A secondary battery distributed dynamic balancing and safety management and control method, system, device and storage medium

Abstract

The present application relates to the technical field of battery management, and relates to a secondary battery distributed dynamic balancing and safety management and control method, system, device and storage medium; wherein the secondary battery distributed dynamic balancing and safety management and control method comprises: collecting operating state parameter data of a secondary battery pack at a preset sampling frequency, the operating state parameter data being time series data; reconstructing the operating state parameter data by using a sliding window technology to generate a plurality of time series samples, each time series sample containing operating state parameters within a continuous time step; inputting the plurality of time series samples into a trained battery health prediction model, the battery health prediction model outputting health score prediction values and future period load power prediction values of each battery monomer; and for each battery monomer, determining a balancing and deployment strategy and a safety protection strategy according to the health score prediction value and the future period load power prediction value of the battery monomer.

Description

Technical Field

[0001] This invention relates to the field of battery management technology, and in particular to a method, system, device and storage medium for distributed dynamic balancing and safety control of secondary batteries. Background Technology

[0002] With the rapid development of the new energy vehicle industry, my country's lithium-ion battery production has increased year by year, and the corresponding number of retired batteries has also been rising annually. Battery reuse has become an important measure to practice green and low-carbon development and enhance the value of batteries throughout their entire life cycle. After being retired from new energy vehicles, lithium-ion power batteries, although no longer meeting the stringent requirements for range and power, still retain approximately 70%-80% of their remaining capacity. These can be "reused" in energy storage base stations, low-speed electric vehicles, and construction machinery—applications with relatively lower energy density and power requirements. Retired lithium-ion power batteries used in this way are called secondary batteries. Distributed BMS (Battery Management System), as the core control unit for reused batteries, plays a crucial role in ensuring the safety of battery packs and extending their lifespan. Existing BMS control schemes for reused batteries mostly adopt the basic control architecture of new batteries, using a centralized management architecture. They lack dedicated control mechanisms designed for the core characteristics of retired batteries, resulting in many limitations in practical applications, specifically: First, the accuracy of health assessment is low. Traditional BMS only collects voltage and current, and cannot directly measure the actual capacity. Relying on indirect estimation leads to the accumulation of errors. Second, the energy utilization efficiency is low, the dispersion of retired cells is large, and the traditional balancing strategy is executed according to the lowest capacitance / current, resulting in energy waste and the risk of over-discharge / overheating. Third, it is difficult to achieve effective balance. The fixed threshold strategy cannot adapt to dynamic operating conditions, and the weakest link effect is amplified. Fourth, the disconnect between safety and resource allocation, and the separation of safety status monitoring and energy balance scheduling functions, prevents rapid and coordinated strategy adjustments, posing a risk of thermal runaway and increasing safety hazards. Summary of the Invention

[0003] This application aims to at least solve the technical problems existing in the prior art, and to provide a method, system, device and storage medium for distributed dynamic balancing and safety management of secondary batteries.

[0004] In a first aspect, the present invention provides a method for distributed dynamic balancing and safety management of secondary batteries, the method comprising: The operating status parameter data of the secondary battery pack is collected at a preset sampling frequency, and the operating status parameter data is time-series data. The sliding window technique is used to reconstruct the running state parameter data, generating several time series samples. Each time series sample contains running state parameters within a continuous time step. Several time series samples are input into the trained battery health prediction model. The battery health prediction model is used to analyze the time series samples to extract the spatial correlation features between the health indicators of each battery cell and the performance difference features between different battery cells. Based on the spatial correlation features between the health indicators of each battery cell and the performance difference features between different battery cells, the model outputs the predicted health score of each battery cell and the predicted load power for the future period. For each battery cell, a balanced allocation strategy and a safety protection strategy are determined based on the predicted health score of the battery cell and the predicted load power for future periods.

[0005] Optionally, the operating status parameters include at least one of the following: individual cell voltage, individual cell temperature, individual cell internal resistance, and load power.

[0006] Optionally, the method further includes a training step for the battery health prediction model: Obtain the training dataset, which includes historical operating state parameter data of one or more secondary battery packs; Construct the network structure for a battery health prediction model; Train the battery health prediction model network using the training dataset until the training termination condition is met: In each training iteration, the loss function is determined based on the output of the battery health prediction model, and the network parameters of the battery health prediction model are optimized based on the loss function to obtain the final battery health prediction model.

