Safety early warning method and device for reassembled battery pack, electronic equipment and medium
By obtaining the historical charging change curve of the recombinant battery pack and iterative training deviation index prediction network, the problem of insufficient accuracy and timeliness of early warning parameters in the prior art is solved, and an accurate and timely safety warning of the recombinant battery pack is achieved.
Patent Information
- Application Number
- CN202411542932.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-31
- Publication Date
- 2025-03-07
AI Technical Summary
In the prior art, during the safety warning process of the recombinant battery pack, the accuracy and timeliness of the warning parameters are poor, making it difficult to achieve accurate and timeliness of the recombinant battery pack.
By obtaining the historical charging change curve of the recombinant battery pack to be detected, the historical charging curve deviation index is determined, and the initial deviation index prediction network is iteratively trained, and a complete curve deviation index prediction network is obtained, and the curve deviation index prediction value is output. If the predicted value is higher than the preset safety threshold, a safety warning will be issued.
It improves the accuracy of early warning parameters, and can early warning of the recombinant battery pack before a fault occurs, which has high warning timeliness.
Smart Images

Figure CN119580468A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of battery safety technology, and in particular to a reorganized battery pack safety warning method, device, electronic equipment and medium. Background Art
[0002] Recombinant battery packs are a way to reorganize and utilize retired batteries. Some retired batteries still have considerable battery capacity and lifespan. By reorganizing battery packs, resources can be used rationally to maximize economic benefits. However, retired batteries have been used for a long time, and there are performance differences between different retired batteries, which can easily affect the battery pack during use, and even cause accidents such as combustion or explosion. Therefore, in the use of recombinant battery packs, timely and effective safety warnings are the basis for ensuring safe use.
[0003] In the prior art, the mainstream early warning system achieves battery safety early warning by setting different alarm levels based on parameters such as battery pressure difference and temperature difference. However, these parameters are usually detected by sensors, and their measurement results are easily affected by the environment, and the accuracy of the acquired parameters is poor. In addition, the existing early warning measures mainly obtain parameters for early warning when the battery is running. At this time, the battery system is already in a high-risk state and cannot achieve the effect of early warning.
[0004] Therefore, the existing technology has the problem that the accuracy and timeliness of warning parameters in the safety warning process of the recombinant battery pack are poor, making it difficult to provide accurate and timely safety warnings for the recombinant battery pack. Summary of the invention
[0005] In view of this, it is necessary to provide a recombinant battery pack safety warning method, device, electronic device and medium to solve the technical problem in the prior art that, during the safety warning process of the recombinant battery pack, the accuracy and timeliness of the warning parameters are poor, making it difficult to provide accurate and timely safety warnings for the recombinant battery pack.
[0006] In order to solve the above technical problems, on the one hand, the present invention provides a recombinant battery pack safety early warning method, comprising: Obtain a historical charging change curve of the reassembled battery pack to be tested, and determine a historical charging curve deviation index of the battery to be tested based on the historical charging change curve; Iteratively training the initial deviation index prediction network according to the historical charging curve deviation index to obtain a fully trained curve deviation index prediction network, and obtaining the curve deviation index prediction value according to the output of the fully trained curve deviation index prediction network; If the curve deviation index prediction value is higher than the preset safety threshold, a safety warning will be issued for the reorganized battery pack to be tested.
[0007] In a possible implementation, the historical charging variation curve includes a constant current charging voltage variation curve and a constant voltage charging current variation curve.
[0008] In a possible implementation, determining a historical charging curve deviation index of a battery to be tested according to a historical charging change curve includes: The average voltage of the recombinant battery pack to be tested during the first constant current charging is used as the reference voltage, and the average current change rate of the recombinant battery pack to be tested during the first constant voltage charging is used as the reference current rate; The voltage consistency index of the recombinant battery pack to be tested is obtained by performing consistency calculation based on the constant current charging voltage variation curve and the reference voltage; The current consistency index of the recombinant battery pack to be tested is obtained by performing consistency calculation based on the constant voltage charging current change curve and the reference current rate; The voltage consistency index and the current consistency index are weighted and combined to obtain a historical charging curve deviation index of the battery to be tested.
