Battery state diagnosis method and equipment in energy storage wireless BMS (Battery Management System) and storage medium

Abstract

The invention discloses a battery state diagnosis method and device in an energy storage wireless BMS system and a storage medium. The method comprises the steps of obtaining state parameters of each battery monomer; time sequence features, statistical features and physical model features are constructed on the basis of the state parameters, the time sequence features, the statistical features and the physical model features are fused, after multi-feature fusion is carried out, the fusion features after multi-feature fusion are analyzed on the basis of a pre-established battery state prediction model, and the health state of each single battery is obtained. Accurate health assessment of the battery cells is realized, and the safety and reliability of the energy storage system are improved.

Description

Technical Field

[0001] The present application belongs to the technical field of energy storage wireless BMS, and in particular relates to a battery status diagnosis method, device and storage medium in an energy storage wireless BMS system. Background Art

[0002] In large-scale energy storage systems, battery cells are the fundamental energy storage units, and their status directly impacts the performance and lifespan of the entire battery pack. Traditional wired BMSs are limited by cable complexity and signal interference. While wireless BMSs (WBMSs) offer advantages in assembly and maintenance due to their freedom from cable constraints, they still face challenges in ensuring stable data transmission and accurate battery status diagnosis.

[0003] Existing WBMS status monitoring relies primarily on basic parameters such as battery voltage and temperature. It lacks in-depth diagnostic methods and struggles to effectively detect abnormalities in individual cells, such as capacity decay, imbalance, and internal impedance changes. Therefore, improving the accuracy of battery status assessment in energy storage wireless BMS systems is a pressing technical challenge. Summary of the Invention

[0004] In view of this, the embodiments of the present application provide a battery status diagnosis method, device and storage medium in an energy storage wireless BMS system. By fusing multiple features of battery cells, the health status of battery cells is detected based on a pre-selected battery status prediction model, thereby achieving accurate health assessment of battery cells and improving the safety and reliability of the energy storage system.

[0005] A first aspect of an embodiment of the present application provides a battery status diagnosis method in an energy storage wireless BMS system, comprising: Obtain the status parameters of each battery cell; constructing a time series feature, a statistical feature, and a physical model feature based on the state parameter, and fusing the time series feature, the statistical feature, and the physical model feature to obtain a fused feature; The fusion features are analyzed based on a pre-established battery state prediction model to obtain the health state of each battery cell.

[0006] In one embodiment, the state parameters include voltage, temperature, current, and internal resistance.

[0007] In one embodiment, constructing a time series feature based on the state parameter includes: Calculating a characteristic vector of each battery cell within n time windows based on the state parameter of each battery cell; According to the feature vector of each battery cell, the mean and variance of each battery cell in the sliding window are calculated.

[0008] In one embodiment, for each battery cell, the statistical features include: a mean drift value of the state parameter and a variation trend of the state parameter; The physical model characteristics include: state of charge and state of health.

[0009] In one embodiment, the pre-established battery state prediction module includes a hybrid model of a long short-term memory network, a self-attention-based deep learning network, and a fully connected layer.

[0010] In one embodiment, the analyzing the fusion features based on a pre-established battery state prediction model to obtain the health state of each battery cell includes: Utilizing the long short-term memory network, extracting the temporal features to form a hidden state; Utilizing the self-attention-based deep learning network to extract the fusion features, enhancing analysis of the implicit state based on the fusion features, and obtaining output features; The fully connected layer is used to map the output features of the self-attention deep learning network to the health status of the corresponding battery cell.

[0011] In one embodiment, for any battery cell, the health status of the battery cell is determined by the output features and weight matrix of a self-attention deep learning network.

[0012] A second aspect of an embodiment of the present application provides a battery status diagnosis device in an energy storage wireless BMS system, comprising: An acquisition module is used to obtain the status parameters of each battery cell; a fusion module, configured to construct time series features, statistical features, and physical model features based on the state parameters, and fuse the time series features, the statistical features, and the physical model features to obtain fused features; The analysis module is used to analyze the fusion features based on a pre-established battery state prediction model to obtain the health state of each battery cell.

[0013] In one embodiment, the state parameters include voltage, temperature, current, and internal resistance.

[0014] In one embodiment, constructing a time series feature based on the state parameter includes: Calculating a characteristic vector of each battery cell within n time windows based on the state parameter of each battery cell; According to the feature vector of each battery cell, the mean and variance of each battery cell in the sliding window are calculated.

