Multi-mode fault prediction method and device for energy storage wireless BMS system and storage medium

Abstract

The invention discloses an energy storage wireless BMS system multi-modal fault prediction method, device and equipment and a storage medium, and the method comprises the steps: collecting preset modal data at preset time intervals, extracting spatial features and local time sequence features from battery operation parameters, and extracting a global dependence feature sequence from communication signals and environment information; performing feature fusion on the spatial feature, the local time sequence feature and the global dependency feature sequence to obtain a fused feature vector; and inputting the fusion feature vector into a multi-path topology model for analysis to obtain different types of fault probabilities of each battery. By fusing the battery operation parameters, the communication signals and the environment number and based on the multi-path topology model, multi-mode fault prediction is carried out, the sensitivity is high, the false alarm rate is low, and the fault prediction precision can be remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent energy storage operation and maintenance, and in particular relates to a multi-modal fault prediction method, device and storage medium for an energy storage wireless BMS system. Background Art

[0002] With the development of the new energy industry and the widespread application of energy storage systems, the Battery Management System (BMS) plays a vital role in ensuring battery safety, extending battery life, and improving system reliability. In large-scale energy storage power stations, electric vehicles, and industrial-grade energy storage systems, the performance of the BMS directly affects the stable operation of the entire system.

[0003] Existing BMS systems generally use threshold judgment mechanisms based on single parameters such as voltage and temperature for fault detection and alarm. Specifically, when the battery voltage is detected to be outside the normal range or the temperature is abnormally elevated, the system triggers a protection mechanism or alarm response. While this approach is relatively simple to implement and has a fast response time, it has significant limitations. Firstly, many actual faults do not immediately cause abnormal voltage or temperature changes. For example, latent faults such as poor contact, micro-shorts, and increased internal resistance are difficult to detect in a timely manner. Secondly, this type of diagnostic method based on single-variable thresholds struggles to cope with the nonlinear evolutionary trends that occur during system operation and cannot identify potential risks from multiple sources of information. Summary of the Invention

[0004] In view of this, the embodiments of the present invention provide a multimodal fault prediction method, device and storage medium for an energy storage wireless BMS system. By integrating battery operating parameters, communication signals and environmental data and performing multimodal fault prediction based on a multipath topology model, the method has high sensitivity and low false alarm rate, and can significantly improve fault prediction accuracy.

[0005] The present application provides a multi-modal fault prediction method for an energy storage wireless BMS system, including: Collecting preset modal data at preset time intervals, the preset modal data including battery operating parameters, communication signals, and environmental information; Extracting spatial features and local temporal features from the battery operating parameters, and extracting a global dependency feature sequence from the communication signal and the environmental information; Fusing the spatial features, the local temporal features, and the global dependency feature sequence to obtain a fused feature vector; The fused feature vector is input into a multi-path topology model for analysis to obtain the probability of different types of failures of each battery.

[0006] In one embodiment, extracting spatial features and local temporal features from the battery operating parameters includes: The battery operating parameters are input into a convolutional neural network, and analyzed in the convolutional neural network using sliding convolution kernels of different lengths and strides to obtain the spatial features and the local time series features; the spatial features refer to the state differences and correlations of different batteries at the same time; the local time series features refer to the state change trends of the same battery within a certain time period.

[0007] In one embodiment, extracting a global dependency feature sequence from the communication signal and the environmental information includes: The communication signal and the environmental information are input into a deep learning model based on a self-attention mechanism for analysis to obtain the global dependency feature sequence; the global dependency feature sequence includes a cross-modal association relationship between the communication signal and the environmental information within a preset time length.

[0008] In one embodiment, inputting the communication signal and the environmental information into a deep learning model based on a self-attention mechanism for analysis to obtain the global dependency feature sequence includes: Inputting the communication signal and the environmental information into a deep learning model based on a self-attention mechanism, respectively encoding them through a modality-specific encoder to obtain a communication modality feature sequence and an environmental modality feature sequence; Aligning the communication modality feature sequence and the environment modality feature sequence in time to form an input feature sequence; Based on dynamic time adaptive rules, homomodal and heteromodal attention response analysis is performed on the input feature sequence to obtain the global dependency feature sequence.

