltage fluctuation with maximum voltage value, minimum voltage value, discharge current and cycle number in the window time, it can be determined that the capacity of the cell No. 204 should be greater than the average level of the cluster, and its actual SOC is lower than the average level of the cluster.

[0121] As shown in FIG. 7, it can be seen that the No. 76 monomer and the No. 204 monomer have obvious outlier characteristics, wherein the aging level of the No. 76 monomer is slightly greater than the average level in the cluster, but does not exceed the threshold of R=3, and the aging level of the No. 204 monomer is obviously lower than the average level in the cluster, considering the above-mentioned large capacity and low SOC level of the No. 204 monomer, the aging of the No. 76 monomer is significant, and the lower discharge threshold should be temporarily increased.

[0122] More preferably, when the number of battery clusters is large, a hierarchical clustering, K-means+, or other clustering method can be used to cluster the normalized correlation coefficients of the abnormal battery, so as to give a batch of diagnosis results.

[0123] Embodiment two:

[0124] The application also provides a battery cluster cell fault diagnosis system 10, the domain controller 100 at least includes a processor 120 and a memory 110, the memory 110 is used to store the computer instructions of a plurality of function modules for realizing the capacity grading and grouping of battery ladder utilization;The processor 120 is communicated with the memory 110 through 130, and is used to execute each computer instruction of the function module stored in the memory 110.

[0125] Among them, the plurality of function modules at least includes: dynamic parameter acquisition module 111: based on BMS to the whole battery cluster and each monomer battery cell Parameter acquisition to obtain diagnostic parameters;Wherein the diagnostic parameters at least include monomer battery cell temperature, monomer battery cell voltage and initial characteristic parameter;Fluctuation characteristic acquisition module 112: respectively based on the monomer battery cell temperature and monomer battery cell voltage to obtain temperature fluctuation parameter and voltage fluctuation parameter;Characteristic analysis module 113: based on window time to extract a plurality of target characteristic values from the initial characteristic parameters, and calculate the correlation coefficient of each target characteristic value and the voltage fluctuation parameter and temperature fluctuation parameter;Normalization diagnosis module 114: the same kind of correlation coefficient is normalized, the normalized correlation coefficient belongs to the cell fault category is judged, and the cell diagnosis result is obtained based on the judgment result.

[0126] In some embodiments, the memory 110 and the processor 120 are connected to each other through the bus 130;The processor 120 can be one or more CPUs, and in the case of a CPU, the CPU can be a single-core CPU or a multi-core CPU, and the processor 120 is used to control the various function modules of the electronic device and process signals.

[0127] The memory 110 includes, but is not limited to, a RAM (Random Access Memory), a ROM (Read-Only Memory), an EPROM (Erasable Programmable Read-Only Memory 110), a CD-ROM (Compact Disc Read-Only Memory), which is used to store a computer program, an operating system, various applications and data, such as a computer program for implementing the battery cluster cell fault diagnosis method.

[0128] Embodiment Three:

[0129] The application also provides a battery cluster cell fault diagnosis cloud server, wherein the cloud server at least includes a battery cluster cell fault diagnosis system 10, and the battery cluster cell fault diagnosis system 10 adopts the battery cluster cell fault diagnosis method as described in Embodiment One to perform fault diagnosis on each single cell in the battery cluster to obtain a corresponding cell diagnosis result.

[0130] In summary, the application provides a battery cluster cell fault diagnosis method, system and cloud server, which further calculates temperature fluctuation parameters and voltage fluctuation parameters by collecting parameters of the battery cluster as a whole and each single cell; then obtains a corresponding correlation coefficient based on the temperature fluctuation parameters and voltage fluctuation parameters and the extracted target characteristic value; and obtains a cell diagnosis result based on the normalized correlation coefficient. The fault diagnosis method of the application does not rely on complex models and high computing power, thereby reducing hardware and labor costs; and the fault diagnosis process is fast and efficient, which facilitates maintenance personnel to take timely measures; the method is easy to implement in existing battery management systems without the need for large-scale modification, thereby facilitating popularization and application.

