Battery cell information cloud management method and equipment of energy storage system and storage medium

Abstract

The invention discloses a battery cell information cloud management method and equipment of an energy storage system and a storage medium, and relates to the technical field of battery cell management. The method comprises the following steps: constructing a multi-layer digital twinborn model corresponding to a physical energy storage system; carrying out at least two-stage progressive feature extraction and information aggregation on the cell sensing data along a data acquisition path of the physical energy storage system so as to generate multi-granularity situation data used for updating different-level node states of the digital twin model; an interactive visualization service in linkage with the digital twin model is provided. The problem of passive interaction is solved, and active, accurate and intelligent probing and positioning of massive battery cells are realized.

Description

Technical Field

[0001] This application belongs to the field of battery management technology, and in particular relates to a cloud-based method, device and storage medium for managing cell information in an energy storage system. Background Technology

[0002] Current monitoring systems for large-scale energy storage power plants face three major bottlenecks: First, information is fragmented, with the data interface disconnected from the hierarchical and spatial structure of the physical system, leading to difficulties in understanding and low location efficiency for maintenance personnel. Second, data processing is flat and inefficient, with massive amounts of low-value raw data being directly uploaded to the cloud, wasting bandwidth and failing to extract multi-granular situational information to serve decision-making at different levels, resulting in weak early warning and root cause analysis capabilities. Finally, user interaction is passive and rigid, lacking proactive exploration and intelligent filtering tools based on multiple dimensions such as space, attributes, and trends, making it difficult to transform massive amounts of data into effective insights. Existing technologies cannot meet the needs of upgrading gigawatt-hour-level energy storage systems from passive monitoring to proactive intelligent governance. Summary of the Invention

[0003] In view of this, embodiments of this application provide a cloud-based management method, device, and storage medium for battery cell information of an energy storage system. By constructing a digital twin model that maps the physical structure, the problem of information fragmentation is solved; by performing at least two levels of progressive feature extraction and aggregation along the data path, the problem of coarse data processing is solved, achieving efficient extraction and hierarchical utilization of data value and significantly reducing system load; by providing visualization services that are linked to the twin model and support spatial navigation and multi-dimensional filtering, the problem of passive interaction is solved, enabling proactive, accurate, and intelligent exploration and positioning of massive battery cells.

[0004] This application provides a cloud-based method for managing battery cell information in an energy storage system, including the following steps: Construct a multi-layer digital twin model corresponding to the physical energy storage system. The multi-layer digital twin model can map the hierarchical organization structure and spatial relationship of the cells in the physical energy storage system. Along the data acquisition path of the physical energy storage system, the cell sensing data is subjected to at least two levels of progressive feature extraction and information aggregation to generate multi-granularity situational data for updating the state of different nodes of the digital twin model. Provide interactive visualization services that are linked with the digital twin model. The services at least support navigation based on the spatial structure of the digital twin model, and support target positioning and information penetration in the digital twin model based on conditional filtering of multi-dimensional attributes of the battery cell.

[0005] In one embodiment, the step of performing at least two levels of progressive feature extraction and information aggregation on the cell sensing data along the data acquisition path of the physical energy storage system includes: At the first-level processing node, the raw cell sensing data is processed to generate first-level feature data containing individual cell dynamic characteristics and local group consistency indicators. At the second-level processing node, which is higher than the first level, the first-level feature data from multiple first-level processing nodes are fused to generate second-level regional situation data that includes spatial distribution visualization information and regional cluster statistical summaries. The second-level regional situational data is uploaded to the cloud to drive the dynamic updates of the digital twin model.

[0006] In one embodiment, the first-level processing node is deployed at the battery pack or battery cluster level, and the second-level processing node is deployed at the container or energy storage unit level.

[0007] In one embodiment, the individual dynamic features in the first-level feature data include at least: the real-time deviation of the cell voltage or temperature relative to the average value of its local group, and the voltage or temperature change trend value calculated based on the time series; the local group consistency index includes at least the voltage range or standard deviation.

