Battery capacity rapid detection method and device

Abstract

The present invention relates to a method and device for rapid detection of battery capacity. The method comprises obtaining the first voltage data of the tested battery in the static stage after full discharge, the second voltage data of the short-time constant current charging stage, and the third voltage data of the static stage after short-time constant current charging; the first voltage data, the second voltage data, and the third voltage data are input into a pre-trained battery capacity detection model to obtain the battery capacity. The advantages are that the traditional full charge and discharge capacity test process is shortened from 3 to 4 hours to less than 20 minutes, which greatly improves the detection efficiency, significantly reduces the electric energy consumed by full charge and discharge, and greatly reduces energy consumption; the detection accuracy is high and the detection error is small, the maximum detection error is less than 1%, and the average detection error is only 0.31%.

Description

Technical Field

[0001] The present invention relates to the field of battery detection and analysis, and in particular to a battery capacity rapid detection method, device, computer equipment and computer-readable storage medium. Background Art

[0002] Battery capacity is the internal state of the battery and cannot be directly measured by sensors. Capacity is a key indicator for evaluating battery status and performance, and directly affects the quality of battery groups and the accuracy of cascade utilization. However, existing capacity detection methods require the battery to be fully charged and discharged, that is, the battery is fully charged and then discharged to calculate the discharge capacity of the battery. The full charge and discharge detection method is time-consuming, energy-consuming, and costly. The current industry urgently needs a rapid battery capacity detection method to improve the detection efficiency of batteries at the production and retirement ends.

[0003] Chinese invention patent application CN113075574A discloses a battery health status prediction method and device based on adaptive information fusion, which fuses the decay trend, local capacity information and available capacity information of sodium ion batteries to obtain the final battery health status prediction value. However, this method requires obtaining the historical aging cycle data of the battery, which cannot or is difficult to obtain during the factory capacity division and retirement detection stage of the battery cell, making this method lack of practicality.

[0004] Chinese invention patent application CN116165559A discloses a sodium ion battery capacity detection method, which is still an improved method of the full charge and discharge method, that is, it has the disadvantages of being time-consuming and energy-consuming, and cannot achieve the effect of rapid detection.

[0005] Chinese invention patent application CN116960487A discloses a sodium ion battery system capacity estimation method and device taking into account the inconsistency of single cells. The method estimates the capacity and inconsistency of a sodium ion battery pack. The characteristic parameters used, such as incremental capacity and differential voltage, are easily affected by acquisition noise, and the time consumption and difficulty of obtaining these parameters are usually relatively large, which in turn affects the detection efficiency.

[0006] Currently, no effective solution has been proposed for the problems of long detection time, high energy consumption, low detection efficiency, and low detection accuracy in related technologies. Summary of the invention

[0007] The purpose of the present invention is to provide a battery capacity rapid detection method, device, computer equipment and computer-readable storage medium to address the deficiencies in the prior art, so as to solve the problems existing in the related art such as long detection time, high energy consumption, low detection efficiency and low detection accuracy.

[0008] To achieve the above object, the technical solution adopted by the present invention is:

[0009] In a first aspect, the present invention provides a method for quickly detecting battery capacity, comprising:

[0010] Acquire the first voltage data of the battery under test in the static stage after full discharge, the second voltage data in the short-time constant current charging stage, and the third voltage data in the static stage after short-time constant current charging;

[0011] The first voltage data, the second voltage data, and the third voltage data are input into a pre-trained battery capacity detection model to obtain the battery capacity.

[0012] In some embodiments, the first voltage data includes:

[0013] A first voltage difference between the ath second in the rest phase after full discharge and the 1st second in the rest phase after full discharge, wherein a>1.

[0014] In some embodiments, the second voltage data includes:

[0015] The second voltage difference between the bth second of the short-time constant current charging stage and the last 1 second of the rest stage after full discharge, wherein b>1.

[0016] In some embodiments, the third voltage data includes:

[0017] A third voltage difference between the cth second of the rest phase after the short-time constant-current charging and the last second of the short-time constant-current charging phase, wherein c>1.

[0018] In some embodiments, the second voltage data further includes:

[0019] A fourth voltage difference at a plurality of equal time intervals during the short-time constant current charging stage.

[0020] In some of the embodiments, the fourth voltage difference values ​​at a plurality of equal time intervals are obtained by interpolation.

[0021] In some embodiments, the training method of the battery capacity detection model includes:

[0022] Get the full charge and discharge data of several batteries;

[0023] According to the full charge and discharge data, obtain battery capacity data, first voltage data in a static stage after full discharge, second voltage data in a short-time constant current charging stage, and third voltage data in a static stage after short-time constant current charging;

[0024] The first voltage data, the second voltage data, and the third voltage data are used as input values ​​and the battery capacity data is used as an output value, and are input into a battery capacity detection model to train the battery capacity detection model, so as to obtain a trained battery capacity detection model.

