Nickel-metal hydride battery capacity prediction method, device, electronic device and storage medium

Abstract

The present invention relates to a nickel-hydrogen battery capacity prediction method, device, electronic device, and storage medium. The method comprises: performing a capacity test and a characteristic parameter extraction test on a target nickel-hydrogen battery to obtain a first battery capacity and a first characteristic parameter of the target nickel-hydrogen battery; calculating the correlation between the first characteristic parameter and the first battery capacity based on a preset correlation coefficient to obtain a second characteristic parameter; constructing an RBF neural network model, and training the model using the second characteristic parameter as input and the first battery capacity as output to obtain a fully trained battery capacity prediction model; and using the battery capacity prediction model to predict the second battery capacity of the nickel-hydrogen battery to be tested. The present invention can accurately predict the remaining capacity of nickel-hydrogen batteries, thereby enabling reasonable battery sorting.

Description

Technical Field

[0001] The present invention relates to the field of battery management technology, and in particular to a nickel-hydrogen battery capacity prediction method, device, electronic equipment and storage medium. Background Art

[0002] Nickel-metal hydride batteries are made of hydrogen ions and metallic nickel. They have a power reserve 30% greater than nickel-cadmium batteries, are lighter than nickel-cadmium batteries, have a longer service life, and are environmentally friendly.

[0003] Nickel-metal hydride batteries are frequently used in previous generations of electric and hybrid vehicles. Many of these batteries retain over 80% of their remaining capacity after retirement, making them suitable for cascade recycling. However, retired nickel-metal hydride batteries are particularly susceptible to consistency issues, which can easily lead to overcharging and over-discharging during use, and in severe cases, can cause safety issues. Therefore, before reusing retired nickel-metal hydride batteries, they must be sorted. This means separating cells with consistent capacity, internal resistance, and voltage and reconnecting them in series and parallel to form battery packs.

[0004] However, existing technologies typically obtain battery capacity through direct measurement, which is time-consuming and energy-intensive. Therefore, it is necessary to develop a method that is energy-efficient, highly accurate, and fast to accurately predict battery capacity and thus enable appropriate battery sorting. Summary of the Invention

[0005] In view of this, it is necessary to provide a nickel-hydrogen battery capacity prediction method, device, electronic device and storage medium to solve the problem of long time and high energy consumption in obtaining battery capacity in the prior art.

[0006] In order to solve the above problems, the present invention provides a nickel-metal hydride battery capacity prediction method in a first aspect, comprising:

[0007] Performing a capacity test and a characteristic parameter extraction test on a target nickel-hydrogen battery to obtain a first battery capacity and a first characteristic parameter of the target nickel-hydrogen battery;

[0008] Calculating the correlation between the first characteristic parameter and the first battery capacity based on a preset correlation coefficient to obtain a second characteristic parameter;

[0009] Constructing an RBF neural network model, and training the model using the second characteristic parameter as input of the RBF neural network model and the first battery capacity as output of the RBF neural network model to obtain a fully trained battery capacity prediction model;

[0010] The battery capacity prediction model is used to predict the second battery capacity of the nickel-hydrogen battery to be tested.

[0011] Furthermore, the performing of a capacity test on the target nickel-hydrogen battery to obtain a first battery capacity of the target nickel-hydrogen battery includes:

[0012] A constant current charge-discharge capacity test is performed on the target nickel-hydrogen battery to obtain a first battery capacity of the target nickel-hydrogen battery.

[0013] Furthermore, the first characteristic parameter includes, after the target nickel-hydrogen battery is charged to the same state, the difference in volume expansion thickness of the target nickel-hydrogen battery before and after charging, the internal resistance and terminal voltage of the target nickel-hydrogen battery, the charge and discharge ohmic internal resistance of the target nickel-hydrogen battery, the charge and discharge polarization internal resistance of the target nickel-hydrogen battery, the charge and discharge pulse power of the target nickel-hydrogen battery, and the rebound voltage difference of the target nickel-hydrogen battery.

