Battery pack monitoring method and device, electronic equipment and storage medium

Abstract

The invention provides a battery pack monitoring method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining multi-dimensional parameters of a target battery pack, the multi-dimensional parameters comprising a standby power duration parameter, a capacity parameter, a reliability parameter, a data integrity parameter, a decay speed parameter, a hidden danger improvement parameter, a hidden danger work order parameter and an offline parameter; according to the multi-dimensional parameters, evaluating the health degree of the target battery pack to obtain a target health degree; and performing maintenance control on the target battery pack according to the target health degree. According to the invention, comprehensive and accurate evaluation of the health degree of the battery pack is realized by collecting the multi-dimensional parameters of the battery pack, the maintenance decision performance is effectively improved, the scientificity and effectiveness of health management and control of the storage battery pack are improved, and the operation cost and the power supply interruption risk are remarkably reduced.

Description

Technical Field

[0001] This invention relates to the field of equipment monitoring technology, and in particular to a battery pack monitoring method, device, electronic equipment, and storage medium. Background Technology

[0002] With the increasing demands for power supply reliability from critical infrastructure such as communication base stations, data centers, and power systems, the accurate assessment and scientific maintenance of battery packs, as the core backup power source for ensuring uninterrupted power supply, have become key technical requirements for ensuring the safe and stable operation of systems. Currently, for battery pack monitoring, existing technologies mainly rely on the electrochemical characteristics of the battery pack itself, such as electrical parameters like charging and discharging current and terminal voltage, to monitor the battery pack's health. This results in a one-sided and inaccurate assessment of health, failing to provide a comprehensive basis for maintenance decisions. Consequently, maintenance may be delayed or excessive, increasing operating costs and system risks. Summary of the Invention

[0003] This invention provides a battery pack monitoring method, device, electronic device, and storage medium to address the shortcomings of existing battery pack health assessments, which are characterized by bias, inaccurate results, and inability to provide a comprehensive basis for maintenance decisions. The invention aims to improve the comprehensiveness and accuracy of health assessments, thereby enhancing the performance of maintenance decisions.

[0004] This invention provides a battery pack monitoring method, comprising: Obtain multi-dimensional parameters of the target battery pack, including backup power duration parameters, capacity parameters, reliability parameters, data integrity parameters, degradation rate parameters, hidden danger remediation parameters, hidden danger work order parameters, and offline parameters; The health of the target battery pack is evaluated based on the multi-dimensional parameters to obtain the target health. Based on the target health status, the target battery pack is maintained and controlled.

[0005] According to a battery pack monitoring method provided by the present invention, the step of evaluating the health of the target battery pack based on the multi-dimensional parameters to obtain the target health includes: The multi-dimensional parameters are preprocessed, including outlier removal and / or missing value imputation. The processed multi-dimensional parameters are standardized to obtain the standardized values ​​of the parameters in each dimension; The health of the target battery pack is evaluated based on the standardized values ​​of the parameters in each dimension and the corresponding weight values ​​of the parameters in each dimension, thereby obtaining the target health.

[0006] According to a battery pack monitoring method provided by the present invention, the step of evaluating the health of the target battery pack based on the standardized values ​​of the parameters in each dimension and the weight values ​​corresponding to the parameters in each dimension, to obtain the target health, includes: Calculate the membership degree of the standardized values ​​of the parameters in each dimension to each preset health level to form a fuzzy evaluation matrix; The target health score is obtained by combining the weight values ​​corresponding to the parameters of each dimension with the fuzzy evaluation matrix.

[0007] According to a battery pack monitoring method provided by the present invention, the steps for determining the weight values ​​corresponding to the parameters in each dimension include: Analyze the impact of the parameters in each dimension on the health assessment of the target battery pack; Based on the degree of influence, determine the weight values ​​corresponding to the parameters of each dimension.

[0008] According to a battery pack monitoring method provided by the present invention, determining the weight values ​​corresponding to the parameters of each dimension based on the degree of influence includes: Based on the degree of influence, determine the initial weight values ​​corresponding to the parameters of each dimension; Based on the lifecycle node of the target battery pack and the scenario type in which the target battery pack is located, the initial weight values ​​corresponding to the parameters of each dimension are adjusted to obtain the weight values ​​corresponding to the parameters of each dimension.

