A battery self-discharge consistency evaluation method, device, equipment and storage medium
By quantifying battery self-discharge consistency and using a model that evaluates SOC difference values and date numerical sequences, the problem of low accuracy in battery self-discharge consistency assessment in existing technologies is solved, enabling accurate estimation and fault warning under most operating conditions.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- EVE POWER CO LTD
- Filing Date
- 2022-12-06
- Publication Date
- 2026-06-05
AI Technical Summary
Existing methods for assessing battery self-discharge consistency are easily affected by voltage plateau characteristics and cannot quantitatively assess the impact of self-discharge consistency, resulting in low estimation accuracy.
By determining the SOC value of all individual cells in the battery pack within a single day, a SOC difference value sequence is generated. Various models (such as fitting functions, neural networks, F distribution functions, etc.) are used to quantify the battery self-discharge consistency. The confidence level is then assessed by combining the date value sequence to determine whether the battery exhibits abnormal self-discharge consistency.
It achieves accurate estimation of battery self-discharge consistency under any operating condition, improves the reliability and accuracy of the judgment results, and provides strong data support for battery fault early warning.
Smart Images
Figure CN116027197B_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 evaluating battery self-discharge consistency. Background Technology
[0002] Abnormal self-discharge consistency can usually be used as a basis for judging whether a battery has a short circuit, battery leakage, capacity decay, etc. Since the battery often has significant safety hazards when the above faults occur, the accurate identification of abnormal self-discharge faults is of great significance.
[0003] Currently, the main methods for identifying battery self-discharge anomalies include voltage analysis and SOC analysis. Voltage analysis primarily extracts the voltage difference characteristics of individual cells and identifies self-discharge anomalies based on the rate of change of the voltage difference. However, this method is easily affected by voltage plateau characteristics and cannot quantitatively assess the impact on the consistency of self-discharge. SOC analysis is largely consistent with voltage analysis in principle, but the difference lies in using the individual cell SOC instead of the individual cell voltage for evaluation data. This method can quantitatively assess the impact on the consistency of self-discharge, but the estimation accuracy is relatively low.
[0004] In summary, there is an urgent need for a method that can effectively estimate battery self-discharge consistency and achieve high accuracy in the estimation results. Summary of the Invention
[0005] This invention provides a method, apparatus, device, and storage medium for evaluating battery self-discharge consistency, in order to accurately identify battery self-discharge consistency.
[0006] In a first aspect, embodiments of the present invention provide a method for evaluating the self-discharge consistency of a battery, comprising:
[0007] Determine the SOC value of all individual cells in the battery pack within a single day, and use the SOC value to determine the daily SOC difference value using the first model;
[0008] Obtain the daily SOC difference value for a specified number of days, generate a SOC difference value sequence, and generate a date value sequence based on the date corresponding to the daily SOC difference value;
[0009] Using the SOC difference value sequence and the date value sequence, the second model is used to determine the battery self-discharge consistency difference value;
[0010] Based on the battery self-discharge consistency difference value, SOC difference value sequence, and date value sequence, a third model is used to determine the battery self-discharge consistency confidence level.
[0011] The battery self-discharge consistency difference value and the battery self-discharge consistency confidence level are used to determine whether the battery has an abnormal self-discharge consistency.
[0012] Optionally, the first model includes:
[0013]
[0014] In the formula, S u This represents the daily SOC difference value, SOC i_max This represents the maximum SOC (State of Charge) of all individual cells at time i within a single day. i_min This represents the minimum SOC value among all individual cells at time i within a single day, and N represents the number of times within a single day.
[0015] Optionally, the second model includes:
[0016]
[0017] In the formula, β1 represents the battery self-discharge consistency difference value, Y i d represents the i-th element in the SOC difference value sequence. i This represents the i-th element in the date numeric sequence. This represents the average value of the elements in the SOC difference value sequence. This represents the average value of the elements in the date value sequence, and n represents the number of elements in the SOC difference value sequence.
