A method, apparatus, device, and storage medium for detecting capacity anomalies.
By analyzing voltage data during battery charging, the detection of capacity anomalies is simplified, solving the problems of long cycles and high data quality requirements in traditional methods, and realizing fast and accurate detection of battery capacity anomalies.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- EVE POWER CO LTD
- Filing Date
- 2023-07-21
- Publication Date
- 2026-07-31
AI Technical Summary
Traditional methods for detecting abnormal battery capacity have long processing times, high data quality requirements, and slow response times, making it difficult to identify abnormal capacity degradation phenomena in battery systems in a timely manner.
By analyzing the voltage data recorded during battery charging, extracting voltage data segments, calculating average values and sorting them, and using simple calculation rules to determine whether the battery capacity is abnormal, the requirements for data quality are reduced, making it suitable for both fast and slow charging.
It enables rapid and accurate detection of abnormal battery capacity, simplifies the detection process, reduces reliance on data quality, and improves detection efficiency.
Smart Images
Figure CN116859274B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to battery testing technology, and more particularly to a method, apparatus, device and storage medium for detecting capacity anomalies. Background Technology
[0002] As usage time increases, the condition of lithium-ion cells deteriorates, exhibiting abnormal capacity (attenuation). This severely restricts the capacity utilization and safety of the battery system. Accurately identifying cells with abnormal capacity attenuation and addressing them promptly becomes crucial.
[0003] Traditional methods for detecting capacity anomalies mainly include: disassembling the battery system and testing the capacity of each disassembled cell; and building a data-driven model to identify cells with abnormal capacity decay.
[0004] The above-mentioned testing methods have certain drawbacks, including: it is impossible to guarantee that each battery cell is intact during the disassembly process; testing each battery cell after disassembly is time-consuming and cannot be promptly fed back to the big data platform for processing; and building a data-driven model requires high data quality, requiring slow and stable full-charge data for calculation.
[0005] In summary, traditional methods for identifying abnormal capacity (attenuation) cells have long cycles, while building a data-driven model requires high data quality and has a slow response speed. Summary of the Invention
[0006] This invention provides a method, apparatus, device, and storage medium for detecting abnormal battery capacity, so as to achieve the purpose of simple, fast, and accurate detection of abnormal battery capacity.
[0007] In a first aspect, embodiments of the present invention provide a capacity anomaly detection method, comprising:
[0008] Perform constant current charging on the battery under test and record the charging process data;
[0009] From the charging process data, at least the voltage data of all individual cells in the battery under test are obtained;
[0010] According to preset rules, voltage data segments are extracted from the voltage data, and a first voltage dataset U1 and a second voltage dataset U2 are extracted from the voltage data segments.
[0011] Let the first voltage dataset U1 be {V 1_j |j=1…m}, let the second voltage dataset U2 be {V 2_j |j=1…m};
[0012] In the formula, V 1_jThis represents the N voltage data points of the j-th individual cell in the first voltage dataset, where V is the voltage value. 2_j This represents the N voltage data points of the j-th individual cell in the second voltage dataset, where m represents the number of individual cells and N is a set value.
[0013] Calculate each V separately 1_j The average value is calculated, and the sequence formed by the results is denoted as the first sequence. Each V is then calculated separately. 2_j The average value of the results is used to construct a sequence, which is then denoted as the second sequence.
[0014] The average values in the first sequence and the second sequence are sorted according to the same sorting rules, and the sorted sequences are respectively denoted as the third sequence and the fourth sequence;
[0015] The third and fourth sequences are used to perform calculations according to preset calculation rules, and the capacity of the battery under test is determined based on the calculation results.
[0016] Optionally, performing calculations using the third sequence and the fourth sequence according to preset calculation rules includes:
[0017] The difference between the third sequence and the fourth sequence is calculated, and the result is denoted as C, where C is:
[0018] {Δr j |j=1…m}
[0019] Determining whether the capacity of the battery under test is abnormal based on the calculation results includes:
[0020] If there exists at least one Δr j Satisfy |Δr j If |>ms, then the capacity of the battery under test is determined to be abnormal, where s is a set integer.