[0009] According to a battery pack monitoring method provided by the present invention, the backup power duration parameter includes at least one of the following: discharge start time, discharge end time, and load current during the discharge process. The capacity parameters include at least one of the capacity calculation duration and the remaining capacity duration; The data integrity parameters include at least one of the following: data collection integrity rate, data reporting success rate, and inaccurate or abnormal data from the device. The hazard remediation parameters include at least one of the following: out-of-service hazard remediation work order data, hazard remediation completion rate, and hazard remediation timeliness rate; The hazard work order parameters include at least one of the following: unarchived hazard data and the number of pending hazard work orders; The offline parameters include at least one of the number of offline times and the total offline duration.

[0010] According to a battery pack monitoring method provided by the present invention, the step of performing maintenance control on the target battery pack based on the target health status includes: Based on the target health level, the health level of the target battery pack is determined from multiple preset health levels to obtain the target health level; the multiple preset health levels include a first health level, a second health level, a third health level, a fourth health level, and a fifth health level; the health level corresponding to the first health level is greater than or equal to a first threshold, the health level corresponding to the second health level is greater than or equal to a second threshold and less than the first threshold, the health level corresponding to the third health level is greater than or equal to a third threshold and less than the second threshold, the health level corresponding to the fourth health level is greater than or equal to a fourth threshold and less than the third threshold, and the health level corresponding to the fifth health level is less than the fourth threshold; When the target health level is the fourth health level or the fifth health level, a target warning mode is determined from multiple preset warning modes according to the target health level; each preset warning mode corresponds to a different warning object, warning method and warning content; The target battery is maintained and controlled according to the target early warning mode.

[0011] The present invention also provides a battery pack monitoring device, comprising: The parameter acquisition unit is used to acquire multi-dimensional parameters of the target battery pack, including backup power duration parameters, capacity parameters, reliability parameters, data integrity parameters, degradation rate parameters, hidden danger remediation parameters, hidden danger work order parameters, and offline parameters. An evaluation unit is used to evaluate the health of the target battery pack based on the multi-dimensional parameters to obtain the target health. A control unit is used to perform maintenance control on the target battery pack based on the target health status.

[0012] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the battery pack monitoring method as described above.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the battery pack monitoring method as described above.

[0014] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the battery pack monitoring method as described above.

[0015] The battery pack monitoring method, device, electronic equipment, and storage medium provided by this invention fundamentally overcome the limitations of existing technologies that rely solely on electrochemical characteristics by acquiring eight multi-dimensional parameters covering backup power duration, capacity, reliability, data integrity, degradation rate, hazard remediation, hazard work orders, and offline status. This expands health assessment from a single physical dimension to a comprehensive system integrating equipment performance, operation and maintenance management, data quality, and risk exposure, enabling accurate identification of availability degradation caused by non-electrochemical factors such as data loss, hazard backlog, or communication interruptions. The target health level obtained based on this multi-dimensional parameter assessment is no longer a one-sided performance indicator but a reliable quantitative result that comprehensively and accurately reflects the actual safe operating status of the battery pack, providing a complete basis for maintenance decisions. Furthermore, by directly triggering differentiated maintenance control based on this target health level, an intelligent linkage mechanism from status assessment to control actions is established, enabling timely early warning and precise maintenance of high-risk battery packs. This avoids the maintenance lag or over-maintenance problems caused by incomplete information in traditional technologies, ultimately significantly reducing the operating costs of critical infrastructure and the risk of power outages. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the battery pack monitoring method provided by the present invention.

[0018] Figure 2 This is a schematic diagram of the battery pack monitoring device provided by the present invention.

[0019] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0021] It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments of the present invention can be combined with each other. The terms "first," "second," etc., used in this invention are only used to distinguish different objects or steps and do not indicate any specific order or importance. The terms "comprising," "including," etc., used in this invention are open-ended descriptions and should not be construed as exclusive limitations.

[0022] Battery packs serve as backup power sources in numerous industries, including telecommunications, power, and finance, and their stable operation is crucial for ensuring uninterrupted system operation. However, current battery pack monitoring often focuses on monitoring single or a few parameters related to electrochemical characteristics. It lacks systematic integrated analysis of key dimensions such as backup power duration, capacity changes, reliability parameters, and operational parameters. This results in incomplete health assessments, failing to provide a comprehensive basis for maintenance decisions and frequently leading to untimely or excessive maintenance, increasing operating costs and system risks.

