A cloud intelligent trend display method and system based on data labeling

Abstract

The application belongs to the technical field of battery safety, and proposes a cloud intelligent trend display method and system based on data labeling. Through secondary calculation of derivative signals and accurate positioning of data labeling, multi-dimensional analysis of battery characteristic parameters can be automatically completed without a large number of manual participation, and the efficiency and accuracy of battery state trend analysis are significantly improved. Through data labeling, only the battery state change at the focus time is focused, rather than collecting continuous data throughout the cycle, which greatly reduces the load pressure of the cloud platform to display the characteristic parameters of the whole life cycle of the battery. The problem that the existing technology can only display short-term data changes due to platform load limitations is solved, and the overall presentation of various state characteristic parameter change trends under the whole life cycle and full-dimensional working conditions of the battery can be realized.

Description

Technical Field

[0001] This invention belongs to the field of battery safety-related technology, and in particular relates to a cloud-based intelligent trend display method and system based on data annotation. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] With the rapid development of the new energy vehicle industry, the relevant regulatory system for new energy vehicle safety is gradually being improved, placing higher demands on the safety monitoring of power batteries throughout their entire life cycle. Against this industry backdrop, major automakers have developed and implemented battery safety warning functions based on their existing vehicle digital business platforms, and the coverage of warnings continues to expand, enabling preliminary monitoring of multi-dimensional battery safety risks.

[0004] As battery warning functions have matured, new functional requirements have emerged in the industry: for the same power battery, it is necessary to explore the correlation between different types of warnings and between the same type of warnings triggered at different times, and at the same time, it is necessary to analyze the changing trends of the battery's various dimensions associated with the warnings, so as to achieve an in-depth assessment of the battery's safety status.

[0005] However, existing battery warning algorithms and supporting platforms have significant defects and shortcomings: 1. Lack of full life cycle trend analysis: Although existing early warning algorithms can achieve real-time monitoring of battery safety from multiple dimensions, they cannot intuitively present the status change trends of multiple early warning points in the same battery throughout its entire life cycle on the platform. This often requires manual analysis by technical personnel. However, the amount of data in the entire battery life cycle is huge, and manual analysis is extremely inefficient and prone to errors.

[0006] 2. Limitations in data display: While some platforms can display changes in battery data, they are limited by their load capacity and can only present monitoring data for a short period of time, failing to provide a comprehensive view of battery lifecycle data. At the same time, the data displayed by existing platforms is limited to continuous monitoring signals. They cannot intuitively analyze and visualize the trends of battery state changes at specific nodes under special operating conditions such as initial voltage changes after resting or voltage drop after charging, making it difficult to meet the safety monitoring needs of batteries under all operating conditions and throughout their entire lifecycle. Summary of the Invention

[0007] To overcome the shortcomings of the prior art, this invention provides a cloud-based intelligent trend display method and system based on data annotation. By using data annotation, only the changes in battery state at the time of interest are observed, which reduces the load on the platform to display battery characteristic parameters throughout the entire life cycle, thereby achieving a comprehensive display of the changing trends of various battery state characteristic parameters under all dimensions of the entire life cycle.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a cloud-based intelligent trend display method based on data annotation, comprising: Based on the preset data annotation naming conventions and derived signal naming conventions, a data annotation list and a derived signal list are created, and a list of associated scenario conditions corresponding to the data annotations, as well as a list of associated signals and calculation methods for calculating derived signals are compiled; wherein, the annotation data in the data annotation list is determined according to the attention time of the functional requirements; According to the data labeling list, the derived signal list, and the associated scenario condition list, the cloud platform's embedded data is tagged, and the derived signals are generated by secondary combination calculation based on the original cloud platform embedded signals and the associated signals and calculation methods of the derived signals. Based on the functional requirements of battery life cycle trend analysis, a list of observation signals and a list of display methods for the observation signals were selected. Based on the list of observed signals and the list of display requirements for the observed signals, a front-end visualization of the changing trends of battery characteristic parameters is completed.

[0009] Secondly, the present invention provides a cloud-based intelligent trend display system based on data annotation, comprising: The list creation module is configured to: create a data annotation list and a derivative signal list according to preset data annotation naming conventions and derivative signal naming conventions, and compile a list of associated scenario conditions corresponding to the data annotations, as well as a list of associated signals and calculation methods for calculating the derivative signals; wherein, the annotation data in the data annotation list is determined according to the attention time required by the functional requirements; The calculation module is configured to: tag the data points of the cloud platform according to the data label list, the derived signal list and the associated scenario condition list, and perform secondary combination calculation to generate derived signals based on the original signals of the cloud platform and the associated signals and calculation methods of the derived signals; The filtering module is configured to: filter out a list of observation signals and a list of display method requirements for the observation signals based on the functional requirements of battery life cycle trend analysis; The display module is configured to: based on the list of observed signals and the list of display method requirements for the observed signals, complete the front-end visualization display of the changing trends of battery characteristic parameters.