[0008] In one embodiment, generating the spatial distribution visualization information includes: Based on predefined cell spatial coordinates, key feature values ​​in the first-level feature data are mapped to visual variables, and a heat map is generated by rendering on the base map of the corresponding physical structure.

[0009] In one embodiment, the step of performing target localization and information penetration in the digital twin model based on conditional screening of multi-dimensional attributes of the battery cell includes: It provides configurable filters, allowing users to combine query conditions involving real-time cell status, historical performance trends, and spatial location attributes; Based on the query conditions, the matching battery cell entity is retrieved in real time from the digital twin model; In the visualization interface, the retrieved battery cell entities are synchronously highlighted in their respective hierarchical structure views, and drill-down is supported from the highlighted areas to obtain related full-dimensional data.

[0010] In one embodiment, the method further includes: In response to the user's selection of a historical time point, the system invokes and reproduces the state snapshot of the digital twin model at the corresponding historical moment to support interactive investigation and analysis of historical events.

[0011] A second aspect of this application provides a cloud-based management device for battery cell information of an energy storage system, comprising: The construction module is used to construct a multi-layer digital twin model corresponding to the physical energy storage system. The multi-layer digital twin model can map the hierarchical organization structure and spatial position relationship of the cells in the physical energy storage system. The aggregation module is used to perform at least two levels of progressive feature extraction and information aggregation on the cell sensing data along the data acquisition path of the physical energy storage system, so as to generate multi-granularity situational data for updating the state of different nodes of the digital twin model. A module is provided to provide interactive visualization services that are linked with the digital twin model. The services at least support navigation based on the spatial structure of the digital twin model and support target positioning and information penetration in the digital twin model based on conditional filtering of multi-dimensional attributes of the battery cell.

[0012] In one embodiment, the aggregation module is specifically used for: At the first-level processing node, the raw cell sensing data is processed to generate first-level feature data containing individual cell dynamic characteristics and local group consistency indicators. At the second-level processing node, which is higher than the first level, the first-level feature data from multiple first-level processing nodes are fused to generate second-level regional situation data that includes spatial distribution visualization information and regional cluster statistical summaries. The second-level regional situational data is uploaded to the cloud to drive the dynamic updates of the digital twin model.

[0013] In one embodiment, the first-level processing node is deployed at the battery pack or battery cluster level, and the second-level processing node is deployed at the container or energy storage unit level.

[0014] In one embodiment, the individual dynamic features in the first-level feature data include at least: the real-time deviation of the cell voltage or temperature relative to the average value of its local group, and the voltage or temperature change trend value calculated based on the time series; the local group consistency index includes at least the voltage range or standard deviation.

[0015] In one embodiment, generating the spatial distribution visualization information includes: Based on predefined cell spatial coordinates, key feature values ​​in the first-level feature data are mapped to visual variables, and a heat map is generated by rendering on the base map of the corresponding physical structure.

[0016] In one embodiment, the providing module is specifically used for: It provides configurable filters, allowing users to combine query conditions involving real-time cell status, historical performance trends, and spatial location attributes; Based on the query conditions, the matching battery cell entity is retrieved in real time from the digital twin model; In the visualization interface, the retrieved battery cell entities are synchronously highlighted in their respective hierarchical structure views, and drill-down is supported from the highlighted areas to obtain related full-dimensional data.

[0017] In one embodiment, the device further includes: The calling module is used to respond to the user's selection of a historical time point, call and reproduce the state snapshot of the digital twin model at the corresponding historical moment, so as to support interactive investigation and analysis of historical events.

[0018] A third aspect of this application provides a cloud-based management device for battery cell information of an energy storage system, characterized in that it includes: a processor, a memory, and a computer program stored in the memory and executable on the processor; the processor executes the computer program to implement the steps of the method described in the first aspect above.

[0019] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described in the first aspect above.