[0018] Optionally, the third model includes the F distribution function.
[0019] Optionally, the confidence level of battery self-discharge consistency can be determined using the following formula:
[0020]
[0021]
[0022]
[0023]
[0024] In the formula, P F Let F represent the confidence level of battery self-discharge consistency, β1 represent the battery self-discharge consistency difference value, and Y represent the confidence level of battery self-discharge consistency. i d represents the i-th element in the SOC difference value sequence. i This represents the i-th element in the date numeric sequence. This represents the average value of the elements in the SOC difference value sequence. This represents the average value of the elements in the date value sequence, and n represents the number of elements in the SOC difference value sequence.
[0025] Optionally, generating a date value sequence based on the date corresponding to the daily SOC difference value includes:
[0026] Obtain the date corresponding to the single-day SOC difference value, determine the number of days difference between the dates corresponding to the two specified single-day SOC difference values, and subtract each number of days difference from a set value to generate the date value sequence.
[0027] Optionally, the fourth model can be used to determine the SOC value of a single cell;
[0028] The inputs to the fourth model include at least the individual cell voltage, battery pack state of charge, battery pack temperature, battery pack current, and vehicle cumulative mileage.
[0029] Secondly, embodiments of the present invention also provide a battery self-discharge consistency evaluation device, including a battery self-discharge consistency evaluation unit, the battery self-discharge consistency evaluation unit being used for:
[0030] Determine the SOC value of all individual cells in the battery pack within a single day, and use the SOC value to determine the daily SOC difference value using the first model;
[0031] Obtain the daily SOC difference value for a specified number of days, generate a SOC difference value sequence, and generate a date value sequence based on the date corresponding to the daily SOC difference value;
[0032] Using the SOC difference value sequence and the date value sequence, the second model is used to determine the battery self-discharge consistency difference value;
[0033] Based on the battery self-discharge consistency difference value, SOC difference value sequence, and date value sequence, a third model is used to determine the battery self-discharge consistency confidence level.
[0034] The battery self-discharge consistency difference value and the battery self-discharge consistency confidence level are used to determine whether the battery has an abnormal self-discharge consistency.
[0035] 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;
[0036] 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 the battery self-discharge consistency evaluation method described in the embodiments of the present invention.
[0037] 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 the battery self-discharge consistency evaluation method described in the embodiments of the present invention.
[0038] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention proposes a method for assessing battery self-discharge consistency. This method quantifies battery self-discharge consistency by using daily SOC difference values within a specified number of days and the corresponding date values. By using daily SOC difference values and corresponding date values as the basis for calculating battery self-discharge consistency, the required parameter types are few, enabling this method to estimate battery self-discharge consistency under any operating condition. Furthermore, the estimated battery self-discharge consistency value determined by the daily SOC difference values and date values within a specified number of days accurately reflects the linear change in SOC difference values within that specified number of days, thus enabling accurate estimation of battery self-discharge consistency under most operating conditions and providing strong data support for battery fault early warning. Simultaneously, this method uses both battery self-discharge consistency difference values and battery self-discharge consistency confidence levels to jointly determine whether the battery exhibits abnormal self-discharge, improving the reliability and accuracy of the judgment results. Attached Figure Description
[0039] Figure 1 This is a flowchart of the battery self-discharge consistency evaluation method in the embodiments;
[0040] Figure 2 This is a graph of battery pack current test data from an embodiment;
[0041] Figure 3 This is a graph showing the battery pack voltage test data in the embodiment;
[0042] Figure 4 This is a diagram of the battery pack SOC data in the embodiment;
[0043] Figure 5 This is a graph showing the maximum SOC to minimum SOC data in the embodiment;
[0044] Figure 6 This is a graph showing the SOC difference data in the embodiment;
[0045] Figure 7 This is a graph showing the daily SOC difference data in the embodiment;
[0046] Figure 8 This is a schematic diagram of the electronic device structure in the embodiment. Detailed Implementation
[0047] 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.