[0010] Thirdly, the present invention provides an electronic device including a memory and a processor, and computer instructions stored in the memory and running on the processor, wherein the computer instructions, when executed by the processor, perform the method described in the first aspect.

[0011] Fourthly, the present invention provides a computer-readable storage medium for storing computer instructions, which, when executed by a processor, perform the method described in the first aspect.

[0012] Fifthly, the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect.

[0013] The above one or more technical solutions have the following beneficial effects: This invention can automatically complete multi-dimensional analysis of battery characteristic parameters through secondary calculation of derived signals and precise positioning of data annotation, without the need for extensive manual intervention, thus significantly improving the efficiency and accuracy of battery status trend analysis.

[0014] This invention focuses on battery state changes at specific moments in time through data annotation, rather than collecting continuous data throughout the entire battery lifecycle. This significantly reduces the load on cloud platforms displaying battery lifecycle characteristic parameters. It solves the problem that existing technologies, due to platform load limitations, can only display short-term data changes, enabling a comprehensive presentation of the changing trends of various state characteristic parameters across the entire battery lifecycle and all operating conditions.

[0015] In this invention, as the data annotation system continues to improve, the number of identifiable battery operating conditions will gradually increase. This covers both conventional operating conditions such as resting, charging, and starting, as well as special operating conditions such as initial voltage changes after resting and voltage drop after charging. The entire lifecycle state change process of the battery under different operating conditions can be gradually and clearly presented, breaking the limitation of existing technologies in lacking analysis of special operating conditions.

[0016] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0017] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0018] Fig. 1This is a schematic diagram of the data annotation system in an embodiment of the present invention; Fig. 2 This is a schematic diagram illustrating the implementation process of trend analysis in an embodiment of the present invention. Detailed Implementation

[0019] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, 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 invention pertains.

[0020] It should be noted that the terminology used herein is for the purpose of describing particular implementations only and is not intended to limit the exemplary implementations of the present invention.

[0021] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0022] Example 1 like Figs. 1-2 As shown, this embodiment discloses a cloud-based intelligent trend display method based on data annotation, including: Based on the preset data annotation naming conventions and derived signal naming conventions, a data annotation list and a derived signal list are created, and a list of associated scenario conditions corresponding to the data annotations, as well as a list of associated signals and calculation methods for calculating derived signals are compiled; among them, the annotation data in the data annotation list is determined according to the attention time of the functional requirements; According to the data labeling list, the derived signal list, and the associated scenario condition list, the cloud platform's embedded data is tagged, and the derived signals are generated by secondary combination calculation based on the original cloud platform embedded signals and the associated signals and calculation methods of the derived signals. Based on the functional requirements of battery life cycle trend analysis, a list of observation signals and a list of display methods for the observation signals were selected. Based on the list of observed signals and the list of display requirements for the observed signals, a front-end visualization of the changing trends of battery characteristic parameters is completed.

[0023] This embodiment uses a data labeling system to tag moments of interest, while adding as many derivative signals as possible on the platform to analyze and display the changing trends of various battery characteristic parameters throughout the battery's life cycle.

[0024] In this embodiment, the labeled data is mainly used to determine and analyze the battery's operating condition, such as static discharge, charging, charging completion, startup, and long-term storage. The labeled data in the data labeling list is defined according to the time of interest required by the functional requirements. The time of interest is usually the time that needs to be observed, such as the moment the vehicle starts or the moment the vehicle is fully charged. Labeling the time of interest is to enable the determination and analysis of the battery's state changes under specific vehicle operating conditions.

[0025] Derived signals are primarily used to extract and comprehensively analyze battery characteristic parameters, such as cell self-discharge performance, cell charge-discharge performance, and cell consistency. Derived signals are secondary development signals, obtained by performing secondary combination calculations based on the original signals uploaded to the vehicle's platform. Examples include: summation calculations, such as ampere-hour integral signals, cumulative total charging ampere-hours, and cumulative total discharging ampere-hours; average value calculations, such as average temperature and average vehicle speed over a certain time period; and difference calculations, such as voltage differences between individual cells before and after charging, and temperature differences before and after battery pack charging.

