Methods, devices, electronic equipment and storage media for predicting the capacity of retired battery modules

Abstract

This invention provides a method, device, electronic device, and storage medium for predicting the capacity of retired battery modules. The method includes: constructing an initial neural network model, using short-time charge / discharge time, short-time charge / discharge capacity, Fréchet distance, module voltage and internal resistance, and the voltage difference and internal resistance difference between the module and individual cells as input values, and the remaining capacity of the module as the output value. Through iterative training, a fully trained neural network model is obtained, and the capacity of the retired power battery module is predicted based on this model. This invention obtains the voltage range for short-time charge / discharge using the IC curve, which better reflects the internal structural characteristics of the module and allows for more accurate capacity sorting. The strong learning ability of the neural network allows it to better adapt to the data relationship between multiple feature parameters and discharge capacity, and by constructing an optimal model, it achieves the goal of rapid capacity prediction for battery modules.

Description

Technical Field

[0001] This invention relates to the field of retired battery capacity prediction technology, specifically to a method, apparatus, electronic device, and storage medium for predicting the capacity of retired battery modules. Background Technology

[0002] Power battery modules refer to the power sources that provide power to tools. They mainly refer to the batteries that provide power to electric vehicles, electric trains, electric bicycles, and golf carts. They are mainly different from the starting batteries used to start car engines. They mostly use valve-sealed lead-acid batteries, open-type tubular lead-acid batteries, and lithium iron phosphate batteries.

[0003] When a power battery module is in poor performance or has been used for a long time, it is usually discarded and becomes a retired battery module. However, even retired battery modules still have a certain amount of residual power, which can play a role in realizing the recycling and reuse of battery modules.

[0004] Therefore, when recycling retired power battery modules, it is necessary to measure and test the remaining capacity of different retired power battery modules. However, the current capacity prediction method generally uses a single complete charge and discharge test, which involves many cycles. This method cannot accurately predict the capacity, and the large number of charge and discharge cycles also affects the performance of retired power battery modules. Summary of the Invention

[0005] In view of this, it is necessary to provide a method, device, electronic device and storage medium for predicting the capacity of retired battery modules, so as to solve the problem that the existing technology requires a large number of complete charge and discharge cycles, and can achieve rapid and accurate prediction of retired battery modules without the need for complete charge and discharge cycles, without affecting the performance of retired battery modules.

[0006] In a first aspect, the present invention provides a method for predicting the capacity of retired battery modules, comprising:

[0007] Obtain the remaining capacity of several retired power battery modules after their first charge-discharge test;

[0008] Obtain the IC curves of the second charge-discharge test of the several retired power battery modules, and select the voltage range that meets the preset conditions as the limiting voltage range segment;

[0009] Within the specified voltage range, the short-time charge-discharge curves, short-time charge-discharge times, and short-time charge-discharge capacity values ​​of the several retired power battery modules under short-time charge-discharge tests are obtained.

[0010] Obtain the Fréchet distance between short-time charge-discharge curves of each pair of battery modules in the plurality of retired power battery modules;

[0011] Obtain the terminal voltage and internal resistance of the plurality of retired power battery modules, as well as the terminal voltage and internal resistance of all individual cells in the plurality of retired power battery modules, and calculate the terminal voltage of each individual cell and the difference between the voltage and the module, and the voltage and internal resistance of each individual cell and the difference between the voltage and the internal resistance of the module.

[0012] An initial neural network model is constructed, using the short-time charge-discharge time, short-time charge-discharge capacity, Fraser distance, module voltage and internal resistance, and the voltage difference and internal resistance difference between the module and the individual cells as input values, and the remaining capacity of the module as the output value. After iterative training, a fully trained neural network model is obtained, and the capacity of retired power battery modules is predicted based on the fully trained neural network model.

[0013] In some possible embodiments, the remaining capacity of several retired power battery modules after their first charge-discharge test is obtained, including:

[0014] A first charge-discharge test was conducted on several retired power battery modules at the first charge-discharge capacity rate to obtain the remaining capacity of the several retired power battery modules.