[0023] To address this issue, this application provides a battery pack monitoring method. This method collects multi-dimensional parameters from the battery pack, including backup power duration, capacity, reliability, data integrity, degradation rate, potential hazard remediation, hazard work order parameters, and offline parameters. After data processing and analysis, it achieves a comprehensive and accurate assessment of the battery pack's health. Based on the assessed health, it makes maintenance decisions for the battery pack, effectively improving the performance of maintenance decisions, enhancing the scientific nature and effectiveness of battery pack health management, reducing failure risks, and consequently lowering operating costs and system risks.

[0024] Figure 1 This is a flowchart illustrating the battery pack monitoring method provided by the present invention, as shown below. Figure 1 As shown, the method includes steps 110, 120 and 130.

[0025] Step 110: Obtain multi-dimensional parameters of the target battery pack. These multi-dimensional parameters include backup power duration parameters, capacity parameters, reliability parameters, data integrity parameters, degradation rate parameters, hidden danger remediation parameters, hidden danger work order parameters, and offline parameters.

[0026] The target battery pack here refers to a battery pack that requires health status monitoring and maintenance management. Specifically, it can be a lead-acid battery pack, lithium-ion battery pack, or other types of energy storage battery pack used as backup power in fields such as communication base stations, data centers, power systems, or rail transportation. This target battery pack is usually composed of multiple individual cells connected in series and parallel, and has a corresponding Battery Management System (BMS) and remote monitoring interface.

[0027] Optionally, when it is necessary to monitor and maintain the health status of the target battery pack, multi-dimensional parameters of the target battery pack can be collected first. For example, multi-dimensional parameters of the battery pack can be collected through sensors and / or data acquisition modules to comprehensively collect relevant parameters that reflect the health status of the battery pack.

[0028] This multi-dimensional parameter specifically includes parameters in the following dimensions: Backup power duration parameter refers to a time-related parameter that reflects the backup power capability of the battery pack. In one possible implementation, backup power duration parameter includes, but is not limited to, at least one of the following: discharge start time, discharge end time, and load current curve during discharge recorded in historical discharge tests, so as to reflect the continuous power supply capability of the target battery pack in actual application scenarios.

[0029] Capacity parameters refer to core parameters reflecting the energy storage capacity of a battery pack. In one possible implementation, this capacity parameter includes at least one of the following: rated capacity calculation time and remaining capacity time. Rated capacity calculation time refers to the time it takes for the battery pack to discharge from a fully charged state to its termination voltage, as measured by a rated capacity discharge test; remaining capacity time refers to the predicted sustainable discharge time based on the current state of the battery pack. This capacity parameter integrates actual rated capacity test data and real-time estimated data, making the data source more comprehensive and reliable.

[0030] Reliability parameters: These are parameters that reflect the stability and reliability of battery pack operation. In one possible implementation, the reliability parameters may include at least one of the following statistical indicators: battery pack cycle life, number of overcharge and over-discharge events, number of temperature exceedances, and voltage fluctuation amplitude, to assess the reliability level of the battery pack during long-term operation.

[0031] Data integrity parameters: These are parameters reflecting the quality of battery pack monitoring data acquisition and transmission. In one possible implementation, these parameters may include at least one of the following: data acquisition completeness rate (the ratio of actual acquired data points to required data points), data reporting success rate (the proportion of data packets successfully reported to the monitoring center), and inaccurate or abnormal data from the equipment (the number of abnormal measurements caused by sensor malfunctions or communication interference). By incorporating data integrity parameters into the health assessment system, the problem of assessment bias caused by missing or erroneous data can be effectively solved.

[0032] Degradation rate parameter: This refers to a parameter reflecting the rate of performance degradation of the battery pack. In one possible implementation, this degradation rate parameter can be calculated by comparing indicators such as capacity retention, internal resistance change rate, and terminal voltage drop rate at different times. The introduction of the degradation rate parameter allows health assessment to not only focus on the current state but also predict future performance trends, achieving proactive health management.

[0033] Hazard remediation parameters: These are operation and maintenance management parameters that reflect the investigation and remediation of safety hazards in battery packs. In one possible implementation, these hazard remediation parameters may include at least one of the following: out-of-service hazard remediation work order data (records of completed hazard remediation work orders), hazard remediation completion rate (the ratio of the number of rectified hazards to the total number of discovered hazards), and hazard remediation timeliness rate (the proportion of work orders that are rectified on time).