[0009] In one embodiment, the performing homomodal and heteromodal attention response analysis on the input feature sequence based on the dynamic time adaptive rule to obtain the global dependency feature sequence includes: The time decay factor and the modal bias are integrated, and the long-term correlation analysis between dynamic homomodality and heteromodality of the input feature sequence is performed based on the attention weight to obtain a global dependency feature sequence with context-awareness.

[0010] In one embodiment, the multi-path topology model includes: a multi-path topology network model composed of three adjacency matrices, wherein the three adjacency matrices represent different fault propagation channels.

[0011] In one embodiment, the inputting the fused feature vector into a multi-path topology model for analysis to obtain different types of failure probabilities of each battery includes: Inputting the fused feature vector into the multipath topology model, and performing analysis based on the weights of different propagation paths in the three adjacency matrices; The analysis results of the three adjacency matrices are aggregated, and the failure probabilities of different types of batteries are obtained based on the aggregated results.

[0012] A second aspect of an embodiment of the present application provides a multi-modal fault prediction device for an energy storage wireless BMS system, comprising: An acquisition module, configured to acquire preset modal data at preset time intervals, wherein the preset modal data includes battery operating parameters, communication signals, and environmental information; An extraction module, configured to extract spatial features and local temporal features from the battery operating parameters, and extract a global dependency feature sequence from the communication signal and the environmental information; A fusion module, configured to fuse the spatial features, the local temporal features, and the global dependency feature sequence to obtain a fused feature vector; The analysis module is used to input the fused feature vector into a multi-path topology model for analysis to obtain the probability of different types of failures of each battery.

[0013] In one embodiment, the extraction module is specifically configured to: The battery operating parameters are input into a convolutional neural network, and analyzed in the convolutional neural network using sliding convolution kernels of different lengths and strides to obtain the spatial features and the local time series features; the spatial features refer to the state differences and correlations of different batteries at the same time; the local time series features refer to the state change trends of the same battery within a certain time period.

[0014] In one embodiment, the extraction module is specifically configured to: The communication signal and the environmental information are input into a deep learning model based on a self-attention mechanism for analysis to obtain the global dependency feature sequence; the global dependency feature sequence includes a cross-modal association relationship between the communication signal and the environmental information within a preset time length.

[0015] In one embodiment, the extraction module is specifically configured to: Inputting the communication signal and the environmental information into a deep learning model based on a self-attention mechanism, respectively encoding them through a modality-specific encoder to obtain a communication modality feature sequence and an environmental modality feature sequence; Aligning the communication modality feature sequence and the environment modality feature sequence in time to form an input feature sequence; Based on dynamic time adaptive rules, homomodal and heteromodal attention response analysis is performed on the input feature sequence to obtain the global dependency feature sequence.

[0016] In one embodiment, the extraction module is specifically configured to: The time decay factor and the modal bias are integrated, and the long-term correlation analysis between dynamic homomodality and heteromodality of the input feature sequence is performed based on the attention weight to obtain a global dependency feature sequence with context-awareness.

[0017] In one embodiment, the multi-path topology model includes: a multi-path topology network model composed of three adjacency matrices, wherein the three adjacency matrices represent different fault propagation channels.

[0018] In one embodiment, the analysis module is specifically configured to: Inputting the fused feature vector into the multipath topology model, and performing analysis based on the weights of different propagation paths in the three adjacency matrices; The analysis results of the three adjacency matrices are aggregated, and the failure probabilities of different types of batteries are obtained based on the aggregated results.

[0019] A third aspect of an embodiment of the present application provides a multi-modal fault prediction device for 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, which stores a computer program. When the computer program is executed by a processor, the steps of the method described in the first aspect above are implemented.

