Method and system for determining battery capacity

Abstract

The embodiment of the invention discloses a battery capacity determination method and system. The battery capacity determination method comprises the following steps: receiving request information of edge end equipment, wherein the edge end equipment is edge end equipment of a plurality of target batteries; generating a cloud computing task according to the request information; and determining a capacity prediction result of each target battery based on a preset model according to the calculation task. According to the battery capacity determination method and system provided by the embodiment of the invention, the capacity prediction requirements of a large number of batteries can be met.

Description

[0001] This application is a divisional application of the application filed on March 26, 2024, with application number 202410350880.9, entitled "A Method and System for Determining Battery Capacity". Technical Field

[0002] This invention relates to battery capacity estimation technology, and more particularly to a method and system for determining battery capacity. Background Technology

[0003] For batteries such as lithium-ion batteries, their characteristics change during use due to factors such as the number of charge-discharge cycles and the operating environment, and battery health is one of the most important characteristics. Obtaining accurate battery health information guides battery management and helps improve battery performance and lifespan. Battery health refers to the battery's ability to store electrical energy relative to a new battery, usually evaluated as the ratio of the current battery's full capacity to the full capacity of a newly manufactured battery. The full capacity of a newly manufactured battery, i.e., its rated capacity, is determined at the time of manufacture; therefore, determining the battery's current full capacity is sufficient to obtain its health. Currently, existing methods for determining battery capacity typically predict capacity at the edge of its lifecycle, and can only predict the capacity of a limited number of batteries. Summary of the Invention

[0004] This invention provides a method and system for determining battery capacity to meet the capacity prediction needs of a large number of batteries.

[0005] In a first aspect, embodiments of the present invention provide a method for determining battery capacity, comprising: Receive request information from edge devices, wherein the edge devices are edge devices for multiple target batteries; Generate cloud-based computing tasks based on the requested information; Based on the computational task, the capacity prediction results of each target battery are determined using a preset model.

[0006] Optionally, generating a cloud-based computing task based on the request information includes: The request information is verified to obtain the verification result; When the verification result is normal, the request task for each target battery is determined according to the request information.

[0007] Optionally, determining the capacity prediction results of each target battery based on a preset model according to the computation task includes: According to the calculation task, read the voltage and current of each target battery; Based on the voltage and current, the capacity of each target battery is determined according to a preset model.

[0008] Optionally, before receiving the request information from the edge device, the following steps are included: Receive the process document request from the edge device; According to the process document request, a target process document is sent to the edge device, the target process document including the charging and discharging information of the target battery.

[0009] Optionally, the computing task includes a task identifier, and after generating the computing task in the cloud, it includes: The task identifier is sent to the edge device.

[0010] Optionally, after determining the capacity prediction results of each target battery based on a preset model, the process includes: When a capacity query request is received from the edge device, the capacity prediction result is sent to the edge device according to the task identifier in the capacity query request.

[0011] In a second aspect, embodiments of the present invention provide a battery capacity determination system, including a cloud device and an edge device, wherein the cloud device is communicatively connected to the edge device, and the cloud device is used to execute the determination method as described in the first aspect.

[0012] Optionally, the cloud device includes: a cloud processing module, a cache module, a task queue module, and a cloud communication module; the cloud communication module is communicatively connected to the edge device and the cloud processing module, and the cloud processing module is communicatively connected to the cache module and the task queue module.

[0013] Optionally, the cloud device further includes a cloud management module and a cloud storage module, both of which are communicatively connected to the cloud processing module.

[0014] Optionally, the edge device includes a data acquisition module, an edge processing module, an edge storage module, and an edge communication module. The data acquisition module, the edge storage module, and the edge communication module are all electrically connected to the edge processing module, and the edge communication module is communicatively connected to the cloud communication module.