[0015] In some possible embodiments, the IC curves of the second charge-discharge test of the plurality of retired power battery modules are obtained, and a voltage range that meets preset conditions is selected as the limiting voltage range segment, including:

[0016] At the second charge / discharge capacity rate, charge / discharge curve tests were performed on the several retired power battery modules to obtain the IC curves of the several retired power battery modules.

[0017] In the IC curve of the battery module, the voltage range is divided according to the trough-peak-trough pattern. By comparing the time periods occupied by each voltage range, the voltage range with the shortest time period is selected as the limiting voltage range segment.

[0018] In some possible embodiments, within the restricted voltage range, the short-time charge-discharge curves, short-time charge-discharge times, and short-time charge-discharge capacity values ​​of the plurality of retired power battery modules under short-time charge-discharge tests are obtained, including:

[0019] Within the specified voltage range, short-time charge-discharge curve tests are performed at the first charge-discharge capacity rate and the first temperature to obtain the short-time charge-discharge curve, short-time charge-discharge time, and short-time charge-discharge capacity value.

[0020] In some possible embodiments, the first charge / discharge rate is 0.3C to 1C, and the first temperature is 15°C to 35°C.

[0021] In some possible embodiments, obtaining the Fréchet distance of the short-time charge-discharge curves between any two battery modules in the plurality of retired power battery modules includes:

[0022] The Frescher distance between the short-time charge-discharge curves of each pair of battery modules in the aforementioned retired power battery modules was calculated using the Frescher distance algorithm.

[0023] The formula for calculating the Frescher distance is as follows:

[0024]

[0025] P and L represent curve P and curve L, respectively; i is the number of trajectory points; and m is the sum of the number of trajectory points for a single selected curve. Let be the trajectory points of the sequential set in the P-curve and L-curve, respectively, and d() be the distance calculation formula.

[0026] In some possible embodiments, the initial neural network model is an Elman neural network model; the Elman neural network model structure is a feedforward connection, which includes an input layer, a hidden layer, and an output layer, wherein the transfer function of the hidden layer is a non-linear function, and the output layer is a linear function.

[0027] Secondly, the present invention also provides a capacity prediction device for retired battery modules, comprising:

[0028] The remaining capacity acquisition module is used to acquire the remaining capacity of several retired power battery modules after their first charge-discharge test.

[0029] The voltage range acquisition module is used to acquire the IC curves of the second charge-discharge test of the several retired power battery modules, and select the voltage range that meets the preset conditions as the limiting voltage range.

[0030] The short-time value acquisition module is used to acquire the short-time charge-discharge curves, short-time charge-discharge times, and short-time charge-discharge capacity values ​​of the plurality of retired power battery modules under short-time charge-discharge tests within the limited voltage range.

[0031] The curve distance acquisition module is used to acquire the Frescher distance between the short-time charge and discharge curves of two battery modules among the plurality of retired power battery modules;

[0032] The voltage and internal resistance acquisition module is used to acquire the terminal voltage and internal resistance of the plurality of retired power battery modules, as well as the terminal voltage and internal resistance of all individual cells in the plurality of retired power battery modules, and to calculate the terminal voltage of each individual cell and the difference between the voltage and the module, as well as the voltage and internal resistance of each individual cell and the difference between the voltage and the internal resistance of the module.

[0033] The capacity prediction module is used to construct an initial neural network model. The short-time charge-discharge time, short-time charge-discharge capacity, Fraser distance, module voltage and internal resistance, and the voltage difference and internal resistance difference between the module and the individual cells are used as the input values ​​of the initial neural network model. The remaining capacity of the module is used as the output value. After iterative training, a fully trained neural network model is obtained, and the capacity of the retired power battery module is predicted based on the fully trained neural network model.

[0034] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein,

[0035] The memory is used to store programs;

[0036] The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the retired battery module capacity prediction method described in any of the above possible implementations.

