Health degree evaluation method, device and equipment of battery system and storage medium

Abstract

The invention discloses a health degree assessment method, device and equipment for a battery system and a storage medium, and the method comprises the steps: firstly obtaining multi-dimensional operation data of the battery system, the multi-dimensional operation data comprises switching value data and analog quantity data, then carrying out the preprocessing of the multi-dimensional operation data, so as to obtain a preprocessing data set, and carrying out the processing of the preprocessing data set; the method comprises the following steps of: preprocessing a data set, then performing switching value fault diagnosis according to switching value data in the preprocessed data set, calculating a switching value health degree according to a diagnosis result, then calculating an analog quantity health degree according to analog quantity data in the preprocessed data set, and finally, calculating the switching value health degree according to the switching value health degree and the analog quantity health degree. And calculating to obtain the overall health degree of the battery system. According to the method, collaborative fault diagnosis of multiple parameters of the battery is successfully realized, meanwhile, a parameter contribution rate analysis system is constructed, the fault feature extraction capability is remarkably enhanced, and accurate fault positioning is realized.

Description

Technical Field

[0001] This invention relates to the field of equipment management technology, and in particular to a method, apparatus, device, and storage medium for assessing the health of a battery system. Background Technology

[0002] With the International Maritime Organization imposing increasingly stringent requirements on greenhouse gas emission reduction from ships, electric propulsion ships have attracted significant attention as a core technology for green shipping. The battery system, as the "power heart" of an electric propulsion ship, is crucial to the ship's continuous sailing capability and the safety of all personnel. A malfunction leading to a power outage can result in serious consequences such as loss of control, collisions, or even fires.

[0003] A typical battery system consists of multiple battery modules, each containing various monitoring parameters such as voltage, current, temperature, and internal resistance. However, existing battery fault diagnosis technologies have several shortcomings. First, they lack multi-parameter coupling analysis capabilities, generally focusing on single-parameter threshold alarms, making it difficult to effectively handle the comprehensive analysis of multi-dimensional, strongly coupled, and heterogeneous data. Fault feature extraction is one-sided, failing to scientifically assess the overall health of the battery system. Second, early fault warning capabilities are poor, with low sensitivity to early, weak anomalies and a lack of early identification and warning mechanisms. Third, health measurement lacks accuracy, lacking dynamic, multi-parameter fusion health assessment models, making it difficult to distinguish fault severity and dominant factors in real time, leading to delayed or excessive maintenance decisions. Fourth, computational complexity is high; existing high-dimensional data analysis algorithms are computationally intensive and cannot meet the needs of online, real-time diagnosis. Furthermore, the false alarm rate is high, failing to fully consider the correlation of multiple parameters; fluctuations in a single parameter easily trigger false alarms, reducing system reliability. Summary of the Invention

[0004] The purpose of this invention is to provide a method, apparatus, device, and storage medium for assessing the health of a battery system. This method innovatively integrates principal component analysis and dynamic weight allocation technology to achieve collaborative fault diagnosis of multiple battery parameters. By processing switch and analog quantities independently, computational resources are saved. At the same time, a parameter contribution rate analysis system is constructed to enhance the ability to extract fault features, thereby achieving accurate fault location. This effectively solves the problems of weak multi-parameter coupling analysis capability, delayed early fault warning response, insufficient accuracy of health measurement, high computational complexity, and frequent false alarms in existing battery fault diagnosis technologies.

[0005] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0006] This invention provides a method for assessing the health of a battery system, comprising: Acquire multi-dimensional operational data of the battery system, including switch data and analog data; The multi-dimensional operational data is preprocessed to obtain a preprocessed dataset; Based on the switch quantity data in the preprocessed dataset, switch quantity fault diagnosis is performed, and the switch quantity health status is calculated based on the diagnosis results. Calculate the analog health status based on the analog data in the preprocessed dataset; Based on the health status of the switch quantity and the health status of the analog quantity, the overall health status of the battery system is calculated. When the overall health status is lower than a preset threshold, a fault warning is triggered.