[0048] Example 1
[0049] Figure 1 This is a flowchart of the battery self-discharge consistency assessment method in the embodiments, for reference. Figure 1 Battery self-discharge consistency assessment methods include:
[0050] S101. Determine the SOC value of all individual cells in the battery pack within a single day, and use the SOC value to determine the daily SOC difference value using the first model.
[0051] For example, in this embodiment, the method for determining the SOC value of a single cell is not specifically limited, and it can be achieved by any SOC estimation method in the prior art.
[0052] For example, in this embodiment, the daily SOC difference value can at least be used to represent the difference between the maximum and minimum SOC values among all individual cells within a single day.
[0053] For example, in this embodiment, the first model can be a fitting function or a neural network model, wherein the input of configuring the first model includes at least: the maximum SOC value and the minimum SOC value of all individual cells at multiple sampling times;
[0054] The output of the first model should include at least the daily SOC difference value.
[0055] S102. Obtain the daily SOC difference value for a specified number of days, generate a SOC difference value sequence, and generate a date value sequence based on the date corresponding to the daily SOC difference value.
[0056] For example, based on step S101, after determining the daily SOC difference value, the daily SOC difference value is stored. When storing, in addition to the daily SOC difference value, at least the date corresponding to the daily SOC difference value is also stored.
[0057] For example, in this embodiment, the specified number of days can be set according to requirements. For example, the specified number of days can be the number of days in a single month, the number of days in a single quarter, etc.
[0058] For example, in this step, a SOC difference value sequence is first generated, wherein the SOC difference value sequence consists of a number of daily SOC difference values within a specified number of days.
[0059] For example, in this embodiment, the number of daily SOC difference values included in the SOC difference value sequence may be the same as or different from the specified number of days, and the length of the SOC difference value sequence is the same as the length of the date value sequence.
[0060] For example, in this embodiment, after determining the specified number of days, the daily SOC difference values stored within the specified number of days before the current date are obtained, and then a SOC difference value sequence is generated;
[0061] If a single-day SOC difference value is stored every day within the above time period (the specified number of days before the current date), then the number of single-day SOC difference values contained in the SOC difference value sequence is the same as the specified number of days.
[0062] If no daily SOC difference value is stored on a certain day within the above time period, the number of daily SOC difference values contained in the SOC difference value sequence will be different from the specified number of days.
[0063] For example, in this embodiment, the elements in the date value sequence represent the position of each daily SOC difference value on the time axis, in days, when considering the default data (single-day SOC difference value).
[0064] For example, if the specified number of days is 3, and the corresponding determined SOC difference value sequence contains three daily SOC difference values, then the date value sequence can be {1,2,3}.
[0065] If the specified number of days is 3, the corresponding SOC difference value sequence contains two daily SOC difference values. The daily SOC difference value on the second day is omitted, so the date value sequence can be {1,3}.
[0066] For example, in this embodiment, the elements in the date value sequence are generated by date conversion corresponding to the daily SOC difference value, and the specific method is not limited.
[0067] S103. Using the SOC difference value sequence and the date value sequence, the second model is used to determine the battery self-discharge consistency difference value.
[0068] For example, in this embodiment, setting the battery self-discharge consistency difference value can at least be used to represent the magnitude of the difference between the daily SOC difference values within the SOC difference value sequence.
[0069] For example, in this embodiment, the second model can be a fitting function or a neural network model, wherein the inputs for configuring the second model include at least: a SOC difference value sequence and a date value sequence;
[0070] The output of the second model should include at least the battery self-discharge consistency difference value.
[0071] S104. Based on the battery self-discharge consistency difference value, SOC difference value sequence, and date value sequence, a third model is used to determine the confidence level of battery self-discharge consistency.
[0072] For example, in this embodiment, the third model adopts a distribution function model, such as the normal distribution function model, the F distribution function model, the Poisson distribution function model, etc.