[0026] The observation signals are mainly used for scene reproduction, showing the behavior and changes of battery characteristic parameters under different operating conditions. The observation signals can be the original embedded signals or derived signals, depending on the needs of the constructed scene.

[0027] Understandably, the data collected by the cloud platform refers to the raw, fundamental data collected from vehicle-side devices (including the Battery Management System (BMS), vehicle controller, charging piles, etc.) at pre-defined data collection points, collected at fixed frequencies or under trigger conditions, and uploaded to the cloud platform. This data serves as the data source for the entire cloud-based intelligent trend display system. Examples include core battery status data, vehicle operating condition data, charging-related data, and timestamp data. This collected data is raw data that has not undergone secondary processing. Based on this data, tagging and derived signal calculations are performed, thereby providing data support for the front-end trend display.

[0028] In this embodiment, the scenario conditions of the data annotation provide precise time / operating condition boundaries for the derived signals. For example, the start / end time of the resting period limits the calculation range of the resting duration and the self-discharge rate, ensuring the operating condition relevance of the data analysis.

[0029] This embodiment can supplement annotations and signals according to new operating conditions (such as low temperature static placement, extreme fast charging, etc.) to adapt to the iterative needs of the data annotation system.

[0030] In this embodiment, the requirements engineer creates a data annotation list and a derived signal list according to the data annotation naming conventions and derived signal naming conventions. Simultaneously, based on functional requirements, they compile a list of associated scenario conditions corresponding to the data annotations and a list of associated signals and calculation methods for calculating derived signals. The cloud platform's backend development engineers then tag the platform's embedded data according to the data annotation list, derived signal list, and associated scenario condition list provided by the requirements engineer, and perform secondary calculations on the platform's embedded signals to generate derived signals. Afterwards, the requirements engineer compiles a list of observed signals and a list of requirements for the specific display methods of the observed signals according to functional requirements. The cloud platform's frontend development engineers then develop the specific display methods for the frontend signals according to these requirements.

[0031] The following explanation uses the battery self-discharge trend as an example: The requirements engineer first sorts out the four core lists according to the preset data labeling and naming specifications and derived signal naming specifications, so as to provide a basis for subsequent labeling and analysis.

[0032] Specifically, this includes: a data annotation list: identifying the critical moment of interest for self-discharge analysis as the initial resting time. and the end of the settling time Each cell is assigned a unique label code (such as DB001 or DB002), clearly indicating that the core observation objects are the battery pack and individual cells.

[0033] List of conditions for data annotation association scenarios: Define the triggering conditions for two annotation times: the start time of stillness and the end time of stillness.

[0034] Initial resting time: The vehicle is turned off, the absolute value of the battery charging and discharging current is ≤0.05A, and this state lasts for ≥5min. The data source is the vehicle controller and the battery BMS. End of rest period: The vehicle triggers the start command, the battery detects a discharge current > 0.1A, and the previous rest period is ≥ 30min. The data source is the vehicle controller and the battery BMS.

[0035] Derivative signal list: Determine the derived signals required for self-discharge analysis, including resting time, changes in single-cell voltage before and after resting, normalized self-discharge rate, difference between adjacent normalized self-discharge rates, and statistical parameters of self-discharge rate over the entire cycle.

[0036] List of derived signal associated signals and calculation methods: Clarify the original data source and specific algorithm of each derived signal, such as resting time = resting end timestamp - resting start timestamp; normalized self-discharge rate needs to be calculated by combining temperature correction factor kT, SOC correction factor kS, and duration correction factor kTt, according to the formula "normalized self-discharge rate = (voltage change value / resting time) × kT × kS × kTt".

[0037] Based on the above list, cloud platform backend development engineers perform annotation and secondary calculation operations on the cloud-based event tracking data: The backend system monitors the raw data uploaded by the battery BMS and vehicle controller in real time. When the data meets the scenario condition of "start of static storage", it automatically tags the data at that time with DB001. When the condition of "end of static storage" is met, it automatically tags the data with DB002, thus completing the accurate marking of specific working condition time nodes and avoiding invalid collection of data throughout the entire cycle.

[0038] The calculation of the derived signal is as follows: Basic derived signal generation: The settling time is calculated using the original timestamp data, and the change in single-cell voltage before and after settling is calculated using the single-cell voltage data at the start / end of settling. Advanced derivative signal generation: Introducing raw signals such as battery temperature and state of charge (SOC), and calculating the normalized self-discharge rate according to a preset correction factor to eliminate the interference of environment and power on self-discharge assessment; at the same time, calculating the difference between adjacent normalized self-discharge rates (the difference between the nth and n-1th self-discharge rates), as well as full-cycle self-discharge rate statistical parameters (such as mean, extreme values, and variance), to achieve multi-dimensional quantification of self-discharge trends.