[0015] In one embodiment, for each battery cell, the statistical features include: a mean drift value of the state parameter and a variation trend of the state parameter; The physical model characteristics include: state of charge and state of health.

[0016] In one embodiment, the pre-established battery state prediction module includes a hybrid model of a long short-term memory network, a self-attention-based deep learning network, and a fully connected layer.

[0017] In one embodiment, the analysis module includes: The formation unit is used to extract the temporal features in the fusion features using the long short-term memory network to form a hidden state vector sequence; An analysis unit, configured to analyze the implicit state vector sequence using a self-attention-based deep learning network to obtain output features; The mapping unit is used to map the output features of the self-attention deep learning network to the health status of the corresponding battery cell using a fully connected layer.

[0018] In one embodiment, for any battery cell, the health status of the battery cell is determined by the output features and weight matrix of a self-attention deep learning network.

[0019] A third aspect of an embodiment of the present application provides a battery status diagnostic device in an energy storage wireless BMS system, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor; when the processor executes the computer program, the steps of the method described in the first aspect above are implemented.

[0020] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect above is implemented.

[0021] The beneficial effects of the embodiments of the present application are as follows: by obtaining the state parameters of each battery cell; constructing time series features, statistical features and physical model features based on the state parameters, fusing the time series features, statistical features and physical model features, and performing multi-feature fusion, the fused features after multi-feature fusion are analyzed based on a pre-established battery state prediction model to obtain the health status of each battery cell, thereby achieving accurate health assessment of the battery cell and improving the safety and reliability of the energy storage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] Figure 1 A schematic diagram of the implementation flow of a battery status diagnosis method in an energy storage wireless BMS system provided in one embodiment of the present application; Figure 2 for Figure 1 Schematic diagram of the specific implementation process of S103; Figure 3 A schematic diagram of a battery status diagnostic device in an energy storage wireless BMS system provided in one embodiment of the present application; Figure 4 A schematic diagram of a battery status diagnostic device in an energy storage wireless BMS system provided in one embodiment of the present application. DETAILED DESCRIPTION

[0024] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0026] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0027] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0028] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0029] In the description of the embodiments of the present application, the term "multi-frame" refers to two or more (including two).

[0030] In the description of the embodiments of the present application, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0031] An embodiment of the present application provides a battery status diagnosis method in an energy storage wireless BMS system. By fusing multiple features of battery cells, the health status of battery cells is detected based on a pre-selected battery status prediction model, thereby achieving accurate health assessment of battery cells and improving the safety and reliability of the energy storage system.

[0032] See also Figure 1 , Figure 1 This is a flowchart of the battery status diagnosis method in the energy storage wireless BMS system provided in one embodiment of the present application. The battery status diagnosis method in the energy storage wireless BMS system is implemented by the software or hardware of the battery status diagnosis device in the energy storage wireless BMS system. The battery status diagnosis device in the energy storage wireless BMS system includes a computer, a terminal or a server, etc. No specific limitation is made here. For example, Figure 1 As shown, the battery status diagnosis method in the energy storage wireless BMS system provided in the embodiment of the present application includes the following steps S101 to S103, which are detailed as follows: S101: Obtaining state parameters of each battery cell.

[0033] In one embodiment, the state parameters of the battery cells include voltage, temperature, current, and internal resistance.

[0034] The voltage of a battery cell can be measured using a voltage sensor or sampling circuit, the temperature of a battery cell can be measured using a thermistor or thermocouple sensor, the current of a battery cell can be measured using a current sensor or shunt resistor, and the internal resistance of a battery cell can be measured using AC impedance measurement or DC pulse testing. Specifically, after measuring and obtaining the above status parameters, the device can obtain them through the wireless communication module.

[0035] S102: constructing time series features, statistical features, and physical model features based on the state parameters, and fusing the time series features, statistical features, and physical model features to obtain fused features.

[0036] In one embodiment, constructing time series features based on state parameters includes: calculating the feature vector of each battery cell in n time windows based on the state parameters of each battery cell; and calculating the mean and variance of each battery cell in the sliding window based on the feature vector of each battery cell.

[0037] In one embodiment, for each battery cell, the statistical features include: a mean drift value of a state parameter and a variation trend of the state parameter; and the physical model features include: state of charge and state of health.

[0038] In this embodiment of the present application, by utilizing the state parameters of battery cells, feature vectors are calculated within multiple time windows, and statistical features (mean and variance) of the sliding windows are further calculated. These time series features can be used to analyze the operating status of battery cells and, in combination with deep learning models, predict the health status of battery cells.