[0007] Optionally, mean squared error can be used as the loss function.

[0008] Optionally, the battery health prediction model includes a cascaded Faster R-CNN module and a temporal convolutional network module; the Faster R-CNN module is used to parse time series samples to extract spatial correlation features between health indicators of each battery cell and performance difference features between different battery cells; the temporal convolutional network module is used to capture the long-term temporal dependencies of the spatial correlation features and performance difference features output by the Faster R-CNN module, to obtain battery performance change information and battery load change information, and to determine the predicted health score and predicted load power of each battery cell for future periods based on the battery performance change information and battery load change information.

[0009] Optionally, the Faster R-CNN module includes: a first two-dimensional convolutional layer, a second two-dimensional convolutional layer, and a max pooling layer; the first two-dimensional convolutional layer is configured with 32 3×3 convolutional kernels, the second two-dimensional convolutional layer is configured with 64 3×3 convolutional kernels, and the max pooling layer uses a 2×2 pooling window.

[0010] Optionally, before reconstructing the runtime status parameter data using the sliding window technique, the following steps are also included: The collected operational status parameter data is cleaned to remove outliers, and the cleaned data is normalized to obtain normalized operational status parameter data. The sliding window technique is used to reconstruct the normalized operational status parameter data to obtain several time series samples.

[0011] Secondly, the present invention provides a distributed dynamic balancing and safety management system for secondary batteries, the system comprising: The acquisition module is used to collect the operating status parameter data of the secondary battery pack at a preset sampling frequency. The operating status parameter data is time-series data. The reconstruction module is used to reconstruct the running status parameter data using the sliding window technique, generating several time series samples, each containing running status parameters within a continuous time step; The prediction module is used to input several time series samples into the trained battery health prediction model. The battery health prediction model is used to analyze the time series samples to extract the spatial correlation features between the health indicators of each battery cell and the performance difference features between different battery cells. Based on the spatial correlation features between the health indicators of each battery cell and the performance difference features between different battery cells, it outputs the predicted health score of each battery cell and the predicted load power for the future period. The output module is used to determine a balanced allocation strategy and a safety protection strategy for each battery cell based on the predicted health score of the battery cell and the predicted load power for future periods.

[0012] Thirdly, the present invention provides an electronic device, the electronic device comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the aforementioned secondary battery distributed dynamic balancing and safety management method.

[0013] Fourthly, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the above-described method for distributed dynamic balancing and safety management of secondary batteries.

[0014] In summary, this application includes the following beneficial technical effects: By collecting time-series operational status parameter data at a preset sampling frequency and reconstructing time-series samples containing operational status parameters within continuous time steps using a sliding window technique, this data is then input into a trained battery health prediction model. The model analyzes the time-series samples to extract spatial correlation features between health indicators of individual battery cells and performance differences between different battery cells, thereby outputting predicted health scores and predicted load power values ​​for each battery cell. Furthermore, for each battery cell, a balanced allocation strategy and a safety protection strategy are simultaneously determined based on these predicted values. Thus, this solution achieves the following technical effects: improving the accuracy of battery health status assessment by utilizing temporal information within continuous time steps and spatial differences between cells; achieving proactive load adaptation and active energy scheduling based on predicted load values ​​for future periods, reducing response lag; and using health scores and load predictions together as decision-making bases for balanced allocation and safety protection, promoting synergistic linkage between safety protection and balanced control, and reducing safety hazards caused by strategy conflicts or scheduling lags. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating a distributed dynamic balancing and safety management method for secondary batteries provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of an electronic device that implements the distributed dynamic balancing and safety management method for secondary batteries according to an embodiment of the present invention.

[0016] Reference numerals: 10, processor; 11, memory; 12, communication bus; 13, communication interface.

[0017] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0019] In the description of this invention, it should be understood that the terms "longitudinal", "lateral", "up", "down", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0020] In the description of this invention, unless otherwise specified and limited, it should be noted that the terms "installation", "connection" and "linking" should be interpreted broadly. For example, they can refer to mechanical or electrical connections, or internal connections between two components. They can be direct connections or indirect connections through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms according to the specific circumstances.