[0007] In one embodiment of the present invention, acquiring multi-dimensional operational data of the battery system includes: High-precision sensors are used to collect multi-dimensional operating data of the battery system in real time. The multi-dimensional operating data includes switch data and analog data. The switch data includes the status signals of the battery system, including fault signals and operation signals. The analog data includes the dynamic parameters and environmental data of the battery system. The dynamic parameters include electrical parameters, thermal management parameters and safety parameters. The environmental data includes temperature and humidity environment and mechanical environment.

[0008] In one embodiment of the present invention, the sampling frequency of the high-precision sensor is set to 1Hz.

[0009] In one embodiment of the present invention, the preprocessing of the multi-dimensional operational data to obtain a preprocessed dataset includes: Based on the dynamic fluctuation characteristics of voltage and current in the multi-dimensional operation data, the multi-dimensional operation data is classified and judged into different data subsets corresponding to different device operation states. A status label is added to each data subset. The device operation states include start-up state, stop state, and stable operation state. Extract all data subsets with stable operating states from the multi-dimensional operating data after completing state classification and discrimination, in order to construct a steady-state operating dataset; The steady-state operating dataset is cleaned and standardized to obtain the preprocessed dataset, wherein the data cleaning includes outlier removal and missing value imputation.

[0010] In one embodiment of the present invention, the step of performing switch fault diagnosis based on the switch quantity data in the preprocessed dataset and calculating the switch quantity health status based on the diagnosis results includes: Based on the switch quantity data in the preprocessed dataset, perform independent fault diagnosis for each switch quantity; If the diagnosis result indicates a fault, the health status corresponding to the switch quantity is set to the preset unhealthy baseline value; If the diagnosis result is no fault, the health status corresponding to the switch quantity will be maintained at the preset initial health baseline value. Based on the health status and preset weight of each switch quantity, the overall switch quantity health status is calculated using a weighted summation formula.

[0011] In one embodiment of the present invention, the step of calculating the analog health status based on the analog data in the preprocessed dataset includes: Calculate the Q statistic corresponding to the analog data based on the analog data in the preprocessed dataset; The health status of the simulated quantity is calculated based on the Q statistic corresponding to the simulated quantity data.

[0012] In one embodiment of the present invention, the method further includes: After a fault warning is triggered, the fault source is determined and solutions and maintenance suggestions are provided based on the diagnostic results of each switch quantity and the contribution of each analog quantity to the Q statistic.

[0013] Based on the same inventive concept, another embodiment of the present invention provides a battery system health assessment device, the device comprising: The data acquisition module is used to acquire multi-dimensional operating data of the battery system. The data types of the multi-dimensional operating data include switch quantity data and analog quantity data. The data preprocessing module is used to preprocess the multi-dimensional running data to obtain a preprocessed dataset; The health calculation module is used to perform switch fault diagnosis based on the switch quantity data in the preprocessed dataset, and calculate the switch quantity health based on the diagnosis results; and to calculate the analog quantity health based on the analog quantity data in the preprocessed dataset. The health assessment module is used to calculate the overall health of the battery system based on the health of the switch quantity and the health of the analog quantity. When the overall health is lower than a preset threshold, a fault warning is triggered.

[0014] Based on the same inventive concept, another embodiment of the present invention also provides an electronic device, the electronic device comprising: One or more processors; A storage device for storing one or more programs that, when executed by one or more processors, cause the electronic device to implement the battery system health assessment method as described in any of the above embodiments.

[0015] Based on the same inventive concept, another embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer processor, causes the computer to perform the battery system health assessment method as described in any of the above embodiments.