[0020] The cloud-based management method, device, and storage medium for battery cell information of the energy storage system provided in this application solve the problem of information fragmentation by constructing a digital twin model that maps the physical structure; it solves the problem of coarse data processing by performing at least two levels of progressive feature extraction and aggregation along the data path, achieving efficient extraction and layered utilization of data value and significantly reducing system load; and it solves the problem of passive interaction by providing a visualization service that is linked with the twin model and supports spatial navigation and multi-dimensional filtering, achieving proactive, accurate, and intelligent exploration and positioning of massive battery cells. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A schematic flowchart illustrating a cloud-based method for managing battery cell information in an energy storage system, as provided in an embodiment of this application; Figure 2A flowchart illustrating a cloud-based method for managing battery cell information in an energy storage system, as provided in another embodiment of this application; Figure 3 A schematic diagram of the structure of a cloud management device for cell information of an energy storage system provided in an embodiment of this application; Figure 4 A schematic diagram of a cloud-based management device for cell information of an energy storage system provided in an embodiment of this application. Detailed Implementation

[0023] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0025] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0026] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0027] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0028] In the description of the embodiments of this application, the term "multiple frames" refers to two or more (including two).

[0029] In the description of the embodiments of this application, the technical terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" 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 the embodiments of this application and simplifying the description, and are not intended to 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 the embodiments of this application.

[0030] Please see Figure 1 As shown, Figure 1 This is a flowchart illustrating a cloud-based method for managing battery cell information in an energy storage system, as provided in one embodiment of this application. The core of this method lies in achieving efficient, intuitive, and in-depth management of massive amounts of battery cell information in a large-scale energy storage system by constructing a digital twin model, designing a progressive data processing flow, and providing an intelligent interactive interface.

[0031] Depend on Figure 1 As can be seen, the cloud-based management method for cell information of the energy storage system in this application includes steps S110 to S130. Details are as follows: S110: Construct a multi-layer digital twin model corresponding to the physical energy storage system. The multi-layer digital twin model can map the hierarchical organization structure and spatial position relationship of the cells in the physical energy storage system.

[0032] This step aims to create a virtual mirror image in the cloud that is completely isomorphic to the physical energy storage system, i.e., a multi-layered digital twin model.

[0033] Specifically, based on the actual deployment structure of the physical energy storage system, a digital twin model hierarchy is defined and created in the cloud. This digital twin model contains at least the following interrelated hierarchies, from macro to micro: the power station hierarchy (root node, corresponding to the entire energy storage power station entity); the energy storage unit hierarchy (or container array, corresponding to one or more physical containers or prefabricated storage units, child nodes of the power station); the battery cluster hierarchy (child nodes of the container, corresponding to a battery rack or battery cluster); the battery pack hierarchy (child nodes of the battery cluster); and the final leaf nodes, each corresponding to a physical battery cell. Each node has a unique identifier (ID) and is linked through parent-child relationship pointers to accurately reproduce the hierarchical relationships of the physical system.

[0034] To accurately reflect the spatial distribution of battery cells, predefined physical coordinate information needs to be injected into each cell node when creating cell-level nodes. This physical coordinate information is usually derived from the design drawings or deployment configuration tables of the energy storage system and can be a three-dimensional coordinate (x, y, z) used to represent the specific location of the cell within its battery pack or cluster. For example, a battery pack with 96 cells can have a matrix coordinate system defined from (0, 0, 0) to (7, 11, 0). This coordinate information is stored as an attribute of the cell node in the digital twin model.

[0035] Define a set of dynamic state attributes for each node in the model (specifically, cell, battery pack, and battery cluster nodes). For cell nodes, attributes should include at least voltage, temperature, and estimated state of health (SOH); for cluster nodes (such as battery clusters), attributes should include average voltage, highest or lowest temperature, and voltage consistency indicators. These attributes constitute the target fields for subsequent data updates.

[0036] S120: Along the data acquisition path of the physical energy storage system, perform at least two levels of progressive feature extraction and information aggregation on the cell sensing data to generate multi-granularity situational data for updating the state of different levels of nodes in the digital twin model.