[0037] Fourthly, the present invention also provides a computer-readable storage medium, characterized in that it is used to store a computer-readable program or instructions, which, when executed by a processor, are capable of implementing the steps in the retired battery module capacity prediction method described in any of the above possible implementations.

[0038] The beneficial effects of the above embodiments are as follows: The present invention first obtains short-time charge-discharge time, short-time charge-discharge capacity, Fraser distance, module voltage and internal resistance, and voltage difference and internal resistance difference between the module and the individual cells through different charge-discharge tests. Then, it constructs a neural network model, using the short-time charge-discharge time, short-time charge-discharge capacity, Fraser distance, module voltage and internal resistance, and voltage difference and internal resistance difference between the module and the individual cells as the input values ​​of the initial neural network model, and the remaining capacity of the module as the output value. After iterative training, a fully trained neural network model is obtained, and the capacity of retired power battery modules is predicted based on the fully trained neural network model. This invention utilizes IC curves to obtain the voltage range of short-term charge and discharge, which better reflects the internal structural characteristics of the module and enables more accurate sorting of the module's capacity. The strong learning ability of neural networks allows for better adaptation to the data relationship between multiple feature parameters and discharge capacity. By constructing an optimal model, it achieves the goal of rapid prediction of battery module capacity. The larger the training set sample size, the more accurate the established network model. This solution enables rapid and accurate prediction of retired battery modules without requiring a complete charge and discharge cycle. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 A schematic flowchart of an embodiment of the method for predicting the capacity of retired battery modules provided by the present invention;

[0041] Figure 2 A schematic diagram of an embodiment of the selected limiting voltage range provided by the present invention;

[0042] Figure 3 A schematic diagram of an embodiment of the retired battery module capacity prediction device provided by the present invention;

[0043] Figure 4 A schematic diagram of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0045] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this invention illustrate operations implemented according to some embodiments of the invention. It should be understood that the operations in the flowcharts may be implemented out of order, and steps without logical contextual relationships may be reversed or performed simultaneously. Furthermore, those skilled in the art, guided by the content of this invention, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor systems and / or microcontroller systems.

[0046] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0047] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0048] This invention provides a method, apparatus, electronic device, and storage medium for predicting the capacity of retired battery modules, which will be described below.

[0049] Figure 1 This is a schematic flowchart of an embodiment of the retired battery module capacity prediction method provided by the present invention, as shown below. Figure 1 As shown, the methods for predicting the capacity of retired battery modules include:

[0050] S101. Obtain the remaining capacity of several retired power battery modules after the first charge-discharge test;

[0051] S102. Obtain the IC curves of the second charge and discharge test of the several retired power battery modules, and select the voltage range that meets the preset conditions as the limiting voltage range segment.

[0052] S103. Within the restricted voltage range, obtain the short-time charge-discharge curves, short-time charge-discharge time, and short-time charge-discharge capacity values ​​of the several retired power battery modules under short-time charge-discharge tests.

[0053] S104. Obtain the Frescher distance between the short-time charge-discharge curves of each pair of battery modules in the plurality of retired power battery modules.

[0054] S105. Obtain the terminal voltage and internal resistance of the plurality of retired power battery modules, as well as the terminal voltage and internal resistance of all individual cells in the plurality of retired power battery modules, and calculate the terminal voltage of each individual cell and the difference between the voltage and the module, as well as the voltage and internal resistance of each individual cell and the difference between the voltage and the internal resistance of the module.

[0055] S106. Construct an initial neural network model, using the short-time charge-discharge time, short-time charge-discharge capacity, Fréchet distance, module voltage and internal resistance, and the voltage difference and internal resistance difference between the module and the individual cells as the input values ​​of the initial neural network model, and the remaining capacity of the module as the output value. After iterative training, a fully trained neural network model is obtained, and the capacity of the retired power battery module is predicted based on the fully trained neural network model.