[0016] As described above, the present invention provides a battery system health assessment method. First, multi-dimensional operational data of the battery system is acquired, including both digital and analog data. Next, the multi-dimensional operational data is preprocessed to obtain a preprocessed dataset. Then, digital fault diagnosis is performed based on the digital data in the preprocessed dataset, and the digital health is calculated based on the diagnosis results. Following this, the analog health is calculated based on the analog data in the preprocessed dataset. Finally, the overall health of the battery system is calculated based on the digital and analog health values. When the overall health is lower than a preset threshold, a fault warning is triggered. This method relies on Principal Component Analysis (PCA) and the Q-model to comprehensively integrate the battery's multi-source coupling parameters, achieving in-depth mining and comprehensive evaluation of fault characteristics, significantly reducing false negatives and false alarms, and making the diagnostic results more reliable. Furthermore, based on the dynamic health model and residual space Q-statistics, warnings can be issued in the early stages of reversible anomalies in the battery, identifying potential risks earlier than traditional threshold methods, thus gaining valuable time for maintenance. Furthermore, by combining contribution analysis with a fault knowledge base, the system can automatically trace and visualize fault propagation paths, helping maintenance personnel quickly pinpoint the fault source and significantly shorten troubleshooting time. Moreover, the PCA algorithm, deeply optimized for ship operating conditions, effectively reduces computational complexity, ensuring diagnostic accuracy while meeting the real-time requirements of online monitoring and supporting parallel processing of large-scale battery packs. In addition, health scores are presented in a graphical dashboard, and fault location results can be expanded with a single click via a visual link, making operation simple and allowing even non-professionals to quickly grasp the system status and formulate maintenance plans. Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above simultaneously. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a method for assessing the health of a battery system, provided as an exemplary embodiment of this application.

[0019] Figure 2 A system block diagram of a battery system health assessment method provided for an exemplary embodiment of this application.

[0020] Figure 3 This is a schematic diagram of the structure of a battery system health assessment device provided as another exemplary embodiment of this application.

[0021] Figure 4 This is a schematic diagram of the structure of an electronic device provided for another exemplary embodiment of this application. Detailed Implementation

[0022] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0023] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0024] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, publicly known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0025] To address the shortcomings of existing battery fault diagnosis technologies, such as weak multi-parameter coupling analysis capabilities, delayed early fault warning response, insufficient accuracy in health measurement, high computational complexity, and frequent false alarms, this invention proposes a battery system health assessment method. This method innovatively integrates principal component analysis and dynamic weight allocation techniques to achieve collaborative fault diagnosis of multiple battery parameters. By processing switch and analog quantities independently, computational resources are saved. At the same time, a parameter contribution rate analysis system is constructed to enhance the ability to extract fault features, thereby achieving accurate fault location.

[0026] Please see Figure 1As shown in an exemplary embodiment of this application, the battery system health assessment method includes the following steps: S100: Acquire multi-dimensional operational data of the battery system, including switch data and analog data; S200: Preprocess the multi-dimensional operational data to obtain a preprocessed dataset; S300: Perform switch quantity fault diagnosis based on the switch quantity data in the preprocessed dataset, and calculate the switch quantity health status based on the diagnosis results; S400: Calculate the health status of the analog quantity based on the analog quantity data in the preprocessed dataset; S500: Calculate the overall health of the battery system based on the health of the switch quantity and the health of the analog quantity. When the overall health is lower than a preset threshold, trigger a fault warning.

[0027] First, step S100 is executed, which involves acquiring multi-dimensional operating data of the battery system, including switch data and analog data.

[0028] Specifically, in this embodiment, high-precision sensors are used to collect multi-dimensional operational data of the battery system in real time. This multi-dimensional operational data includes switch data (boolean type) and analog data (float type). The switch data includes battery system status signals, which include fault signals and operation signals. The analog data includes dynamic parameters and environmental data of the battery system. The dynamic parameters include electrical parameters, thermal management parameters, and safety parameters. The environmental data includes temperature and humidity conditions and mechanical environment conditions. In this embodiment, the fault signals include, but are not limited to, emergency fan fault signals and battery management system (BMS) protection actions. The electrical parameters include, but are not limited to, voltage, current, insulation resistance, state of charge (SOC), and state of health (SOH). The thermal management parameters include, but are not limited to, cooling medium temperature, charging interface temperature, and battery box temperature. The safety parameters include, but are not limited to, combustible gas concentration (e.g., H2, CO). The operation signals include, but are not limited to, charging status and relay status. The temperature and humidity conditions include, but are not limited to, the equipment operating environment temperature and humidity. The mechanical environment includes, but is not limited to, the mechanical vibration intensity during equipment operation. It should be noted that in this embodiment, the sampling frequency of the high-precision sensor is set to 1Hz. Of course, in other embodiments, the sampling frequency can be flexibly set to other frequency values ​​according to the actual situation, as long as the set frequency can capture the transient changes of the battery system.