[0037] The process of performing at least two levels of progressive feature extraction and information aggregation on the cell sensing data along the data acquisition path of the physical energy storage system includes: at the first-level processing node, processing the raw cell sensing data to generate first-level feature data containing individual cell dynamic characteristics and local group consistency indicators; at the second-level processing node, which is higher than the first level, fusing the first-level feature data from multiple first-level processing nodes to generate second-level regional situation data containing spatial distribution visualization information and regional cluster statistical summaries; and uploading the second-level regional situation data to the cloud to drive the dynamic update of the digital twin model.

[0038] The first-level processing node is deployed at the battery pack or battery cluster level, and the second-level processing node is deployed at the container or energy storage unit level.

[0039] Specifically, the first-level processing nodes are deployed in the battery pack management unit or battery cluster controller of the energy storage system. These devices typically possess ARM Corter-M / A series microprocessors, enabling edge computing capabilities. The first-level processing node collects raw voltage and temperature sensing data from each cell under its jurisdiction at a high frequency, calculates the difference ΔV between the voltage value of each cell and the average voltage of all cells in its battery cluster (or within the node); calculates the difference ΔT between the temperature of each cell and the average temperature; calculates the voltage drift rate dV / dt using linear regression or the finite difference method based on a sliding time window (e.g., the voltage sequence over the most recent 5 minutes); similarly calculates the temperature rise rate dT / dt; calculates the range (maximum and minimum values) and standard deviation of the voltages of all cells under its jurisdiction to quantify the consistency level of this local group; and packages the individual characteristics of each cell (e.g., cell ID, ΔV, ΔT, dV / dt, dT / dt) and node-level aggregated indicators to form structured first-level feature data. The size of this data packet is much smaller than the original second-level data stream. This data is sent to the next higher-level node at a low frequency (e.g., once every 30 seconds).

[0040] The second-level processing node is deployed as a local industrial gateway or server within the energy storage container, or on the centralized controller of an energy storage unit. The second processing node receives first-level feature data uploaded from all first-level processing nodes within its jurisdiction (e.g., controllers for 20 battery clusters within a container) and generates the spatial distribution visualization information. Specifically, based on predefined cell spatial coordinates (either pre-stored in the second processing node or synchronized from the cloud), key feature values ​​from the first-level feature data, such as selecting one or more key feature values ​​(e.g., ΔT temperature deviation), are used as the data source. Visual mapping rules are defined; for example, the value of ΔT is mapped to a color gradient: ΔT=0 corresponds to green, ΔT>+2°C corresponds to dark red, and ΔT<-2°C corresponds to blue. Based on the coordinates of each cell and the mapped color value, color rendering is performed on a two-dimensional or simplified three-dimensional base map grid representing the internal structure of the container, ultimately generating a temperature deviation heatmap. This heatmap visually displays which areas within the container exhibit overheating or undercooling anomalies.

[0041] Statistical analysis is performed on the characteristic data of all battery cells within the region to generate a summary report. This report may include: the average, median, maximum / minimum voltage / temperature values ​​and their locations, a histogram of characteristic value distributions, and the proportion of clusters with consistency indicators exceeding thresholds. The generated second-level regional situational data (including metadata or miniaturized images of heatmaps and statistical summaries) is then uploaded to the cloud platform.

[0042] S130: Provide an interactive visualization service that is linked with the digital twin model. The service at least supports navigation based on the spatial structure of the digital twin model and supports target positioning and information penetration in the digital twin model based on conditional filtering of multi-dimensional attributes of the battery cell.

[0043] On the cloud platform, a visual interactive interface is provided via web services. This interface is developed using modern web technologies (such as HTML5, WebGL, and WebSocket) and supports smooth access in a browser.

[0044] The initial interface presents an overall view of the power plant hierarchy, possibly against a satellite map or floor plan background, with icons marking the locations of each container. The visual style of the icons (such as color and shape) is tied to the aggregate health status of their corresponding nodes in the digital twin model (such as green for health, yellow for warning, and red for failure). When a user clicks on a container icon, the interface dynamically switches to a detailed view of that container hierarchy by querying the digital twin model, displaying its internal heat map and key statistical instruments. Users can continue drilling down to specific battery clusters, battery packs, and eventually see the parameter cards for individual cells. It also supports scrolling back to higher-level views. This navigation method is completely consistent with the spatial exploration logic of the physical world.