[0039] Based on the functional requirements of self-discharge trend analysis, the requirements engineer determines the list of observation signals, including raw signals (battery state of charge, battery temperature) and derived signals (resting time, changes in single-cell voltage before and after resting, normalized self-discharge rate, difference between adjacent self-discharge rates, and full-cycle statistical parameters).

[0040] The front-end display format of the observed signals is clearly defined as a multi-dimensional linked chart, and display rules are established.

[0041] Front-end developers created charts based on requirements, ultimately presenting a visualization of battery self-discharge trends on a cloud platform. Line chart 1: The horizontal axis represents time (sorted by resting period), and the vertical axis represents the normalized self-discharge rate. It intuitively presents the overall trend of self-discharge rate throughout the entire life cycle. If the self-discharge rate suddenly increases in a certain period, abnormal nodes can be quickly located. Bar chart: The horizontal axis represents the resting period, and the vertical axis represents the difference in normalized self-discharge rate between adjacent periods, showing the fluctuation range of self-discharge rate between adjacent periods and helping to judge the stability of battery self-discharge performance. Data panel: Simultaneously displays statistical parameters such as the mean, maximum, and variance of the self-discharge rate throughout the entire cycle, as well as key operating condition data such as battery temperature, SOC, and resting time for the corresponding cycle, enabling linked analysis of trends and operating conditions, which facilitates technicians in tracing the causes of abnormal self-discharge.

[0042] As shown in Tables 1-4 below, examples are provided for the data annotation list, the derived signal list, the list of associated scenario conditions corresponding to the data annotation, and the list of associated signals and calculation methods for calculating the derived signals.

[0043] Table 1: Data Labeling List

[0044] Table 2: List of Derivative Signals

[0045] Table 3: List of Associated Scenarios for Data Labeling

[0046] Table 4: List of Correlated Signals and Calculation Methods for Calculating Derivative Signals

[0047] By continuously improving the data annotation system, the range of operating conditions that can be identified will become increasingly rich, and the process of battery state changes under different operating conditions will become clearer and clearer. At the same time, by using data annotation to observe only the battery state changes at the moment of interest, the platform's load on displaying battery characteristic parameters throughout its entire life cycle is reduced, thereby enabling a comprehensive display of the changing trends of various battery state characteristic parameters under all dimensions of operating conditions throughout the entire life cycle.

[0048] Example 2 The purpose of this embodiment is to provide a cloud-based intelligent trend display system based on data annotation, including: The list creation module is configured to: create a data annotation list and a derivative signal list according to preset data annotation naming conventions and derivative signal naming conventions, and compile a list of associated scenario conditions corresponding to the data annotations, as well as a list of associated signals and calculation methods for calculating the derivative signals; wherein, the annotation data in the data annotation list is determined according to the attention time required by the functional requirements; The calculation module is configured to: tag the data points of the cloud platform according to the data label list, the derived signal list and the associated scenario condition list, and perform secondary combination calculation to generate derived signals based on the original signals of the cloud platform and the associated signals and calculation methods of the derived signals; The filtering module is configured to: filter out a list of observation signals and a list of display method requirements for the observation signals based on the functional requirements of battery life cycle trend analysis; The display module is configured to: based on the list of observed signals and the list of display method requirements for the observed signals, complete the front-end visualization display of the changing trends of battery characteristic parameters.

[0049] In further embodiments, the following is also provided: An electronic device includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor. When executed by the processor, the computer instructions perform the method described in Embodiment 1. For brevity, further details are omitted here.

[0050] It should be understood that in this embodiment, the processor can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0051] Memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of memory may also include non-volatile random access memory. For example, memory may also store information about the device type.

[0052] A computer-readable storage medium for storing computer instructions, which, when executed by a processor, perform the method described in Embodiment 1.

[0053] The method in Embodiment 1 can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor. The software modules can reside in readily available storage media in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, a detailed description is not provided here.

[0054] A computer program product includes a computer program that, when executed by a processor, implements the method described in Embodiment 1.

[0055] The present invention also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, which execute in a device on a target real or virtual processor to perform the processes / methods described above. Typically, program modules include routines, programs, libraries, objects, classes, components, data structures, etc., that perform specific tasks or implement specific abstract data types. In various embodiments, the functionality of program modules can be combined or divided among program modules as needed. The machine-executable instructions for the program modules can execute within a local or distributed device. In a distributed device, the program modules can reside in both local and remote storage media.