[0056] Compared with existing technologies, the retired battery module capacity prediction method provided by this invention utilizes IC curves to obtain the voltage range of short-term charge and discharge, which can better reflect the internal structural characteristics of the module and provide more accurate sorting of the module's capacity. Through the strong learning ability of neural networks, it can better adapt to the data relationship between multiple feature parameters and discharge capacity, and by constructing the optimal model, it can achieve the goal of rapid prediction of battery module capacity. The larger the number of training set samples, the more accurate the established network model. This solution can achieve rapid and accurate prediction of retired battery modules without requiring a complete charge and discharge cycle.

[0057] It should be understood that the model structure of the initial neural network model includes, but is not limited to, deep neural network models (DNN), recurrent neural network models (RNN), convolutional neural network models (CNN), Elman neural network models, deep generative models (DGM), generative adversarial networks (GAN), long short-term memory network models (LSTM), support vector machines (SVM), deep crossover models, etc.

[0058] In some embodiments of the present invention, obtaining the remaining capacity of several retired power battery modules after the first charge-discharge test includes:

[0059] A first charge-discharge test was conducted on several retired power battery modules at the first charge-discharge capacity rate to obtain the remaining capacity of the several retired power battery modules.

[0060] It should be noted that the first charge / discharge capacity rate refers to 0.3C~1C, and after selecting several retired power battery modules, they need to be left to stand at room temperature for a sufficient period of time before the charge / discharge test is carried out.

[0061] In some embodiments of the present invention, the IC curves of the second charge-discharge test of the plurality of retired power battery modules are obtained, and a voltage range that meets preset conditions is selected as a limiting voltage range segment, including:

[0062] Charge and discharge curve tests were performed on the retired power battery modules at the second charge and discharge capacity rate to obtain the IC curves (dQ / dV vs V) of the retired power battery modules.

[0063] In the IC curve of the battery module, the voltage range is divided according to the trough-peak-trough pattern. By comparing the time periods occupied by each voltage range, the voltage range with the shortest time period is selected as the limiting voltage range segment.

[0064] It should be noted that the second charge / discharge capability is 0.05C~1C.

[0065] Please see Figure 2 , Figure 2 This is a schematic diagram of an embodiment of the selective limiting voltage range provided by the present invention. Figure 2 As can be seen, the voltage range with the shortest time period is selected as the limiting voltage range segment.

[0066] In some embodiments of the present invention, within the restricted voltage range, acquiring the short-time charge-discharge curves, short-time charge-discharge time t, and short-time charge-discharge capacity value Q of the plurality of retired power battery modules under short-time charge-discharge testing includes:

[0067] Within the specified voltage range, a short-time charge-discharge curve test is performed at the first charge-discharge capacity rate and the first temperature to obtain the short-time charge-discharge curve, the short-time charge-discharge time t, and the short-time charge-discharge capacity value Q.

[0068] In some embodiments of the present invention, the first charge / discharge capacity is 0.3C to 1C, preferably 1C, and the first temperature is 15°C to 35°C, preferably 25°C.

[0069] In some embodiments of the present invention, obtaining the Fréchet distance of the short-time charge-discharge curves between any two battery modules in the plurality of retired power battery modules includes:

[0070] The Frescher distance between the short-time charge-discharge curves of each pair of battery modules in the aforementioned retired power battery modules was calculated using the Frescher distance algorithm.

[0071] The formula for calculating the Frescher distance is as follows:

[0072]

[0073] P and L represent curve P and curve L, respectively; i is the number of trajectory points; and m is the sum of the number of trajectory points for a single selected curve. Let be the trajectory points of the sequential set in the P-curve and L-curve, respectively, and d() be the distance calculation formula.

[0074] In a specific embodiment, the similarity between the short-time charge-discharge curves P and L of the two modules is calculated using the Fréchet distance algorithm: Let curve P be composed of p trajectory points and curve L be composed of l trajectory points. Let σ(P) and σ(L) represent the sequential sets of the two trajectory points respectively. Then we have σ(P) = (u1, ..., up) and σ(L) = (v1, ..., vp). The Fréchet distance between the curves is calculated using the Fréchet distance algorithm.