[0029] Next, step S200 is performed, which involves preprocessing the multi-dimensional running data to obtain a preprocessed dataset.

[0030] In an exemplary embodiment of this application, step S200 further includes the following steps: S210: Based on the dynamic fluctuation characteristics of voltage and current in the multi-dimensional operation data, the multi-dimensional operation data is classified and judged into different data subsets corresponding to different device operation states, and a state label is added to each data subset. The device operation states include start-up state, stop state, and stable operation state. S220: Extract all data subsets with stable operating states from the multi-dimensional operating data after completing state classification and discrimination, in order to construct a steady-state operating dataset; S230: Perform data cleaning and standardization on the steady-state operating dataset to obtain the preprocessed dataset, wherein the data cleaning includes outlier removal and missing value imputation.

[0031] Specifically, the dynamic fluctuation characteristics of voltage and current data in the multi-dimensional operational data are first analyzed in depth. In this embodiment, curves showing the changes in voltage and current over time are plotted to analyze the amplitude, frequency, and trend of these fluctuations. Based on the analysis of the dynamic fluctuation characteristics of voltage and current, the multi-dimensional operational data is classified according to pre-defined state classification rules. Specifically, data conforming to the start-up state rule is labeled "Start-up State," data conforming to the stop-up state rule is labeled "Stop-up State," and data conforming to the stable operation state rule is labeled "Stable Operation State." Subsequently, from the multi-dimensional operational data after state classification, all data labeled "Stable Operation State" are selected to construct a complete steady-state operational dataset. Finally, the steady-state operational dataset is cleaned, including outlier removal and missing value imputation, and the analog data in the steady-state operational dataset is standardized to obtain the preprocessed dataset. It is worth noting that the standardization method used in this embodiment is Z-Score standardization. Of course, in other embodiments, other standardization methods may be used depending on the actual needs.

[0032] It is important to note that a Principal Component Analysis (PCA) model needs to be constructed before formally assessing the battery system's health. Specifically, firstly, historical multi-dimensional operational data of the battery system within different complete start-stop cycles is acquired, and this historical multi-dimensional operational data is used as training samples for building the PCA model. During data processing, fault diagnosis is prioritized for the switching quantity data in the historical multi-dimensional operational data. Subsequently, PCA dimensionality reduction processing is performed on the analog quantity data in the historical multi-dimensional operational data that is in a stable operating state. This process mainly includes extracting the principal component subspace and residual subspace, and determining the specific number of principal components based on the cumulative contribution rate method. After completing the construction of the PCA model, the formal health assessment process of the battery system can be carried out. This assessment will rely on the constructed PCA model to quantitatively analyze the health status of the battery system reflected at the multi-dimensional operational data level.

[0033] Next, step S300 is executed, which involves performing switch fault diagnosis based on the switch quantity data in the preprocessed dataset and calculating the switch quantity health status based on the diagnosis results.

[0034] In an exemplary embodiment of this application, step S300 further includes the following steps: S310: Perform independent fault diagnosis for each switch quantity based on the switch quantity data in the preprocessed dataset; S320: If the diagnostic result indicates a fault, the health status corresponding to the switch quantity is set to the preset unhealthy baseline value; S330: If the diagnostic result is no fault, the health status corresponding to the switch quantity will be maintained at the preset initial health benchmark value. S340: Based on the health status and preset weight of each switch quantity, the overall switch quantity health status is calculated using a weighted summation formula.