[0025] In some embodiments, the training method of the battery capacity detection model further includes:

[0026] Get the full charge and discharge data of several batteries;

[0027] According to the full charge and discharge data, obtain first voltage data in the static stage after full discharge, second voltage data in the short-time constant current charging stage, and third voltage data in the static stage after short-time constant current charging;

[0028] The first voltage data, the second voltage data, and the third voltage data are used as input values ​​and input into a trained battery capacity detection model to test the battery capacity detection model.

[0029] In some embodiments, the training method of the battery capacity detection model further includes:

[0030] Get cross validation results;

[0031] According to the cross-validation result, the parameters of the battery capacity detection model are adjusted.

[0032] In a second aspect, the present invention provides a battery capacity rapid detection device, which is used to execute the battery capacity rapid detection method as described in the first aspect, comprising:

[0033] A voltage data acquisition module is used to acquire the first voltage data of the battery under test in the static stage after full discharge, the second voltage data in the short-time constant current charging stage, and the third voltage data in the static stage after short-time constant current charging;

[0034] The capacity detection module is used to input the first voltage data, the second voltage data, and the third voltage data into a pre-trained battery capacity detection model to obtain the battery capacity.

[0035] In some of the embodiments, it also includes:

[0036] A training data acquisition module, used to acquire full charge and discharge data of a plurality of batteries, obtain battery capacity data, first voltage data of a static stage after full discharge, second voltage data of a short-time constant current charging stage, and third voltage data of a static stage after short-time constant current charging according to the full charge and discharge data;

[0037] The model training module is used to input the first voltage data, the second voltage data, the third voltage data as input values ​​and the battery capacity data as output values ​​into a battery capacity detection model to train the battery capacity detection model to obtain a trained battery capacity detection model.

[0038] In some of the embodiments, it also includes:

[0039] A test data acquisition module, used to acquire full charge and discharge data of a plurality of batteries, and to obtain first voltage data of a static stage after full discharge, second voltage data of a short-time constant current charging stage, and third voltage data of a static stage after short-time constant current charging according to the full charge and discharge data;

[0040] The model testing module is used to input the first voltage data, the second voltage data, and the third voltage data as input values ​​into the trained battery capacity detection model to test the battery capacity detection model.

[0041] In some of the embodiments, it also includes:

[0042] The parameter optimization module is used to obtain cross-validation results and adjust the parameters of the battery capacity detection model according to the cross-validation results.

[0043] In a third aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the battery capacity rapid detection method as described in the first aspect when executing the computer program.

[0044] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the battery capacity rapid detection method as described in the first aspect.

[0045] The present invention adopts the above technical solution, and has the following technical effects compared with the prior art:

[0046] The traditional full charging and discharging capacity testing process is shortened from 3 to 4 hours to less than 20 minutes, which greatly improves the detection efficiency, significantly reduces the electric energy consumed by full charging and discharging, and greatly reduces energy consumption; the detection accuracy is high and the detection error is small. The maximum detection error is less than 1% and the average detection error is only 0.31%. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of a method for rapid battery capacity detection according to an embodiment of the present invention (I);

[0048] Figure 2is a flow chart of a method for rapid battery capacity detection according to an embodiment of the present invention (II);

[0049] Figure 3 is a flow chart of a method for rapid battery capacity detection according to an embodiment of the present invention (III);

[0050] Figure 4 is a flow chart of a method for rapid battery capacity detection according to an embodiment of the present invention (IV);

[0051] Figure 5 is a framework diagram of a battery capacity rapid detection device according to an embodiment of the present invention;

[0052] Figure 6 is a voltage variation curve diagram of a full charge and discharge test of a sodium ion battery according to an embodiment of the present invention;

[0053] Figure 7 is a battery capacity distribution diagram of a sodium ion battery training data set according to an embodiment of the present invention;

[0054] Figure 8 is a schematic diagram of short-time constant current charging and feature extraction of a sodium ion battery according to an embodiment of the present invention;

[0055] Fig. 9 is a comparison diagram of a sodium ion battery capacity detection value and a reference value according to an embodiment of the present invention;

[0056] Fig.10 is an error diagram of rapid capacity detection of a sodium ion battery according to an embodiment of the present invention;

[0057] Fig.11 is a voltage variation curve diagram of a full charge and discharge test of a lithium-ion battery according to an embodiment of the present invention;

[0058] Fig.12 is a battery capacity distribution diagram of a lithium-ion battery training data set according to an embodiment of the present invention;

[0059] Fig.13 is a schematic diagram of short-time constant current charging and feature extraction of a lithium-ion battery according to an embodiment of the present invention;

[0060] Fig.14 is a comparison diagram of a lithium-ion battery capacity detection value and a reference value according to an embodiment of the present invention;

[0061] Fig.15 4 is an error diagram of rapid detection of lithium-ion battery capacity according to an embodiment of the present invention.

[0062] The accompanying drawings are marked as follows: 500, battery capacity rapid detection device; 510, voltage data acquisition module; 520, capacity testing module; 530, training data acquisition module; 540, model training module; 550, test data acquisition module; 560, model testing module; 570, parameter optimization module. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0064] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0065] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0066] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or units (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships, for example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0067] Example 1

[0068] This embodiment relates to a method for quickly detecting battery capacity of the present invention.