[0015] The battery capacity determination method and system provided in this invention include: receiving request information from an edge device, wherein the edge device is an edge device for multiple target batteries; generating a cloud-based computing task based on the request information; and determining the capacity prediction result of each target battery based on a preset model according to the computing task. The battery capacity determination method and system provided in this invention, by determining the capacity prediction result of each target battery based on a preset model and request information from an edge device, can achieve capacity prediction for a large number of batteries in the cloud, thereby meeting the capacity prediction needs of a large number of batteries. Attached Figure Description

[0016] Figure 1 This is a flowchart of a method for determining battery capacity provided in Embodiment 1 of the present invention; Figure 2 This is a flowchart of a method for determining battery capacity provided in Embodiment 2 of the present invention; Figure 3 This is a structural block diagram of a battery capacity determination system provided in Embodiment 3 of the present invention; Figure 4 This is a structural block diagram of a cloud device provided in Embodiment 3 of the present invention; Figure 5 This is a structural block diagram of an edge device provided in Embodiment 3 of the present invention. Detailed Implementation

[0017] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0018] Example 1 Figure 1 This is a flowchart of a method for determining battery capacity according to Embodiment 1 of the present invention. This embodiment can be applied to determining battery capacity, etc. This method can be executed by a cloud device for the battery, and the method specifically includes the following steps: Step 110: Receive request information from the edge device, which is an edge device for multiple target batteries.

[0019] The request information may include requests for capacity prediction of each target battery. Before receiving the request information from the edge device, the cloud device has already sent the target process document to the edge device and received the data transmitted by the edge device (the edge device sends a process document request to the cloud device, and the cloud device sends the target process document to the edge device according to the process document request). The edge device controls the charging and discharging state of the target battery according to the target process document, and collects data such as voltage, current, and temperature during the battery charging and discharging process, and then processes the collected data and transmits it to the cloud device.

[0020] Step 120: Generate cloud computing tasks based on the request information.

[0021] Specifically, based on the request information, the pre-stored data such as voltage, current, and temperature of each target battery are determined to generate a computing task in the cloud. The computing task may include a capacity calculation task for each target battery, which may include data such as voltage, current, and temperature of the battery during the charging and discharging process.

[0022] Step 130: Based on the calculation task, determine the capacity prediction results of each target battery according to the preset model.

[0023] Specifically, the preset model can take the voltage and current of the target battery as input and output the capacity prediction result of the target battery. The preset model can be a model of the battery capacity with respect to the battery voltage and current. The specific composition of the model can refer to existing battery capacitance prediction models, and is not limited here.

[0024] The battery capacity determination method provided in this embodiment includes: receiving request information from an edge device, wherein the edge device is an edge device for multiple target batteries; generating a cloud computing task based on the request information; and determining the capacity prediction result of each target battery based on a preset model according to the computing task. The battery capacity determination method provided in this embodiment, by determining the capacity prediction result of each target battery based on a preset model and request information from the edge device, can realize capacity prediction for a large number of batteries in the cloud, thereby meeting the capacity prediction needs of a large number of batteries.

[0025] Example 2 Figure 2 This is a flowchart of a method for determining battery capacity according to Embodiment 2 of the present invention. This embodiment can be applied to determining battery capacity, etc. This method can be executed by a cloud device for the battery, and the method specifically includes the following steps: Step 210: Receive request information from edge devices. The edge devices are edge devices for multiple target batteries.

[0026] The request information may include the capacity prediction request information for each target battery. Before receiving the request information from the edge device, the cloud device has already sent the target process document to the edge device and received the data transmitted by the edge device (the edge device sends a process document request to the cloud device, and the cloud device sends the target process document to the edge device according to the process document request).

[0027] Specifically, before receiving the request information from the edge device, the cloud device receives the process document request from the edge device. Based on the process document request, it sends the target process document to the edge device. The target process document includes the charging and discharging information of the target battery, such as charging and discharging time. The edge device controls the charging and discharging state of the target battery according to the target process document, and collects data such as voltage, current, and temperature during the battery charging and discharging process. After processing the collected data, it transmits it to the cloud device.

[0028] Step 220: Verify the request information and obtain the verification result.

[0029] The request information may include the identity information of the edge device, such as the device number. The cloud device may pre-store the identity information of the edge devices it communicates with. The cloud device determines whether the edge device is the edge device it is communicating with based on the request information.