[0034] Hazard Work Order Parameters: These parameters reflect the status of unresolved hazards. In one possible implementation, the hazard work order parameters specifically include at least one of the following: unarchived hazard data (hazard information that has been discovered but not entered into the system) and the number of pending hazard work orders (the number of hazard remediation tasks currently being processed). This parameter reflects the current risk exposure of the battery pack and directly affects the health assessment results.

[0035] Offline parameters: These are parameters reflecting the communication status of the battery pack monitoring equipment. In one possible implementation, these offline parameters include at least one of the following: number of offline occurrences (the number of times the monitoring equipment disconnects from the host computer within a statistical period) and total offline duration (cumulative offline time). The introduction of offline parameters effectively identifies the risk of data loss due to communication interruptions, improving the robustness of the evaluation system.

[0036] It should be noted that the acquisition of the aforementioned multi-dimensional parameters includes two modes: active acquisition and passive reception. Active acquisition refers to the automatic collection of multi-dimensional parameters by sensors and data acquisition modules deployed at the target battery pack according to a preset cycle (e.g., every 5 minutes). Passive reception refers to retrieving management information of the target battery pack from the upper-level operation and maintenance management system (such as a power environment monitoring system or an asset management system) to obtain multi-dimensional parameters, etc. This embodiment does not specifically limit this.

[0037] Step 120: Evaluate the health of the target battery pack based on the multi-dimensional parameters to obtain the target health.

[0038] Optionally, the core idea of ​​the health assessment process is to transform multi-dimensional parameters with different sources, dimensions, and physical meanings into a unified health quantification index, thereby achieving a leap from local state observation to overall health cognition.

[0039] Specifically, after collecting multi-dimensional parameters, the acquired parameters can be combined to calculate a comprehensive health score, i.e., the target health score, using a pre-defined health assessment model. This health assessment model can be a linear model that assigns different weights to each dimension parameter and then performs a weighted summation, or it can be a non-linear model based on machine learning algorithms, such as neural networks or support vector machines.

[0040] Step 130: Perform maintenance control on the target battery pack based on the target health status.

[0041] Optionally, after obtaining the target health level, corresponding dimensional management actions can be triggered based on the target health level. This maintenance control includes, but is not limited to: generating a health assessment report, triggering tiered alerts, generating inspection work orders, adjusting charging and discharging strategies, initiating remote diagnostics, and scheduling maintenance resources. For example, when the target health level is lower than a preset threshold, the system automatically sends an alert to maintenance personnel and recommends prioritizing the handling of potential hazard work orders; when the health level is higher than the preset threshold, the system can extend the regular inspection cycle and optimize the allocation of maintenance resources.

[0042] Understandably, this embodiment overcomes the limitations of existing technologies that rely solely on the electrochemical characteristics of the battery pack itself for health assessment by integrating multi-dimensional parameters. It incorporates parameters such as backup power duration, capacity, degradation rate, reliability, operation and maintenance management data, and data quality indicators into the assessment system, achieving an upgrade from single performance monitoring to comprehensive health management. This multi-dimensional integrated assessment method can more accurately identify potential risks in the battery pack, particularly identifying risks of misjudgment due to data quality issues or missing management processes, as well as availability degradation caused by accumulated hidden dangers or frequent offline operations. This provides a reliable basis for refined operation and maintenance and precise resource allocation. Simultaneously, by directly translating the assessment results into executable control actions through maintenance control steps, a closed-loop management system of monitoring-assessment-control is formed, significantly improving the intelligence level and response efficiency of battery pack operation and maintenance, and reducing the risk of power outages due to battery pack failure.

[0043] The method provided in this embodiment fundamentally breaks through the limitations of existing technologies that rely solely on electrochemical characteristics by acquiring eight multi-dimensional parameters covering backup power duration, capacity, reliability, data integrity, degradation rate, hazard remediation, hazard work orders, and offline status. This expands health assessment from a single physical dimension to a comprehensive system integrating equipment performance, operation and maintenance management, data quality, and risk exposure. This allows for accurate identification of availability degradation caused by non-electrochemical factors such as data loss, hazard backlog, or communication interruptions. The target health level obtained from this multi-dimensional parameter assessment is no longer a one-sided performance indicator but a reliable quantitative result that comprehensively and accurately reflects the actual safe operating status of the battery pack, providing a complete basis for maintenance decisions. Furthermore, by directly triggering differentiated maintenance control based on this target health level, an intelligent linkage mechanism from status assessment to control actions is established. This enables timely early warning and precise maintenance of high-risk battery packs, avoiding the maintenance delays or over-maintenance problems caused by incomplete information in traditional technologies. Ultimately, this significantly reduces the operating costs of critical infrastructure and the risk of power outages.