[0021] Optionally, the battery under test is one of lithium cobalt oxide battery, lithium manganese oxide battery, binary lithium battery, and ternary lithium battery;
[0022] When a voltage data segment is extracted from the voltage data according to a preset rule, the voltage data segment satisfies the following:
[0023] During the time period corresponding to the voltage data segment, the initial capacity of the battery under test is less than the first capacity and the final capacity is greater than the second capacity.
[0024] The first capacity has a SOC of 29% to 31%, and the second capacity has a SOC of 94% to 96%.
[0025] Optionally, the battery under test is a lithium iron phosphate battery.
[0026] Extracting voltage data segments from the voltage data according to preset rules includes:
[0027] Based on the voltage data, determine whether there is a voltage plateau period during the charging process of all the individual cells. When all the individual cells have the voltage plateau period, extract all the voltage data outside the voltage plateau period.
[0028] Optionally, after obtaining the voltage data of all individual cells in the battery under test, the method further includes:
[0029] The voltage data is processed to remove at least one of the following: missing values, duplicate values, zero values, communication anomalies, and invalid values.
[0030] Optionally, for the j-th individual cell, the first N voltage data points are extracted from the voltage data segment to form the first voltage dataset, and the last N voltage data points are extracted from the voltage data segment to form the second voltage dataset.
[0031] Optionally, the first capacity is 30% SOC and the second capacity is 95% SOC.
[0032] Secondly, embodiments of the present invention also provide a capacity anomaly detection device, including a capacity anomaly detection unit, the capacity anomaly detection unit being used for:
[0033] Charge the battery under test and record the charging process data;
[0034] From the charging process data, at least the voltage data of all individual cells in the battery under test are obtained;
[0035] According to preset rules, voltage data segments are extracted from the voltage data, and a first voltage dataset U1 and a second voltage dataset U2 are extracted from the voltage data segments.
[0036] Let the first voltage dataset U1 be {V 1_j |j=1…m}, let the second voltage dataset U2 be {V 2_j |j=1…m};
[0037] In the formula, V 1_j This represents the N voltage data points of the j-th individual cell in the first voltage dataset, where V is the voltage value. 2_j This represents the N voltage data points of the j-th individual cell in the second voltage dataset, where m represents the number of individual cells and N is a set value.
[0038] Calculate each V separately 1_j The average value is calculated, and the sequence formed by the results is denoted as the first sequence. Each V is then calculated separately. 2_j The average value of the results is used to construct a sequence, which is then denoted as the second sequence.
[0039] The average values in the first sequence and the second sequence are sorted according to the same sorting rules, and the sorted sequences are respectively denoted as the third sequence and the fourth sequence;
[0040] The third and fourth sequences are used to perform calculations according to preset calculation rules, and the capacity of the battery under test is determined based on the calculation results.
[0041] Thirdly, embodiments of the present invention also provide an electronic device, including at least one processor and a memory communicatively connected to the at least one processor;
[0042] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform any of the capacity anomaly detection methods described in the embodiments of the present invention.
[0043] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute any of the capacity anomaly detection methods described in the embodiments of the present invention.
[0044] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention proposes a capacity anomaly detection method, in which voltage data recorded during battery charging is used to determine whether the battery capacity is abnormal. In the process of determining whether the battery capacity is abnormal, only voltage data is used to complete the detection and judgment of capacity anomaly, and the requirements for data quality are low and there are no requirements for the battery charging speed. It can effectively solve the problem of detecting the capacity anomaly of individual battery cells. Attached Figure Description
[0045] Figure 1 This is a flowchart of the capacity anomaly detection method in the embodiment;
[0046] Figure 2 This is a flowchart of another capacity anomaly detection method in the embodiment;
[0047] Figure 3 This is a schematic diagram of the abnormal lithium battery cell voltage curve in the embodiment.
[0048] Figure 4 This is a schematic diagram of the normal lithium battery cell voltage curve in the embodiment.