[0045] The process of filtering based on multi-dimensional attributes of the battery cell to perform target localization and information penetration in the digital twin model includes: providing a configurable filter that allows users to combine and set query conditions involving the real-time status, historical performance trends, and spatial location attributes of the battery cell; retrieving matching battery cell entities in the digital twin model in real time based on the query conditions; and simultaneously highlighting the retrieved battery cell entities in their respective hierarchical structure views in the visualization interface, and supporting drill-down from the highlighted area to obtain related full-dimensional data.

[0046] Specifically, the interface provides an advanced filtering panel. Users can combine complex query conditions using drop-down menus, input boxes, range sliders, and other controls. For example, the conditions can be set as: "voltage deviation ΔV>50mV" and "temperature rise rate dT / dt>0.1°C / min" and "location belongs to 'Area A container'". After the user clicks "Query", the request is sent to the backend service. The backend service converts the conditions into a query statement for the digital twin model and performs a real-time search across all cell nodes in the model. After the search is completed, the system performs multi-view synchronous highlighting on the interface: on the power plant overview map, the container icon of the cell that meets the conditions will flash or be bordered; in the current hierarchical view (such as a container view), the cell that meets the conditions will be displayed with a prominent mark (such as a flashing light) on the heat map; at the same time, the sidebar will list a list of cells that meet the conditions, displaying their ID, key parameters, and location path. Users can trigger a "drill down" action by clicking on any battery cell in the list or a bright spot on the heat map. The interface will directly locate and expand the detailed data panel of that battery cell, displaying its real-time data, historical curves, and status information of its subordinate aggregation nodes at all levels, achieving seamless penetration from problem discovery to problem analysis.

[0047] As can be seen from the above analysis, the cloud-based cell information management method for energy storage systems provided in this application solves the problem of information fragmentation by constructing a digital twin model that maps the physical structure; it solves the problem of coarse data processing by performing at least two levels of progressive feature extraction and aggregation along the data path, achieving efficient extraction and hierarchical utilization of data value and significantly reducing system load; and it solves the problem of passive interaction by providing a visualization service that is linked with the twin model and supports spatial navigation and multi-dimensional filtering, achieving proactive, accurate, and intelligent exploration and positioning of massive cell data.

[0048] Please see Figure 2 , Figure 2 This is a flowchart illustrating a cloud-based method for managing battery cell information in an energy storage system, as provided in another embodiment of this application. Figure 2 It can be seen that this embodiment is similar to... Figure 1 Compared to the illustrated embodiment, S210 to S230 are implemented in the same way as S110 to S130, except that S240 is included after S230. Details are as follows: S210: Construct a multi-layer digital twin model corresponding to the physical energy storage system. The multi-layer digital twin model can map the hierarchical organization structure and spatial relationship of the cells in the physical energy storage system.

[0049] S220: Along the data acquisition path of the physical energy storage system, perform at least two levels of progressive feature extraction and information aggregation on the cell sensing data to generate multi-granularity situational data for updating the state of different levels of nodes in the digital twin model.

[0050] S230: Provide an interactive visualization service that is linked with the digital twin model. The service at least supports navigation based on the spatial structure of the digital twin model and supports target positioning and information penetration in the digital twin model based on conditional filtering of multi-dimensional attributes of the battery cell.

[0051] S240: In response to the user's selection of a historical time point, invoke and reproduce the state snapshot of the digital twin model at the corresponding historical moment to support interactive investigation and analysis of historical events.

[0052] Through step S240, this invention expands the digital twin model from a static real-time mirror into a complete, interactive spatiotemporal database. This not only meets the rigid requirement for detailed post-accident investigations but also provides a valuable data sandbox for trend analysis, pattern mining, and algorithm optimization, representing a key capability for achieving intelligent and refined operation and maintenance of energy storage systems.