[0075] In some embodiments of the present invention, an internal resistance tester is used to test the terminal voltage and internal resistance of the battery module to obtain U and R. The terminal voltage and internal resistance of each cell in the module are tested, and the voltage of each cell and the difference between the voltage of each cell and the module voltage, as well as the voltage internal resistance of each cell and the difference between the voltage internal resistance of each cell and the module internal resistance, are calculated and denoted as ΔU and ΔR, respectively.

[0076] In some embodiments of the present invention, the initial neural network model is an Elman neural network model. The Elman neural network model structure is a feedforward connection, which includes an input layer, a hidden layer, and an output layer. The transfer function of the hidden layer is a nonlinear function, the output layer is a linear function, and the correlation layer is also a linear function. A training set and a prediction set are set, with at least 20 modules in the training set and at least 10 modules in the prediction set. The calculated short-time charge / discharge time t, short-time charge / discharge capacity Q, Fréchet distance δ, module voltage and internal resistance U and R, and the voltage and internal resistance difference ΔU and ΔR are used as input values ​​to the Elman neural network model, and the remaining capacity of the module is used as the output value to construct a capacity prediction model for the battery module, thereby predicting the capacity of the battery module and achieving the purpose of rapid sorting.

[0077] To better implement the retired battery module capacity prediction method in this embodiment of the invention, based on the retired battery module capacity prediction method, the corresponding method is as follows: Figure 3 As shown, this embodiment of the invention also provides a retired battery module capacity prediction device 300, comprising:

[0078] The remaining capacity acquisition module 301 is used to acquire the remaining capacity of several retired power battery modules after the first charge-discharge test.

[0079] The voltage range acquisition module 302 is used to acquire the IC curves of the second charge and discharge test of the plurality of retired power battery modules, and select the voltage range that meets the preset conditions as the limiting voltage range.

[0080] The short-time value acquisition module 303 is used to acquire the short-time charge-discharge curve, short-time charge-discharge time and short-time charge-discharge capacity value of the plurality of retired power battery modules under short-time charge-discharge test within the limited voltage range.

[0081] The curve distance acquisition module 304 is used to acquire the Frescher distance between the short-time charge and discharge curves of two battery modules in the plurality of retired power battery modules.

[0082] The voltage and internal resistance acquisition module 305 is used to acquire the terminal voltage and internal resistance of the plurality of retired power battery modules, as well as the terminal voltage and internal resistance of all individual cells in the plurality of retired power battery modules, and to calculate the terminal voltage of each individual cell and the difference between the voltage and the module, as well as the voltage and internal resistance of each individual cell and the difference between the voltage and the internal resistance of the module.

[0083] The capacity prediction module 306 is used to construct an initial neural network model. The short-time charge-discharge time, short-time charge-discharge capacity, Fraser distance, module voltage and internal resistance, and the voltage difference and internal resistance difference between the module and the individual cells are used as the input values ​​of the initial neural network model. The remaining capacity of the module is used as the output value. After iterative training, a fully trained neural network model is obtained, and the capacity of the retired power battery module is predicted based on the fully trained neural network model.

[0084] The retired battery module capacity prediction device 400 provided in the above embodiments can realize the technical solutions described in the above embodiments of the retired battery module capacity prediction method. The specific implementation principles of each module can be found in the corresponding content in the above embodiments of the retired battery module capacity prediction method, which will not be repeated here.

[0085] like Figure 4 As shown, the present invention also provides an electronic device 400. The electronic device 400 includes a processor 401, a memory 402, and a display 403. Figure 4 Only some components of the electronic device 400 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0086] In some embodiments, memory 402 may be an internal storage module of electronic device 400, such as a hard disk or memory of electronic device 400. In other embodiments, memory 402 may also be an external storage device of electronic device 400, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 400.

[0087] Furthermore, the memory 402 may include both internal storage modules of the electronic device 400 and external storage devices. The memory 402 is used to store application software and various types of data installed on the electronic device 400.

[0088] In some embodiments, processor 401 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 402 or process data, such as the retired battery module capacity prediction method of the present invention.