[0009] In a possible implementation, the voltage consistency index and the current consistency index are weighted and combined to obtain a historical charging curve deviation index of the battery to be tested, including: Determine the combined weight of the voltage consistency index and the current consistency index according to the constant current charging time and the constant voltage charging time of the battery to be tested; The voltage consistency index and the current consistency index are weighted and combined according to the combined weight to obtain the historical charging curve deviation index of the battery to be tested.
[0010] In a possible implementation, iteratively training an initial curve deviation index prediction network according to historical charging curve deviation indexes to obtain a fully trained curve deviation index prediction network includes: Construct curve deviation index time series training data based on historical charging curve deviation index; An initial curve deviation index prediction network is constructed, and the curve deviation index time series training data is input into the initial curve deviation index prediction network. The initial curve deviation index prediction network is iteratively optimized based on the whale optimization algorithm to obtain a fully trained curve deviation index prediction network.
[0011] In a possible implementation, constructing curve deviation index time series training data according to the historical charging curve deviation index includes: Arrange the historical charging curve deviation indicators according to the recording time to obtain the time series indicator data; The time series indicator data is slidingly sampled according to the preset sliding window value to obtain input data, and the time series indicator data at the next moment of each input data is used as output data, and the curve deviation indicator time series training data is constructed according to the input data and the output data.
[0012] In a possible implementation, the initial curve deviation index prediction network is iteratively optimized based on the whale optimization algorithm to obtain a fully trained curve deviation index prediction network, including: The initial population of the whale optimization algorithm is constructed based on the network parameters predicted by the initial curve deviation index; The initial population is sequentially subjected to simulations of surrounding prey behavior, bubble net attack behavior and prey search behavior to update the initial population and obtain an optimized population; The optimized population is substituted into the initial curve deviation index prediction network, and the training error of the optimized population is determined according to the curve deviation index time series training data. The optimization process is iterated until the training error reaches the preset error threshold, and a fully trained curve deviation index prediction network is obtained.
[0013] On the other hand, the present invention also provides a recombinant battery pack safety warning device, comprising: A historical index acquisition unit, used to acquire a historical charging change curve of the reorganized battery pack to be detected, and determine a historical charging curve deviation index of the battery to be detected according to the historical charging change curve; A deviation index prediction unit, used for iteratively training an initial deviation index prediction network according to a historical charging curve deviation index to obtain a fully trained curve deviation index prediction network, and obtaining a curve deviation index prediction value according to an output of the fully trained curve deviation index prediction network; The safety warning unit is used to issue a safety warning to the reorganized battery pack to be tested if the predicted value of the curve deviation index is higher than a preset safety threshold.
[0014] On the other hand, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned reorganized battery pack safety warning method is implemented.
[0015] On the other hand, the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned reorganized battery pack safety warning method is implemented.
[0016] The beneficial effect of the present invention is that in the safety early warning method for the recombinant battery pack provided by the present invention, the historical charging change curve of the recombinant battery pack to be detected is first obtained, and the historical charging curve deviation index of the battery to be detected is determined according to the historical charging change curve; then the initial deviation index prediction network is iteratively trained according to the historical charging curve deviation index to obtain a fully trained curve deviation index prediction network, and the curve deviation index prediction value is obtained according to the output of the fully trained curve deviation index prediction network; finally, if the curve deviation index prediction value is higher than the preset safety threshold, a safety early warning is issued for the recombinant battery pack to be detected. The present invention uses the historical charging curve deviation index of the battery pack charging observation station as an early warning parameter, and the collection of early warning parameters will not be affected by the environment, and has higher accuracy. At the same time, using the historical charging curve deviation index as an early warning parameter can warn the recombinant battery pack in advance before a fault occurs, and the early warning timeliness is high. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the 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 work.
[0018] Figure 1 A schematic diagram of a flow chart of an embodiment of a recombinant battery pack safety early warning method provided by the present invention; Figure 2 A schematic diagram of a process for determining a deviation index of a historical charging curve according to an embodiment of the present invention; Figure 3 A schematic diagram of a process for weighted merging of consistency indicators according to an embodiment of the present invention; Figure 4 A schematic diagram of a flow chart of a curve deviation index prediction network according to an embodiment of the present invention; Figure 5 A schematic diagram of a process for constructing training data according to an embodiment of the present invention; Figure 6 A schematic diagram of the iterative optimization process of the whale optimization algorithm according to an embodiment of the present invention; Figure 7 A schematic structural diagram of an embodiment of a recombinant battery pack safety warning device provided by the present invention; Figure 8 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION
[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0020] In the description of the embodiments of the present invention, unless otherwise specified, "multiple" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone.