[0021] The beneficial effects of the embodiments of the present application include: collecting preset modal data at preset time intervals, extracting spatial features and local temporal features from battery operating parameters, and extracting a global dependency feature sequence from communication signals and environmental information; fusing the spatial features, local temporal features, and global dependency feature sequences to obtain a fused feature vector; and inputting the fused feature vector into a multipath topology model for analysis to determine the different types of fault probabilities for each battery. By fusing battery operating parameters, communication signals, and environmental data and performing multimodal fault prediction based on the multipath topology model, the system achieves high sensitivity, low false alarm rate, and significantly improves fault prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] 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 embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 A schematic diagram of the implementation flow of a multi-modal fault prediction method for an energy storage wireless BMS system provided in one embodiment of the present application; Figure 2 A schematic diagram of a multi-modal fault prediction device for an energy storage wireless BMS system provided in one embodiment of the present application; Figure 3 A schematic diagram of a multi-modal fault prediction device for 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 to "embodiments" herein 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] The embodiment of the present invention provides a multimodal fault prediction method for an energy storage wireless BMS system. The method can predict possible faults of the energy storage system in real time based on multi-dimensional operation data analysis, so that maintenance measures can be taken in advance to improve the safety and reliability of system operation.

[0032] See also Figure 1 As shown, Figure 1 This is a schematic diagram of the implementation process of a multi-modal fault prediction method for an energy storage wireless BMS system provided in one embodiment of the present application. This multi-modal fault prediction method for an energy storage wireless BMS system is applicable to an energy storage wireless BMS system and is implemented by a multi-modal fault prediction device for an energy storage wireless BMS system. Details are as follows: S110: Collecting preset modal data at preset time intervals, where the preset modal data includes battery operating parameters, communication signals, and environmental information.

[0033] For example, battery operating parameters include basic electrical indicators such as voltage, current, temperature, and state of charge. Communication signals include indicators such as wireless signal strength, packet loss rate, and number of retransmissions. Environmental information includes vibration level, ambient temperature, external temperature, and EMI interference intensity.

[0034] S120: Extracting spatial features and local temporal features from battery operating parameters, and extracting global dependency feature sequences from communication signals and environmental information.

[0035] It should be noted that the battery operating parameters, communication signals, and environmental information can first be time-synchronized, missing value filled, noise filtered, and normalized to unify the data scale and ensure the accuracy and stability of feature extraction. The specific process of time synchronization, missing value filling, noise filtering, and normalization of the data will not be explained in detail here.

[0036] In one embodiment, spatial features and local temporal features are extracted from battery operating parameters, including: inputting the battery operating parameters into a convolutional neural network, and analyzing them in the convolutional neural network using sliding convolution kernels of different lengths and strides to obtain spatial features and local temporal features; spatial features refer to the state differences and correlations of different batteries at the same time; local temporal features refer to the state change trends of the same battery within a certain time period.

[0037] For example, assume that a wireless BMS node in an energy storage system collects the following battery operating parameters once per second: voltage, current, temperature, and state of charge. Every 10 minutes, a 60-row × 4-column time series data matrix is generated. This 60-row × 4-column (time × channel) data is input into a convolutional neural network, such as a 1D-CNN. This convolutional neural network uses sliding convolution kernels of varying lengths and strides to extract state change trends within different time windows, such as rapid voltage drops (a sign of a short circuit), abnormal SOC fluctuations (sampling distortion), and sudden temperature rises (abnormal heat dissipation). These state change trends within different time windows are used as corresponding local time series features. The state parameters of different batteries at each time point where a local trend change occurs are extracted, and the differences and correlations between the state parameters are analyzed to determine spatial features. This embodiment uses a CNN, which can effectively detect small fluctuation patterns within a short period of time and is more suitable for extracting local time series features than an RNN. By combining spatial and local time series features, this embodiment not only helps locate local anomalies and identify structural problems (spatial features), but also helps identify fault trends and predict future conditions (local time series features).