[0014] Furthermore, the performing of a characteristic parameter extraction test on the target nickel-hydrogen battery to obtain a first characteristic parameter of the target nickel-hydrogen battery includes:

[0015] After the target nickel-hydrogen battery is charged at a constant current to the same state of charge, the battery thickness is measured before and after charging to obtain a volume expansion thickness difference of the target nickel-hydrogen battery before and after charging;

[0016] After the target nickel-hydrogen battery charged to the same state of charge is left to rest for a first preset time, the target nickel-hydrogen battery is tested to obtain the internal resistance and terminal voltage of the target nickel-hydrogen battery;

[0017] Performing a charge-discharge pulse test on a target nickel-hydrogen battery charged to the same state of charge, and calculating the charge-discharge ohmic internal resistance of the target nickel-hydrogen battery, the charge-discharge polarization internal resistance of the target nickel-hydrogen battery, and the charge-discharge pulse power of the target nickel-hydrogen battery;

[0018] The target nickel-hydrogen battery after the charge-discharge pulse test is discharged at a constant current to a cut-off voltage, and the rebound voltage difference of the target nickel-hydrogen battery is recorded after the battery is left to stand for a second preset time.

[0019] Furthermore, the preset correlation coefficient includes a Pearson correlation coefficient;

[0020] The performing correlation calculation on the first characteristic parameter and the first battery capacity based on a preset correlation coefficient to obtain a second characteristic parameter includes:

[0021] Calculating the correlation between each first characteristic parameter of the target nickel-hydrogen battery and the first battery capacity based on the Pearson correlation coefficient, and obtaining a correlation value between each first characteristic parameter and the first battery capacity;

[0022] A first characteristic parameter having a correlation value greater than a preset threshold is determined as a second characteristic parameter, wherein the second characteristic parameter includes a volume expansion thickness difference before and after charging of the target nickel-hydrogen battery, an internal resistance of the target nickel-hydrogen battery, and a charge-discharge polarization internal resistance of the target nickel-hydrogen battery.

[0023] Furthermore, the target nickel-metal hydride batteries include training set nickel-metal hydride batteries and prediction set nickel-metal hydride batteries;

[0024] The method of using the second characteristic parameter as the input of the RBF neural network model and the first battery capacity as the output of the RBF neural network model for training to obtain a fully trained battery capacity prediction model includes:

[0025] Obtaining a third characteristic parameter and a third battery capacity of the training set nickel-hydrogen battery from the second characteristic parameter and the first battery capacity of the target nickel-hydrogen battery;

[0026] The third characteristic parameter and the third battery capacity of the nickel-hydrogen battery in the training set are used as the input and output values ​​of the RBF neural network model, respectively, and the neural network parameters are set for training to obtain a fully trained battery capacity prediction model, wherein the neural network parameters include any one of an error tolerance, a diffusion factor, or the number of neurons.

[0027] Furthermore, the above method also includes:

[0028] The nickel-hydrogen batteries to be tested are sorted based on the second battery capacity to obtain a sorting result.

[0029] In a second aspect, the present invention further provides a nickel-hydrogen battery capacity prediction device, comprising:

[0030] A testing module, configured to perform a capacity test and a characteristic parameter extraction test on a target nickel-hydrogen battery to obtain a first battery capacity and a first characteristic parameter of the target nickel-hydrogen battery;

[0031] a calculation module, configured to perform a correlation calculation on the first characteristic parameter and the first battery capacity based on a preset correlation coefficient to obtain a second characteristic parameter;

[0032] a training module, configured to construct an RBF neural network model, and perform training using the second characteristic parameter as input of the RBF neural network model and the first battery capacity as output of the RBF neural network model, to obtain a fully trained battery capacity prediction model;

[0033] The prediction module is used to predict the second battery capacity of the nickel-hydrogen battery to be tested by using the battery capacity prediction model.

[0034] In a third aspect, the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the above-mentioned nickel-hydrogen battery capacity prediction method when executing the computer program.

[0035] In a fourth aspect, the present invention further provides a computer storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned nickel-metal hydride battery capacity prediction method are implemented.