[0021] The descriptions of "first" and "second" in the embodiments of the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" and "second" may explicitly or implicitly include at least one of the features.
[0022] Reference to "embodiments" herein 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 invention. The appearance of the 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.
[0023] The present invention provides a recombinant battery pack safety warning method, device, electronic device and medium, which are described below respectively.
[0024] Figure 1 A schematic diagram of a process flow of an embodiment of a recombinant battery pack safety warning method provided by the present invention, as shown in FIG. Figure 1 As shown, the reorganized battery pack safety warning method includes: S101, obtaining a historical charging change curve of the recombinant battery pack to be tested, and determining a historical charging curve deviation index of the battery to be tested according to the historical charging change curve; S102, iteratively training an initial deviation index prediction network according to historical charging curve deviation indexes to obtain a fully trained curve deviation index prediction network, and obtaining a curve deviation index prediction value according to an output of the fully trained curve deviation index prediction network; S103: If the predicted value of the curve deviation index is higher than a preset safety threshold, a safety warning is issued for the reorganized battery pack to be tested.
[0025] Compared with the prior art, the safety warning method for the recombinant battery pack provided in the embodiment of the present invention first obtains the historical charging change curve of the recombinant battery pack to be detected, and determines the historical charging curve deviation index of the battery to be detected based on the historical charging change curve; then, the initial deviation index prediction network is iteratively trained based on the historical charging curve deviation index to obtain a fully trained curve deviation index prediction network, and the curve deviation index prediction value is obtained based on the output of the fully trained curve deviation index prediction network; finally, if the curve deviation index prediction value is higher than the preset safety threshold, a safety warning is issued for the recombinant battery pack to be detected. The present invention uses the historical charging curve deviation index of the battery pack charging observation station as a warning parameter, and the collection of warning parameters will not be affected by the environment, and has higher accuracy. At the same time, using the historical charging curve deviation index as a warning parameter can warn the recombinant battery pack in advance before a fault occurs, and the warning timeliness is high.
[0026] In some embodiments of the present invention, the historical charging variation curve includes a constant current charging voltage variation curve and a constant voltage charging current variation curve.
[0027] In some embodiments of the present invention, Figure 2 FIG. 1 is a flow chart of determining a historical charging curve deviation index according to an embodiment of the present invention. Figure 2 As shown, determining the historical charging curve deviation index of the battery to be tested according to the historical charging change curve includes: S201, taking the average voltage of the recombinant battery pack to be tested during the first constant current charging as the reference voltage, and taking the average current change rate of the recombinant battery pack to be tested during the first constant voltage charging as the reference current rate; S202, performing consistency calculation according to the constant current charging voltage variation curve and the reference voltage to obtain a voltage consistency index of the recombinant battery pack to be tested; S203, performing consistency calculation according to the constant voltage charging current variation curve and the reference current rate to obtain a current consistency index of the recombinant battery pack to be tested; S204 , weightedly combining the voltage consistency index and the current consistency index to obtain a historical charging curve deviation index of the battery to be tested.
[0028] Specifically, the charging process of the recombinant battery pack includes two parts: constant current charging and constant voltage charging. The embodiment determines the warning parameters of the battery safety warning by respectively collecting the voltage change curve during constant current charging and the current change curve during constant voltage charging during the battery pack charging process.
[0029] Among them, for the constant current charging process, the embodiment records the first constant current charging of the recombinant battery pack time, Moment and The voltage value corresponding to the moment , and , indicating the different stages of constant current charging, and defining the average voltage of all recombinant battery packs to be tested at different times during the first charging as the reference voltage, the formula is expressed as:
[0030] in, express The average voltage of the reassembled battery pack when it is first charged. express Moment The voltage value of a reassembled battery pack when it is charged for the first time. Indicates the number of battery packs, Moment and The calculation of the average voltage corresponding to the time is similar.
[0031] Then the embodiment calculates the During the first charge, the discreteness of the voltage values at the three locations and the reference voltage is obtained. During the constant current charging, the voltage consistency index , the formula is:
[0032] in, Indicates the battery pack The deviation degree of voltage curve during the constant current charging, Indicates the number of battery packs, , and Respectively Battery Pack , and Voltage values at three moments. The smaller it is, the tighter the voltage curve is during constant current charging and the better the consistency is.