[0038] In one embodiment, a global dependency feature sequence is extracted from a communication signal and environmental information, including: inputting the communication signal and environmental information into a deep learning model based on a self-attention mechanism for analysis to obtain a global dependency feature sequence; the global dependency feature sequence includes a cross-modal correlation relationship between the communication signal and the environmental information within a preset time length.

[0039] Exemplarily, the communication signal and the environmental information are input into a deep learning model based on a self-attention mechanism for analysis to obtain the global dependency feature sequence, including: inputting the communication signal and the environmental information into a deep learning model based on a self-attention mechanism, encoding them respectively through a modality-specific encoder to obtain a communication modality feature sequence and an environmental modality feature sequence; aligning the communication modality feature sequence and the environmental modality feature sequence in time to form an input feature sequence; performing homomodal and heteromodal attention response analysis on the input feature sequence based on a dynamic time adaptive rule to obtain a global dependency feature sequence.

[0040] It should be noted that when processing time series data, the conventional self-attention mechanism assumes by default that the influence between each time point is equal or statically defined. This step introduces dynamic time adaptation rules, which allows the model to independently decide "which time period to focus on" and "attention intensity" based on the structure of historical data or the structure between data. In addition, the traditional self-attention mechanism is prone to "mixed modality" when processing multimodal data, that is, it is unable to distinguish the difference in the contribution of different modal information to the attention distribution. However, the use of homomodal and heteromodal attention response analysis in this embodiment can clearly guide the model to analyze the internal correlation between homomodal (such as between communication features) and the interactive influence between heteromodal (such as communication and environment); this has significant value in improving the accuracy of cross-modal dependency analysis.

[0041] In one embodiment, the input feature sequence is subjected to homomodal and heteromodal attention response analysis based on dynamic time adaptive rules to obtain a global dependent feature sequence, including: fusing the time decay factor and the modal bias, and performing dynamic homomodal and heteromodal long-term correlation analysis on the input feature sequence based on the attention weight to obtain a global dependent feature sequence with context-awareness.

[0042] Exemplarily, the time decay factor is expressed as: ;in, is a learnable time-aware parameter, is the interval between the i-th time point and the j-th time point; is the time decay factor, which controls the effect of time span on attention distribution.

[0043] Attention weight, expressed as: ;in, is a modal label used to distinguish between the same modality and different modalities. =1 is the same mode, =0 is heteromodal; is the modal bias coefficient, is the time attenuation coefficient, and They are used to dynamically adjust attention weights and guide information fusion; , is the attention key-value pair, To query the distance, represents the fused attention weight between the i-th time point and the j-th time point.

[0044] Finally, the time decay factor and modality bias are integrated, and the long-term correlation analysis between dynamic homomodality and heteromodality of the input feature sequence is performed based on the attention weight. The global dependency feature sequence with context-awareness at the i-th time point is obtained, which is expressed as: ;in, is the context-aware feature representation at the i-th time point, It is the feature vector corresponding to the j-th time point or mode in the input feature sequence, and is the feature vector generated by linear mapping.

[0045] By aligning communication signals (such as RSSI, packet loss rate, and number of retransmissions) with environmental information (such as temperature, EMI, and humidity) in time to form an input feature sequence, and then introducing learnable time-aware parameters, the time-distance impact of input features at different time points is modeled through the time decay factor, enhancing the flexibility of modeling long-term dependencies. We further construct a modal label matrix Mᵢⱼ to distinguish between homomodality and heteromodality, guide the distribution of attention weights through the modal bias coefficient β and the time decay coefficient γ, and output the context-aware features at each time point through the attention mechanism. , that is, a global feature representation sequence containing cross-modal relationships and dynamic time dependencies = { ,..., }.