[0053] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0054] Please see Figure 3 , Figure 3 This is a schematic diagram of a cloud-based cell information management device for an energy storage system according to an embodiment of this application. The cloud-based cell information management device for the energy storage system includes modules or units used for performing... Figure 1 or Figure 2 The steps in the corresponding embodiments. Please refer to the details. Figure 1 or Figure 2 The relevant descriptions in the corresponding embodiments are shown below. For ease of explanation, only the parts relevant to this embodiment are shown. See also... Figure 3 The energy storage system's cell information cloud management device 300 includes: The construction module 310 is used to construct a multi-layer digital twin model corresponding to the physical energy storage system. The multi-layer digital twin model can map the hierarchical organization structure and spatial position relationship of the cells in the physical energy storage system. The aggregation module 320 is used to perform at least two levels of progressive feature extraction and information aggregation on the cell sensing data along the data acquisition path of the physical energy storage system, so as to generate multi-granularity situational data for updating the state of different level nodes of the digital twin model. Module 330 is provided to provide interactive visualization services that are linked with the digital twin model. The services at least support navigation based on the spatial structure of the digital twin model and support target positioning and information penetration in the digital twin model based on conditional filtering of multi-dimensional attributes of the battery cell.

[0055] In one embodiment, the aggregation module 320 is specifically used for: At the first-level processing node, the raw cell sensing data is processed to generate first-level feature data containing individual cell dynamic characteristics and local group consistency indicators. At the second-level processing node, which is higher than the first level, the first-level feature data from multiple first-level processing nodes are fused to generate second-level regional situation data that includes spatial distribution visualization information and regional cluster statistical summaries. The second-level regional situational data is uploaded to the cloud to drive the dynamic updates of the digital twin model.

[0056] In one embodiment, the first-level processing node is deployed at the battery pack or battery cluster level, and the second-level processing node is deployed at the container or energy storage unit level.

[0057] In one embodiment, the individual dynamic features in the first-level feature data include at least: the real-time deviation of the cell voltage or temperature relative to the average value of its local group, and the voltage or temperature change trend value calculated based on the time series; the local group consistency index includes at least the voltage range or standard deviation.

[0058] In one embodiment, generating the spatial distribution visualization information includes: Based on predefined cell spatial coordinates, key feature values ​​in the first-level feature data are mapped to visual variables, and a heat map is generated by rendering on the base map of the corresponding physical structure.

[0059] In one embodiment, the providing module 330 is specifically used for: It provides configurable filters, allowing users to combine query conditions involving real-time cell status, historical performance trends, and spatial location attributes; Based on the query conditions, the matching battery cell entity is retrieved in real time from the digital twin model; In the visualization interface, the retrieved battery cell entities are synchronously highlighted in their respective hierarchical structure views, and drill-down is supported from the highlighted areas to obtain related full-dimensional data.

[0060] In one embodiment, the device 300 further includes: The calling module is used to respond to the user's selection of a historical time point, call and reproduce the state snapshot of the digital twin model at the corresponding historical moment, so as to support interactive investigation and analysis of historical events.

[0061] Please see Figure 4 , Figure 4 This is a schematic diagram of a cloud-based energy storage system cell information management device according to an embodiment of this application. The cloud-based energy storage system cell information management device 400 provided in this embodiment is an electronic device or server used to execute the aforementioned method embodiments. This device 400 can be a core server of a cloud management platform, an edge computing gateway, an industrial control computer, or a dedicated energy storage monitoring workstation. Figure 4 As shown, the device 400 includes at least: Processor 410 and memory 420. The memory 420 stores computer-executable instructions that constitute a computer program 430. When the processor 410 loads and executes the computer program 430, the device 400, as a whole, can perform the aforementioned functions. Figure 1 The cloud-based management method for cell information in the energy storage system shown, particularly steps S110 to S130 and their detailed steps (including S240, etc.), and the implementation Figure 3 The logic of each functional module in the illustrated device embodiment.