[0033] For the constant voltage charging process, the current changes significantly, so the embodiment uses the change of the current curve to characterize the consistency of this process. The embodiment defines the average current change rate of all the recombinant battery packs to be tested during the first constant voltage charging as the reference current rate, which is expressed as:
[0034]
[0035] in, represents the reference current rate, Indicates The current change rate of a battery pack during the first constant voltage charging.
[0036] Then the embodiment calculates the During the first charge, the degree of dispersion of the current change rate and the reference current rate is obtained. During the constant voltage charging, the current consistency index , the formula is:
[0037] in, is the reference current rate, For the Battery Pack The current change rate during constant voltage charging is For battery pack The degree of deviation of the current curve during constant voltage charging.
[0038] Then, the embodiment performs weighted combination of the voltage consistency index and the current consistency index to obtain a historical charging curve deviation index of the battery to be detected.
[0039] In some embodiments of the present invention, Figure 3 FIG. 1 is a flow chart of weighted merging of consistency indicators according to an embodiment of the present invention. Figure 3 As shown, the voltage consistency index and the current consistency index are weighted and combined to obtain the historical charging curve deviation index of the battery to be tested, including: S301, determining a combined weight of a voltage consistency index and a current consistency index according to a constant current charging time and a constant voltage charging time of a battery to be tested; S302: weightedly combine the voltage consistency index and the current consistency index according to the combination weight to obtain a historical charging curve deviation index of the battery to be tested.
[0040] Specifically, considering that different types of batteries have different proportions of constant current and constant voltage charging time during the battery charging process, the voltage consistency index of constant current charging and the current consistency index of constant voltage charging provide different effects on battery safety warning. For this reason, according to the proportion of constant current and constant voltage charging time, different weights are matched to the voltage consistency index and the current consistency index respectively, and the consistency index is weighted and combined according to the weight to obtain the historical charging curve deviation index, which is expressed as follows:
[0041] in, Indicates that the historical charging curve deviates from the indicator, is the weight, defined as The ratio of the constant current charging time to the sum of the constant voltage and constant current charging times during the first charge.
[0042] In some embodiments of the present invention, Figure 4 FIG. 4 is a flow chart of a curve deviation index prediction network according to an embodiment of the present invention. Figure 4 As shown, the initial curve deviation index prediction network is iteratively trained according to the historical charging curve deviation index to obtain a fully trained curve deviation index prediction network, including: S401, constructing curve deviation index time series training data according to historical charging curve deviation index; S402, constructing an initial curve deviation index prediction network, inputting the curve deviation index time series training data into the initial curve deviation index prediction network, and iteratively optimizing the initial curve deviation index prediction network based on the whale optimization algorithm to obtain a fully trained curve deviation index prediction network.
[0043] Specifically, in the embodiment, the curve deviation index time series training data is constructed according to the historical charging curve deviation index to train the curve deviation index prediction network, and the curve deviation index of the battery in the subsequent charging process is predicted by the trained curve deviation index prediction network. Greater than the safety threshold If the battery is at a low voltage, it is considered that there is a safety hazard and the battery pack needs to be repaired and replaced before the next charge.
[0044] During the training process, the neural network used in the embodiment consists of three parts: input layer, hidden layer and output layer. During the prediction process, the neural network passes the curve deviation index time series training data through the input layer to the hidden layer to obtain the input variable of the hidden layer. :
[0045] in, The input layer nodes to the hidden layer The weight of the node, The input layer The charging curve deviates from the index value. The hidden layer The error of the nodes, is the sliding window value.
[0046] The input variables of the hidden layer are activated by the activation function to obtain the output variables of the hidden layer. :
[0047] in, represents the activation function of the hidden layer.
[0048] The output variables of the hidden layer are passed to the output layer and become the input variables of the output layer. :
[0049] in, represents the hidden layer Node to the output layer The weights between nodes, The output layer The error of the nodes, is the number of hidden layer nodes.
[0050] The input variables of the output layer are passed through the activation function to finally obtain the output variables of the output layer. :
[0051] in, represents the activation function of the output layer.