[0044] In some embodiments, step 120 specifically includes steps 121, 122 and 123.

[0045] Step 121: Preprocess the multi-dimensional parameters, including outlier removal and / or missing value imputation.

[0046] Optionally, after obtaining the multi-dimensional parameters, in order to improve the quality of the multi-dimensional parameters and avoid low-quality data from interfering with the evaluation results, outlier removal and / or missing value imputation can be performed on the multi-dimensional parameters.

[0047] In one possible implementation, outlier removal can be achieved using methods such as box plots. Box plots are an anomaly detection method based on the statistical distribution characteristics of data. They do not require a pre-defined data distribution pattern and are highly adaptable to non-normally distributed data. For a parameter dataset of a certain dimension, the first quartile Q1 (i.e., the 25th quartile) and the third quartile Q3 (i.e., the 75th quartile) are first calculated, and then the interquartile range IQR = Q3 - Q1 is obtained. The range of normal data is defined as [Q1 - 1.5 × IQR, Q3 + 1.5 × IQR]. Data points exceeding this range are considered outliers and removed. For example, in the capacity measurement duration parameter, if a test value deviates significantly from the historical data distribution due to test equipment failure or operational error (e.g., exceeding the upper limit of the normal range), this data point is determined to be an outlier and will not participate in subsequent health calculations, thus preventing a single outlier test from distorting the overall evaluation result.

[0048] In one possible implementation, missing value imputation can be achieved using interpolation. Interpolation is a method of estimating missing values ​​based on the changing trends of known data points, which can maintain the continuity of the time series even when data is missing. For time series parameters (such as backup power duration parameters and capacity parameters), linear interpolation, polynomial interpolation, or spline interpolation can be used to imput missing values. For non-time series parameters, mean interpolation or mean interpolation of similar equipment can be used to ensure the integrity of the dataset.

[0049] Step 122: Standardize the processed multi-dimensional parameters to obtain the standardized values ​​of the parameters in each dimension.

[0050] Optionally, since parameters of different dimensions have different physical dimensions and numerical ranges, directly processing them together can lead to parameters with larger numerical ranges dominating the evaluation, while the contribution of parameters with smaller numerical ranges is diluted, resulting in biased evaluation results. Therefore, standardization can be used to eliminate the influence of dimensions, making parameters of different dimensions comparable on a uniform numerical scale.

[0051] Specifically, the processed multi-dimensional parameters can be standardized to convert parameters of different magnitudes to a unified numerical range, thereby obtaining the standardized values ​​of each dimension parameter. For example, the min-max standardization method can be used to convert parameters of different magnitudes to the [-1,1] range, etc. This embodiment does not specifically limit this.

[0052] Step 123: Evaluate the health of the target battery pack based on the standardized values ​​of the parameters in each dimension and the corresponding weight values ​​of the parameters in each dimension, and obtain the target health.

[0053] Optionally, after obtaining the standardized values ​​of each dimension parameter, the health of the target battery pack can be assessed by combining the standardized values ​​of each dimension parameter with the corresponding weight values ​​of each dimension parameter to obtain the target health.

[0054] In one possible implementation, the standardized values ​​of each dimension parameter are directly weighted and summed with the corresponding weight values ​​of each dimension parameter to obtain the target health score. The specific calculation formula is: Target health score = ∑ (standardized value of each dimension parameter × weight value of each dimension parameter), where the sum of the weight values ​​of all dimension parameters is 1.

[0055] In another possible implementation, the fuzzy comprehensive evaluation method is combined with the fuzzy membership degree calculation of the standardized values ​​of each dimension parameter, and then the weighted sum is performed with the weight values ​​corresponding to each dimension parameter to obtain the target health degree.