[0049] Figure 5 This is a schematic diagram of the lithium iron phosphate battery voltage curve in the embodiment;
[0050] Figure 6This is a schematic diagram of the voltage curve of the ternary lithium battery in the embodiment;
[0051] Figure 7 This is a schematic diagram of the electronic device structure in the embodiment. Detailed Implementation
[0052] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.
[0053] Example 1
[0054] Figure 1 This is a flowchart of the capacity anomaly detection method in the embodiment, for reference. Figure 1 Methods for detecting capacity anomalies include:
[0055] S101. Perform constant current charging on the battery under test and record the charging process data.
[0056] For example, in this embodiment, the specific method of constant current charging is not limited. For a certain type of battery, it can be charged using the method specified by the battery manufacturer, the method specified by the national standard, or a custom method.
[0057] For example, in this embodiment, the charging process data includes sampled values of a specified type of data during the constant current charging process of the battery under test. The specified type of data includes at least the voltage (data) of each individual cell. In addition, the specified type of data may also include timestamps, charging current, battery remaining state of charge (SOC), etc.
[0058] S102. Obtain the voltage data of at least all individual cells in the battery under test from the charging process data.
[0059] In this embodiment, the voltage data of all individual cells in the battery under test is the voltage data of each cell from the start time of charging to the end time of charging.
[0060] S103. Extract voltage data segments from the voltage data according to preset rules, and extract the first voltage dataset U1 and the second voltage dataset U2 from the voltage data segments.
[0061] For example, in this embodiment, voltage data segments are extracted from voltage data according to preset rules, wherein the preset rules may be to extract voltage data within a specified percentage range from the voltage data.
[0062] Alternatively, the preset rule can be based on the remaining battery charge level, extracting voltage data corresponding to a specified range of remaining battery charge levels.
[0063] In this embodiment, for each individual cell, the voltage data in the first voltage dataset U1 extracted from the voltage data segment is continuous on the sampling time axis, and the voltage data in the second voltage dataset U2 is connected on the sampling time axis.
[0064] Furthermore, the time periods corresponding to the first voltage dataset U1 are different from those corresponding to the second voltage dataset U2, and the time periods corresponding to the two do not overlap.
[0065] In this embodiment, the first voltage dataset U1 is denoted as {V 1_j Let the second voltage dataset U2 be {V |j=1…m}, and denote it as {V 2_j |j=1…m}, where V 1_j V 2_j Each represents a data sequence;
[0066] Specifically, in the formula, V 1_j This represents the N voltage data points of the j-th individual cell in the first voltage dataset, where V is the voltage value. 2_j This represents the N voltage data points of the j-th individual cell in the second voltage dataset, where m represents the number of individual cells.
[0067] For example, in this embodiment, m is the total number of individual cells in the battery under test, and N is a set value, N>3. The number of N can be freely set according to requirements.
[0068] S104. Calculate each V separately. 1_j The average value is calculated, and the sequence formed by the results is denoted as the first sequence. Each V is then calculated separately. 2_j The average value of the results is used to construct a sequence, which is then denoted as the second sequence.
[0069] S105. Sort the average values in the first sequence and the second sequence according to the same sorting rules, and denote the sorted sequences as the third sequence and the fourth sequence, respectively.
[0070] In this embodiment, the sorting rule used is not limited; it can be either ascending or descending order.
[0071] S106. The third and fourth sequences are used to perform calculations according to preset calculation rules, and the capacity of the battery under test is judged based on the calculation results.
[0072] For example, in this embodiment, the preset calculation rule can be to determine the function model based on the simulation experiment. Correspondingly, the result of the above function model can be compared with the preset threshold to determine whether the battery under test has an abnormal capacity.
[0073] Alternatively, the preset calculation rule can be to use one of the four arithmetic operations to perform calculations on the third and fourth sequences, and compare the result of the calculation with one or more voltage values with a preset threshold to determine whether the battery under test has an abnormal capacity.
[0074] For example, in this embodiment, the method for determining the above threshold is not limited, and it can be determined based on experience, simulation experiments, calibration experiments, etc.