[0035] Specifically, when assessing the health of a battery system containing switching parameters (such as fault signals or operation signals), fault diagnosis of the switching parameters should be prioritized. In this embodiment, "1" represents a fault state and "0" represents a normal operating state. Taking the emergency fan fault signal as an example, when the detected emergency fan fault signal is 1, it indicates that the emergency fan has failed. At this time, it is necessary to comprehensively consider the importance of this signal to the operation of the battery system and the severity of the fault it reflects, and then assign a specific unhealthy benchmark value to the health index corresponding to this signal. The unhealthy benchmark value can be customized according to actual needs. When the detected emergency fan fault signal is 0, it indicates that the emergency fan is in a normal operating state. At this time, no operation is performed on the health index corresponding to this signal, and its value remains unchanged at the preset initial health benchmark value of 100. Finally, based on the health of each switching quantity and the preset weight, the overall switching quantity health is calculated using a weighted summation formula. .

[0036] Next, step S400 is executed, which is to calculate the analog health status based on the analog data in the preprocessed dataset.

[0037] In an exemplary embodiment of this application, step S400 further includes the following steps: S410: Calculate the Q statistic corresponding to the analog data based on the analog data in the preprocessed dataset; S420: Calculate the health status of the analog quantity based on the Q statistic corresponding to the analog quantity data.

[0038] Specifically, please refer to Figure 2 As shown, firstly, all analog parameters (such as voltage, current, temperature, etc.) in the historical multi-dimensional operational data are standardized:

[0039] in, For standardized data, The raw data collected, and The first The mean and standard deviation of each variable.

[0040] Next, the standardized data Perform PCA dimensionality reduction and calculate the standardized data. covariance matrix And perform eigenvalue decomposition:

[0041] in, It is a diagonal matrix. Covariance matrix eigenvalues, and satisfying ; It is an orthogonal matrix. The column vectors are the covariance matrix. eigenvectors; yes The former The column contains all principal information. for The remaining columns.

[0042] For new samples That is, the simulated data in the preprocessed dataset, and the Q statistic of the new sample is calculated:

[0043] in, It is an identity matrix, where all elements on the main diagonal are 1 and all other elements are 0.

[0044] In addition, the control limits for the Q statistic Calculated using the following formula:

[0045] in, , , This represents the confidence limit for the standard normal distribution.

[0046] Health status corresponding to analog quantity The calculation formula is as follows:

[0047] in, This represents the maximum health level. To characterize an unhealthy level of health.

[0048] Finally, step S500 is executed, which calculates the overall health of the battery system based on the health of the switch quantity and the health of the analog quantity. When the overall health is lower than a preset threshold, a fault warning is triggered.

[0049] Specifically, based on the health assessment results of the switching quantities. To obtain the overall health status of the equipment :

[0050] in, To simulate the weight of health status, For the first The weight of each switch quantity's health status. For the first The health status corresponding to each switch quantity.

[0051] It should be noted that the method also includes: after the fault warning is triggered, determining the fault source and providing solutions and operation and maintenance suggestions based on the diagnostic results of each switch quantity and the contribution of each analog quantity to the Q statistic.

[0052] Specifically, correlation analysis is performed on each signal, and based on expert experience, the analytic hierarchy process (AHP) is applied to calculate the dynamic weight corresponding to each signal. The contribution level is set according to the value of the switch input:

[0053] in, For the first The contribution of each switching quantity No. Data for each switch quantity, The number of unhealthy switching signals. For analog data, contribution rate analysis is used to locate abnormal parameters.

[0054] The parameter with the highest calculated contribution is the most significant source of failure. Based on the failure knowledge base, solutions and maintenance suggestions are provided for reference.