[0056] It should be noted that the weight values ​​corresponding to each dimension parameter can be pre-configured according to actual needs, allowing for rapid weight setting based on operational experience, reducing system implementation complexity and improving deployment efficiency; alternatively, they can be automatically obtained through analytic hierarchy process (AHP), quantifying subjective experience by constructing a parameter importance judgment matrix and mathematically solving for it, significantly improving the scientific and objective nature of weight allocation, and making the evaluation results more consistent with actual impact patterns; or, they can be obtained by associating the target battery pack's life cycle node with the scenario type in which it operates, enabling the weights to dynamically adapt to different stages of the battery pack, such as new commissioning, stable operation, performance degradation, and near retirement, as well as different scenarios such as high reliability, conventional, and economical. The differentiated needs of application scenarios enhance the scenario adaptability and result relevance of the evaluation system; alternatively, the initial weight values ​​can be automatically obtained by analyzing the analytic hierarchy process first, and then the corresponding weight coefficient allocation strategy can be obtained by associating the life cycle node of the target battery pack with the scenario type of the target battery pack. The initial weight values ​​can then be adjusted according to the corresponding weight coefficient allocation strategy. This ensures both the theoretical rigor of the initial weight setting and the dynamic optimization adjustment based on actual working conditions, making the evaluation model both scientific and flexible. It can continuously output the optimal evaluation results in complex and ever-changing operation and maintenance environments, thereby greatly improving the accuracy and engineering practicality of health assessment. This embodiment does not make specific limitations on this.

[0057] The method provided in this embodiment systematically preprocesses data to effectively eliminate abnormal interference and fill in missing data. Through standardized processing, it solves the problem of fusion caused by differences in the magnitude of multi-dimensional data, enabling parameters of different types and physical meanings to work synergistically under a unified framework. This significantly improves the scientificity, adaptability, and anti-interference ability of the evaluation model, and significantly improves the accuracy, comparability, and model adaptability of health assessment.

[0058] In some embodiments, step 123 specifically includes steps 123-1 and 123-2.

[0059] Step 123-1: Calculate the membership degree of the standardized values ​​of the parameters in each dimension to each preset health level, forming a fuzzy evaluation matrix.

[0060] Optionally, the battery pack health status can be divided into m preset health levels. For example, it can be divided into 5 levels: first health level (or excellent), second health level (or good), third health level (or average), fourth health level (or poor), and fifth health level (or severe), which correspond to different availability levels of the battery pack in actual applications. The health level of the first health level is greater than or equal to a first threshold, the health level of the second health level is greater than or equal to a second threshold and less than a first threshold, the health level of the third health level is greater than or equal to a third threshold and less than a second threshold, the health level of the fourth health level is greater than or equal to a fourth threshold and less than a third threshold, and the health level of the fifth health level is less than a fourth threshold.

[0061] For each dimension parameter, its membership degree to each preset health level is calculated based on its standardized value x' using a preset membership function. The membership function can be a triangular or trapezoidal function. The shape and boundary points of the membership function can be determined based on historical data and expert experience to effectively address the problem of rigid division when parameter values ​​are at level boundaries through fuzzification, making the assessment smoother and more reasonable.

[0062] Therefore, after obtaining the membership degrees of the standardized values ​​of each dimension parameter to each preset health level, an n×m fuzzy evaluation matrix R can be constructed, where n is the total number of parameter dimensions and m is the number of health levels. The matrix element r_{ij} in the fuzzy evaluation matrix R represents the membership degree of the i-th dimension parameter to the j-th health level, satisfying 0≤r_{ij}≤1. This matrix integrates the fuzzy membership relationships of all dimension parameters to each health level.

[0063] Step 123-2: Combine and calculate the weight values ​​and fuzzy evaluation matrix corresponding to each dimension parameter to obtain the target health score.

[0064] Optionally, after obtaining the fuzzy evaluation matrix, a fuzzy synthesis operator can be used to synthesize the weight vector W=(w_1, w_2, ..., w_n) with the fuzzy evaluation matrix R to obtain a comprehensive fuzzy evaluation vector; finally, based on the maximum membership principle or the weighted average principle, the specific value of the target health degree is determined from the comprehensive fuzzy evaluation vector.

[0065] The method provided in this embodiment transforms deterministic parameter values ​​into fuzzy membership relationships to health levels through membership functions, and then performs weighted synthesis. This method can better handle the fuzziness of the evaluation boundary and the complex nonlinear coupling relationship between parameters, making the evaluation results more consistent with the actual laws of engineering practice.