[0075] This embodiment proposes a capacity anomaly detection method. In this method, voltage data recorded during battery charging is used to determine whether the battery capacity is abnormal. In the process of determining whether the battery capacity is abnormal, only voltage data is used to complete the detection and judgment of capacity anomaly. Moreover, the requirements for data quality are low and there are no requirements for the charging speed of the battery. This method can effectively solve the problem of detecting the capacity anomaly of individual battery cells.
[0076] Specifically, in this method, when using voltage data to determine whether the capacity is abnormal, it only involves simple average value calculation, sorting, and simple comparison operations. It does not depend on the function model of the load, nor does it require a complex data calculation process. The detection cycle is short and the execution efficiency is high.
[0077] exist Figure 1 Based on the scheme shown, in one feasible implementation, the calculation using the third and fourth sequences according to preset calculation rules includes:
[0078] The difference between the third and fourth sequences is calculated, and the result is denoted as C, where C is:
[0079] {Δr j |j=1…m}
[0080] Determining whether the capacity of the battery under test is abnormal based on the calculation results includes:
[0081] If there exists at least one Δr j Satisfy |Δr j If |>m-10, then the capacity of the battery under test is determined to be abnormal.
[0082] For example, in this scheme, the third sequence is denoted as U. s U s ={r s_j |j=1…m}, let the fourth sequence be denoted as U e U e ={r e_j|j=1…m}, then Δr j Specifically:
[0083] r s_j -r e_j
[0084] For example, in this solution, the abnormality of the capacity of the battery under test can also be determined in the following way:
[0085] If Δr m Satisfy |Δr m If |>ms, then the capacity of the battery under test is determined to be abnormal, where s is a set integer, for example, s can be 10.
[0086] exist Figure 1 Based on the scheme shown, in one possible implementation, if the battery under test is a non-lithium iron phosphate battery, the voltage data segment extracted from the voltage data according to preset rules includes:
[0087] Within the time period corresponding to the voltage data segment, the initial capacity of the battery under test is less than the first capacity and the final capacity is greater than the second capacity.
[0088] For example, in this solution, the battery under test is set to be a lithium battery, and the type of non-lithium iron phosphate battery is not limited. For example, the non-lithium iron phosphate battery can be one of lithium cobalt oxide battery, lithium manganese oxide battery, binary lithium battery, or ternary lithium battery.
[0089] In this scheme, the charging process data should also include the battery's remaining state of charge, where the first capacity can be 29% to 31% SOC and the second capacity can be 94% to 96% SOC.
[0090] In this scheme, the voltage data segment is extracted based on the SOC of the battery under test. That is, the starting voltage data of the voltage data segment corresponds to the voltage data when the battery under test is at the first capacity, and the ending voltage data of the voltage data segment corresponds to the second capacity.
[0091] In this solution, when the lithium battery is not a lithium iron phosphate battery, a portion of the voltage data with a suitable SOC is extracted as the voltage data segment, which can improve the accuracy of capacity anomaly detection during subsequent calculations and judgments.
[0092] Preferably, in one possible implementation, the first capacity is set to 30% SOC and the second capacity to 95% SOC.
[0093] exist Figure 1 Based on the scheme shown, in one possible implementation, if the battery under test is a lithium iron phosphate battery, the voltage data segment extracted from the voltage data according to preset rules includes:
[0094] Based on the voltage data, determine whether there is a voltage plateau period in all individual cells during the charging process. If at least one individual cell does not have a voltage plateau period, discard all voltage data; otherwise, retain all voltage data.
[0095] For example, in this solution, the voltage plateau period is the initial stage of battery charging, during which the voltage changes very slowly and the voltage curve is almost horizontal.
[0096] For example, in this solution, when all voltage data is retained, the voltage data within the voltage plateau period is removed, and the remaining voltage data is used as the voltage data segment.
[0097] In this solution, when the battery under test is a lithium iron phosphate battery, the voltage data is screened by checking whether there is a voltage plateau period in the charging voltage of a single cell. This can effectively eliminate voltage data that does not meet the usage requirements, thereby improving the accuracy of capacity anomaly detection.
[0098] exist Figure 1 Based on the scheme shown, in one possible implementation, after obtaining the voltage data of all individual cells in the battery under test, the method further includes:
[0099] Remove at least one of the following from voltage data: missing values, duplicate values, zero values, communication anomalies, and invalid values.