[0055] In summary, this invention provides a battery system health assessment method. This method acquires multi-dimensional operational data of the battery system, including switching quantity data and analog quantity data. The multi-dimensional operational data is then preprocessed to obtain a preprocessed dataset. Next, switching quantity fault diagnosis is performed based on the switching quantity data in the preprocessed dataset, and the switching quantity health is calculated based on the diagnosis results. Then, the analog quantity health is calculated based on the analog quantity data in the preprocessed dataset. Finally, the overall health of the battery system is calculated based on the switching quantity health and the analog quantity health. When the overall health is lower than a preset threshold, a fault warning is triggered. This method relies on Principal Component Analysis (PCA) and the Q-model to comprehensively integrate the battery's multi-source coupling parameters, achieving in-depth mining and comprehensive evaluation of fault characteristics, significantly reducing false negatives and false alarms, and making the diagnostic results more reliable. Furthermore, based on the dynamic health model and residual space Q statistics, warnings can be issued in the early stages of reversible anomalies in the battery, identifying potential risks earlier than traditional threshold methods and gaining valuable time for maintenance. Furthermore, by combining contribution analysis with a fault knowledge base, the system can automatically trace and visualize fault propagation paths, helping maintenance personnel quickly pinpoint the fault source and significantly shorten troubleshooting time. Moreover, the PCA algorithm, deeply optimized for ship operating conditions, effectively reduces computational complexity, ensuring diagnostic accuracy while meeting the real-time requirements of online monitoring and supporting parallel processing of large-scale battery packs. In addition, health scores are presented in a graphical dashboard, and fault location results can be expanded with a single click via a visual link. The system has a low operational threshold, allowing even non-professionals to quickly grasp the system status and formulate maintenance plans.

[0056] Based on the same inventive concept, please refer to Figure 3 As shown, another embodiment of the present invention also provides a battery system health assessment device 100, the device comprising: The data acquisition module 110 is used to acquire multi-dimensional operating data of the battery system, including switch data and analog data. Data preprocessing module 120 is used to preprocess the multi-dimensional running data to obtain a preprocessed dataset; The health calculation module 130 is used to perform switch quantity fault diagnosis based on the switch quantity data in the preprocessed dataset, and calculate the switch quantity health based on the diagnosis results; and to calculate the analog quantity health based on the analog quantity data in the preprocessed dataset. The health assessment module 140 is used to calculate the overall health of the battery system based on the health of the switch quantity and the health of the analog quantity, and to trigger a fault warning when the overall health is lower than a preset threshold.

[0057] It should be noted that the battery system health assessment device 100 includes the battery system health assessment method described in any of the above embodiments. Since the battery system health assessment device 100 provided in this embodiment belongs to the same inventive concept as the battery system health assessment method provided in any of the above embodiments, it has at least the same beneficial effects, and will not be described in detail here.

[0058] Based on the same inventive concept, please refer to Figure 4 As shown, another embodiment of the present invention also provides an electronic device 11, which may include a memory 111, a processor 112 and a bus, and may also include a computer program stored in the memory 111 and executable on the processor 112, such as a battery system health assessment program.

[0059] The memory 111 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 111 can be an internal storage unit of the electronic device 11, such as a portable hard drive of the electronic device 11. In other embodiments, the memory 111 can be an external storage device of the electronic device 11, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., equipped on the electronic device 11. Furthermore, the memory 111 can include both internal and external storage units of the electronic device 11. The memory 111 can be used not only to store application software and various types of data installed on the electronic device 11, such as code for assessing the health of the battery system, but also to temporarily store data that has been output or will be output.

[0060] In some embodiments, the processor 112 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 112 is the control unit of the electronic device 11, connecting various components of the electronic device 11 via various interfaces and lines. It executes programs or modules stored in the memory 111 (e.g., battery system health assessment programs) and calls data stored in the memory 111 to perform various functions and process data for the electronic device 11.

[0061] The processor 112 executes the operating system of the electronic device 11 and various installed applications. The processor 112 executes the applications to implement the steps in the above-described battery system health assessment method.

[0062] For example, the computer program may be divided into one or more modules, which are stored in the memory 111 and executed by the processor 112 to complete this application. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the electronic device 11. For example, the computer program may be divided into a data acquisition module 110, a data preprocessing module 120, a health calculation module 130, and a health assessment module 140.

[0063] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium, which can be non-volatile or volatile. The software functional module, stored in the storage medium, includes several instructions to cause a computer device (which may be a personal computer, computer equipment, or network device, etc.) or processor to execute some functions of the battery system health assessment method described in the various embodiments of this application.