[0069] Figure 1 FIG. 1 is a flow chart of a method for rapid battery capacity detection according to an embodiment of the present invention (I). Figure 1 As shown, a rapid battery capacity detection method includes:

[0070] Step S102, obtaining the first voltage data of the battery under test in the static stage after full discharge, the second voltage data in the short-time constant current charging stage, and the third voltage data in the static stage after short-time constant current charging;

[0071] Step S104: input the first voltage data, the second voltage data, and the third voltage data into a pre-trained battery capacity detection model to obtain the battery capacity.

[0072] In the present invention, batteries include but are not limited to sodium ion batteries, lithium ion batteries, lead-acid batteries, lithium sulfur batteries, etc.

[0073] In the present invention, the application scenarios of the present invention include but are not limited to battery capacity division before leaving the factory, capacity estimation during operation, and capacity division after retirement.

[0074] In step S102, the first voltage data includes:

[0075] A first voltage difference between the ath second in the rest phase after full discharge and the 1st second in the rest phase after full discharge, wherein a>1.

[0076] Generally, a is not the last 1 second of the rest period after full discharge.

[0077] In some of the embodiments, a∈(1, 60]. Preferably, a∈(1, 45]. More preferably, a∈(1, 30]. More preferably, a∈(1, 15]. More preferably, a∈(5, 15].

[0078] In step S102, the second voltage data includes:

[0079] The second voltage difference between the bth second of the short-time constant current charging stage and the last 1 second of the rest stage after full discharge, wherein b>1.

[0080] Generally, b is not the last second of the short-time constant current charging stage.

[0081] In some of the embodiments, b∈(1, 60]. Preferably, b∈(1, 45]. More preferably, b∈(1, 30]. More preferably, b∈(1, 15]. More preferably, b∈(5, 15].

[0082] In step S102, the third voltage data includes:

[0083] A third voltage difference between the cth second of the rest phase after the short-time constant-current charging and the last second of the short-time constant-current charging phase, wherein c>1.

[0084] Generally, c is not the last second of the rest phase after short-time constant current charging.

[0085] In some of the embodiments, c∈(1, 60]. Preferably, c∈(1, 45]. More preferably, c∈(1, 30]. More preferably, c∈(1, 15]. More preferably, c∈(5, 15].

[0086] Furthermore, the second voltage data also includes:

[0087] A fourth voltage difference at a plurality of equal time intervals during the short-time constant current charging stage.

[0088] Specifically, the time period from the beginning of the short-time constant current charging stage to the end of the short-time constant current charging stage is divided into a number of equal time intervals.

[0089] Generally, the number n∈[2,60] of the fourth voltage difference values. Preferably, the number n∈[2,50] of the fourth voltage difference values. More preferably, the number n∈[5,50] of the fourth voltage difference values. More preferably, the number n∈[5,40] of the fourth voltage difference values. More preferably, the number n∈[5,30] of the fourth voltage difference values. More preferably, the number n∈[5,20] of the fourth voltage difference values. More preferably, the number n∈[5,15].

[0090] In some of the embodiments, a plurality of fourth voltage difference values ​​at equal time intervals are obtained by interpolation.

[0091] For a plurality of fourth voltage difference values, different fourth voltage difference values ​​may be equal or may be different.

[0092] In step S104, the first voltage difference, the second voltage difference, the third voltage difference, and n fourth voltage differences are input into a battery capacity detection model to obtain the battery capacity.

[0093] In step S104, the battery capacity detection model includes but is not limited to a random forest regression model, a Gaussian process regression model, a support vector machine model, a neural network model and other models.

[0094] In step S104, the time to obtain the battery capacity is generally within 30 minutes. Preferably, the time to obtain the battery capacity is within 20 minutes.

[0095] Through steps S102 to S104, the traditional full charging and discharging capacity test process is shortened from 3 to 4 hours to less than 20 minutes, which greatly improves the detection efficiency, significantly reduces the electric energy consumed by full charging and discharging, and greatly reduces energy consumption; the detection accuracy is high and the detection error is small, the maximum detection error is less than 1%, and the average detection error is only 0.31%.

[0096] Figure 2 FIG. 2 is a flow chart of a method for rapid battery capacity detection according to an embodiment of the present invention. Figure 2 As shown, the training method of the battery capacity detection model includes:

[0097] Step S202, obtaining full charge and discharge data of a plurality of batteries;

[0098] Step S204, according to the full charge and discharge data, obtain battery capacity data, first voltage data in the static stage after full discharge, second voltage data in the short-time constant current charging stage, and third voltage data in the static stage after short-time constant current charging;

[0099] Step S206: input the first voltage data, the second voltage data, and the third voltage data as input values ​​and the battery capacity data as output values ​​into a battery capacity detection model to train the battery capacity detection model, so as to obtain a trained battery capacity detection model.

[0100] In step S202, full charge and discharge data is obtained through full charge and discharge test. The details are as follows:

[0101] Discharging the battery at a constant current to a lower cut-off voltage and leaving it alone for a first preset time;

[0102] The battery is charged at a constant current and constant voltage until the battery is fully charged, and then left to stand for a second preset time;

[0103] Discharging the battery again at a constant current to a lower cut-off voltage until the battery is completely discharged, and then leaving the battery to stand for a third preset time;

[0104] The battery is charged with constant current again until it reaches the battery shipping state, and is left to stand for a fourth preset time.