[0036] The beneficial effects of adopting the above embodiment are:

[0037] The present invention constructs the data set required for model training by performing capacity testing and characteristic parameter extraction tests on target nickel-metal hydride batteries. The model then calculates the correlation between the first characteristic parameter and the first battery capacity, screening characteristic parameters that meet the correlation requirements and improving training efficiency. The neural network's learning capabilities are then used to learn the data relationships between multiple second characteristic parameters and the first discharge capacity, resulting in a fully trained battery capacity prediction model. This allows for rapid sorting of the remaining capacity of retired batteries without requiring a complete charge and discharge cycle. Furthermore, the prediction model predicts the remaining charge of retired batteries with low energy consumption, high accuracy, and high speed, and accurately predicts the battery capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A schematic flow chart of an embodiment of a method for predicting nickel-hydrogen battery capacity provided by the present invention;

[0039] Figure 2 A side view of a charge and discharge pulse in one embodiment of the present invention;

[0040] Figure 3 A schematic structural diagram of an embodiment of a nickel-hydrogen battery capacity prediction device provided by the present invention;

[0041] Figure 4 This is a structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0042] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, and are not used to limit the scope of the present invention.

[0043] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, "multiple" means two or more, unless otherwise clearly and specifically defined. Reference to "embodiments" in this document means that the specific features, structures or characteristics described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places 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 skilled in the art that the embodiments described herein may be combined with other embodiments.

[0044] The present invention provides a nickel-metal hydride battery capacity prediction method, device, electronic device, and storage medium. This method addresses the time-consuming and energy-intensive problem of direct measurement in existing technologies. By leveraging the robust learning capabilities of a neural network model to learn the relationships between multiple characteristic parameters and discharge capacity, the optimal model is constructed to rapidly predict battery capacity, enabling rational battery sorting.

[0045] Before describing the embodiments, the following definitions are given for the relevant terms:

[0046] RBF, short for Radial Basis Function, is a neural network. It can approximate arbitrary nonlinear functions and handle difficult-to-analyze regularities within a system. It has good generalization capabilities and fast learning convergence. It has been successfully applied to nonlinear function approximation, time series analysis, data classification, pattern recognition, information processing, image processing, system modeling, control, and fault diagnosis.

[0047] The Pearson Correlation Coefficient is used to measure whether two data sets are on the same line. It is used to measure the linear relationship between interval variables.

[0048] The specific embodiments are described in detail below:

[0049] See also Figure 1 , Figure 1 This is a flow chart of an embodiment of a method for predicting the capacity of a nickel-hydrogen battery provided by the present invention. A specific embodiment of the present invention discloses a method for predicting the capacity of a nickel-hydrogen battery, comprising:

[0050] Step S101: performing a capacity test and a characteristic parameter extraction test on a target nickel-metal hydride battery to obtain a first battery capacity and a first characteristic parameter of the target nickel-metal hydride battery;

[0051] Step S102: performing correlation calculation on the first characteristic parameter and the first battery capacity based on a preset correlation coefficient to obtain a second characteristic parameter;

[0052] Step S103: constructing an RBF neural network model, and training the model using the second characteristic parameter as input and the first battery capacity as output to obtain a fully trained battery capacity prediction model.

[0053] Step S104: predicting the second battery capacity of the nickel-hydrogen battery to be tested using the battery capacity prediction model.

[0054] The target nickel-metal hydride batteries include a plurality of retired nickel-metal hydride batteries to be sorted. It is understood that in order to construct a battery capacity prediction model, a sample data set must first be constructed. Specifically, capacity testing and characteristic parameter extraction testing can be performed on the target nickel-metal hydride batteries to obtain initial sample data. Then, based on the correlation between the initial sample data, sample data for training and prediction is determined, specifically the second characteristic parameter and the first battery capacity of the target nickel-metal hydride batteries.

[0055] During the training process, the strong learning ability of the RBF neural network can better adapt to the data relationship between multiple characteristic parameters and battery capacity, and thus obtain a fully trained battery capacity prediction model. During the prediction process, the second battery capacity of the nickel-hydrogen battery to be tested is predicted based on the fully trained battery capacity model. It should be noted that the nickel-hydrogen battery to be tested is included in the target nickel-hydrogen battery, so during the prediction process, the fourth characteristic parameter corresponding to the nickel-hydrogen battery to be tested can be extracted from the second characteristic parameter of the target nickel-hydrogen battery. It should be noted that the parameter types in the second characteristic parameter and the fourth characteristic parameter are the same, and the difference lies in the different parameter values. Then the fourth characteristic parameter is input into the fully trained battery capacity prediction model to predict the second battery capacity of the nickel-hydrogen battery to be tested.