[0100] In this scheme, after performing the above data processing on the voltage data, voltage data segments are then extracted from the remaining voltage data according to preset rules.
[0101] exist Figure 1 Based on the scheme shown, in one possible implementation, the first voltage dataset is set to include the first N voltage data of the j-th individual cell; the second voltage dataset includes the last N voltage data of the j-th individual cell.
[0102] In this scheme, the first and last parts of the voltage data segment are used as the first voltage data segment and the second voltage data segment, respectively.
[0103] Figure 2 This is a flowchart of another capacity anomaly detection method in the embodiment, see reference. Figure 2 In one possible implementation, the capacity anomaly detection method includes:
[0104] S201. Perform constant current charging on the battery under test and record the charging process data.
[0105] In this scheme, a capacity anomaly detection scheme is set up for the capacity anomaly detection of lithium iron phosphate batteries.
[0106] In this scheme, the charging process data includes timestamps, charging current, and voltage (data) of each individual battery cell.
[0107] In this solution, the charging process data is also processed, including removing at least one of the following: missing values, duplicate values, zero values, communication anomalies, and invalid values.
[0108] For example, in this solution, the charging process data is recorded in the following format:
[0109] The charging process data consists of n rows, and the charging current term is denoted as I, where I = {I...} i |i=1…n}, let the voltage data item be U, U={U j |j=1…m}, where U j ={u j_i |i=1…n}.
[0110] S202. From the charging process data, obtain the voltage data of at least all individual cells in the battery under test according to national standards.
[0111] In this scheme, the national standard is set as GB / T 32960-2016, and the voltage data of all individual cells in the battery under test are obtained from the remaining charging process data after data processing.
[0112] S203. Determine whether there is a voltage plateau period during the charging process of all individual cells based on the voltage data. If so, retain all voltage data.
[0113] In this scheme, if it is determined that all individual cells have a voltage plateau period during the charging process, then all voltage data are retained.
[0114] If at least one individual cell does not have a voltage plateau during charging, all voltage data is discarded. In this case, the charging process data is determined to be inconsistent with the judgment criteria, and the capacity anomaly detection ends.
[0115] In this scheme, if all voltage data is retained, then the voltage data within the voltage plateau period is removed, and the remaining voltage data is used as the voltage data segment.
[0116] S204. For each individual cell, extract the first 10 voltage data points from the voltage data segment to form a first voltage dataset, and extract the last 10 voltage data points to form a second voltage dataset.
[0117] Let the first voltage dataset U1 be {V 1_j |j=1…m},V 1_j ={u 1_j_1 ,u 1_j_2 …u 1_j_10 Let the second voltage dataset U2 be {V}. 2_j |j=1…m},V2_j ={u 2_j_1 ,u 2_j_2 …u 2_j_10}
[0118] S205. Calculate each V separately. 1_j The average value is calculated, and the sequence formed by the results is denoted as the first sequence. Each V is then calculated separately. 2_j The average value of the results is used to construct a sequence, which is then denoted as the second sequence.
[0119] S206. Sort the average values in the first sequence and the second sequence according to the same sorting rules, and denote the sorted sequences as the third sequence and the fourth sequence, respectively.
[0120] In this scheme, the third sequence is denoted as U. s U s ={r s_j |j=1…m}, let the fourth sequence be denoted as U e U e ={r e_j |j=1…m}.
[0121] S207. Calculate the difference between the third and fourth sequences, and determine whether the capacity of the battery under test is abnormal based on the calculation result.
[0122] The difference between the third and fourth sequences is calculated, and the result is denoted as C, where C is:
[0123] {Δr j |j=1…m}
[0124] In this scheme, Δr j Specifically:
[0125] r s_j -r e_j
[0126] If Δr m Satisfying Δr m If the value is greater than m-10, the capacity of the battery under test is determined to be abnormal.