[0052] In some embodiments of the present invention, Figure 5 FIG. 1 is a flow chart of constructing training data according to an embodiment of the present invention. Figure 5 As shown, the curve deviation index time series training data is constructed according to the historical charging curve deviation index, including: S501, arranging the historical charging curve deviation indexes according to the recording time to obtain time series index data; S502, sliding sampling is performed on the time series indicator data according to the preset sliding window value to obtain input data, and the time series indicator data at the next moment of each input data is used as output data, and curve deviation indicator time series training data is constructed according to the input data and the output data.
[0053] Specifically, the curve deviation index prediction network records the charging curve deviation index R value of each charging as a timing signal, uses the existing R value as the input signal of the curve deviation index prediction network, selects the first k R values as a group, and regards them as input to predict the R value of k+1 charges, so as to predict the charging curve deviation index R value of the reorganized battery pack in the future charging process.
[0054] To this end, in the process of constructing the training set, the embodiment first sorts the historical charging curve deviation indicators according to the recording time to obtain the time series indicator data, and then sorts the historical charging curve deviation indicators according to the preset sliding window value. , and change the 1st to the R value as input, R values are taken as output to form a set of data; R value as input, R value as output, forming the second set of data, and so on, finally getting a The group input layer is , a dataset with an output layer of 1.
[0055] In some embodiments of the present invention, Figure 6 Schematic diagram of the iterative optimization process of the whale optimization algorithm according to an embodiment of the present invention. Figure 6 As shown, based on the whale optimization algorithm, the initial curve deviation index prediction network is iteratively optimized to obtain a fully trained curve deviation index prediction network, including: S601, constructing an initial population of a whale optimization algorithm based on network parameters predicted by an initial curve deviation index; S602, performing a prey encirclement behavior simulation, a bubble net attack behavior simulation, and a prey search behavior simulation on the initial population in sequence to update the initial population to obtain an optimized population; S603, substituting the optimized population into the initial curve deviation index prediction network, determining the training error of the optimized population according to the curve deviation index time series training data, iterating the optimization process until the training error reaches a preset error threshold, and obtaining a fully trained curve deviation index prediction network.
[0056] Specifically, during the network training process, the embodiment uses the whale optimization algorithm to optimize the network parameters of the curve deviation index prediction network. The embodiment first converts the initial weights and thresholds to be optimized of the curve deviation index prediction network into the position vector of the whale optimization algorithm, generates an initial population, calculates the individual fitness value, finds the position of the optimal fitness value, records the position vector and uses it as the current optimal individual position. .
[0057] Then the optimization process of the whale optimization algorithm mainly includes the behavioral simulation of three steps: surrounding prey, bubble net attack and searching for prey.
[0058] Among them, in the simulation of surrounding prey behavior, the whale closest to the prey is first taken as the best whale, that is, the current optimal solution. Other whales are self-updated as the position of the best whale changes. The formula corresponding to the surrounding process is expressed as follows:
[0059]
[0060] in, is the distance vector between the current optimal solution and other selected solutions, is the number of iterations, is the position vector of the current best whale, is the position vector of other whales. and is the coefficient vector, and the formula is expressed as:
[0061]
[0062] in, for A random number between is the convergence factor, and it will gradually decrease linearly from 2 to 0 as the number of iterations t increases.
[0063] In the bubble net attack behavior simulation, after locking onto the prey, the whale begins to continuously narrow the encirclement while swimming upward in a spiral shape toward the prey, and the probability of these two behaviors occurring is the same. The new position will randomly appear somewhere between the previous position and the current optimal solution position as the search continues to narrow. The updated whale position model formula is as follows:
[0064] in, is the logarithmic spiral shape constant; A random number between -1 and 1.
[0065] In the prey search behavior simulation, the whale will randomly select a whale from the population to approach, and update the positions of other whales according to the position of the selected whale, forcing the whale to deviate from the prey and find a more suitable prey. This can enhance the algorithm's search ability and enable the algorithm to perform global optimization. The formula is expressed as:
[0066]
[0067] in, Randomly select a whale location to approach.
[0068] After optimizing and updating the network parameters of the curve deviation index prediction network through the whale optimization algorithm, the updated network parameters are substituted into the training error to determine whether the preset error threshold is met. If not, the network parameters of the curve deviation index prediction network are continuously optimized and iteratively updated until the error threshold is met or the maximum number of iterations is obtained.