[0021] Reference Figure 1 The diagram shown is a flowchart illustrating a distributed dynamic balancing and safety management method for secondary batteries according to an embodiment of the present invention. In this embodiment, the distributed dynamic balancing and safety management method for secondary batteries includes: S1. Collect the operating status parameter data of the secondary battery pack at a preset sampling frequency. The operating status parameter data is time-series data.

[0022] Operating status parameters include at least one of the following: individual cell voltage, individual cell temperature, individual cell internal resistance, and load power. In practice, these parameters are acquired using a non-inductive Hall current sensor, a high-precision thermistor array, and a CAN bus.

[0023] In a preferred embodiment of this example, after collecting the initial operating state parameter data of the secondary battery pack at a preset sampling frequency, the initial operating state parameter data is cleaned to remove outliers, and the cleaned data is normalized to obtain the final operating state parameter data. The normalized operating state parameter data is reconstructed using a sliding window technique to obtain several time series samples.

[0024] Specifically, the 3σ principle is used to identify and eliminate outliers caused by sensor malfunctions or communication errors, such as sudden voltage changes, abnormal temperatures, and negative internal resistance. For brief data loss, linear interpolation is used to fill in the gaps and ensure the continuity of the time series.

[0025] The cleaned data is then normalized. Due to the significant differences in the dimensions and numerical ranges of different features (e.g., voltage 0-5V, temperature -20-80℃, internal resistance in the mΩ range), to avoid gradient explosion or getting trapped in local optima during neural network training, this embodiment uses Min-Max normalization to map all feature values ​​to the [0,1] interval. The calculation formula is as follows: The reason for choosing Min-Max normalization is that input features such as voltage, temperature, and internal resistance have clear physical limits, making them suitable for Min-Max normalization. It can accurately preserve the relative relationships of the data and completely retain the distribution pattern of the original data.

[0026] S2. The sliding window technique is used to reconstruct the running status parameter data to generate several time series samples. Each time series sample contains running status parameters within a continuous time step.

[0027] In a preferred embodiment of this invention, the sliding window length is set to 60 time steps (sampling frequency 10Hz, corresponding to 6 seconds). The 60 sets of continuous data within the window (including voltage, temperature, internal resistance, and load power) are considered as a time series sample. The window slides along the time axis with a fixed step size, generating a large number of time series samples. Several of these time series samples can be used to predict the battery's health status or for subsequent model training. The reason for choosing 60 time steps in this application is that the charge / discharge state and load changes of retired batteries are mostly short-term dynamic processes, and a 6-second window length is sufficient to capture a complete dynamic operating condition event; at the same time, the window length is moderate, balancing computational complexity and hardware resource adaptability.

[0028] S3. Input several time series samples into the trained battery health prediction model. The battery health prediction model is used to analyze the time series samples to extract the spatial correlation features between the health indicators of each battery cell and the performance difference features between different battery cells. Based on the spatial correlation features between the health indicators of each battery cell and the performance difference features between different battery cells, the model outputs the predicted health score of each battery cell and the predicted load power for the future period.

[0029] S4. For each battery cell, determine the balancing strategy and safety protection strategy based on the predicted health score of the battery cell and the predicted load power for future periods.

[0030] Specifically, when a cell has a high health score, it is prioritized for high-load tasks; when a cell has a health score below a preset threshold, its output is limited or it is isolated; when the load power prediction indicates that a high load surge will occur in the future, the balancing strategy is adjusted in advance to avoid over-discharge or insufficient power supply.

[0031] In practical applications, the trained battery health prediction model and its weight file can be lightweighted, compressed, and optimized using model conversion tools (such as TensorRT) and deployed to the vehicle's intelligent control unit within the distributed BMS. During system operation, battery status data is collected in real time, preprocessed in real time, and inferred and predicted in real time. Based on the prediction results, equalization control commands and safety protection commands are generated, realizing the fully automated operation of distributed dynamic equalization allocation and safety management of secondary batteries.