[0056] The computer program code used to implement the methods of the present invention may be written in one or more programming languages. This computer program code may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the computer or other programmable data processing device, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a computer, partially on a computer, as a stand-alone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server.

[0057] In the context of this invention, computer program code or related data may be carried by any suitable carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, and the like. Examples of signals may include electrical, optical, radio, sound, or other forms of propagation signals, such as carrier waves, infrared signals, etc.

[0058] Those skilled in the art will recognize that the units and algorithm steps described in conjunction with the embodiments 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.

[0059] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A cloud-based intelligent trend display method based on data annotation, characterized in that, include: Based on the preset data annotation naming conventions and derived signal naming conventions, a data annotation list and a derived signal list are created, and a list of associated scenario conditions corresponding to the data annotations, as well as a list of associated signals and calculation methods for calculating derived signals are compiled; wherein, the annotation data in the data annotation list is determined according to the attention time of the functional requirements; According to the data labeling list, the derived signal list, and the associated scenario condition list, the cloud platform's embedded data is tagged, and the derived signals are generated by secondary combination calculation based on the original cloud platform embedded signals and the associated signals and calculation methods of the derived signals. Based on the functional requirements of battery life cycle trend analysis, a list of observation signals and a list of display methods for the observation signals were selected. Based on the list of observed signals and the list of display requirements for the observed signals, a front-end visualization of the changing trends of battery characteristic parameters is completed.

2. The cloud-based intelligent trend display method based on data annotation as described in claim 1, characterized in that, The moments of interest include at least one of the following: the moment the vehicle starts, the moment the vehicle is fully charged, the moment the vehicle begins to stand still, the moment the vehicle ends to stand still, and the moment the charging ends.

3. The cloud-based intelligent trend display method based on data annotation as described in claim 1, characterized in that, The type of secondary combination calculation includes at least one of cumulative summation calculation, average value calculation, and difference calculation; wherein, the cumulative summation calculation is used to generate an ampere-hour integral signal, the cumulative total charging ampere-hours, and the cumulative total discharging ampere-hours; the average value calculation is used to generate the average temperature and average vehicle speed within a specified time period; and the difference calculation is used to generate the difference in single-cell voltage before and after the time, and the difference in battery pack temperature before and after charging.

4. The cloud-based intelligent trend display method based on data annotation as described in claim 1, characterized in that, The observation signal is either the original signal from the cloud platform's embedded points or the derived signal generated by calculation. The observation signal is used to reproduce specific battery operating conditions and analyze the changes in battery characteristic parameters under those conditions.

5. The cloud-based intelligent trend display method based on data annotation as described in claim 1, characterized in that, The front-end visualization is presented in the form of charts, which are used to show the changing trends of characteristic parameters throughout the battery's entire life cycle.

6. The cloud-based intelligent trend display method based on data annotation as described in claim 1, characterized in that, The labeled data is used to determine and analyze the operating condition of the battery, which includes static discharge, charging, charging completed, startup, and long-term storage. The derived signals are used to extract and comprehensively analyze the characteristic parameters of the battery, including the cell's self-discharge performance, charge and discharge performance, and consistency performance.

7. A cloud-based intelligent trend display system based on data annotation, characterized in that, include: The list creation module is configured to: create a data annotation list and a derivative signal list according to preset data annotation naming conventions and derivative signal naming conventions, and compile a list of associated scenario conditions corresponding to the data annotations, as well as a list of associated signals and calculation methods for calculating the derivative signals; wherein, the annotation data in the data annotation list is determined according to the attention time required by the functional requirements; The calculation module is configured to: tag the data points of the cloud platform according to the data label list, the derived signal list and the associated scenario condition list, and perform secondary combination calculation to generate derived signals based on the original signals of the cloud platform and the associated signals and calculation methods of the derived signals; The filtering module is configured to: filter out a list of observation signals and a list of display method requirements for the observation signals based on the functional requirements of battery life cycle trend analysis; The display module is configured to: based on the list of observed signals and the list of display method requirements for the observed signals, complete the front-end visualization display of the changing trends of battery characteristic parameters.

8. An electronic device, characterized in that, It includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor, which, when executed by the processor, perform the method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, Used to store computer instructions, which, when executed by a processor, perform the method described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program, which, when executed by a processor, implements the method described in any one of claims 1-6.

Images