[0039] For example, assuming that the sampling time is divided into multiple time windows with fixed intervals, for a certain battery cell i, in the t-th time window, the feature vector of the time window is constructed as follows: in, is the voltage of battery cell i in the tth time window, is the temperature of battery cell i in the tth time window, is the current of battery cell i in the tth time window, is the internal resistance of battery cell i in the tth time window.

[0040] Then the time series feature matrix constructed in n time windows (tn to t) is expressed as: The mean and variance of each battery cell in the sliding window can be calculated based on the feature matrix. For example, the volume within the sliding window is used to smooth the fluctuation of the state parameter, which is defined as: in, represents a state parameter (such as voltage, current, temperature or internal resistance), and n is the number of time windows.

[0041] Variance is used to measure the volatility of state parameters and is defined as: in, A large variance indicates more dramatic fluctuations in the state parameters, suggesting anomalies in the battery cells. The mean and variance can help analyze the long-term health of battery cells and predict anomalies.

[0042] For each battery cell, the statistical features include: the mean drift value of the state parameter and the change trend of the state parameter; the physical model features include: state of charge and health state.

[0043] For example, the mean shift value can measure the rate of change of the state parameter of the battery cell. It is defined as: in, is the state parameter at time t (such as voltage, temperature or current, etc.), is the state parameter of the previous moment. Specifically, if If the value is too large, it may indicate a sudden change in the battery cell parameters, such as capacity drop or abnormal overheating.

[0044] The change trend represents the linear change rate of the state parameter over a long period of time and is defined as: in, is the state parameter at the initial moment, is the state parameter at time t. The changing trend can be used to determine the aging trend of the battery cell. For example, if the voltage gradually decreases, it may be a sign of capacity decay. If the internal resistance continues to increase, it may be that the battery cell is aging faster.

[0045] The physical model features include state of charge and state of health. The state of charge reflects the remaining power of the battery cell and can be expressed as: in, is the initial SOC of the i-th battery cell, is the rated capacity of the i-th battery cell, is the current of the i-th battery cell.

[0046] The health status reflects the aging state of the battery cell and is defined as: in, is the rated capacity of the i-th battery cell, is the current capacity of the i-th battery cell.

[0047] The resulting fusion features include the mean and variance within the sliding window, and a multidimensional feature vector is extracted, including mean drift, trend, SOC, and SOH. This multidimensional feature vector can be used for battery cell health monitoring, anomaly detection, and life prediction.

[0048] S103: Analyze the fusion features based on the pre-established battery status prediction model to obtain the health status of each battery cell.

[0049] In one embodiment, the pre-established battery state prediction module includes a hybrid model of a long short-term memory network, a self-attention-based deep learning network, and a fully connected layer.

[0050] In one embodiment, see Figure 2 As shown, Figure 2 for Figure 1 Schematic diagram of the specific implementation process of S103. Figure 2 It can be seen that the fusion features are analyzed based on the pre-established battery status prediction model to obtain the health status of each battery cell, including: S2011: Using long short-term memory networks, we extract temporal features from fused features and form a latent state vector sequence.

[0051] Among them, the long short-term memory network is a recurrent neural network structure that specializes in processing time series data and can retain long-term dependency information. In battery status monitoring, for each battery cell, the constructed fusion features include data in the time series dimension (such as voltage changes, SOC curves, etc.). It is usually extracted in a sliding window manner, for example, the data of the past 5 minutes constitutes a window. The long short-term memory network sequentially models the input features of each time step to form a latent state vector sequence. Specifically, the latent state vector sequence represents the features within each time step in the input sequence. It is the result of extracting the historical evolution pattern and is usually a two-dimensional tensor, represented by the time step multiplied by the feature.

[0052] S2012: Use a self-attention-based deep learning network to analyze the implicit state vector sequence and obtain output features.

[0053] A self-attention-based deep learning network can model the mutual influence between different positions in the input sequence, thereby capturing long-range dependencies. Compared to long-short-term memory networks, it is more suitable for global feature modeling and is particularly well-suited for extracting long-term trends and key change points. Because each time point in the implicit state vector sequence corresponds to a state representation, the self-attention-based deep learning network takes the implicit state of all time steps as input and calculates the "attention weight" of each time point with respect to all other time points. Using these weight matrices, the entire sequence is reweighted and combined to produce a feature vector with greater global understanding. Specifically, the global contextual representation of the implicit state can be used to further discern the battery's health status. The self-attention-based deep learning network analyzes the implicit features extracted by the long-short-term memory network here, which can be understood as weighting and amplifying the "key change points" in the time series in the global context, which is conducive to identifying abnormal trends such as chronic degradation and mutations.