[0105] In step S202, the full charge and discharge data of a number of batteries are used as a training set.

[0106] In step S204, the battery capacity data is calculated by the ampere-hour integration method.

[0107] In step S204, the first voltage data includes:

[0108] A first voltage difference between the ath second in the rest phase after full discharge and the 1st second in the rest phase after full discharge, wherein a>1.

[0109] Generally, a is not the last 1 second of the rest period after full discharge.

[0110] In some of the embodiments, a∈(1, 60]. Preferably, a∈(1, 45]. More preferably, a∈(1, 30]. More preferably, a∈(1, 15]. More preferably, a∈(5, 15].

[0111] In step S204, the second voltage data includes:

[0112] The second voltage difference between the bth second of the short-time constant current charging stage and the last 1 second of the rest stage after full discharge, wherein b>1.

[0113] Generally, b is not the last second of the short-time constant current charging stage.

[0114] In some of the embodiments, b∈(1, 60]. Preferably, b∈(1, 45]. More preferably, b∈(1, 30]. More preferably, b∈(1, 15]. More preferably, b∈(5, 15].

[0115] In step S204, the third voltage data includes:

[0116] A third voltage difference between the cth second of the rest phase after the short-time constant-current charging and the last second of the short-time constant-current charging phase, wherein c>1.

[0117] Generally, c is not the last second of the rest phase after short-time constant current charging.

[0118] In some of the embodiments, c∈(1, 60]. Preferably, c∈(1, 45]. More preferably, c∈(1, 30]. More preferably, c∈(1, 15]. More preferably, c∈(5, 15].

[0119] Furthermore, the second voltage data also includes:

[0120] A fourth voltage difference at a plurality of equal time intervals during the short-time constant current charging stage.

[0121] Specifically, the time period from the beginning of the short-time constant current charging stage to the end of the short-time constant current charging stage is divided into a number of equal time intervals.

[0122] Generally, the number n∈[2,60] of the fourth voltage difference values. Preferably, the number n∈[2,50] of the fourth voltage difference values. More preferably, the number n∈[5,50] of the fourth voltage difference values. More preferably, the number n∈[5,40] of the fourth voltage difference values. More preferably, the number n∈[5,30] of the fourth voltage difference values. More preferably, the number n∈[5,20] of the fourth voltage difference values. More preferably, the number n∈[5,15].

[0123] In some of the embodiments, a plurality of fourth voltage difference values ​​at equal time intervals are obtained by interpolation.

[0124] For a plurality of fourth voltage difference values, different fourth voltage difference values ​​may be equal or may be different.

[0125] In step S206, the battery capacity detection model includes but is not limited to a random forest regression model, a Gaussian process regression model, a support vector machine model, a neural network model and other models.

[0126] Through steps S202 to S206, a battery capacity detection model can be trained to perform rapid and accurate detection of battery capacity, greatly improving detection efficiency, significantly reducing electrical energy consumed by full charging and discharging, and substantially reducing energy consumption.

[0127] Figure 3 FIG. 3 is a flowchart of a method for rapid battery capacity detection according to an embodiment of the present invention. Figure 3 As shown, the training method of the battery capacity detection model also includes:

[0128] Step S302, obtaining full charge and discharge data of a plurality of batteries;

[0129] Step S304, according to the full charge and discharge data, obtain the first voltage data of the static stage after full discharge, the second voltage data of the short-time constant current charging stage, and the third voltage data of the static stage after short-time constant current charging;

[0130] Step S306: input the first voltage data, the second voltage data, and the third voltage data as input values ​​to the trained battery capacity detection model to test the battery capacity detection model.

[0131] Among them, steps S302 to S304 are basically the same as steps S202 to S204, and are not repeated here.

[0132] In step S302, full charge and discharge data of a number of batteries are used as a test set.

[0133] In step S306, the first voltage data, the second voltage data, and the third voltage data are used as input values ​​and input into a trained battery capacity detection model to obtain the battery capacity.

[0134] Furthermore, after step S306, the method further includes:

[0135] Step S308, comparing the battery capacity with the battery capacity obtained based on the full charge and discharge data;

[0136] Step S310: According to the comparison result, determine whether the battery capacity detection model has been trained.

[0137] Through steps S302 to S310, the battery capacity detection model is tested to determine the training result.

[0138] Figure 4 FIG. 4 is a flowchart of a method for rapid battery capacity detection according to an embodiment of the present invention. Figure 4 As shown, the training method of the battery capacity detection model also includes:

[0139] Step S402, obtaining cross-validation results;

[0140] Step S404: Adjust the parameters of the battery capacity detection model according to the cross-validation result.

[0141] In step S402, the cross-validation result is obtained from the training set of steps S202 to S206.

[0142] In step S404, hyperparameters such as "n_estimators", "max_depth", and "min_samples_split" are adjusted.