[0131] Although the example embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the above-described example embodiments are merely exemplary and are not intended to limit the scope of the application. Those of ordinary skill in the art can make various changes and modifications without departing from the scope and spirit of the application. All such changes and modifications are intended to be included within the scope of the application as claimed in the appended claims.

[0132] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0133] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the above-described device embodiments are only illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0134] Embodiments of various components of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some modules according to the embodiments of the present application. The present application can also be implemented as a device program (for example, a computer program and a computer program product) for executing part or all of the methods described herein. Such program implementing the present application can be stored on a computer readable medium, or can have one or more signals in the form. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0135] It should be noted that in this paper, relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or device including the element.

[0136] While the application has been described in connection with specific embodiments thereof, it will be understood that many modifications, substitutions and changes will be apparent to those skilled in the art in light of the foregoing description. Accordingly, it is intended to embrace all changes and modifications that fall within the spirit and scope of the claims.

Claims

1. A method of diagnosing a cell failure in a battery cluster, wherein, The method comprises the following steps: collecting parameters of the battery cluster as a whole and each single battery cell based on the BMS to obtain diagnostic parameters, wherein the diagnostic parameters at least include single battery cell temperature, single battery cell voltage and initial characteristic parameters (S100); obtaining temperature fluctuation parameters and voltage fluctuation parameters based on the single battery cell temperature and single battery cell voltage respectively (S200); extracting a plurality of target characteristic values from the initial characteristic parameters based on a window time, and calculating the correlation coefficients of each target characteristic value with the voltage fluctuation parameters and temperature fluctuation parameters (S300); normalizing the same kind of correlation coefficients, judging the normalized correlation coefficients to belong to which kind of battery cell fault, and obtaining a battery cell diagnosis result based on the judgment result (S400).

2. The cell-in-battery string fault diagnosis method according to claim 1, wherein, After the S100, the method further comprises: performing data cleaning on the diagnostic parameters.

3. The cell-in-battery string fault diagnosis method according to claim 2, wherein, After the data cleaning is completed, the method further comprises: judging whether the single battery cell temperature and single battery cell voltage correspond to each other, if yes, then turn to S200; otherwise, perform temperature interpolation calculation on the single battery cell temperature, and then turn to S200.

4. The cell-in-battery string fault diagnosis method according to claim 3, wherein, The target characteristic values at least include single battery cell characteristic values and battery cluster characteristic values; the S300 of extracting a plurality of target characteristic values from the initial characteristic parameters based on a window time comprises: performing first characteristic extraction and second characteristic extraction on the single battery cell and battery cluster respectively based on the window time to obtain single battery cell characteristic values and battery cluster characteristic values.

5. The cell-in-battery string fault diagnostic method according to claim 4, wherein, The first characteristic extraction specifically comprises: obtaining a first voltage value with a cycle number not greater than a preset cycle number based on the window time, and obtaining a second voltage value based on the window time.

6. The cell-in-battery string fault diagnostic method according to claim 5, wherein The first characteristic extraction specifically comprises: The first voltage value at least includes maximum voltage value, minimum voltage value, voltage value before charging and voltage value after charging; and the second voltage value at least includes voltage mean value, voltage mode value and voltage median value.

7. The cell-in-battery string fault diagnostic method according to claim 6, wherein The second characteristic extraction specifically comprises: obtaining target current value, target SOC and battery capacity based on the window time.

8. The cell-in-battery string fault diagnostic method according to claim 7, wherein The second characteristic extraction specifically comprises: The target current value at least includes average non-zero current, average charging current and average discharging current; the target SOC at least includes pre-charging SOC, post-charging SOC, post-discharging SOC, charging SOC change, discharging SOC change, window cycle number and cumulative cycle number; and the battery capacity at least includes charging capacity and discharging capacity.