[0046] Through the above process, the strength of cross-temporal dependency and the complementary information of cross-modal features can be simultaneously perceived, thereby generating a global dependency feature sequence with context-awareness capabilities, providing multi-dimensional feature support for subsequent fault analysis and status assessment.

[0047] S130: Fusing spatial features, local temporal features, and global dependency feature sequences to obtain a fused feature vector.

[0048] The spatial features, local temporal features, and global dependency feature sequences can be fused in series or by weighted summation to obtain a fused feature vector. Specifically, this embodiment does not impose any limitation on the fusion method.

[0049] S140: Input the fused feature vector into the multi-path topology model for analysis to obtain the probability of different types of failures for each battery.

[0050] In one embodiment, the multi-path topology model includes: a multi-path topology network model composed of three adjacency matrices, where the three adjacency matrices represent different fault propagation channels.

[0051] Specifically, the three adjacency matrices include the physical connection adjacency matrix, which represents the electrical connection relationship between batteries, such as series and parallel structures; the thermal coupling adjacency matrix, which represents the heat conduction or temperature rise relationship between batteries; and the communication link adjacency matrix, which represents the communication structure and relay path between wireless communication nodes.

[0052] Exemplarily, the fused feature vector is input into the multi-path topology model for analysis to obtain the different types of failure probabilities of each battery, including: inputting the fused feature vector into the multi-path topology model, and performing analysis based on the weights of different propagation paths in three adjacency matrices; aggregating the analysis results of the three adjacency matrices, and obtaining the different types of failure probabilities of each battery based on the aggregation results.

[0053] Specifically, by inputting the fused feature vector into the multi-path topology model, graph neural network propagation and feature update are performed separately under the path corresponding to each adjacency matrix to capture the impact of different structural relationships on fault evolution; then, the node feature update results from the three paths are aggregated (such as weighted fusion or attention fusion) to obtain a node representation containing multi-source dependency information; finally, based on the fused node feature vector, it is input into the fault classification subnetwork or probabilistic reasoning module to output the predicted probability of each battery having different types of faults (such as overheating, overcharging, communication interruption, etc.) at the current moment.

[0054] The above analysis shows that the multimodal fault prediction method for the energy storage wireless BMS system provided in the embodiment of the present application collects preset modal data at preset time intervals, extracts spatial features and local temporal features from battery operating parameters, and extracts global dependency feature sequences from communication signals and environmental information; performs feature fusion on the spatial features, local temporal features, and global dependency feature sequences to obtain a fused feature vector; and inputs the fused feature vector into a multipath topology model for analysis to obtain the different types of fault probabilities for each battery. By fusing battery operating parameters, communication signals, and environmental data and performing multimodal fault prediction based on a multipath topology model, the method has high sensitivity and low false alarm rate, significantly improving fault prediction accuracy.

[0055] See Figure 2 , Figure 2 Schematic diagram of a multi-modal fault prediction device for a wireless BMS system for energy storage provided in one embodiment of the present application. The multi-modal fault prediction device for a wireless BMS system for energy storage includes modules or units for executing Figure 1 Each step in the corresponding embodiment. Please refer to Figure 1 For the convenience of explanation, only the parts related to this embodiment are shown. Figure 2 , a multi-modal fault prediction device 200 for an energy storage wireless BMS system, comprising: The acquisition module 210 is configured to acquire preset modal data at preset time intervals, wherein the preset modal data includes battery operating parameters, communication signals, and environmental information; An extraction module 220 is configured to extract spatial features and local temporal features from the battery operating parameters, and to extract a global dependency feature sequence from the communication signal and the environmental information; A fusion module 230 is configured to fuse the spatial features, the local temporal features, and the global dependency feature sequence to obtain a fused feature vector; The analysis module 240 is configured to input the fused feature vector into a multi-path topology model for analysis to obtain the probability of different types of failures of each battery.