[0143] Through steps S402 to S404, the model parameters are adjusted using the cross-validation results, so as to improve the detection accuracy of the battery capacity detection model and reduce the detection error.

[0144] In addition, the battery capacity rapid detection method of the embodiment of the present application can be implemented by a computer device. The components of the computer device may include but are not limited to a processor and a memory storing computer program instructions.

[0145] In some embodiments, the processor may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0146] In some embodiments, the memory may include a large capacity memory for data or instructions. By way of example and not limitation, the memory may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory may include a removable or non-removable (or fixed) medium. Where appropriate, the memory may be inside or outside a data processing device. In a specific embodiment, the memory is a non-volatile memory. In a specific embodiment, the memory includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable ProgrammableRead-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable ProgrammableRead-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0147] The memory may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor.

[0148] The processor implements any one of the battery capacity rapid detection methods in the above embodiments by reading and executing computer program instructions stored in the memory.

[0149] In some embodiments, the computer device may further include a communication interface and a bus, wherein the processor, the memory, and the communication interface are connected via the bus and communicate with each other.

[0150] The communication interface is used to realize the communication between each unit, device, unit and / or device in the embodiment of the present application. The communication interface can also realize data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0151] The bus includes hardware, software or both, and couples the components of the computer device to each other. The bus includes but is not limited to at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0152] The computer device can execute the battery capacity rapid detection method in the embodiment of the present application.

[0153] In addition, in combination with the battery capacity rapid detection method in the above embodiment, the present application embodiment can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the battery capacity rapid detection methods in the above embodiment is implemented.

[0154] Example 2

[0155] This embodiment relates to a battery capacity rapid detection device of the present invention.

[0156] Figure 5 is a framework diagram of a battery capacity rapid detection device according to an embodiment of the present invention. Figure 5 As shown, a battery capacity rapid detection device 500 is used to perform the battery capacity rapid detection method as described in Example 1, including a voltage data acquisition module 510 and a capacity detection module 520. The voltage data acquisition module 510 is used to obtain the first voltage data of the battery to be tested in the static stage after full discharge, the second voltage data in the short-time constant current charging stage, and the third voltage data in the static stage after short-time constant current charging; the capacity detection module 520 is used to input the first voltage data, the second voltage data, and the third voltage data into a pre-trained battery capacity detection model to obtain the battery capacity.

[0157] The voltage data acquisition module 510 and the capacity detection module 520 are used to execute steps S102 to S104 of the first embodiment.

[0158] Furthermore, the battery capacity rapid detection device 500 also includes a training data acquisition module 530 and a model training module 540. The training data acquisition module 530 is used to acquire full charge and discharge data of a number of batteries, obtain battery capacity data, first voltage data in the static stage after full discharge, second voltage data in the short-time constant current charging stage, and third voltage data in the static stage after short-time constant current charging according to the full charge and discharge data; the model training module 540 is used to input the first voltage data, the second voltage data, and the third voltage data as input values ​​and the battery capacity data as output values ​​into the battery capacity detection model to train the battery capacity detection model, so as to obtain a trained battery capacity detection model.

[0159] The training data acquisition module 530 and the model training module 540 are used to execute steps S202 to S206 of Example 1.

[0160] Furthermore, the battery capacity rapid detection device 500 also includes a test data acquisition module 550 and a model test module 560. The test data acquisition module 550 is used to acquire full charge and discharge data of a number of batteries, and obtain the first voltage data of the static stage after full discharge, the second voltage data of the short-time constant current charging stage, and the third voltage data of the static stage after short-time constant current charging according to the full charge and discharge data; the model test module 560 is used to input the first voltage data, the second voltage data, and the third voltage data as input values ​​into the trained battery capacity detection model to test the battery capacity detection model.

[0161] The test data acquisition module 550 and the model test module 560 are used to execute steps S302 to S306 of the first embodiment.

[0162] Furthermore, the battery capacity rapid detection device 500 further includes a parameter optimization module 570. The parameter optimization module 570 is used to obtain a cross-validation result, and adjust the parameters of the battery capacity detection model according to the cross-validation result.

[0163] The parameter optimization module 570 is used to execute steps S402 to S404 of the first embodiment.

[0164] The technical effects of this embodiment are basically the same as those of Embodiment 1 and will not be described in detail here.

[0165] Example 3

[0166] This embodiment is a specific implementation of the present invention.

[0167] A battery capacity rapid detection method based on voltage increment and voltage sequence, comprising:

[0168] Step 1: Perform full charge and discharge tests on the battery and collect historical battery data

[0169] Step 1.1, select a batch of batteries and conduct full charge and discharge tests on the batteries. Specifically, discharge the batteries to the lower cut-off voltage with constant current, let them stand for a while, then fully charge the batteries with constant current and constant voltage charging, let them stand for a few minutes, and then discharge the batteries to the lower cut-off voltage with constant current to completely empty the batteries, and let them stand for a while; then, charge the batteries with constant current for a while to reach the shipping state of the batteries;

[0170] Step 1.2, collect factory historical data, such as the full charge and discharge data in step 1.1, as a supplementary data set; at least one of steps 1.1 and 1.2 must be able to obtain a battery data set;

[0171] Step 1.3: Record all test data during the test, including the current, voltage, time and other data of each battery, and remove abnormal battery data. Based on the current and time data of the complete discharge process of the battery, use the ampere-hour integration method to calculate the discharge capacity of each battery, and use this as the capacity label to eventually form the battery original data set.