[0032] In some examples of this embodiment, the distributed dynamic balancing and safety management method for secondary batteries also includes a training step for a battery health prediction model: S51. Obtain the training dataset.

[0033] The training dataset includes historical operating status parameter data of more than one secondary battery pack; the historical dataset is divided into training set (70%), validation set (15%) and test set (15%) in chronological order, ensuring that the data in the validation set and test set are later than the data in the training set.

[0034] S52. Construct the network structure for the battery health prediction model; The battery health prediction model includes a cascaded Faster R-CNN module and a temporal convolutional network module.

[0035] The Faster R-CNN module is used to parse time series samples to extract spatial correlation features between health indicators of individual battery cells and performance difference features between different battery cells. The temporal convolutional network module is used to capture the long-term temporal dependencies of spatial correlation features and performance difference features output by the Faster R-CNN module, obtain battery performance change information and battery load change information, and determine the health score prediction value and future load power prediction value of each battery cell based on the battery performance change information and battery load change information.

[0036] The Faster R-CNN module comprises a first two-dimensional convolutional layer, a second two-dimensional convolutional layer, and a max-pooling layer. The first two-dimensional convolutional layer has 32 3×3 convolutional kernels, the second two-dimensional convolutional layer has 64 3×3 convolutional kernels, and the max-pooling layer uses a 2×2 pooling window. The first two-dimensional convolutional layer with 32 3×3 kernels is used to initially extract spatial correlation features between various battery health indicators and capture performance differences between different battery cells. The second two-dimensional convolutional layer with 64 3×3 kernels is used to further abstract higher-level spatial features based on the features extracted in the first layer, improving feature representation capabilities. The ReLU activation function is used after each convolutional layer to introduce non-linearity and alleviate the gradient vanishing problem. The max-pooling layer uses a 2×2 pooling window to downsample the feature maps output by the convolutional layers, reducing data dimensionality and extracting key features. The Faster R-CNN module's function is to analyze time-series samples, extract spatial correlation features between health indicators of individual battery cells, and extract performance difference features between different battery cells.

[0037] The Temporal Convolutional Network (TCN) module contains a single TCN layer with 64 hidden units, which embeds an LSTM gating structure (including a forget gate, input gate, and output gate). The TCN module receives the feature vector sequence output by the Faster R-CNN module and captures long-term temporal dependencies in the feature vector sequence through temporal convolution operations, thereby obtaining information on battery performance changes and battery load changes.

[0038] The network structure of the battery health prediction model also includes an output layer, which contains a fully connected layer with 2 neurons. The output layer outputs the health score prediction value and the load power prediction value for the future period (in this embodiment, the load power prediction value for the next 30 minutes) for each battery cell, and uses a linear activation function.

[0039] S53. Train the battery health prediction model network using the training dataset until the training termination condition is met: In each training iteration, the loss function is determined based on the output of the battery health prediction model, and the network parameters of the battery health prediction model are optimized based on the loss function to obtain the final battery health prediction model.

[0040] In this embodiment, mean squared error (MSE) is used as the loss function to measure the difference between the predicted and the true values; the Adam optimizer is used, which has the advantage of adaptive learning rate; the batch size is set to 32; in each training session, the loss function value is determined based on the model's output (predicted health score and predicted load power), and the network parameters of the model are optimized based on the loss function until the training termination condition is met, resulting in the final battery health prediction model.

[0041] In this embodiment, the training termination condition is that the validation set performance converges or the preset maximum number of training rounds is reached. The initial number of iterations is set to 100, and an early stopping method is used to stop training when the validation set loss no longer decreases within 10 consecutive iterations, thus preventing the model from overfitting.

[0042] After training, the model is evaluated using a test set. The root mean square error (RMSE) and coefficient of determination between the predicted and actual values ​​are calculated. This is used to quantify the predictive accuracy of the model. In this embodiment, the coefficient of determination for health score prediction is... The coefficient of determination for load power prediction reaches 0.95. The RMSE for health score prediction and load power prediction was controlled at 0.02 and 0.3kW, respectively, reaching 0.97.

[0043] The trained battery health prediction model is lightweighted, compressed, and optimized using a model conversion tool (such as TensorRT), and then deployed to the intelligent control unit of the distributed BMS. BMS stands for Battery Management System.