9. The cell-in-battery string fault diagnostic method according to claim 8, wherein, The method of obtaining window cycle number and cumulative cycle number specifically comprises: selecting data samples based on the pre-charging SOC, post-charging SOC or post-discharging SOC, and obtaining effective frame number of the data samples and time sequence number of the current window time; obtaining window cycle number based on the data samples, effective frame number and time sequence number; performing cumulative summation on each window cycle number based on a plurality of time sequence numbers to obtain cumulative cycle number.

10. The cell-in-battery string fault diagnostic method according to claim 9, wherein, The battery cell fault categories at least include first fault category and second fault category; and the battery cell diagnosis result at least includes first fault diagnosis result and second fault diagnosis result.

11. The cell-in-battery string fault diagnostic method according to claim 10, wherein, The judgment in the S400 is that the normalized correlation coefficient belongs to the battery cell fault category, and the battery cell diagnosis result is obtained based on the judgment result, specifically including: The normalized correlation coefficient is used as a diagnosis coefficient; If the diagnosis coefficient is in the first interval, the single battery cell corresponding to the diagnosis coefficient is marked as paranoid; If the diagnosis coefficient is in the second interval, it is determined that the single battery cell corresponding to the diagnosis coefficient belongs to the first fault category, and the first fault diagnosis result corresponding to the first fault category is obtained; If the diagnosis coefficient is in the third interval, it is determined that the single battery cell corresponding to the diagnosis coefficient belongs to the second fault category, and the second fault diagnosis result corresponding to the first fault category is obtained.

12. A battery cluster internal battery cell fault diagnosis system (10) comprising at least a domain controller (100), the domain controller (100) collects parameters of the entire battery cluster and each single battery cell based on the BMS to obtain diagnosis parameters; obtains temperature fluctuation parameters and voltage fluctuation parameters based on the diagnosis parameters; extracts a plurality of target characteristic values based on window time on the initial characteristic parameters, and calculates the correlation coefficient of each target characteristic value and the voltage fluctuation parameter and the temperature fluctuation parameter; normalize the same correlation coefficient, judge the normalized correlation coefficient belonging to the battery cell fault category, and obtain the battery cell diagnosis result based on the judgment result.

13. The battery cluster internal battery cell fault diagnosis system (10) according to claim 12, the domain controller (100) comprises at least a processor (120) and a memory (110), The memory (110) is used to store computer instructions for implementing a plurality of function modules of the capacity matching and grouping of battery ladder utilization; The processor (120) communicates with the memory (110) through the bus (130), and is used to execute each computer instruction of the function modules stored in the memory (110).

14. The battery cluster internal battery cell fault diagnosis system (10) according to claim 13, the plurality of function modules at least include: Dynamic parameter acquisition module (111): based on the BMS, the parameters of the entire battery cluster and each single battery cell are collected to obtain diagnosis parameters; wherein the diagnosis parameters at least include single battery cell temperature, single battery cell voltage and initial characteristic parameters; Fluctuation characteristic acquisition module (112): respectively based on the single battery cell temperature and the single battery cell voltage, the temperature fluctuation parameter and the voltage fluctuation parameter are obtained; Characteristic analysis module (113): based on window time, a plurality of target characteristic values are extracted from the initial characteristic parameters, and the correlation coefficient of each target characteristic value and the voltage fluctuation parameter and the temperature fluctuation parameter is calculated; Normalization diagnosis module (114): normalize the same correlation coefficient, judge the normalized correlation coefficient belonging to the battery cell fault category, and obtain the battery cell diagnosis result based on the judgment result.

15. A cloud server, wherein, The cloud server at least comprises a battery cluster cell fault diagnosis system (10), and the battery cluster cell fault diagnosis system (10) adopts the battery cluster cell fault diagnosis method in claim 1 to perform fault diagnosis on each single cell in the battery cluster to obtain a corresponding cell diagnosis result.

Images