[0054] S2013: Use the fully connected layer to map the output features of the self-attention deep learning network to the health status of the corresponding battery cells.

[0055] Fully connected layers map high-dimensional features into specific outputs. Their purpose is to convert the representations learned by the model into interpretable metrics or categories. The resulting "global output features" represent the overall characteristics of the sequence after incorporating context. These include indicators of the health status of battery cells, such as regression outputs of SOH (State of Health) values (e.g., 0.93 indicates 93% health), or classification outputs of labels such as healthy, abnormal, or severely degraded.

[0056] Specifically, the long short-term memory network can process historical state parameters and obtain time series features, and the self-attention deep learning network can obtain global features under the entire time series and improve the long-term trend prediction ability.

[0057] In one embodiment, for any battery cell, the health status of the battery cell is determined by the output features and weight matrix of the self-attention deep learning network.

[0058] The battery status diagnosis method in the energy storage wireless BMS system provided in the embodiment of the present application can realize intelligent health management of the battery and improve the safety and life prediction ability of the battery by obtaining status parameters such as voltage, temperature, current and internal resistance of the battery cell and combining it with a deep learning model.

[0059] See Figure 3 , Figure 3 Schematic diagram of a battery status diagnosis device in an energy storage wireless BMS system provided by an embodiment of the present application. The battery status diagnosis device in the energy storage wireless BMS system includes various modules or units for performing Figures 1 to 2Each step in the corresponding embodiment. Please refer to Figures 1 to 2 For the convenience of explanation, only the parts related to this embodiment are shown. Figure 3 The battery status diagnostic device 30 in the energy storage wireless BMS system includes: An acquisition module 310 is used to acquire the state parameters of each battery cell; A fusion module 320 is configured to construct a time series feature, a statistical feature, and a physical model feature based on the state parameters, and fuse the time series feature, the statistical feature, and the physical model feature to obtain a fused feature; The analysis module 330 is configured to analyze the fusion features based on a pre-established battery state prediction model to obtain the health state of each battery cell.

[0060] In one embodiment, the state parameters include voltage, temperature, current, and internal resistance.

[0061] In one embodiment, constructing a time series feature based on the state parameter includes: Calculating a characteristic vector of each battery cell within n time windows based on the state parameter of each battery cell; According to the feature vector of each battery cell, the mean and variance of each battery cell in the sliding window are calculated.

[0062] In one embodiment, for each battery cell, the statistical features include: a mean drift value of the state parameter and a variation trend of the state parameter; The physical model characteristics include: state of charge and state of health.

[0063] In one embodiment, the pre-established battery state prediction module includes a hybrid model of a long short-term memory network, a self-attention-based deep learning network, and a fully connected layer.

[0064] In one embodiment, the analysis module 330 includes: The formation unit is used to extract the temporal features in the fusion features using the long short-term memory network to form a hidden state vector sequence; An analysis unit, configured to analyze the implicit state vector sequence using a self-attention-based deep learning network to obtain output features; The mapping unit is used to map the output features of the self-attention deep learning network to the health status of the corresponding battery cell using a fully connected layer.

[0065] In one embodiment, for any battery cell, the health status of the battery cell is determined by the output features and weight matrix of a self-attention deep learning network.

[0066] See Figure 4 , Figure 4 This is a schematic diagram of a battery status diagnostic device in an energy storage wireless BMS system provided by an embodiment of the present application. Figure 4 It can be seen that the battery status diagnosis device 400 in the energy storage wireless BMS system includes: a processor 410, a memory 420, and a computer program 430 stored in the memory 420 and executable on the processor 410; when the processor 410 executes the computer program 430, the steps in the above-mentioned embodiments of the battery status diagnosis method in the energy storage wireless BMS system are implemented, such as Figures 1 to 2 Alternatively, when the processor 410 executes the computer program 430, the functions of the modules / units in the above-mentioned device embodiments are realized, for example Figure 3 Functions of modules 310 to 330 are shown.

[0067] Exemplarily, the computer program 430 can be divided into one or more modules / units, which are stored in the memory 420 and executed by the processor 410 to complete the present application. The one or more modules / units can be a series of computer program instruction segments that can perform specific functions, and the instruction segments are used to describe the execution process of the computer program 430 in the battery status diagnostic device in the energy storage wireless BMS system. For example, the computer program 430 can be divided into an acquisition module, a fusion module, and an analysis module.