[0172] Step 2: Extract effective features based on the voltage static stage and short-time constant current charging stage to form a training data set

[0173] Step 2.1, analyze the static stage S1 after the battery is fully discharged, calculate the difference between the voltage at the 10th second and the voltage at the 1st second of stage S1, and use it as feature V1; analyze the short-time constant current charging stage S2 and the static stage S1 of the battery, calculate the difference between the voltage at the 10th second of stage S2 and the voltage at the last second of stage S1, and use it as feature V2; analyze the static stage S3 and the constant current charging stage S2 after the short-time constant current charging stage of the battery, calculate the difference between the voltage at the 10th second of stage S3 and the voltage at the last second of stage S2, and use it as feature V3;

[0174] Step 2.2, analyze the short-time constant current charging stage S2 of the battery, and interpolate the voltage of the S2 stage into n points with equal time intervals as the feature V4-Vn+3;

[0175] Step 2.3: Integrate the V1-Vn+3 features of each battery and the capacity label of step 1.3 to form a training data set.

[0176] Step 3: Select and train a machine learning model based on the training data set

[0177] Step 3.1. According to the size of the training data set, select several appropriate machine learning models, such as random forest regression, Gaussian process regression, support vector machine, neural network and other models;

[0178] Step 3.2: Based on the training data set in step 2.3, with V1-Vn+3 features as input and capacity labels as output, the model in step 3.1 is used for training on the training data set. The hyperparameters of the model are adjusted according to the cross-validation error, and the model with the smallest cross-validation error is selected as the final model.

[0179] Step 3.3: When new battery data available for training is obtained, the final model in step 3.2 can be used to retrain the model on a larger training set to complete the model update;

[0180] Step 3.4: After the final model training is completed, save the model for online estimation.

[0181] Step 4: Perform a short-term charge and discharge test on the battery to be tested, extract features, and input the model to complete the rapid capacity detection

[0182] Step 4.1, first discharge the battery to be tested at a constant current to the lower cut-off voltage, then perform a short constant current charging test and record the test data;

[0183] Step 4.2: Based on the test data, extract the same features V1-Vn+3 as in step 2.3;

[0184] Step 4.3: Features V1-Vn+3 are directly input into the model in step 3.4, and the model outputs the rapid detection result of battery capacity.

[0185] The technical effects of this embodiment are as follows:

[0186] 1) It can significantly shorten the time and energy consumption of the battery capacity test process: the traditional capacity test process based on full charge and discharge usually takes more than 4 hours, and the use of this technology can shorten the capacity test time to 20 minutes;

[0187] 2) High capacity detection accuracy: For a batch of batteries, the maximum detection error is less than 1% and the average detection error is only 0.31%.

[0188] Example 4

[0189] This embodiment is a specific implementation of the present invention.

[0190] In this embodiment, a sodium ion battery with a rated capacity of 1.3 Ah is taken as an example for description.

[0191] A method for rapid detection of sodium ion battery capacity based on voltage increment and voltage sequence, comprising:

[0192] Step 1: Select 70 sodium-ion batteries with a rated capacity of 1.3Ah as the research object, and conduct full charge and discharge tests on the batteries (the constant current charge and discharge current is 0.65A). The voltage curve changes as shown in the figure below: Figure 6 Specifically, the battery is first discharged at a constant current to a lower cut-off voltage of 1.5V, left to stand for 5 minutes, then charged at a constant current and constant voltage to an upper cut-off voltage of 3.95V, left to stand for 5 minutes, then discharged at a constant current to a lower cut-off voltage of 1.5V, left to stand for 5 minutes, then charged at a constant current for 10 minutes, and then left to stand for 5 minutes. Based on the complete discharge process of the battery, the capacity of the battery is calculated using the ampere-hour integration method. The capacities of these batteries are shown in Figure 7 As shown, it can be seen that the battery distribution is between 1.28Ah-1.33Ah.

[0193] Step 2: Based on Figure 6 The short-term charging process S1-S3 of the battery in the figure is as follows: Figure 8As shown. Analyze the static stage S1 after the battery is fully discharged, calculate the difference between the voltage at the 10th second and the voltage at the 1st second of stage S1, and use it as feature V1; analyze the battery's short-time constant current charging stage S2 and static stage S1, calculate the difference between the voltage at the 10th second of stage S2 and the voltage at the last second of stage S1, and use it as feature V2; analyze the static stage S3 and constant current charging stage S2 after the battery's short-time constant current charging stage, and calculate the difference between the voltage at the 10th second of stage S3 and the voltage at the last second of stage S2, and use it as feature V3; in addition, analyze the battery's short-time constant current charging stage S2, and interpolate the voltage of stage S2 into 10 points with equal time intervals, and use them as features V4-V13; on this basis, integrate the V1-V13 features of each battery and the discharge capacity label corresponding to the battery to form a training data set.