[0064] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for assessing the health of a battery system, characterized in that, include: Acquire multi-dimensional operational data of the battery system, including switch data and analog data; The multi-dimensional operational data is preprocessed to obtain a preprocessed dataset; Based on the switch quantity data in the preprocessed dataset, switch quantity fault diagnosis is performed, and the switch quantity health status is calculated based on the diagnosis results. Calculate the analog health status based on the analog data in the preprocessed dataset; Based on the health status of the switch quantity and the health status of the analog quantity, the overall health status of the battery system is calculated. When the overall health status is lower than a preset threshold, a fault warning is triggered.

2. The method for assessing the health of a battery system according to claim 1, characterized in that, The acquisition of multi-dimensional operational data of the battery system includes: High-precision sensors are used to collect multi-dimensional operating data of the battery system in real time. The multi-dimensional operating data includes switch data and analog data. The switch data includes the status signals of the battery system, including fault signals and operation signals. The analog data includes the dynamic parameters and environmental data of the battery system. The dynamic parameters include electrical parameters, thermal management parameters and safety parameters. The environmental data includes temperature and humidity environment and mechanical environment.

3. The method for assessing the health of a battery system according to claim 2, characterized in that, The sampling frequency of the high-precision sensor is set to 1Hz.

4. The method for assessing the health of a battery system according to claim 1, characterized in that, The preprocessing of the multi-dimensional operational data to obtain a preprocessed dataset includes: Based on the dynamic fluctuation characteristics of voltage and current in the multi-dimensional operation data, the multi-dimensional operation data is classified and judged into different data subsets corresponding to different device operation states. A status label is added to each data subset. The device operation states include start-up state, stop state, and stable operation state. Extract all data subsets with stable operating states from the multi-dimensional operating data after completing state classification and discrimination, in order to construct a steady-state operating dataset; The steady-state operating dataset is cleaned and standardized to obtain the preprocessed dataset, wherein the data cleaning includes outlier removal and missing value imputation.

5. The method for assessing the health of a battery system according to claim 1, characterized in that, The step of performing switch fault diagnosis based on the switch quantity data in the preprocessed dataset, and calculating the switch quantity health status based on the diagnosis results, includes: Based on the switch quantity data in the preprocessed dataset, perform independent fault diagnosis for each switch quantity; If the diagnosis result indicates a fault, the health status corresponding to the switch quantity is set to the preset unhealthy baseline value; If the diagnosis result is no fault, the health status corresponding to the switch quantity will be maintained at the preset initial health baseline value. Based on the health status and preset weight of each switch quantity, the overall switch quantity health status is calculated using a weighted summation formula.

6. The method for assessing the health of a battery system according to claim 1, characterized in that, The step of calculating the analog health status based on the analog data in the preprocessed dataset includes: Calculate the Q statistic corresponding to the analog data based on the analog data in the preprocessed dataset; The health status of the simulated quantity is calculated based on the Q statistic corresponding to the simulated quantity data.

7. The method for assessing the health of a battery system according to claim 1, characterized in that, The method further includes: After a fault warning is triggered, the fault source is determined and solutions and maintenance suggestions are provided based on the diagnostic results of each switch quantity and the contribution of each analog quantity to the Q statistic.

8. A battery system health assessment device, characterized in that, The device includes: The data acquisition module is used to acquire multi-dimensional operating data of the battery system, including switch quantity data and analog quantity data. The data preprocessing module is used to preprocess the multi-dimensional running data to obtain a preprocessed dataset; The health calculation module is used to perform switch fault diagnosis based on the switch quantity data in the preprocessed dataset, and calculate the switch quantity health based on the diagnosis results; and to calculate the analog quantity health based on the analog quantity data in the preprocessed dataset. The health assessment module is used to calculate the overall health of the battery system based on the health of the switch quantity and the health of the analog quantity. When the overall health is lower than a preset threshold, a fault warning is triggered.

9. An electronic device, characterized in that, The electronic device includes: One or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the battery system health assessment method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by the computer's processor, causes the computer to perform the health assessment method for the battery system as described in any one of claims 1 to 7.

Images