[0068] The battery status diagnostic device in the energy storage wireless BMS system provided in this embodiment may include, but is not limited to, a processor and a memory. It will be understood by those skilled in the art that Figure 4 The diagram is merely an example of a battery status diagnostic device in an energy storage wireless BMS system and does not constitute a limitation on the battery status diagnostic device in the energy storage wireless BMS system. The diagram may include more or fewer components than shown in the diagram, or a combination of certain components, or different components. For example, the battery status diagnostic device in the energy storage wireless BMS system may also include input and output devices, network access devices, buses, and the like.

[0069] The processor 410 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0070] The memory 420 can be an internal storage unit of the battery status diagnostic device in the energy storage wireless BMS system, such as a hard drive or memory of the battery status diagnostic device in the energy storage wireless BMS system. The memory 420 can also be an external storage device of the battery status diagnostic device in the energy storage wireless BMS system, such as a plug-in hard drive, a smart media card (SMC), a secure digital (SD) card, a flash memory card, etc. Furthermore, the energy storage wireless BMS system management device can include both the internal storage unit of the battery status diagnostic device in the energy storage wireless BMS system and an external storage device. The memory 420 is used to store the computer program and other programs and data required by the battery status diagnostic device in the energy storage wireless BMS system. The memory 420 can also be used to temporarily store data that has been output or is about to be output.

[0071] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0072] An embodiment of the present application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps of any of the above-mentioned method embodiments when executing the computer program.

[0073] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0074] An embodiment of the present application provides a computer program product. When the computer program product is run on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned various method embodiments when executing the computer program product.

[0075] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, removable hard drives, magnetic disks, or optical disks. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0076] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0077] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0078] In the embodiments provided in this application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0079] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0080] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A battery status diagnosis method in an energy storage wireless BMS system, characterized in that: include: Obtain the status parameters of each battery cell; constructing a time series feature, a statistical feature, and a physical model feature based on the state parameter, and fusing the time series feature, the statistical feature, and the physical model feature to obtain a fused feature; The fusion features are analyzed based on a pre-established battery state prediction model to obtain the health state of each battery cell.

2. The battery status diagnosis method in the energy storage wireless BMS system according to claim 1, characterized in that: The state parameters include voltage, temperature, current and internal resistance.

3. The battery status diagnosis method in the energy storage wireless BMS system according to claim 2, characterized in that: The constructing of a time series feature based on the state parameter includes: Calculating a characteristic vector of each battery cell within n time windows based on the state parameter of each battery cell; According to the feature vector of each battery cell, the mean and variance of each battery cell in the sliding window are calculated.

4. The battery status diagnosis method in the energy storage wireless BMS system according to claim 3, characterized in that: For each battery cell, the statistical features include: a mean drift value of the state parameter and a change trend of the state parameter; The physical model characteristics include: state of charge and state of health.

5. The battery status diagnosis method in the energy storage wireless BMS system according to claim 1, characterized in that: The pre-established battery state prediction module includes a hybrid model of a long short-term memory network, a self-attention-based deep learning network, and a fully connected layer.

6. The battery status diagnosis method in the energy storage wireless BMS system according to claim 5, characterized in that: The fusion features are analyzed based on a pre-established battery status prediction model to obtain the health status of each battery cell, including: Using the long short-term memory network, the temporal features in the fusion features are extracted to form a hidden state vector sequence; Use a deep learning network based on self-attention to analyze the implicit state vector sequence and obtain output features; The fully connected layer is used to map the output features of the self-attention deep learning network to the health status of the corresponding battery cells.

7. The battery status diagnosis method in the energy storage wireless BMS system according to claim 6, characterized in that: For any battery cell, the health status of the battery cell is determined by the output features and weight matrix of the self-attention deep learning network.

8. A battery status diagnostic device in an energy storage wireless BMS system, characterized in that: include: An acquisition module is used to obtain the status parameters of each battery cell; a fusion module, configured to construct a time series feature, a statistical feature, and a physical model feature based on the state parameters, and fuse the time series feature, the statistical feature, and the physical model feature to obtain a fusion feature; The analysis module is used to analyze the fusion features based on a pre-established battery state prediction model to obtain the health state of each battery cell.

9. A battery status diagnostic device in an energy storage wireless BMS system, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor; When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images