[0089] In some embodiments, display 403 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 403 is used to display information from electronic device 400 and to display a visual user interface. Components 401-403 of electronic device 400 communicate with each other via a system bus.

[0090] In some embodiments of the present invention, when the processor 401 executes the computer program in the memory 402, the following steps may be performed:

[0091] Obtain the remaining capacity of several retired power battery modules after their first charge-discharge test;

[0092] Obtain the IC curves of the second charge-discharge test of the several retired power battery modules, and select the voltage range that meets the preset conditions as the limiting voltage range segment;

[0093] Within the specified voltage range, the short-time charge-discharge curves, short-time charge-discharge times, and short-time charge-discharge capacity values ​​of the several retired power battery modules under short-time charge-discharge tests are obtained.

[0094] Obtain the Fréchet distance between short-time charge-discharge curves of each pair of battery modules in the plurality of retired power battery modules;

[0095] Obtain the terminal voltage and internal resistance of the plurality of retired power battery modules, as well as the terminal voltage and internal resistance of all individual cells in the plurality of retired power battery modules, and calculate the terminal voltage of each individual cell and the difference between the voltage and the module, and the voltage and internal resistance of each individual cell and the difference between the voltage and the internal resistance of the module.

[0096] An initial neural network model is constructed, using the short-time charge-discharge time, short-time charge-discharge capacity, Fraser distance, module voltage and internal resistance, and the voltage difference and internal resistance difference between the module and the individual cells as input values, and the remaining capacity of the module as the output value. After iterative training, a fully trained neural network model is obtained, and the capacity of retired power battery modules is predicted based on the fully trained neural network model.

[0097] It should be understood that when the processor 401 executes the computer program in the memory 402, in addition to the functions described above, it can also perform other functions, as can be found in the description of the corresponding method embodiments above.

[0098] Furthermore, this embodiment of the invention does not specifically limit the type of electronic device 400 mentioned. Electronic device 400 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, electronic device 400 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0099] Accordingly, this application also provides a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps in the retired battery module capacity prediction method or the functions in the retired battery module capacity prediction device provided in the above-described method embodiments.

[0100] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0101] The above provides a detailed description of the method, apparatus, electronic device, and storage medium for predicting the capacity of retired battery modules provided by this invention. Specific examples have been used to illustrate the principles and implementation methods of this invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. A method for predicting the capacity of retired battery modules, characterized in that, include: Obtain the remaining capacity of several retired power battery modules after their first charge-discharge test; Obtain the IC curves of the second charge-discharge test of the plurality of retired power battery modules, and select a voltage range that meets the preset conditions as the limiting voltage range segment, including: conducting charge-discharge curve tests on the plurality of retired power battery modules at the second charge-discharge capacity rate to obtain the IC curves of the plurality of retired power battery modules; dividing the voltage range in the IC curve of the battery module according to the trough-peak-trough, comparing the time periods occupied by each voltage range, and selecting the voltage range with the shortest time period as the limiting voltage range segment; Within the specified voltage range, the short-time charge-discharge curves, short-time charge-discharge times, and short-time charge-discharge capacity values ​​of the several retired power battery modules under short-time charge-discharge tests are obtained. Obtain the Fréchet distance between short-time charge-discharge curves of each pair of battery modules in the plurality of retired power battery modules; Obtain the terminal voltage and internal resistance of the plurality of retired power battery modules, as well as the terminal voltage and internal resistance of all individual cells in the plurality of retired power battery modules, and calculate the terminal voltage of each individual cell and the difference between the voltage and the module, and the voltage and internal resistance of each individual cell and the difference between the voltage and the internal resistance of the module. An initial neural network model is constructed, using the short-time charge-discharge time, short-time charge-discharge capacity, Fraser distance, module voltage and internal resistance, and the voltage difference and internal resistance difference between the module and the individual cells as input values, and the remaining capacity of the module as the output value. After iterative training, a fully trained neural network model is obtained, and the capacity of retired power battery modules is predicted based on the fully trained neural network model.