[0030] Step 230: When the verification result is normal, determine the request tasks for each target battery based on the request information to generate cloud computing tasks.

[0031] Specifically, when the cloud device determines that the edge device is the one it is communicating with based on the request information, it determines the pre-stored data such as voltage, current, and temperature of each target battery based on the request information to generate a cloud computing task. Furthermore, the computing task includes a task identifier, and after generating the cloud computing task, the cloud device can send the task identifier to the edge device.

[0032] Step 240: According to the calculation task, read the voltage and current of each target battery.

[0033] Step 250: Determine the capacity of each target battery based on the voltage and current, using a preset model.

[0034] Specifically, the preset model employs a preset battery charging and discharging process, which consists of basic steps such as charging, discharging, resting, and cycling. When performing rapid capacity estimation for batteries in different usage scenarios or of different models, the number and order of these steps in the preset process may vary. Based on the number and order of these steps in the preset process, the preset model uses appropriate feature extraction methods to obtain key features of the target battery's charging and discharging process, thereby further determining the capacity of each target battery. The preset model can take the voltage and current of the target battery as input and output the predicted capacity result. The preset model can be a model of battery capacity relative to the battery's voltage and current; the specific structure of the model can refer to existing battery capacitance prediction models and is not limited here.

[0035] Furthermore, after determining the capacity prediction results for each target battery based on the preset model, when a capacity query request is received from the edge device, the cloud device can send the capacity prediction results to the edge device according to the task identifier in the capacity query request.

[0036] The battery capacity determination method provided in this embodiment determines the capacity prediction results of each target battery based on the request information from the edge device and a preset model. This enables capacity prediction of a large number of batteries in the cloud, thereby meeting the capacity prediction needs of a large number of batteries. Furthermore, the cloud device and the edge device have a division of labor. Complex data calculations and model inference updates are performed in the cloud with abundant computing resources, while low-latency data collection is performed at the edge, which is closer to the battery and related devices. Lower-cost, low-computing-power devices are used as edge devices, while avoiding data leakage problems that may occur when sensitive resources such as models, charge and discharge data, and process documents are placed at the edge. The cloud decouples various functional modules such as computing, storage, and network communication, and improves the computing efficiency of the cloud through parallel processing. This allows the cloud to process battery capacity detection requests from multiple edge devices simultaneously, thereby meeting the needs of large-scale practical applications.

[0037] Example 3 Figure 3 This is a structural block diagram of a battery capacity determination system provided in Embodiment 3 of the present invention. (Reference) Figure 3 The battery capacity determination system includes a cloud device 100 and an edge device 200. The cloud device 100 and the edge device 200 are communicatively connected. The cloud device 100 is used to execute the battery capacity determination method as described in any embodiment of the present invention.

[0038] Among them, the cloud device 100 communicates with the edge device 200. The cloud device 100 can process the capacity prediction requests of multiple target batteries controlled by the edge device 200, realize the capacity prediction of multiple target batteries, meet the needs of rapid capacity detection of large batches and multiple models of batteries in practical applications, and fully protect the security of core data assets such as battery charging and discharging raw data and battery capacity mapping model.

[0039] Figure 4 This is a structural block diagram of a cloud device provided in Embodiment 3 of the present invention. (Reference) Figure 4 Optionally, the cloud device 100 includes: a cloud processing module 11, a cache module 12, a task queue module 13, and a cloud communication module 14; the cloud communication module 14 is communicatively connected to the edge device 200 and the cloud processing module 11, and the cloud processing module 11 is communicatively connected to the cache module 12 and the task queue module 13.