[0062] Specifically, the computer program 430 is logically configured to perform the following core functions, which can be implemented through one or more software modules: Digital Twin Model Construction and Maintenance Module: This module is configured to execute step S110 of the aforementioned method. Specifically, it includes instantiating and persisting a multi-level digital twin model in the device's memory or database based on the configuration information of the physical energy storage system (such as hierarchical topology and cell spatial coordinate mapping table). This module provides interfaces for adding, deleting, modifying, and querying model nodes and is responsible for maintaining the hierarchical relationship and spatial attributes of the model. Multi-level Data Processing Pipeline Scheduling Module: This module is configured to coordinate the execution logic of step S120. Its functions include: If device 400 acts as an edge computing node (such as deployed in a battery cluster controller), this module is responsible for scheduling sensor data acquisition, performing first-level feature extraction (calculating voltage / temperature deviation, trend values, and local consistency indicators), and encapsulating and uploading the first-level feature data. If device 400 acts as a regional aggregation node (such as deployed in an industrial gateway within a container), this module is responsible for receiving lower-level data, scheduling second-level aggregation tasks (including spatial heatmap generation and regional statistical summary calculation), and uploading second-level regional situation data. If device 400 acts as a cloud server, this module is responsible for receiving data from all regions and calling the digital twin model update interface. Interactive Visualization Service Engine Module: This module is configured to execute steps S130 and S240 of the aforementioned method. Its core functions include: View rendering engine: Based on the current state of the digital twin model or a specified historical snapshot, it generates visualization elements such as a power plant overview, hierarchical navigation view, and heat map.

[0063] Query and Filtering Engine: Parses the multi-dimensional and complex query conditions submitted by users through the graphical interface, converts them into retrieval requests for the digital twin model, and returns a list of matching battery cell entities.

[0064] Historical backtracking controller: manages the storage and retrieval logic of time-series state snapshots, responds to user operations on the timeline, calls and loads model snapshot data at a specified historical moment, and drives the interface to reproduce the state.

[0065] Data interface service: Provides interfaces such as RESTful API or WebSocket to deliver real-time and historical data to the front-end visualization interface, and handles interactive commands such as drill-down and filtering.

[0066] The memory 420 or its connected external storage system is used to store: metadata and topology of the digital twin model; a time-series database for storing historical cell status, regional situation data, and model snapshots; and a relational database for storing system configuration, user information, event logs, etc.

[0067] Understandable. Figure 4The image shows a basic hardware configuration of device 400. In actual deployments, its specific form and peripheral components may differ depending on the different roles the device plays (edge ​​node, aggregation node, or cloud central node). When used as an edge / regional node, device 400 may further include sensor interfaces (such as CAN bus, RS485 interface) for connecting to the battery management system (BMS), and industrial network interfaces for communicating with upper and lower layer devices. Its processor 410 may be an embedded microcontroller (MCU) or an industrial-grade SoC, and its memory 420 may primarily be Flash storage.

[0068] When acting as a central node in the cloud, device 400 is typically a high-performance server, and may also include high-speed network interface cards, massive storage arrays, and GPUs for accelerating visualization rendering. In this case, the various modules of the computer program 430 may be deployed as microservices on a cluster consisting of multiple devices 400.

[0069] The processor 410 can be any type of processing unit suitable for the above-described scenario, including but not limited to a general-purpose CPU, digital signal processor (DSP), graphics processor (GPU), application-specific integrated circuit (ASIC), or field-programmable gate array (FPGA). The memory 420 includes volatile memory (such as RAM) and non-volatile storage media (such as SSD, HDD) for storing program instructions and persistent data.

[0070] Through the above configuration, the cloud management device 400 for cell information of the energy storage system transforms the abstract steps in the method embodiment into a technical system implemented by specific hardware executing specific instructions, thereby providing a clear physical carrier and implementation basis for the implementation of the present invention.

[0071] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0072] This 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 executes the computer program to implement the steps in any of the above method embodiments.