[0127] Figure 3 This is a schematic diagram of the abnormal lithium battery cell voltage curve in the embodiment. Figure 4 This is a schematic diagram of a normal lithium battery cell voltage curve in the embodiment. Figure 5 This is a schematic diagram of the lithium iron phosphate battery voltage curve in the embodiment, for reference. Figures 3-5For lithium iron phosphate batteries, outside the voltage plateau period, the voltage data at the beginning and end of the abnormal voltage curve are significantly abnormal compared to the normal voltage curve. In this solution, the first 10 and last 10 voltage data points in the voltage data segment are selected and used for subsequent calculations and judgments. This can reduce the number of data points used and ensure the accuracy of capacity anomaly detection and judgment.
[0128] Figure 6 This is a schematic diagram of the voltage curve of the ternary lithium battery in the embodiment, for reference. Figure 6 Taking ternary lithium batteries as an example, the capacity anomaly detection method proposed in this solution can also be used for capacity anomaly detection of non-lithium iron phosphate batteries. In this case, step S203 is replaced by selecting the voltage data corresponding to the SOC between 30% and 95% based on the battery's remaining state of charge, as the voltage data segment. The content of the remaining steps in this method remains unchanged, and the specific details will not be described in detail.
[0129] The proposed capacity anomaly detection method solves the problem of identifying abnormal capacity decay of individual cells in battery systems in practical application scenarios; the voltage data obtained is applicable regardless of whether the battery is fast or slow charged, and the data quality requirements are lower than those of data-driven models; the detection cycle is short, and the results can be quickly fed back to the big data platform.
[0130] Example 2
[0131] This embodiment proposes a capacity anomaly detection device, including a capacity anomaly detection unit, which is used for:
[0132] Charge the battery under test and record the charging process data;
[0133] From the charging process data, at least the voltage data of all individual cells in the battery under test should be obtained;
[0134] According to preset rules, voltage data segments are extracted from voltage data, and first voltage dataset U1 and second voltage dataset U2 are extracted from the voltage data segments.
[0135] Let the first voltage dataset U1 be {V 1_j Let the second voltage dataset U2 be {V |j=1…m}, and denote it as {V 2_j |j=1…m};
[0136] In the formula, V 1_j This represents the N voltage data points of the j-th individual cell in the first voltage dataset, where V is the voltage value. 2_j This represents the N voltage data points of the j-th individual cell in the second voltage dataset, where m represents the number of individual cells.
[0137] Calculate each V separately 1_jThe average value is calculated, and the sequence formed by the results is denoted as the first sequence. Each V is then calculated separately. 2_j The average value of the results is used to construct a sequence, which is then denoted as the second sequence.
[0138] Sort the average values in the first and second sequences according to the same sorting rules, and denote the sorted sequences as the third and fourth sequences, respectively.
[0139] The third and fourth sequences are used to perform calculations according to preset calculation rules, and the capacity of the battery under test is judged based on the calculation results.
[0140] In this embodiment, the capacity anomaly detection unit can be specifically designed to implement any one of the capacity anomaly detection methods in Embodiment 1. Its implementation process and beneficial effects are the same as the corresponding content recorded in Embodiment 1, and will not be repeated here.
[0141] Example 3
[0142] Figure 7 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0143] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0144] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0145] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as capacity anomaly detection methods.
[0146] In some embodiments, the capacity anomaly detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the capacity anomaly detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the capacity anomaly detection method by any other suitable means (e.g., by means of firmware).
[0147] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0148] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0149] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0150] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0151] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0152] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0153] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.