[0066] In some embodiments, the steps for determining the weight values ​​corresponding to the parameters of each dimension include: Analyze the impact of the parameters in each dimension on the health assessment of the target battery pack; Based on the degree of influence, determine the weight values ​​corresponding to the parameters of each dimension.

[0067] Optionally, in determining the weight values ​​corresponding to each dimension parameter, the analytic hierarchy process can be used. By constructing a parameter importance judgment matrix, the relative importance of each parameter to the health assessment can be compared pairwise, thereby obtaining the degree of influence of each dimension parameter on the health assessment of the target battery pack.

[0068] After completing the influence analysis, the results are quantified into standardized weight coefficients. When using the analytic hierarchy process (AHP) for influence analysis, the initial weight values ​​for each dimension parameter can be obtained by calculating the largest eigenvalue of the judgment matrix and its corresponding eigenvector, and then normalizing the eigenvector.

[0069] After obtaining the initial weight values ​​of each dimension parameter, they can be directly used as the final weight values ​​corresponding to each dimension parameter, or the initial weight values ​​of each dimension parameter can be adjusted based on the specific application scenario, such as the life cycle node of the target battery pack and / or the scenario type of the target battery pack, to obtain the final weight values ​​corresponding to each dimension parameter, etc. This embodiment does not make specific limitations in this regard.

[0070] The method provided in this embodiment systematically analyzes the degree of influence and establishes the weight allocation on an objective quantitative basis, which significantly improves the scientificity, consistency and traceability of the weight setting, avoids the arbitrariness of the weight setting, and makes the health assessment results more reflect the true contribution of each parameter.

[0071] In some embodiments, the step of determining the weight values ​​corresponding to each dimension parameter based on the degree of influence further includes: Based on the degree of influence, determine the initial weight values ​​corresponding to the parameters of each dimension; Based on the lifecycle node of the target battery pack and the scenario type in which the target battery pack is located, the initial weight values ​​corresponding to the parameters of each dimension are adjusted to obtain the weight values ​​corresponding to the parameters of each dimension.

[0072] Optionally, when using the analytic hierarchy process (AHP) to analyze the degree of influence, the initial weight values ​​of each dimension parameter can be obtained by calculating the largest eigenvalue of the judgment matrix and its corresponding eigenvector, and then normalizing the eigenvector.

[0073] Since the weight of each dimension parameter on health varies at different lifecycle stages, and the degree of importance attached to each dimension parameter varies in different application scenarios, in order to dynamically adapt the weight allocation to the actual working conditions of battery pack operation and maintenance, after obtaining the initial weight values ​​of each dimension parameter, the initial weight values ​​of each dimension parameter can be adjusted in conjunction with the lifecycle node of the target battery pack and the scenario type of the target battery pack, so as to obtain the corresponding weight values ​​of each dimension parameter.

[0074] Specifically, based on the correlation between lifecycle nodes, scenario types, and weight adjustment strategies, the weight adjustment strategy associated with the target battery pack's lifecycle node and scenario type can be obtained. The initial weight values ​​of each dimension parameter can then be adjusted to obtain the corresponding weight values ​​for each dimension parameter. The correspondence between different lifecycle nodes, different scenario types, and different weight adjustment strategies is pre-established.

[0075] The method provided in this embodiment enables the health assessment model to have scenario adaptability through a dynamic weight adjustment mechanism. It can automatically optimize the parameter weight allocation according to the focus of different operation and maintenance stages and the reliability requirements of different application scenarios, thereby significantly improving the accuracy, relevance and engineering practical value of the assessment results.

[0076] In some embodiments, step 130 specifically includes steps 131, 132 and 133.

[0077] Step 131: Based on the target health level, determine the health level of the target battery pack from multiple preset health levels to obtain the target health level; the multiple preset health levels include a first health level, a second health level, a third health level, a fourth health level, and a fifth health level; the health level corresponding to the first health level is greater than or equal to a first threshold, the health level corresponding to the second health level is greater than or equal to a second threshold and less than the first threshold, the health level corresponding to the third health level is greater than or equal to a third threshold and less than the second threshold, the health level corresponding to the fourth health level is greater than or equal to a fourth threshold and less than the third threshold, and the health level corresponding to the fifth health level is less than the fourth threshold.