[0056] The present invention constructs the data set required for model training by performing capacity testing and characteristic parameter extraction tests on target nickel-metal hydride batteries. The model then calculates the correlation between the first characteristic parameter and the first battery capacity, screening characteristic parameters that meet the correlation requirements and improving training efficiency. The neural network's learning capabilities are then used to learn the data relationships between multiple second characteristic parameters and the first discharge capacity, resulting in a fully trained battery capacity prediction model. This allows for rapid sorting of the remaining capacity of retired batteries without requiring a complete charge and discharge cycle. Furthermore, the prediction model predicts the remaining charge of retired batteries with low energy consumption, high accuracy, and high speed, and accurately predicts the battery capacity.

[0057] In a specific embodiment of the present invention, performing a capacity test on a target nickel-hydrogen battery to obtain a first battery capacity of the target nickel-hydrogen battery includes:

[0058] A constant current charge and discharge capacity test is performed on the target nickel-hydrogen battery to obtain a first battery capacity of the target nickel-hydrogen battery.

[0059] Specifically, a number of retired nickel-hydrogen batteries to be sorted, such as 30 or 40, can be selected and left to stand at room temperature for a sufficiently long time, such as one day, and then a constant current charge and discharge capacity test is performed on the batteries at 0.3C to 1C to obtain the remaining capacity of the target nickel-hydrogen batteries.

[0060] In a specific embodiment of the present invention, the first characteristic parameter includes, after the target nickel-hydrogen battery is charged to the same state, the difference in volume expansion thickness of the target nickel-hydrogen battery before and after charging, the internal resistance and terminal voltage of the target nickel-hydrogen battery, the charge and discharge ohmic internal resistance of the target nickel-hydrogen battery, the charge and discharge polarization internal resistance of the target nickel-hydrogen battery, the charge and discharge pulse power of the target nickel-hydrogen battery, and the rebound voltage difference of the target nickel-hydrogen battery.

[0061] It is understandable that by standardizing the initial states of the target nickel-metal hydride batteries, the parameter differences during the test process can be better utilized to perform capacity sorting on the batteries.

[0062] In a specific embodiment of the present invention, a characteristic parameter extraction test is performed on a target nickel-metal hydride battery to obtain a first characteristic parameter of the target nickel-metal hydride battery, including:

[0063] After charging the target nickel-metal hydride battery at a constant current to the same state of charge, the battery thickness is measured before and after charging to obtain the difference in volume expansion and thickness of the target nickel-metal hydride battery before and after charging;

[0064] It can be understood that after the capacity test of the target nickel-metal hydride battery, the battery is left to stand for a sufficiently long time, and then the battery is charged with a constant current at 0.3C to 1C to the same state of charge. The battery thickness before and after charging is measured using a vernier caliper to obtain the volume expansion thickness difference Δd. The calculation formula is as follows: Δd = d2 - d1, where d1 represents the battery thickness before charging and d2 represents the battery thickness after charging.

[0065] After the target nickel-hydrogen battery charged to the same state of charge is left to rest for a first preset time, the target nickel-hydrogen battery is tested to obtain the internal resistance and terminal voltage of the target nickel-hydrogen battery;

[0066] Specifically, the battery charged to the same state of charge is left to rest for a sufficiently long time, and then tested using a voltage and internal resistance tester to obtain the internal resistance R1 and terminal voltage U1 of the battery.

[0067] Performing a charge-discharge pulse test on a target nickel-hydrogen battery charged to the same state of charge, and calculating the charge-discharge ohmic internal resistance of the target nickel-hydrogen battery, the charge-discharge polarization internal resistance of the target nickel-hydrogen battery, and the charge-discharge pulse power of the target nickel-hydrogen battery;

[0068] Specifically, the target nickel-metal hydride battery charged to the same state of charge is subjected to charge and discharge pulse testing under 2C to 20C conditions, and the charge and discharge ohmic internal resistance R of the battery is calculated. n1 and R n2 , charge and discharge polarization internal resistance R f1 and R f2 And the charge and discharge pulse powers P1 and P2.