[0073] Correspondingly, in this embodiment, the confidence level of battery self-discharge consistency is the confidence level calculated using the selected distribution function model.
[0074] For example, in this embodiment, the battery self-discharge consistency difference value, the SOC difference value sequence, and the date value sequence are used to input the probability density function of the selected distribution function. The degrees of freedom of the selected distribution function model are set according to requirements (or experience).
[0075] S105. Determine whether the battery has an abnormal self-discharge consistency based on the battery self-discharge consistency difference value and the battery self-discharge consistency confidence level.
[0076] For example, in this embodiment, a self-discharge consistency difference range and a confidence range can be set. If the battery self-discharge consistency difference value is within the self-discharge consistency difference range and the battery self-discharge consistency confidence is within the confidence range, then the battery self-discharge consistency is determined to be normal; otherwise, the battery self-discharge consistency is determined to be abnormal.
[0077] This embodiment proposes a method for assessing battery self-discharge consistency. This method quantifies battery self-discharge consistency by using daily SOC difference values within a specified number of days and the corresponding date values. By using the daily SOC difference values and corresponding date values as the basis for calculating battery self-discharge consistency, the method requires fewer parameter types, enabling it to estimate battery self-discharge consistency under any operating condition. Furthermore, the estimated battery self-discharge consistency value determined by the daily SOC difference values and date values within a specified number of days accurately reflects the linear change in SOC difference values within that specified number of days. This allows for accurate estimation of battery self-discharge consistency under most operating conditions, providing strong data support for battery fault early warning. Additionally, this method uses both the battery self-discharge consistency difference value and the battery self-discharge consistency confidence level to jointly determine whether the battery exhibits abnormal self-discharge, improving the reliability and accuracy of the judgment results.
[0078] As one possible implementation, based on the content recorded in step S101, the daily SOC difference value is determined by the following formula, i.e., the first model is:
[0079]
[0080] In the formula, S u This represents the daily SOC difference value, SOC i_max This represents the maximum SOC (State of Charge) of all individual cells at time i within a single day. i_min This represents the minimum SOC value among all individual cells at time i within a single day, and N represents the number of times within a single day.
[0081] For example, in this solution, the first model is a linear model. By using a linear model to calculate the daily SOC difference value, the algorithm complexity of battery self-discharge consistency estimation can be reduced and the computational efficiency can be improved.
[0082] As one possible implementation, based on the content recorded in step S103, the battery self-discharge consistency difference value can be determined by the following formula, i.e., the second model is:
[0083]
[0084] In the formula, β1 represents the battery self-discharge consistency difference value, Y i d represents the i-th element in the SOC difference value sequence. i This represents the i-th element in the date numeric sequence. This represents the average value of the elements in the SOC difference value sequence. This represents the average value of the elements in the date value sequence, and n represents the number of elements in the SOC difference value sequence.
[0085] For example, in this scheme, the second model is a linear model. The calculation of the battery self-discharge consistency difference value is realized through the linear model, which can reduce the algorithm complexity of battery self-discharge consistency estimation and improve computational efficiency.
[0086] As one possible implementation, based on the content recorded in step S104, the third model includes the F distribution function. Specifically, the confidence level of battery self-discharge consistency is determined by the following formula:
[0087]
[0088] In the above formula, the following is adopted: As the probability density function of the F-distribution function, 1 is the first degree of freedom of the F-distribution function, n-2 is the second degree of freedom of the F-distribution function, and P F The confidence level for battery self-discharge consistency, where SSR and SSE are expressed by the following formula:
[0089]
[0090]
[0091]
[0092] In the formula, β1 represents the battery self-discharge consistency difference value, Y i d represents the i-th element in the SOC difference value sequence. i This represents the i-th element in the date numeric sequence. This represents the average value of the elements in the SOC difference value sequence. This represents the average value of the elements in the date value sequence, and n represents the number of elements in the SOC difference value sequence.