2. The method for predicting the capacity of decommissioned battery modules according to claim 1, characterized in that, Obtain the remaining capacity of several retired power battery modules after their first charge-discharge test, including: A first charge-discharge test was conducted on several retired power battery modules at the first charge-discharge capacity rate to obtain the remaining capacity of the several retired power battery modules.

3. The method for predicting the capacity of retired battery modules according to claim 2, characterized in that, Within the specified voltage range, the short-time charge-discharge curves, short-time charge-discharge times, and short-time charge-discharge capacity values ​​of the plurality of retired power battery modules under short-time charge-discharge tests are obtained, including: Within the specified voltage range, short-time charge-discharge curve tests are performed at the first charge-discharge capacity rate and the first temperature to obtain the short-time charge-discharge curve, short-time charge-discharge time, and short-time charge-discharge capacity value.

4. The method for predicting the capacity of retired battery modules according to claim 3, characterized in that, The first charge / discharge capacity is 0.3C~1C, and the first temperature is 15℃~35℃.

5. The method for predicting the capacity of retired battery modules according to claim 1, characterized in that, Obtaining the Fréchet distance between short-time charge-discharge curves of each pair of battery modules in the plurality of retired power battery modules includes: The Frescher distance between the short-time charge-discharge curves of each pair of battery modules in the aforementioned retired power battery modules was calculated using the Frescher distance algorithm. The formula for calculating the Frescher distance is as follows: P and L represent curve P and curve L, respectively; i is the number of trajectory points; and m is the sum of the number of trajectory points for a single selected curve. Let be the trajectory points of the sequential set in the P-curve and L-curve, respectively, and d() be the distance calculation formula.

6. The method for predicting the capacity of retired battery modules according to claim 1, characterized in that, The initial neural network model is an Elman neural network model; the Elman neural network model structure is a feedforward connection, which includes an input layer, a hidden layer, and an output layer. The transfer function of the hidden layer is a non-linear function, and the output layer is a linear function.

7. A device for predicting the capacity of retired battery modules, characterized in that, include: The remaining capacity acquisition module is used to acquire the remaining capacity of several retired power battery modules after their first charge-discharge test. The voltage range acquisition module is used to acquire the IC curves of the second charge-discharge test of the plurality of retired power battery modules, and select a voltage range that meets preset conditions as a limiting voltage range segment. This includes: performing charge-discharge curve tests on the plurality of retired power battery modules at a second charge-discharge capacity rate to acquire the IC curves of the plurality of retired power battery modules; dividing the voltage range in the IC curve of the battery module according to the trough-peak-trough pattern, comparing the time periods occupied by each voltage range, and selecting the voltage range with the shortest time period as the limiting voltage range segment. The short-time value acquisition module is used to acquire the short-time charge-discharge curves, short-time charge-discharge times, and short-time charge-discharge capacity values ​​of the plurality of retired power battery modules under short-time charge-discharge tests within the limited voltage range. The curve distance acquisition module is used to acquire the Frescher distance between the short-time charge and discharge curves of two battery modules among the plurality of retired power battery modules; The voltage and internal resistance acquisition module is used to acquire the terminal voltage and internal resistance of the plurality of retired power battery modules, as well as the terminal voltage and internal resistance of all individual cells in the plurality of retired power battery modules, and to calculate the terminal voltage of each individual cell and the difference between the voltage and the module, as well as the voltage and internal resistance of each individual cell and the difference between the voltage and the internal resistance of the module. The capacity prediction module is used to construct an initial neural network model. The short-time charge-discharge time, short-time charge-discharge capacity, Fraser distance, module voltage and internal resistance, and the voltage difference and internal resistance difference between the module and the individual cells are used as the input values ​​of the initial neural network model. The remaining capacity of the module is used as the output value. After iterative training, a fully trained neural network model is obtained, and the capacity of the retired power battery module is predicted based on the fully trained neural network model.

8. An electronic device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the method for predicting the capacity of a decommissioned battery module as described in 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 in the method for predicting the capacity of retired battery modules as described in any one of claims 1 to 6.

Images