[0040] Specifically, the cloud communication module 14 communicates and interacts with the edge device 200, such as receiving information transmitted by the edge device 200 and transmitting that information to the cloud processing module 11, and also receiving information transmitted by the cloud processing module 11 and transmitting that information to the edge device 200. The caching module 12 caches information from various modules in the cloud device 100, such as process documents and battery capacity prediction results, to improve the read / write speed and execution efficiency of each module in the cloud device 100. The task queue module 13 stores and forwards information. Other modules can publish information to the task queue module 13, and the task queue module 13 can receive the latest information published in real time by subscribing to specific topics, thus achieving module decoupling and traffic smoothing. The task queue module 13 includes a capacity prediction request queue and a single-unit prediction task queue. The capacity prediction request queue stores the edge device capacity prediction request information transmitted by the cloud communication module 14 and transmits this information to the cloud processing module 11. The cloud processing module 11 includes a pre-processing unit and a general capacity prediction unit. A capacity prediction request queue can transmit information to the pre-processing unit that subscribes to the information. A single-cell prediction task queue stores the battery cell capacity prediction task information transmitted by the pre-processing unit and forwards this information to the general capacity prediction unit that subscribes to the information. The pre-processing unit handles capacity prediction requests from edge devices. Due to differences in battery type, number of battery cells, sorting process, etc., the pre-processing unit needs to split the capacity prediction request into multiple standard battery cell capacity prediction tasks, which are then executed in parallel by the general capacity prediction unit.

[0041] refer to Figure 4Optionally, the cloud device 100 also includes a cloud management module 15 and a cloud storage module 16, both of which are communicatively connected to the cloud processing module 11.

[0042] Specifically, the cloud storage module 16 is used to permanently save various important data, files, logs, etc., and provides information writing and reading services to other modules through the data interface; the cloud management module 15 is used to monitor and regulate the operating status of the entire cloud device, such as monitoring the usage of various resources such as cloud CPU, memory, hard disk, etc., and making reasonable allocation of resources according to the usage, while issuing alarms when module malfunctions or resources are insufficient.

[0043] Figure 5 This is a structural block diagram of a cloud device provided in Embodiment 3 of the present invention. (Reference) Figure 5 Optionally, the edge device 200 includes a data acquisition module 21, an edge processing module 22, an edge storage module 23, and an edge communication module 24. The data acquisition module 21, the edge storage module 23, and the edge communication module 24 are all electrically connected to the edge processing module 22, and the edge communication module 24 is communicatively connected to the cloud communication module 14.

[0044] Specifically, the data acquisition module 21 is used to collect data such as voltage, current, and temperature during the battery charging and discharging process; the edge processing module 22 is used to perform preliminary data preprocessing on the data collected by the data acquisition module 21, such as filtering out abnormal data, duplicate data, adding timestamps, and data encryption. The edge communication module 24 is used to communicate and interact with the cloud device, such as uploading battery charging and discharging data, obtaining target process documents, and battery capacity prediction results; the edge storage module 23 is used to store the data and file resources required for the operation of various software and hardware modules in the edge device, such as charging and discharging data, target process documents, battery capacity prediction results, and log information; the edge processing module 22 is used to parse the target process document and convert it into control instructions that the edge device can recognize, so that the edge device can control the battery charging and discharging process according to the requirements of the process document. Thus, the edge device 200 can perform data acquisition, preprocessing, encryption, transmission, storage, and result display, and communicate with the cloud device 100 through a unified standard communication interface. The cloud device 100 adopts a distributed system, decoupling functional modules such as communication, capacity computing, model training, and storage and deploying them to independent computing units that can be parallelized. Stateless communication between modules is achieved through message queues and in-memory databases. All modules are monitored and scheduled for resources, and the number of available computing units for each module is allocated or adjusted in real time according to actual business needs.

[0045] Furthermore, the specific process of interaction and communication between the cloud device and the edge device is as follows: Before controlling the battery charging and discharging, the edge device sends a process document request to the cloud device. After receiving the request, the cloud device sends the target process document to the edge device. The edge device controls the battery charging and discharging according to the target process document and collects battery charging and discharging data and related information. After completing the battery charging and discharging process, it packages the charging and discharging data and related information and sends a capacity prediction request to the cloud device. After receiving the prediction request, the cloud device performs authentication. After successful authentication, it generates and starts executing the corresponding calculation task and sends the task identifier to the edge device. After receiving the task identifier, the edge device sends a capacity prediction result query request to the cloud device in a polling manner. After receiving the query request, the cloud device sends the currently calculated partial results of the task to the edge device. When the cloud device receives another query request from the edge device after completing the capacity prediction of all battery cells in the capacity prediction request task, it packages the remaining capacity prediction results of all battery cells that have not yet been sent to the edge device, and sends a task calculation completion signal to the edge device, thus completing a rapid battery capacity detection.