[0093] As one possible implementation, based on the content recorded in step S102, generating a date value sequence according to the date corresponding to the daily SOC difference value includes:
[0094] Obtain the date corresponding to the daily SOC difference value, determine the number of days difference between two specified dates, and subtract each number of days difference from the set value to generate a date value sequence.
[0095] For example, in this scheme, the specified number of days is set to 49, the number of daily SOC difference values obtained within the corresponding time period is set to n, and the date corresponding to the i-th daily SOC difference value is set to D. i Then, a date sequence D can be generated, that is:
[0096] D = {D1, D2, ..., D} n}
[0097] Select D n For the reference date, calculate D1 and D2 respectively. n D2 and D n …D n-1 With D n The difference in the number of days between them is calculated by subtracting each of the above differences in the number of days from 49 to obtain d1 to d2. n-1 At the same time, set d n The value is 48, which generates a date value sequence d, i.e.:
[0098] d = {d1, d2, ... d} n}
[0099] As one possible implementation, based on the content recorded in step S101, the SOC value of a single cell is determined using a fourth model.
[0100] For example, in this solution, the fourth model adopts the XGBoost model. The input of the XGBoost model is set to include at least the voltage of a single cell, the state of charge of the battery pack, the temperature of the battery pack, the current of the battery pack, and the cumulative driving range of the vehicle. The output of the XGBoost model is set to the SOC value of a single cell.
[0101] For example, in this solution, the training process of the XGBoost model is the same as that of existing technologies, and its specific process will not be described in detail.
[0102] For example, in this solution, by using the XGBoost model to estimate the SOC value of a single cell, the accuracy of the SOC estimate can be improved, thereby improving the accuracy of the battery self-discharge consistency estimate.
[0103] For example, in this embodiment of the invention, the methods for determining the SOC value of any single cell, the first model, the second model, the third model, and the method for determining the date value sequence described above can be arranged and combined to form an implementation scheme. For example, in one implementation scheme, the battery self-discharge consistency assessment method can be:
[0104] Using the individual cell voltage, battery pack charging status, battery pack temperature, battery pack current, and vehicle cumulative mileage as inputs, the XGBoost model is used to determine the SOC value of all individual cells in the battery pack at each sampling time point within a single day.
[0105] The daily SOC difference is determined using the SOC values of all individual cells by the following formula:
[0106]
[0107] Obtain the daily SOC difference value for a specified number of days and generate the SOC difference value sequence Y;
[0108] Obtain the date corresponding to the daily SOC difference value, determine the number of days difference between two specified dates, and subtract each number of days difference from a set value to generate a date value sequence d;
[0109] The battery self-discharge consistency difference value is determined using the SOC difference value sequence Y and the date value sequence d, according to the following formula:
[0110]
[0111] Based on the battery self-discharge consistency difference value β1, the SOC difference value sequence Y, and the date value sequence d, the battery self-discharge consistency confidence level is determined by the following formula:
[0112]
[0113]
[0114]
[0115]
[0116] Determine whether the battery has an abnormal self-discharge consistency based on the battery self-discharge consistency difference value and the battery self-discharge consistency confidence level.
[0117] Specifically, if the battery self-discharge consistency difference value β1 > 0.1 and the battery self-discharge consistency confidence level P F If the value is less than 0.05, the battery is considered to have an abnormal self-discharge consistency.