[0194] Step 3: Based on the training data set, take V1-V13 features as input and battery discharge capacity as output, select random forest model for training, and adjust hyperparameters such as "n_estimators", "max_depth", and "min_samples_split" based on the cross-validation results on the training set. After the hyperparameters are determined, the model training is completed and the model is saved locally for easy calling during online capacity detection.

[0195] Step 4: Select another 25 sodium-ion batteries as test objects and perform the following test on the batteries: Figure 8 The short-time charge and discharge test shown is to first discharge the battery to be tested to 1.5V at a constant current, let it stand for 5 minutes, then charge it at a constant current for 10 minutes, and finally let it stand for 5 minutes to record the test data. Using the feature extraction method in step 2, calculate the V1-V13 features. Then, input the V1-V13 features into the trained random forest model in step 3 to obtain the rapid capacity detection results of each battery. In order to demonstrate the rapid capacity detection effect, the full charge and discharge capacity values ​​(reference values) of the 25 batteries to be tested are calculated.

[0196] Comparison of reference value and rapid test value Fig. 9 As shown, it can be seen that the detected value and the reference value are very close.

[0197] The error between the rapid test value and the reference value is as follows: Fig.10 As shown, the detection errors of all the tested batteries are less than 1%, the average absolute percentage error is only 0.31%, and the maximum percentage error is 0.92%.

[0198] From the above results, we can know that:

[0199] 1) The technology of the present invention uses short-time charging data to achieve high-precision battery capacity detection effect.

[0200] 2) If Figure 6As shown, the traditional capacity testing method based on full charge and discharge takes an average of more than 4 hours for a single battery cell, while the technology of the present invention only requires 20 minutes of detection time. This shows that while maintaining high-precision capacity detection, the technology also greatly shortens the capacity testing time. It has broad industrial application prospects and can significantly reduce the time and energy consumption of the battery cell capacity division process.

[0201] Example 5

[0202] This embodiment is a specific implementation of the present invention.

[0203] In this embodiment, a lithium-ion battery with a rated capacity of 2Ah is taken as an example for description.

[0204] A method for quickly detecting the capacity of a lithium-ion battery based on voltage increment and voltage sequence, comprising:

[0205] Step 1: Select 60 lithium-ion batteries with a rated capacity of 1.8Ah as the research object, and perform full charge and discharge tests on the batteries (the constant current charge and discharge current is 1.8A). The voltage curve changes as shown in the figure below: Fig.11 Specifically, the battery is first discharged at a constant current to a lower cut-off voltage of 2.75V, left to stand for 5 minutes, then charged at a constant current and constant voltage to an upper cut-off voltage of 4.2V, left to stand for 5 minutes, then discharged at a constant current to a lower cut-off voltage of 2.75V, left to stand for 5 minutes, then charged at a constant current for 3 minutes, and then left to stand for 5 minutes. Based on the complete discharge process of the battery, the capacity of the battery is calculated using the ampere-hour integration method. The capacities of these batteries are shown in Fig.12 As shown, it can be seen that the batteries are distributed between 1.8Ah-2Ah.

[0206] Step 2: Based on Fig.11 The short-term charging process S1-S3 of the battery in the figure is as follows: Fig.12 As shown. Analyze the static stage S1 after the battery is fully discharged, calculate the difference between the voltage at the 10th second and the voltage at the 1st second of stage S1, and use it as feature V1; analyze the battery's short-time constant current charging stage S2 and static stage S1, calculate the difference between the voltage at the 10th second of stage S2 and the voltage at the last second of stage S1, and use it as feature V2; analyze the static stage S3 and constant current charging stage S2 after the battery's short-time constant current charging stage, and calculate the difference between the voltage at the 10th second of stage S3 and the voltage at the last second of stage S2, and use it as feature V3; in addition, analyze the battery's short-time constant current charging stage S2, and interpolate the voltage of stage S2 into 7 points with equal time intervals, and use them as features V4-V10; on this basis, integrate the V1-V10 features of each battery and the discharge capacity label corresponding to the battery to form a training data set.

[0207] Step 3: Based on the training data set, with V1-V10 features as input and battery discharge capacity as output, select the random forest model for training. Adjust hyperparameters such as "n_estimators", "max_depth", and "min_samples_split" based on the cross-validation results on the training set. After the hyperparameters are determined, the model training is completed and the model is saved locally for easy calling during online capacity detection.

[0208] Step 4: Select another 20 lithium-ion batteries as test objects and perform the following Fig.13 The short-time charge and discharge test shown is to discharge the battery to be tested to 2.75V at a constant current, let it stand for 5 minutes, then charge it at a constant current for 3 minutes, and finally let it stand for 5 minutes to record the test data. Using the feature extraction method in step 2, calculate the V1-V10 features. Then, input the V1-V10 features into the trained random forest model in step 3 to obtain the rapid capacity detection results of each battery. In order to demonstrate the effect of rapid capacity detection, the full charge and discharge capacity values ​​(reference values) of the 20 batteries to be tested are calculated.