[0044] In actual operation, the operating status parameter data of the secondary battery pack are collected in real time according to the steps of the distributed dynamic balancing and safety management method of the secondary battery in this application. The data is then cleaned, normalized, and reconstructed using a sliding window. The generated time series samples are input into the battery health prediction model in real time. The model outputs the predicted health score of each battery cell and the predicted load power for the next 30 minutes in real time.

[0045] For each battery cell, a balancing and safety protection strategy is determined based on its predicted health score and the predicted load power for future periods. Specifically, when a battery cell has a high health score, it is prioritized for handling high-load tasks; when a battery cell's health score is below a preset threshold, its output is limited or it is isolated; when the predicted load power indicates a high-load surge in the future, the balancing strategy is adjusted in advance to avoid over-discharge or insufficient power supply.

[0046] Based on the same inventive concept, one embodiment of the present invention provides a distributed dynamic balancing and safety management system for secondary batteries.

[0047] The distributed dynamic balancing and safety management system for secondary batteries described in this invention can be installed in electronic devices. According to the functions implemented, the distributed dynamic balancing and safety management system for secondary batteries includes: The acquisition module is used to collect the operating status parameter data of the secondary battery pack at a preset sampling frequency. The operating status parameter data is time-series data. The reconstruction module is used to reconstruct the running status parameter data using the sliding window technique, generating several time series samples, each containing running status parameters within a continuous time step; The prediction module is used to input several time series samples into the trained battery health prediction model. The battery health prediction model is used to analyze the time series samples to extract the spatial correlation features between the health indicators of each battery cell and the performance difference features between different battery cells. Based on the spatial correlation features between the health indicators of each battery cell and the performance difference features between different battery cells, it outputs the predicted health score of each battery cell and the predicted load power for the future period. The output module is used to determine a balanced allocation strategy and a safety protection strategy for each battery cell based on the predicted health score of the battery cell and the predicted load power for future periods.

[0048] The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0049] The various variations and specific examples of the secondary battery distributed dynamic balancing and safety management method provided in the above embodiments are also applicable to the secondary battery distributed dynamic balancing and safety management system of this embodiment. Through the foregoing detailed description of the secondary battery distributed dynamic balancing and safety management method, those skilled in the art can clearly understand the implementation method of the secondary battery distributed dynamic balancing and safety management system of this embodiment. For the sake of brevity, it will not be described in detail here.

[0050] This application also discloses an electronic device, such as Figure 2 The diagram shown is a structural schematic of an electronic device for a method of distributed dynamic balancing and safety management of secondary batteries according to an embodiment of the present invention. The electronic device may include at least one processor 10, a memory 11 communicatively connected to the at least one processor, a communication bus 12, and a communication interface 13. It may also include a computer program, such as a method program for distributed dynamic balancing and safety management of secondary batteries, stored in the memory 11 and executable on the processor 10.

[0051] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., methods for distributed dynamic balancing and safety management of secondary batteries), and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0052] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as code for methods and programs for distributed dynamic balancing and safety management of secondary batteries, but also to temporarily store data that has been output or will be output.

[0053] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0054] Communication interface 13 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), and optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0055] Figure 2 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 2 The structure shown does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0056] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to at least one processor 10 via a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be elaborated further here.

[0057] It should be understood that the embodiments are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0058] Furthermore, if the modules / units integrated into the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile.

[0059] This application provides a computer-readable storage medium, including, for example, any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM). The computer-readable storage medium stores a computer program that can be loaded by a processor and execute the secondary battery distributed dynamic balancing and safety management method described in the above embodiments.

[0060] In the description of this specification, the references to terms such as "an embodiment," "some embodiments," "example," "specific example," "a implementation," "a preferred implementation," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0061] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A method for distributed dynamic balancing and safety management of secondary batteries, characterized in that, The method includes: The operating status parameter data of the secondary battery pack is collected at a preset sampling frequency, and the operating status parameter data is time-series data. The sliding window technique is used to reconstruct the running state parameter data, generating several time series samples. Each time series sample contains running state parameters within a continuous time step. Several time series samples are input into the trained battery health prediction model. The battery health prediction model is used to analyze the time series samples to extract the spatial correlation features between the health indicators of each battery cell and the performance difference features between different battery cells. Based on the spatial correlation features between the health indicators of each battery cell and the performance difference features between different battery cells, the model outputs the predicted health score of each battery cell and the predicted load power for the future period. For each battery cell, a balanced allocation strategy and a safety protection strategy are determined based on the predicted health score of the battery cell and the predicted load power for future periods.