[0069] For detailed calculation, please refer to Figure 2 and the following formula, where Figure 2 A side view of a charge and discharge pulse according to an embodiment of the present invention.

[0070]

[0071]

[0072] Among them, R n1 is the discharge ohmic internal resistance, R n2 is the charging ohmic internal resistance, R f1 is the discharge polarization internal resistance, R f2 is the charging polarization internal resistance, I1 is the pulse discharge current, I2 is the pulse charging current, W1 is the energy during the pulse discharge process, Δt1 is the pulse discharge time, W2 is the energy during the pulse charging process, and Δt2 is the pulse charging time.

[0073] The target nickel-hydrogen battery after the charge-discharge pulse test is discharged at a constant current to a cut-off voltage, and the rebound voltage difference of the target nickel-hydrogen battery is recorded after the battery is left to stand for a second preset time.

[0074] Specifically, the battery after the pulse test is discharged at a constant current of 0.3C to 1C to the cut-off voltage. After standing for a sufficiently long time, the rebound voltage difference ΔU of the battery is recorded. The calculation formula is as follows: ΔU = U3 - U2.

[0075] In a specific embodiment of the present invention, the preset correlation coefficient includes a Pearson correlation coefficient;

[0076] The first characteristic parameter and the first battery capacity are correlated based on a preset correlation coefficient to obtain a second characteristic parameter, including:

[0077] Calculating the correlation between each first characteristic parameter of the target nickel-hydrogen battery and the first battery capacity based on the Pearson correlation coefficient, and obtaining a correlation value between each first characteristic parameter and the first battery capacity;

[0078] The first characteristic parameter having a correlation value greater than a preset threshold is determined as a second characteristic parameter, wherein the second characteristic parameter includes a volume expansion thickness difference before and after charging of the target nickel-hydrogen battery, an internal resistance of the target nickel-hydrogen battery, and a charge-discharge polarization internal resistance of the target nickel-hydrogen battery.

[0079] It is understandable that by selecting characteristic parameters with a high correlation with the first battery capacity from the first characteristic parameters, the amount of calculation in the subsequent training process can be reduced, thereby improving training efficiency.

[0080] Specifically, the calculation formula of the correlation value is as follows:

[0081]

[0082] Where r ranges from -1 to 1, N is the number of target NiMH batteries, x is the input value, specifically the first characteristic parameter, and y is the output value, specifically the first battery capacity. When the calculated r value is closer to 1, it indicates that the characteristic parameter is more positively linearly correlated with the battery capacity. When it is closer to -1, it indicates that the correlation is more negatively linear. When r is 0, it indicates that there is no linear correlation between the characteristic parameter and the battery capacity.

[0083] Specifically, in one embodiment of the present invention, the absolute value of the preset threshold value may be 0.6, and thus the first characteristic parameter with a correlation value greater than 0.6 or less than -0.6 is the second characteristic parameter. In the embodiment of the present invention, the second characteristic parameters selected by the above formula are the volume expansion thickness difference Δd before and after charging of the target nickel-hydrogen battery, the internal resistance R1 of the target nickel-hydrogen battery, and the charge and discharge polarization internal resistance R f1 and R f2 .

[0084] In a specific embodiment of the present invention, the target nickel-metal hydride battery includes a training set nickel-metal hydride battery and a prediction set nickel-metal hydride battery;

[0085] The second characteristic parameter is used as the input of the RBF neural network model, and the first battery capacity is used as the output of the RBF neural network model for training to obtain a fully trained battery capacity prediction model, including:

[0086] Obtaining a third characteristic parameter and a third battery capacity of the nickel-hydrogen battery in the training set from the second characteristic parameter and the first battery capacity of the target nickel-hydrogen battery, wherein the second characteristic parameter and the third characteristic parameter have the same parameter type but different parameter values;

[0087] The third characteristic parameter and the third battery capacity of the nickel-hydrogen battery in the training set are used as the input and output values ​​of the RBF neural network model respectively, and the neural network parameters are set for training to obtain a battery capacity prediction model, wherein the neural network parameters include any one of an error tolerance, a diffusion factor or the number of neurons.