[0069] In summary, in order to make accurate and timely safety warnings. The present invention first obtains the historical charging change curve of the recombinant battery pack to be detected, and determines the historical charging curve deviation index of the battery to be detected according to the historical charging change curve; then, the initial deviation index prediction network is iteratively trained according to the historical charging curve deviation index to obtain a fully trained curve deviation index prediction network, and the curve deviation index prediction value is obtained according to the output of the fully trained curve deviation index prediction network; finally, if the curve deviation index prediction value is higher than the preset safety threshold, a safety warning is issued for the recombinant battery pack to be detected. The present invention uses the historical charging curve deviation index of the battery pack charging observation station as a warning parameter, and the collection of warning parameters will not be affected by the environment, and has higher accuracy. At the same time, using the historical charging curve deviation index as a warning parameter can warn the recombinant battery pack in advance before a fault occurs, and the warning timeliness is high.
[0070] In order to better implement the recombinant battery pack safety early warning method in the embodiment of the present invention, based on the recombinant battery pack safety early warning method, correspondingly, Figure 7 As shown, the present invention also provides a recombinant battery pack safety warning device, and the recombinant battery pack safety warning device 700 includes: A historical indicator acquisition unit 701 is used to acquire a historical charging change curve of the recombinant battery pack to be detected, and determine a historical charging curve deviation index of the battery to be detected according to the historical charging change curve; The deviation index prediction unit 702 is used to iteratively train the initial deviation index prediction network according to the historical charging curve deviation index to obtain a fully trained curve deviation index prediction network, and obtain the curve deviation index prediction value according to the output of the fully trained curve deviation index prediction network; The safety warning unit 703 is used to issue a safety warning to the recombinant battery pack to be detected if the predicted value of the curve deviation index is higher than a preset safety threshold.
[0071] The recombinant battery pack safety warning device 700 provided in the above embodiment can implement the technical solution described in the above embodiment of the recombinant battery pack safety warning method. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above embodiment of the recombinant battery pack safety warning method, which will not be repeated here.
[0072] like Figure 8 As shown, the present invention also provides an electronic device 800. The electronic device 800 includes a processor 801, a memory 802 and a display 803. Figure 8 Only some components of the electronic device 800 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.
[0073] In some embodiments, the processor 801 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 802, such as the reassembled battery pack safety warning method of the present invention.
[0074] In some embodiments, the processor 801 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 801 may be local or remote. In some embodiments, the processor 801 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.
[0075] In some embodiments, the memory 802 may be an internal storage unit of the electronic device 800, such as a hard disk or memory of the electronic device 800. In other embodiments, the memory 802 may also be an external storage device of the electronic device 800, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 800.
[0076] Furthermore, the memory 802 may include both an internal storage unit of the electronic device 800 and an external storage device. The memory 802 is used to store application software installed in the electronic device 800 and various data.
[0077] In some embodiments, the display 803 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 803 is used to display information of the electronic device 800 and to display a visual user interface. The components 801-803 of the electronic device 800 communicate with each other via a system bus.
[0078] In one embodiment, when the processor 801 executes the reassembled battery pack safety warning program in the memory 802, the following steps may be implemented: Obtain a historical charging change curve of the reassembled battery pack to be tested, and determine a historical charging curve deviation index of the battery to be tested based on the historical charging change curve; Iteratively training the initial deviation index prediction network according to the historical charging curve deviation index to obtain a fully trained curve deviation index prediction network, and obtaining the curve deviation index prediction value according to the output of the fully trained curve deviation index prediction network; If the curve deviation index prediction value is higher than the preset safety threshold, a safety warning will be issued for the reorganized battery pack to be tested.
[0079] It should be understood that: when the processor 801 executes the reassembled battery pack safety warning program in the memory 802, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.
[0080] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 800 mentioned, and the electronic device 800 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may 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 present invention, the electronic device 800 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).
[0081] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions of the recombinant battery pack safety warning method provided in the above-mentioned method embodiments can be implemented.
[0082] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.
[0083] The above is a detailed introduction to the recombinant battery pack safety warning method, device, electronic device and storage medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.