2. The distributed dynamic balancing and safety management method for secondary batteries as described in claim 1, characterized in that, The operating status parameters include at least one of the following: individual cell voltage, individual cell temperature, individual cell internal resistance, and load power.

3. The distributed dynamic balancing and safety management method for secondary batteries as described in claim 1, characterized in that, The method also includes a training step for the battery health prediction model: Obtain the training dataset, which includes historical operating state parameter data of one or more secondary battery packs; Construct the network structure for a battery health prediction model; Train the battery health prediction model network using the training dataset until the training termination condition is met: In each training iteration, the loss function is determined based on the output of the battery health prediction model, and the network parameters of the battery health prediction model are optimized based on the loss function to obtain the final battery health prediction model.

4. The distributed dynamic balancing and safety management method for secondary batteries as described in claim 3, characterized in that, The mean squared error is used as the loss function.

5. The distributed dynamic balancing and safety management method for secondary batteries as described in any one of claims 1 to 4, characterized in that, The battery health prediction model includes a cascaded Faster R-CNN module and a temporal convolutional network module. The Faster R-CNN module is used to parse time series samples to extract spatial correlation features between health indicators of each battery cell and performance difference features between different battery cells. The temporal convolutional network module is used to capture the long-term temporal dependencies of the spatial correlation features and performance difference features output by the Faster R-CNN module, to obtain battery performance change information and battery load change information, and to determine the predicted health score and predicted load power of each battery cell for future periods based on the battery performance change information and battery load change information.

6. The distributed dynamic balancing and safety management method for secondary batteries as described in claim 5, characterized in that, The Faster R-CNN module includes a first two-dimensional convolutional layer, a second two-dimensional convolutional layer, and a max pooling layer; the first two-dimensional convolutional layer is configured with 32 3×3 convolutional kernels, the second two-dimensional convolutional layer is configured with 64 3×3 convolutional kernels, and the max pooling layer uses a 2×2 pooling window.

7. The distributed dynamic balancing and safety management method for secondary batteries as described in claim 1, characterized in that, Before reconstructing the running status parameter data using the sliding window technique, the following steps are also included: The collected operational status parameter data is cleaned to remove outliers, and the cleaned data is normalized to obtain normalized operational status parameter data. The sliding window technique is used to reconstruct the normalized operational status parameter data to obtain several time series samples.

8. A distributed dynamic balancing and safety management system for secondary batteries, used to implement the distributed dynamic balancing and safety management method for secondary batteries as described in any one of claims 1 to 7, characterized in that, include: The acquisition module is used to collect the operating status parameter data of the secondary battery pack at a preset sampling frequency. The operating status parameter data is time-series data. The reconstruction module is used to reconstruct the running status parameter data using the sliding window technique, generating several time series samples, each containing running status parameters within a continuous time step; The prediction module is used to input several time series samples into the trained battery health prediction model. The battery health prediction model is used to analyze the time series samples to extract the spatial correlation features between the health indicators of each battery cell and the performance difference features between different battery cells. Based on the spatial correlation features between the health indicators of each battery cell and the performance difference features between different battery cells, it outputs the predicted health score of each battery cell and the predicted load power for the future period. The output module is used to determine a balanced allocation strategy and a safety protection strategy for each battery cell based on the predicted health score of the battery cell and the predicted load power for future periods.

9. An electronic device, characterized in that, The electronic device includes: At least one processor (10); and, A memory (11) communicatively connected to the at least one processor (10); The memory (11) stores a computer program that can be executed by the at least one processor (10), which is executed by the at least one processor (10) to enable the at least one processor (10) to execute the secondary battery distributed dynamic balancing and safety management method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program; when the computer program is executed by a processor, it implements the distributed dynamic balancing and safety management method for secondary batteries as described in any one of claims 1 to 7.

Images