[0088] It is understandable that the target nickel-hydrogen batteries include training set nickel-hydrogen batteries and prediction set nickel-hydrogen batteries, and the prediction set nickel-hydrogen batteries are the nickel-hydrogen batteries to be tested, wherein the number of batteries in the training set is at least 20 and the number of batteries in the prediction set is at least 10.

[0089] During the training process, the nickel-hydrogen batteries in the training set are used for training. Specifically, the characteristic parameters of the nickel-hydrogen batteries in the training set whose relevant values ​​exceed the preset threshold, that is, the volume expansion thickness difference before and after charging of the nickel-hydrogen batteries in the training set corresponding to the third characteristic parameter, the internal resistance of the nickel-hydrogen batteries in the training set, and the charge and discharge polarization internal resistance of the nickel-hydrogen batteries in the training set are used as input values ​​of the neural network, and the third battery capacity in the nickel-hydrogen batteries in the training set is used as the output value of the neural network to construct an RBF neural network model. The radial basis function expression formula of the RBF neural network model is as follows:

[0090]

[0091] Among them, a is the input sample, c i Memory samples for sample vectors, specifically, That is, c i is the average value of each set of input sample data, L is the number of characteristic parameters, and b is the width parameter of the radial basis function. The neural network parameters are then set. These parameters can include error tolerance, diffusion factor, number of neurons, etc. The neural network is fully trained using the sample data in the training set to obtain a fully trained battery capacity prediction model.

[0092] It should be noted that, during the prediction process, when predicting the second battery capacity of the nickel-hydrogen battery to be tested, that is, the prediction set nickel-hydrogen battery, based on the fully trained battery capacity prediction model, it is only necessary to extract the fourth characteristic parameter of the prediction set nickel-hydrogen battery from the second characteristic parameter of the target nickel-hydrogen battery, and then input the fourth characteristic parameter into the fully trained battery capacity prediction model, wherein the second characteristic parameter and the third characteristic parameter also have the same parameter type but different parameter values.

[0093] Furthermore, the predicted second battery capacity may be compared with the predicted fourth battery capacity corresponding to the nickel-hydrogen battery to further verify the prediction accuracy of the battery capacity prediction model.

[0094] It should also be noted that the battery capacity prediction model in the present invention can not only predict the capacity of concentrated nickel-hydrogen batteries, but can also further predict the remaining capacity of other retired nickel-hydrogen batteries. Specifically, only characteristic parameter extraction tests need to be performed on other nickel-hydrogen batteries, and there is no need to perform capacity tests again to reduce damage to the batteries.

[0095] In a specific embodiment of the present invention, the above method further includes:

[0096] The nickel-hydrogen batteries to be tested are sorted based on the second battery capacity, and a sorting result is obtained.

[0097] It is understandable that the consistency problem of retired nickel-hydrogen batteries is particularly obvious, which can easily cause overcharging, over-discharging and other problems during use, and in severe cases will lead to safety problems. Therefore, after predicting the battery capacity of retired nickel-hydrogen batteries, they are sorted. Specifically, batteries with consistent capacity, internal resistance and voltage are sorted out and re-connected in series and parallel to form battery packs for cascade utilization.

[0098] In order to better implement the nickel-hydrogen battery capacity prediction method in the embodiment of the present invention, based on the nickel-hydrogen battery capacity prediction method, correspondingly, please refer to Figure 3 , Figure 3 This is a schematic structural diagram of an embodiment of a nickel-hydrogen battery capacity prediction device provided by the present invention. This embodiment of the present invention provides a nickel-hydrogen battery capacity prediction device 300, comprising:

[0099] A testing module 301 is configured to perform a capacity test and a characteristic parameter extraction test on a target nickel-hydrogen battery to obtain a first battery capacity and a first characteristic parameter of the target nickel-hydrogen battery;

[0100] A calculation module 302 is configured to calculate a correlation between the first characteristic parameter and the first battery capacity based on a preset correlation coefficient to obtain a second characteristic parameter;

[0101] A training module 303 is used to construct an RBF neural network model, and train the model using the second characteristic parameter as input and the first battery capacity as output of the RBF neural network model to obtain a fully trained battery capacity prediction model;

[0102] The prediction module 304 is configured to predict the second battery capacity of the nickel-hydrogen battery to be tested by using the battery capacity prediction model.