[0209] Comparison of reference value and rapid test value Fig.14 As shown, it can be seen that the detected value and the reference value are very close.

[0210] The error between the rapid test value and the reference value is as follows: Fig.15 As shown, the average absolute percentage error is only 0.62% and the maximum percentage error is 1.88%.

[0211] From the above results, we can know that:

[0212] 1) The technology of the present invention uses short-time charging data to achieve high-precision battery capacity detection effect.

[0213] 2) If Fig.11 As shown, the traditional capacity testing method based on full charge and discharge takes an average of more than 3 hours for a single battery cell, while the technology of the present invention only requires 8 minutes of detection time. This shows that while maintaining high-precision capacity detection, the technology also greatly shortens the capacity testing time. It has broad industrial application prospects and can significantly reduce the time and energy consumption of the battery cell capacity division process.

[0214] The above description is only a preferred embodiment of the present invention, and does not limit the implementation mode and protection scope of the present invention. For those skilled in the art, it should be aware that all solutions obtained by equivalent substitutions and obvious changes made using the description and illustrations of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for rapid detection of battery capacity, characterized in that: include: Acquire the first voltage data of the battery under test in the static stage after full discharge, the second voltage data in the short-time constant current charging stage, and the third voltage data in the static stage after short-time constant current charging; Inputting the first voltage data, the second voltage data, and the third voltage data into a pre-trained battery capacity detection model to obtain the battery capacity; Wherein, the first voltage data includes: The first voltage difference between the ath second in the resting stage after full discharge and the 1st second in the resting stage after full discharge, where a>1; Wherein, the second voltage data includes: The second voltage difference between the bth second of the short-time constant current charging stage and the last 1 second of the rest stage after full discharge, where b>1; Wherein, the third voltage data includes: A third voltage difference between the cth second of the rest phase after the short-time constant-current charging and the last second of the short-time constant-current charging phase, wherein c>1.

2. The method for rapid detection of battery capacity according to claim 1, characterized in that: The second voltage data also includes: A fourth voltage difference at a plurality of equal time intervals during the short-time constant current charging stage.

3. The method for rapid detection of battery capacity according to claim 2, characterized in that: The fourth voltage difference values ​​at a plurality of equal time intervals are obtained by interpolation.

4. The method for rapid detection of battery capacity according to any one of claims 1 to 3, characterized in that: The training method of the battery capacity detection model includes: Get the full charge and discharge data of several batteries; According to the full charge and discharge data, obtain battery capacity data, first voltage data in a static stage after full discharge, second voltage data in a short-time constant current charging stage, and third voltage data in a static stage after short-time constant current charging; The first voltage data, the second voltage data, and the third voltage data are used as input values ​​and the battery capacity data is used as an output value, and are input into a battery capacity detection model to train the battery capacity detection model, so as to obtain a trained battery capacity detection model.

5. The method for rapid detection of battery capacity according to claim 4, characterized in that: The training method of the battery capacity detection model also includes: Get the full charge and discharge data of several batteries; According to the full charge and discharge data, obtain first voltage data in the static stage after full discharge, second voltage data in the short-time constant current charging stage, and third voltage data in the static stage after short-time constant current charging; Using the first voltage data, the second voltage data, and the third voltage data as input values ​​to the trained battery capacity detection model to test the battery capacity detection model; and / or Get cross validation results; According to the cross-validation result, the parameters of the battery capacity detection model are adjusted.

6. A battery capacity rapid detection device, used to execute the battery capacity rapid detection method according to any one of claims 1 to 5, characterized in that: include: A voltage data acquisition module is used to acquire the first voltage data of the battery under test in the static stage after full discharge, the second voltage data in the short-time constant current charging stage, and the third voltage data in the static stage after short-time constant current charging; a capacity detection module, configured to input the first voltage data, the second voltage data, and the third voltage data into a pre-trained battery capacity detection model to obtain a battery capacity; Wherein, the first voltage data includes: The first voltage difference between the ath second in the resting stage after full discharge and the 1st second in the resting stage after full discharge, where a>1; Wherein, the second voltage data includes: The second voltage difference between the bth second of the short-time constant current charging stage and the last 1 second of the rest stage after full discharge, where b>1; Wherein, the third voltage data includes: A third voltage difference between the cth second of the rest phase after the short-time constant-current charging and the last second of the short-time constant-current charging phase, wherein c>1.

7. The battery capacity rapid detection device according to claim 6, characterized in that: Also includes: A training data acquisition module, used to acquire full charge and discharge data of a plurality of batteries, obtain battery capacity data, first voltage data of a static stage after full discharge, second voltage data of a short-time constant current charging stage, and third voltage data of a static stage after short-time constant current charging according to the full charge and discharge data; The model training module is used to input the first voltage data, the second voltage data, the third voltage data as input values ​​and the battery capacity data as output values ​​into a battery capacity detection model to train the battery capacity detection model to obtain a trained battery capacity detection model.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the battery capacity rapid detection method as described in any one of claims 1 to 5 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the battery capacity rapid detection method as described in any one of claims 1 to 5 is implemented.

Images