Claims
1. A recombinant battery pack safety early warning method, characterized in that: include: Obtaining a historical charging change curve of the recombinant battery pack to be detected, and determining a historical charging curve deviation index of the battery to be detected according to the historical charging change curve; Iteratively training an initial deviation index prediction network according to the historical charging curve deviation index to obtain a fully trained curve deviation index prediction network, and obtaining a curve deviation index prediction value according to the output of the fully trained curve deviation index prediction network; If the predicted value of the curve deviation index is higher than a preset safety threshold, a safety warning is issued for the recombinant battery pack to be detected.
2. The recombinant battery pack safety early warning method according to claim 1, characterized in that: The historical charging change curve includes a constant current charging voltage change curve and a constant voltage charging current change curve.
3. The recombinant battery pack safety early warning method according to claim 2, characterized in that: Determining the historical charging curve deviation index of the battery to be tested according to the historical charging change curve includes: The average voltage of the recombinant battery pack to be tested during the first constant current charging is used as the reference voltage, and the average current change rate of the recombinant battery pack to be tested during the first constant voltage charging is used as the reference current rate; Performing consistency calculation according to the constant current charging voltage variation curve and the reference voltage to obtain a voltage consistency index of the recombinant battery pack to be tested; Performing consistency calculation according to the constant voltage charging current change curve and the reference current rate to obtain a current consistency index of the recombinant battery pack to be tested; The voltage consistency index and the current consistency index are weighted and combined to obtain a historical charging curve deviation index of the battery to be detected.
4. The recombinant battery pack safety early warning method according to claim 3, characterized in that: The weighted combination of the voltage consistency index and the current consistency index to obtain the historical charging curve deviation index of the battery to be detected includes: Determining a combined weight of the voltage consistency index and the current consistency index according to the constant current charging time and the constant voltage charging time of the battery to be detected; The voltage consistency index and the current consistency index are weighted and combined according to the combined weight to obtain a historical charging curve deviation index of the battery to be detected.
5. The recombinant battery pack safety early warning method according to claim 1, characterized in that: The iterative training of the initial curve deviation index prediction network according to the historical charging curve deviation index to obtain a fully trained curve deviation index prediction network includes: Constructing curve deviation index time series training data according to the historical charging curve deviation index; An initial curve deviation index prediction network is constructed, the curve deviation index time series training data is input into the initial curve deviation index prediction network, and the initial curve deviation index prediction network is iteratively optimized based on the whale optimization algorithm to obtain a fully trained curve deviation index prediction network.
6. The recombinant battery pack safety early warning method according to claim 5, characterized in that: The constructing curve deviation index time series training data according to the historical charging curve deviation index includes: Arranging the historical charging curve deviation indexes according to the recording time to obtain time series index data; The timing indicator data is slidingly sampled according to a preset sliding window value to obtain input data, and the timing indicator data at the next moment of each input data is used as output data, and curve deviation indicator timing training data is constructed according to the input data and the output data.
7. The recombinant battery pack safety early warning method according to claim 5, characterized in that: The iterative optimization of the initial curve deviation index prediction network based on the whale optimization algorithm to obtain a fully trained curve deviation index prediction network includes: Constructing an initial population of a whale optimization algorithm based on the network parameters of the prediction network according to the initial curve deviation index; The initial population is sequentially subjected to prey encirclement behavior simulation, bubble net attack behavior simulation and prey search behavior simulation to update the initial population to obtain an optimized population; The optimized population is substituted into the initial curve deviation index prediction network, the training error of the optimized population is determined according to the curve deviation index time series training data, and the optimization process is iterated until the training error reaches a preset error threshold to obtain a fully trained curve deviation index prediction network.
8. A recombinant battery pack safety warning device, characterized in that: include: A historical index acquisition unit, used to acquire a historical charging change curve of the recombinant battery pack to be detected, and determine a historical charging curve deviation index of the battery to be detected according to the historical charging change curve; A deviation index prediction unit, used for iteratively training an initial deviation index prediction network according to the historical charging curve deviation index to obtain a fully trained curve deviation index prediction network, and obtaining a curve deviation index prediction value according to the output of the fully trained curve deviation index prediction network; A safety warning unit is used to issue a safety warning to the recombinant battery pack to be detected if the predicted value of the curve deviation index is higher than a preset safety threshold.
9. An electronic device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the reorganized battery pack safety warning method according to any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the reorganized battery pack safety warning method according to any one of claims 1 to 7 is implemented.