[0103] It should be noted here that the device 300 provided in the above embodiment can implement the technical solutions described in the above method embodiments. The specific implementation principles of the above modules or units can be found in the corresponding contents in the above method embodiments, which will not be repeated here.

[0104] Based on the above-mentioned nickel-metal hydride battery capacity prediction method, an embodiment of the present invention also provides an electronic device, including: a processor and a memory, and a computer program stored in the memory and executable on the processor; when the processor executes the computer program, the steps of the nickel-metal hydride battery capacity prediction method in the above-mentioned embodiments are implemented.

[0105] Figure 4 4 shows a schematic diagram of the structure of an electronic device 400 suitable for implementing an embodiment of the present invention. The electronic devices in the embodiments of the present invention may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0106] The electronic device includes: a memory and a processor, wherein the processor here may be referred to as the processing device 401 below, and the memory may include at least one of the read-only memory (ROM) 402, the random access memory (RAM) 403, and the storage device 408 below, as shown below:

[0107] like Figure 4As shown, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403. Various programs and data required for the operation of the electronic device 400 are also stored in the RAM 403. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0108] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 400 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0109] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication device 409, or installed from the storage device 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of the embodiment of the present invention are performed.

[0110] Based on the above-mentioned nickel-metal hydride battery capacity prediction method, an embodiment of the present invention also provides a computer-readable storage medium, which stores one or more programs. The one or more programs can be executed by one or more processors to implement the steps in the nickel-metal hydride battery capacity prediction method as described in the above-mentioned embodiments.

[0111] Those skilled in the art will appreciate that all or part of the process steps of the above-described embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, such as a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0112] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with this technical field within the technical scope disclosed by the present invention should be covered by the scope of protection of the present invention.

Claims

1. A method for predicting the capacity of a nickel-hydrogen battery, characterized in that: include: Performing a capacity test and a characteristic parameter extraction test on a target nickel-hydrogen battery to obtain a first battery capacity and a first characteristic parameter of the target nickel-hydrogen battery; The first characteristic parameters include, after charging the target nickel-hydrogen battery to the same state, the difference in volume expansion and thickness of the target nickel-hydrogen battery before and after charging, the internal resistance and terminal voltage of the target nickel-hydrogen battery, the charge and discharge ohmic internal resistance of the target nickel-hydrogen battery, the charge and discharge polarization internal resistance of the target nickel-hydrogen battery, the charge and discharge pulse power of the target nickel-hydrogen battery, and the rebound voltage difference of the target nickel-hydrogen battery; Calculating the correlation between the first characteristic parameter and the first battery capacity based on a preset correlation coefficient to obtain a second characteristic parameter; Constructing an RBF neural network model, and training the model using the second characteristic parameter as input of the RBF neural network model and the first battery capacity as output of the RBF neural network model to obtain a fully trained battery capacity prediction model; The battery capacity prediction model is used to predict the second battery capacity of the nickel-hydrogen battery to be tested.

2. The battery capacity prediction method according to claim 1, characterized in that: The performing a capacity test on the target nickel-hydrogen battery to obtain a first battery capacity of the target nickel-hydrogen battery includes: A constant current charge-discharge capacity test is performed on the target nickel-hydrogen battery to obtain a first battery capacity of the target nickel-hydrogen battery.