[0073] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0074] This application provides a computer program product that, when run on a mobile terminal, enables the mobile terminal to implement the steps described in the above-described method embodiments.

[0075] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0076] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0077] Those skilled in the art will recognize that the units and algorithm steps of the various examples 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 implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art 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 apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0079] The units described as separate components may or may not be physically separate. 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 the units can 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 this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A cloud-based management method for cell information in an energy storage system, characterized in that, include: Construct a multi-layer digital twin model corresponding to the physical energy storage system. The multi-layer digital twin model can map the hierarchical organization structure and spatial relationship of the cells in the physical energy storage system. Along the data acquisition path of the physical energy storage system, the cell sensing data is subjected to at least two levels of progressive feature extraction and information aggregation to generate multi-granularity situational data for updating the state of different nodes of the digital twin model. Provide interactive visualization services that are linked with the digital twin model. The services at least support navigation based on the spatial structure of the digital twin model, and support target positioning and information penetration in the digital twin model based on conditional filtering of multi-dimensional attributes of the battery cell.

2. The method according to claim 1, characterized in that, The process of performing at least two levels of progressive feature extraction and information aggregation on the cell sensing data along the data acquisition path of the physical energy storage system includes: At the first-level processing node, the raw cell sensing data is processed to generate first-level feature data containing individual cell dynamic characteristics and local group consistency indicators. At the second-level processing node, which is higher than the first level, the first-level feature data from multiple first-level processing nodes are fused to generate second-level regional situation data that includes spatial distribution visualization information and regional cluster statistical summaries. The second-level regional situational data is uploaded to the cloud to drive the dynamic updates of the digital twin model.

3. The method according to claim 2, characterized in that, The first-level processing node is deployed at the battery pack or battery cluster level, and the second-level processing node is deployed at the container or energy storage unit level.

4. The method according to claim 2, characterized in that, The individual dynamic features in the first-level feature data include at least: the real-time deviation of the cell voltage or temperature relative to the average value of its local group, and the voltage or temperature change trend value calculated based on the time series; the local group consistency index includes at least the voltage range or standard deviation.

5. The method according to claim 2, characterized in that, Generating the spatial distribution visualization information includes: Based on predefined cell spatial coordinates, key feature values ​​in the first-level feature data are mapped to visual variables, and a heat map is generated by rendering on the base map of the corresponding physical structure.

6. The method according to claim 1, characterized in that, The conditional screening based on the multi-dimensional attributes of the battery cell, and the target localization and information penetration in the digital twin model, include: It provides configurable filters, allowing users to combine query conditions involving real-time cell status, historical performance trends, and spatial location attributes; Based on the query conditions, the matching battery cell entity is retrieved in real time from the digital twin model; In the visualization interface, the retrieved battery cell entities are synchronously highlighted in their respective hierarchical structure views, and drill-down is supported from the highlighted areas to obtain related full-dimensional data.

7. The method according to claim 1 or 6, characterized in that, The method further includes: In response to the user's selection of a historical time point, the system invokes and reproduces the state snapshot of the digital twin model at the corresponding historical moment to support interactive investigation and analysis of historical events.

8. A cloud-based management device for battery cell information in an energy storage system, characterized in that, include: The construction module is used to construct a multi-layer digital twin model corresponding to the physical energy storage system. The multi-layer digital twin model can map the hierarchical organization structure and spatial position relationship of the cells in the physical energy storage system. The aggregation module is used to perform at least two levels of progressive feature extraction and information aggregation on the cell sensing data along the data acquisition path of the physical energy storage system, so as to generate multi-granularity situational data for updating the state of different nodes of the digital twin model. A module is provided to provide interactive visualization services that are linked with the digital twin model. The services at least support navigation based on the spatial structure of the digital twin model and support target positioning and information penetration in the digital twin model based on conditional filtering of multi-dimensional attributes of the battery cell.

9. A cloud-based management device for battery cell information in an energy storage system, characterized in that, include: Processor, memory, and computer programs stored in said memory and executable on said processor; When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images