[0056] In one embodiment, the extraction module 220 is specifically configured to: The battery operating parameters are input into a convolutional neural network, and analyzed in the convolutional neural network using sliding convolution kernels of different lengths and strides to obtain the spatial features and the local time series features; the spatial features refer to the state differences and correlations of different batteries at the same time; the local time series features refer to the state change trends of the same battery within a certain time period.

[0057] In one embodiment, the extraction module 220 is specifically configured to: The communication signal and the environmental information are input into a deep learning model based on a self-attention mechanism for analysis to obtain the global dependency feature sequence; the global dependency feature sequence includes a cross-modal association relationship between the communication signal and the environmental information within a preset time length.

[0058] In one embodiment, the extraction module 220 is specifically configured to: Inputting the communication signal and the environmental information into a deep learning model based on a self-attention mechanism, respectively encoding them through a modality-specific encoder to obtain a communication modality feature sequence and an environmental modality feature sequence; Aligning the communication modality feature sequence and the environment modality feature sequence in time to form an input feature sequence; Based on dynamic time adaptive rules, homomodal and heteromodal attention response analysis is performed on the input feature sequence to obtain the global dependency feature sequence.

[0059] In one embodiment, the extraction module 220 is specifically configured to: The time decay factor and the modal bias are integrated, and the long-term correlation analysis between dynamic homomodality and heteromodality of the input feature sequence is performed based on the attention weight to obtain a global dependency feature sequence with context-awareness.

[0060] In one embodiment, the multi-path topology model includes: a multi-path topology network model composed of three adjacency matrices, wherein the three adjacency matrices represent different fault propagation channels. In one embodiment, the analysis module 240 is specifically configured to: Inputting the fused feature vector into the multipath topology model, and performing analysis based on the weights of different propagation paths in the three adjacency matrices; The analysis results of the three adjacency matrices are aggregated, and the failure probabilities of different types of batteries are obtained based on the aggregated results.

[0061] See Figure 3 , Figure 3 This is a schematic diagram of a multi-modal fault prediction device for an energy storage wireless BMS system provided by an embodiment of the present application. Figure 3 It can be seen that the multi-modal fault prediction device 300 for a wireless energy storage BMS system includes: a processor 310, a memory 320, and a computer program 330 stored in the memory 320 and executable on the processor 310; when the processor 310 executes the computer program 330, the steps in the above-mentioned embodiments of the multi-modal fault prediction method for a wireless energy storage BMS system are implemented, such as Figure 1 Alternatively, when the processor 310 executes the computer program 330, the functions of the modules / units in the above-mentioned device embodiments are realized, for example Figure 2 The functions of the modules 210 to 240 are shown.

[0062] Exemplarily, computer program 330 can be divided into one or more modules / units, one or more of which are stored in memory 320 and executed by processor 310 to implement the present application. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of computer program 330 in the multi-modal fault prediction device of the energy storage wireless BMS system. For example, computer program 330 can be divided into an acquisition module, an extraction module, a fusion module, and an analysis module.

[0063] The multi-modal fault prediction device for 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 3 The present invention is merely an example of a multimodal fault prediction device for an energy storage wireless BMS system and does not constitute a limitation on the multimodal fault prediction device for an energy storage wireless BMS system. The present invention may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the multimodal fault prediction device for an energy storage wireless BMS system may also include input and output devices, network access devices, buses, etc.

[0064] The processor 310 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.

[0065] Memory 320 can be an internal storage unit of the multimodal fault prediction device for a wireless energy storage BMS system, such as a hard drive or memory within the device. Memory 320 can also be an external storage device, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, or a flash memory card. Furthermore, the multimodal fault prediction device for a wireless energy storage BMS system can include both the internal storage unit and an external storage device. Memory 320 is used to store computer programs and other programs and data required by the multimodal fault prediction device. Memory 320 can also be used to temporarily store data that has been output or is about to be output.

[0066] 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.

[0067] 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.

[0068] 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.

[0069] 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.

[0070] 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.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] 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.