[0118] Figure 2 This is a graph showing the battery pack current test data in the embodiment. Figure 3 This is a graph showing the battery pack voltage test data in the embodiment. Figure 4 This is a diagram of the battery pack SOC data in the embodiment. Figure 5 This is a graph showing the maximum SOC versus minimum SOC data in the embodiment. Figure 6 This is a graph showing the SOC difference values in the embodiment. Figure 7 This is a graph showing the daily SOC difference data in the embodiment;
[0119] refer to Figures 2-7 Based on the selected XGBoost model, Figure 2 and Figure 3 The current and voltage data are used as the individual cell voltage and battery pack current required when the XGBoost model calculates the SOC value;
[0120] The SOC value of a single battery cell can be obtained through calculations using the XGBoost model, which yields results such as... Figure 3 The SOC value shown;
[0121] Based on the above SOC values, the maximum and minimum SOC values of all individual cells at each sampling time can be determined. These maximum and minimum SOC values are as follows: Figure 5 As shown;
[0122] Based on the maximum and minimum SOC values at each sampling time, the SOC difference value of all individual cells at each sampling time can be determined. This SOC difference value is as follows: Figure 6 As shown;
[0123] Based on the above SOC difference values, the daily SOC difference value can be determined. Figure 7 As shown;
[0124] If based on Figure 7 The daily SOC difference value and the corresponding date sequence shown can be used to calculate the battery self-discharge consistency difference value β1 as 0.115, and the battery self-discharge consistency confidence level P. F =0;
[0125] Since the battery self-discharge consistency difference β1 > 0.1, and the battery self-discharge consistency confidence level P F <0.05, therefore it can be determined that it is related to Figure 2 , Figure 3 The self-discharge consistency of the batteries corresponding to the test data shown is abnormal.
[0126] Example 2
[0127] This embodiment proposes a battery self-discharge consistency assessment device, including a battery self-discharge consistency assessment unit, which is used for:
[0128] Determine the SOC value of all individual cells in the battery pack within a single day, and use the SOC value to determine the daily SOC difference value using the first model;
[0129] Get the daily SOC difference value for a specified number of days, generate a SOC difference value sequence, and generate a date value sequence based on the date corresponding to the daily SOC difference value;
[0130] The battery self-discharge consistency difference value is determined by using the SOC difference value sequence and the date value sequence;
[0131] Based on the battery self-discharge consistency difference value, SOC difference value sequence, and date value sequence, a third model is used to determine the confidence level of battery self-discharge consistency.
[0132] The battery self-discharge consistency difference value and the confidence level of battery self-discharge consistency are used to determine whether the battery has an abnormal self-discharge consistency.
[0133] For example, in this embodiment, a battery self-discharge consistency evaluation unit can be configured to implement any of the battery self-discharge consistency evaluation methods described in Embodiment 1. The implementation process and beneficial effects are the same as the corresponding content described in Embodiment 1, and will not be repeated here.
[0134] Example 3
[0135] Figure 8 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.
[0136] like Figure 8 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.
[0137] 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.
[0138] 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 battery self-discharge consistency assessment methods.
[0139] In some embodiments, the battery self-discharge consistency assessment 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 installed 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 battery self-discharge consistency assessment method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the battery self-discharge consistency assessment method by any other suitable means (e.g., by means of firmware).
[0140] 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.
[0141] 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.
[0142] 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.
[0143] 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).
[0144] 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.
[0145] 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.
[0146] 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 evaluating the consistency of battery self-discharge, characterized in that, include: Determine the SOC value of all individual cells in the battery pack within a single day, and use the SOC value to determine the daily SOC difference value using the first model; The daily SOC difference value represents the difference between the maximum and minimum SOC values of all individual cells within a single day. Obtain the daily SOC difference value for a specified number of days, generate a SOC difference value sequence, and generate a date value sequence based on the date corresponding to the daily SOC difference value; The elements in the date value sequence represent the position of each daily SOC difference value on the time axis, in days, when considering the default daily SOC difference value. Using the SOC difference value sequence and the date value sequence, the second model is used to determine the battery self-discharge consistency difference value; The battery self-discharge consistency difference value is used to represent the magnitude of the difference between the daily SOC difference values within the SOC difference value sequence; Based on the battery self-discharge consistency difference value, SOC difference value sequence, and date value sequence, a third model is used to determine the battery self-discharge consistency confidence level. Determine whether the battery has an abnormal self-discharge consistency based on the battery self-discharge consistency difference value and the battery self-discharge consistency confidence level. The SOC value of a single battery cell is determined using the XGBoost model. The inputs to the XGBoost model include at least the single battery cell voltage, the state of charge of the battery pack, the temperature of the battery pack, the current of the battery pack, and the cumulative mileage of the vehicle. The output of the XGBoost model is the SOC value of the single battery cell. The second model includes: In the formula, This indicates the difference in battery self-discharge consistency. This represents the i-th element in the SOC difference value sequence. This represents the i-th element in the date numeric sequence. This represents the average value of the elements in the SOC difference value sequence. This represents the average value of the elements in the date value sequence, and n represents the number of elements in the SOC difference value sequence.