Claims
1. A method for detecting capacity anomalies, characterized in that, include: Perform constant current charging on the battery under test and record the charging process data; From the charging process data, at least the voltage data of all individual cells in the battery under test are obtained; Voltage data segments are extracted from the voltage data according to preset rules, and a first voltage dataset is extracted from the voltage data segments. Second voltage dataset The first voltage dataset and the second voltage dataset These are the beginning and end portions of the voltage data segment, respectively. Record the first voltage dataset for Let the second voltage dataset be... for ; In the formula, In the first voltage dataset, the first... N voltage data points for a single battery cell In the second voltage dataset, the first N voltage data points for a single battery cell, where m represents the number of single battery cells and N is a set value; Calculate each The average value is calculated, and the sequence formed by the results is denoted as the first sequence. Each... The average value of the results is used to construct a sequence, which is then denoted as the second sequence. The average values in the first sequence and the second sequence are sorted according to the same sorting rules, and the sorted sequences are respectively denoted as the third sequence and the fourth sequence; The third sequence and the fourth sequence are used to perform calculations according to preset calculation rules, and the capacity of the battery under test is determined based on the calculation results. The calculation using the third sequence and the fourth sequence according to the preset calculation rules includes: The difference between the third sequence and the fourth sequence is calculated, and the result is denoted as C, where C is: Determining whether the capacity of the battery under test is abnormal based on the calculation results includes: If at least one satisfy If s is a set integer, then the capacity of the battery under test is determined to be abnormal.
2. The capacity anomaly detection method as described in claim 1, characterized in that, The battery under test is one of the following: lithium cobalt oxide battery, lithium manganese oxide battery, binary lithium battery, and ternary lithium battery. When a voltage data segment is extracted from the voltage data according to a preset rule, the voltage data segment satisfies the following: During the time period corresponding to the voltage data segment, the initial capacity of the battery under test is less than the first capacity and the final capacity is greater than the second capacity. The first capacity has a SOC of 29%~31%, and the second capacity has a SOC of 94%~96%.
3. The capacity anomaly detection method as described in claim 1, characterized in that, The battery under test is a lithium iron phosphate battery. Extracting voltage data segments from the voltage data according to preset rules includes: Based on the voltage data, determine whether there is a voltage plateau period during the charging process of all the individual cells. When all the individual cells have the voltage plateau period, extract all the voltage data outside the voltage plateau period.
4. The capacity anomaly detection method as described in any one of claims 1 to 3, characterized in that, After obtaining the voltage data of all individual cells in the battery under test, the method further includes: The voltage data is processed to remove at least one of the following: missing values, duplicate values, zero values, communication anomalies, and invalid values.
5. The capacity anomaly detection method as described in any one of claims 1 to 3, characterized in that, Regarding the first For each individual battery cell, the first N voltage data points are extracted from the voltage data segment to form the first voltage dataset, and the last N voltage data points are extracted from the voltage data segment to form the second voltage dataset.
6. The capacity anomaly detection method as described in claim 2, characterized in that, The first capacity is 30% SOC, and the second capacity is 95% SOC.
7. A capacity anomaly detection device, characterized in that, Includes a capacity anomaly detection unit, the capacity anomaly detection unit being used for: Charge the battery under test and record the charging process data; From the charging process data, at least the voltage data of all individual cells in the battery under test are obtained; Voltage data segments are extracted from the voltage data according to preset rules, and a first voltage dataset is extracted from the voltage data segments. Second voltage dataset The first voltage dataset and the second voltage dataset These are the beginning and end portions of the voltage data segment, respectively. Record the first voltage dataset for Let the second voltage dataset be... for ; In the formula, In the first voltage dataset, the first... N voltage data points for a single battery cell In the second voltage dataset, the first N voltage data points for a single battery cell, where m represents the number of single battery cells and N is a set value; Calculate each The average value is calculated, and the sequence formed by the results is denoted as the first sequence. Each... The average value of the results is used to construct a sequence, which is then denoted as the second sequence. The average values in the first sequence and the second sequence are sorted according to the same sorting rules, and the sorted sequences are respectively denoted as the third sequence and the fourth sequence; The third sequence and the fourth sequence are used to perform calculations according to preset calculation rules, and the capacity of the battery under test is determined based on the calculation results. The calculation using the third sequence and the fourth sequence according to the preset calculation rules includes: The difference between the third sequence and the fourth sequence is calculated, and the result is denoted as C, where C is: Determining whether the capacity of the battery under test is abnormal based on the calculation results includes: If at least one satisfy If s is a set integer, then the capacity of the battery under test is determined to be abnormal.
8. An electronic device, characterized in that, It includes at least one processor and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the capacity anomaly detection method according to any one of claims 1-6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the capacity anomaly detection method according to any one of claims 1-6.