[0075] 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 multi-modal fault prediction method for an energy storage wireless BMS system, characterized in that: include: Collecting preset modal data at preset time intervals, the preset modal data including battery operating parameters, communication signals, and environmental information; Extracting spatial features and local temporal features from the battery operating parameters, and extracting a global dependency feature sequence from the communication signal and the environmental information; Fusing the spatial features, the local temporal features, and the global dependency feature sequence to obtain a fused feature vector; The fused feature vector is input into a multi-path topology model for analysis to obtain the probability of different types of failures of each battery.

2. The multi-modal fault prediction method for the energy storage wireless BMS system according to claim 1, characterized in that: The extracting of spatial features and local temporal features from the battery operating parameters includes: The battery operating parameters are input into a convolutional neural network, and analyzed in the convolutional neural network using sliding convolution kernels of different lengths and strides to obtain the spatial features and the local time series features; the spatial features refer to the state differences and correlations of different batteries at the same time; the local time series features refer to the state change trends of the same battery within a certain time period.

3. The multi-modal fault prediction method for the energy storage wireless BMS system according to claim 1 or 2, characterized in that: The extracting a global dependency feature sequence from the communication signal and the environmental information includes: The communication signal and the environmental information are input into a deep learning model based on a self-attention mechanism for analysis to obtain the global dependency feature sequence; the global dependency feature sequence includes a cross-modal association relationship between the communication signal and the environmental information within a preset time length.

4. The multi-modal fault prediction method for the energy storage wireless BMS system according to claim 3, characterized in that: The inputting the communication signal and the environmental information into a deep learning model based on a self-attention mechanism for analysis to obtain the global dependency feature sequence includes: Inputting the communication signal and the environmental information into a deep learning model based on a self-attention mechanism, respectively encoding them through a modality-specific encoder to obtain a communication modality feature sequence and an environmental modality feature sequence; Aligning the communication modality feature sequence and the environment modality feature sequence in time to form an input feature sequence; Based on dynamic time adaptive rules, homomodal and heteromodal attention response analysis is performed on the input feature sequence to obtain the global dependency feature sequence.

5. The multi-modal fault prediction method for the energy storage wireless BMS system according to claim 4, characterized in that: The performing homomodal and heteromodal attention response analysis on the input feature sequence based on the dynamic time adaptive rule to obtain the global dependency feature sequence includes: The time decay factor and the modal bias are integrated, and the long-term correlation analysis between dynamic homomodality and heteromodality of the input feature sequence is performed based on the attention weight to obtain a global dependency feature sequence with context-awareness.

6. The multi-modal fault prediction method for the energy storage wireless BMS system according to claim 1, characterized in that: The multi-path topology model includes: a multi-path topology network model composed of three adjacency matrices, wherein the three adjacency matrices represent different fault propagation channels.

7. The multi-modal fault prediction method for the energy storage wireless BMS system according to claim 6, characterized in that: The fused feature vector is input into a multi-path topology model for analysis to obtain different types of failure probabilities of each battery, including: Inputting the fused feature vector into the multipath topology model, and performing analysis based on the weights of different propagation paths in the three adjacency matrices; The analysis results of the three adjacency matrices are aggregated, and the failure probabilities of different types of batteries are obtained based on the aggregated results.

8. A multi-modal fault prediction device for an energy storage wireless BMS system, characterized in that: include: An acquisition module, configured to acquire preset modal data at preset time intervals, wherein the preset modal data includes battery operating parameters, communication signals, and environmental information; An extraction module, configured to extract spatial features and local temporal features from the battery operating parameters, and extract a global dependency feature sequence from the communication signal and the environmental information; A fusion module, configured to fuse the spatial features, the local temporal features, and the global dependency feature sequence to obtain a fused feature vector; The analysis module is used to input the fused feature vector into a multi-path topology model for analysis to obtain the probability of different types of failures of each battery.

9. A multi-modal fault prediction device for 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 steps of the method according to any one of claims 1 to 7 are implemented.

Images