3. The battery capacity prediction method according to claim 1, characterized in that: Performing a characteristic parameter extraction test on the target nickel-hydrogen battery to obtain a first characteristic parameter of the target nickel-hydrogen battery includes: After the target nickel-hydrogen battery is charged at a constant current to the same state of charge, the battery thickness is measured before and after charging to obtain a volume expansion thickness difference of the target nickel-hydrogen battery before and after charging; After the target nickel-hydrogen battery charged to the same state of charge is left to rest for a first preset time, the target nickel-hydrogen battery is tested to obtain the internal resistance and terminal voltage of the target nickel-hydrogen battery; Performing a charge-discharge pulse test on a target nickel-hydrogen battery charged to the same state of charge, and calculating the charge-discharge ohmic internal resistance of the target nickel-hydrogen battery, the charge-discharge polarization internal resistance of the target nickel-hydrogen battery, and the charge-discharge pulse power of the target nickel-hydrogen battery; The target nickel-hydrogen battery after the charge-discharge pulse test is discharged at a constant current to a cut-off voltage, and the rebound voltage difference of the target nickel-hydrogen battery is recorded after the battery is left to stand for a second preset time.

4. The battery capacity prediction method according to claim 1, wherein: The preset correlation coefficient includes the Pearson correlation coefficient; The performing correlation calculation on the first characteristic parameter and the first battery capacity based on a preset correlation coefficient to obtain a second characteristic parameter includes: Calculating the correlation between each first characteristic parameter of the target nickel-hydrogen battery and the first battery capacity based on the Pearson correlation coefficient, and obtaining a correlation value between each first characteristic parameter and the first battery capacity; A first characteristic parameter having a correlation value greater than a preset threshold is determined as a second characteristic parameter, wherein the second characteristic parameter includes a volume expansion thickness difference before and after charging of the target nickel-hydrogen battery, an internal resistance of the target nickel-hydrogen battery, and a charge-discharge polarization internal resistance of the target nickel-hydrogen battery.

5. The battery capacity prediction method according to claim 1, wherein: The target nickel-metal hydride batteries include training set nickel-metal hydride batteries and prediction set nickel-metal hydride batteries; The method of using the second characteristic parameter as the input of the RBF neural network model and the first battery capacity as the output of the RBF neural network model for training to obtain a fully trained battery capacity prediction model includes: Obtaining a third characteristic parameter and a third battery capacity of the nickel-hydrogen battery in the training set from the second characteristic parameter and the first battery capacity of the target nickel-hydrogen battery, wherein the second characteristic parameter and the third characteristic parameter have the same parameter type but different parameter values; The third characteristic parameter and the third battery capacity of the nickel-hydrogen battery in the training set are used as the input and output values ​​of the RBF neural network model, respectively, and the neural network parameters are set for training to obtain a fully trained battery capacity prediction model, wherein the neural network parameters include any one of an error tolerance, a diffusion factor, or the number of neurons.

6. The battery capacity prediction method according to claim 1, characterized in that: Also includes: The nickel-hydrogen batteries to be tested are sorted based on the second battery capacity to obtain a sorting result.

7. A nickel-hydrogen battery capacity prediction device, characterized in that: include: A testing module, configured to perform a capacity test and a characteristic parameter extraction test on a target nickel-hydrogen battery to obtain a first battery capacity and a first characteristic parameter of the target nickel-hydrogen battery; a calculation module, configured to calculate a correlation between the first characteristic parameter and the first battery capacity based on a preset correlation coefficient to obtain a second characteristic parameter; the first characteristic parameter including, after charging the target nickel-hydrogen battery to the same state, a volume expansion thickness difference before and after charging of the target nickel-hydrogen battery, an internal resistance and terminal voltage of the target nickel-hydrogen battery, a charge and discharge ohmic internal resistance of the target nickel-hydrogen battery, a charge and discharge polarization internal resistance of the target nickel-hydrogen battery, a charge and discharge pulse power of the target nickel-hydrogen battery, and a rebound voltage difference of the target nickel-hydrogen battery; a training module, configured to construct an RBF neural network model, and perform training using the second characteristic parameter as input of the RBF neural network model and the first battery capacity as output of the RBF neural network model, to obtain a fully trained battery capacity prediction model; The prediction module is used to predict the second battery capacity of the nickel-hydrogen battery to be tested by using the battery capacity prediction model.

8. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory is used to store a program; and the processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the nickel-metal hydride battery capacity prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the nickel-metal hydride battery capacity prediction method according to any one of claims 1 to 6.

Images