[0046] Compared with existing technologies, the edge devices in this embodiment do not require model deployment or complex data processing. Lower-power edge computing devices can meet the requirements, reducing costs while improving data and model security. Furthermore, deploying the model in the cloud and using a distributed architecture to decouple cloud functional modules fully leverages the advantages of cloud computing resources, improving the accuracy of the prediction model and meeting the needs of a large number of edge devices simultaneously performing rapid battery capacity testing. For example, a cloud server was built on the Alibaba Cloud computing platform, and five 320-channel battery capacity assessment devices (one 320-channel device can simultaneously control 320 battery cells for charging and discharging) and five Raspberry Pi 4B / 4G microcomputers were used as edge devices for testing. The results show that the cloud server can process the capacity prediction requests of the five capacity assessment devices in parallel. The time from each device sending a capacity prediction request to receiving the capacity prediction results of all battery cells does not exceed 30 seconds, demonstrating good performance and meeting the requirements of practical applications.

[0047] The battery capacity determination system provided in this embodiment belongs to the same inventive concept as the battery capacity determination method provided in any embodiment of the present invention, and has corresponding beneficial effects. For technical details not covered in this embodiment, please refer to the battery capacity determination method provided in any embodiment of the present invention.

[0048] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, combinations, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for determining battery capacity, characterized in that, include: Receive request information from edge devices, wherein the edge devices are edge devices for multiple target batteries; Generate cloud-based computing tasks based on the requested information; Based on the computational task, the capacity prediction results of each target battery are determined using a preset model.

2. The determination method according to claim 1, characterized in that, The step of generating a cloud-based computing task based on the request information includes: The request information is verified to obtain the verification result; When the verification result is normal, the request task for each target battery is determined according to the request information.

3. The determination method according to claim 1, characterized in that, The step of determining the capacity prediction results of each target battery based on a preset model according to the calculation task includes: According to the calculation task, read the voltage and current of each target battery; Based on the voltage and current, the capacity of each target battery is determined according to a preset model.

4. The determination method according to claim 1, characterized in that, Before receiving the request information from the edge device, the following is included: Receive the process document request from the edge device; According to the process document request, a target process document is sent to the edge device, the target process document including the charging and discharging information of the target battery.

5. The determination method according to claim 1, characterized in that, The computing task includes a task identifier, and after generating the computing task in the cloud, it includes: The task identifier is sent to the edge device.

6. The determination method according to claim 5, characterized in that, After determining the capacity prediction results of each target battery based on the preset model, the process includes: When a capacity query request is received from the edge device, the capacity prediction result is sent to the edge device according to the task identifier in the capacity query request.

7. A system for determining battery capacity, characterized in that, It includes a cloud device and an edge device, the cloud device being communicatively connected to the edge device, and the cloud device being used to perform the determination method as described in any one of claims 1-6.

8. The determining system according to claim 7, characterized in that, The cloud device includes: a cloud processing module, a cache module, a task queue module, and a cloud communication module; the cloud communication module is communicatively connected to the edge device and the cloud processing module, and the cloud processing module is communicatively connected to the cache module and the task queue module.

9. The determining system according to claim 8, characterized in that, The cloud device also includes a cloud management module and a cloud storage module, both of which are communicatively connected to the cloud processing module.

10. The determining system according to claim 8, characterized in that, The edge device includes a data acquisition module, an edge processing module, an edge storage module, and an edge communication module. The data acquisition module, the edge storage module, and the edge communication module are all electrically connected to the edge processing module, and the edge communication module is communicatively connected to the cloud communication module.

Images