2. The battery self-discharge consistency evaluation method as described in claim 1, characterized in that, The first model includes: In the formula, This represents the daily SOC difference value. This represents the maximum SOC (State of Charge) of all individual cells at time i within a single day. This represents the minimum SOC value among all individual cells at time i within a single day, and N represents the number of times within a single day.
3. The battery self-discharge consistency evaluation method as described in claim 1, characterized in that, The third model includes the F distribution function.
4. The battery self-discharge consistency evaluation method as described in claim 3, characterized in that, The confidence level of battery self-discharge consistency is determined by the following formula: In the formula, The confidence level for battery self-discharge consistency is given by F, which represents the F-distribution function. This indicates the difference in battery self-discharge consistency. This represents the i-th element in the SOC difference value sequence. This represents the i-th element in the date numeric sequence. This represents the average value of the elements in the SOC difference value sequence. This represents the average value of the elements in the date value sequence, and n represents the number of elements in the SOC difference value sequence.
5. The battery self-discharge consistency evaluation method as described in any one of claims 1 to 4, characterized in that, A date value sequence is generated based on the date corresponding to the daily SOC difference value, including: Obtain the date corresponding to the single-day SOC difference value, determine the number of days difference between the dates corresponding to the two specified single-day SOC difference values, and subtract each number of days difference from a set value to generate the date value sequence.
6. A battery self-discharge consistency evaluation device, characterized in that, Includes a battery self-discharge consistency assessment unit, which is used for: Determine the SOC value of all individual cells in the battery pack within a single day, and use the SOC value to determine the daily SOC difference value using the first model; The daily SOC difference value represents the difference between the maximum and minimum SOC values of all individual cells within a single day. Obtain the daily SOC difference value for a specified number of days, generate a SOC difference value sequence, and generate a date value sequence based on the date corresponding to the daily SOC difference value; The elements in the date value sequence represent the position of each daily SOC difference value on the time axis, in days, when considering the default daily SOC difference value. Using the SOC difference value sequence and the date value sequence, the second model is used to determine the battery self-discharge consistency difference value; The battery self-discharge consistency difference value is used to represent the magnitude of the difference between the daily SOC difference values within the SOC difference value sequence; Based on the battery self-discharge consistency difference value, SOC difference value sequence, and date value sequence, a third model is used to determine the battery self-discharge consistency confidence level. Determine whether the battery has an abnormal self-discharge consistency based on the battery self-discharge consistency difference value and the battery self-discharge consistency confidence level. The SOC value of a single battery cell is determined using the XGBoost model. The inputs to the XGBoost model include at least the single battery cell voltage, the state of charge of the battery pack, the temperature of the battery pack, the current of the battery pack, and the cumulative mileage of the vehicle. The output of the XGBoost model is the SOC value of the single battery cell. The second model includes: In the formula, This indicates the difference in battery self-discharge consistency. This represents the i-th element in the SOC difference value sequence. This represents the i-th element in the date numeric sequence. This represents the average value of the elements in the SOC difference value sequence. This represents the average value of the elements in the date value sequence, and n represents the number of elements in the SOC difference value sequence.
7. 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 battery self-discharge consistency assessment method according to any one of claims 1-5.
8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which are used to cause the processor to execute the battery self-discharge consistency evaluation method according to any one of claims 1-5.