[0078] Optionally, this embodiment can pre-divide the health status of the battery pack into five progressive health levels to achieve refined, hierarchical management of health status: First health level (or excellent): The corresponding health level H is greater than or equal to the first threshold (e.g., H≥90%). This level indicates that the battery pack's various performance indicators are good and its operation is stable and reliable.

[0079] Second health level (or good): The corresponding health level is greater than or equal to the second threshold and less than the first threshold (e.g., 80% ≤ H < 90%). This level indicates that the battery pack has slight performance degradation, but it is still within an acceptable range.

[0080] The third health level (or general): The corresponding health level is greater than or equal to the third threshold and less than the second threshold (e.g., 70% ≤ H < 80%). This level indicates a significant decline in battery pack performance and a certain operational risk.

[0081] Fourth health level (or poor): The corresponding health level is greater than or equal to the fourth threshold and less than the third threshold (e.g., 60% ≤ H < 70%). This level indicates that the battery pack has a high risk of failure and may not be able to meet critical backup power requirements.

[0082] Fifth health level (or severe): The corresponding health level is less than the fourth threshold (e.g., H < 60%). This level indicates that the battery pack has severely deteriorated and has essentially lost its backup power function.

[0083] It should be noted that the first threshold, second threshold, third threshold, and fourth threshold can be flexibly set according to the reliability requirements of the application scenario, industry standards, or historical statistical data. This embodiment does not impose specific limitations on them.

[0084] After obtaining the target health level, the target health level can be matched with the range corresponding to each preset health level. The preset health level corresponding to the range that matches the target health level is determined as the health level of the target battery pack, i.e., the target health level.

[0085] Step 132: When the target health level is the fourth health level or the fifth health level, determine the target warning mode from multiple preset warning modes according to the target health level; each preset warning mode corresponds to a different warning object, warning method and warning content.

[0086] This embodiment pre-sets multiple early warning modes, each corresponding to different early warning triggering conditions, early warning objects, early warning methods, and early warning content, in order to achieve graded response.

[0087] Among them, the warning recipients are defined as the personnel roles that receive the warning information, which may include personnel at different levels such as operations and maintenance supervisors, on-site managers, operations and maintenance specialists, and system administrators.

[0088] Warning methods: Determine the channels for pushing warning information, including but not limited to SMS, telephone voice, mobile application software (APP) push, email, platform pop-ups, and sound and light alarms.

[0089] Warning content: Specifies the specific content template of the warning information, which may include health status value, detailed analysis report of parameters in each dimension, related hidden danger work order information, suggested handling measures, and expected handling time limit.

[0090] For example, the following warning modes can be configured: Mode A (or Emergency Warning Mode): The trigger condition is the fifth health level; the warning targets are the operations and maintenance supervisor and the on-site manager; the warning methods include SMS, telephone, and platform pop-up; the warning content includes the health value, a detailed analysis report of each dimension parameter, and a recommendation to replace the battery immediately.

[0091] Mode B (or Important Warning Mode): The trigger condition is the fourth health level; the warning target is the operation and maintenance specialist; the warning method includes SMS and email; the warning content includes the downward trend of health level, related hidden danger work order information, and a suggestion to complete on-site verification within 72 hours.

[0092] Step 133: Perform maintenance control on the target battery according to the target early warning mode.

[0093] Optionally, after obtaining the target early warning mode, an early warning message can be automatically generated based on the early warning content in the selected target early warning mode, and the early warning message can be sent to the early warning object indicated in the target early warning mode according to the early warning method in the target early warning mode, so as to provide a reliable basis for formulating targeted maintenance strategies for the early warning object, reduce maintenance costs, and improve maintenance efficiency.

[0094] The method provided in this embodiment transforms abstract health values ​​into clear risk levels and specific control actions through a five-level health grading and differentiated early warning mode mechanism. This enables accurate identification, graded response, and automatic handling of high-risk battery packs, effectively avoiding the maintenance decision-making difficulties and response delays caused by the lack of clear action guidelines in existing technologies. It significantly reduces maintenance costs, lowers the risk of power outages due to battery failure, and improves the precision of operation and maintenance management and emergency response efficiency.

[0095] The battery pack monitoring device provided by the present invention is described below. The battery pack monitoring device described below can be referred to in correspondence with the battery pack monitoring method described above.

[0096] Figure 2 This is a schematic diagram of the battery pack monitoring device provided by the present invention; as shown. Figure 2 As shown, the device includes: The parameter acquisition unit 210 is used to acquire multi-dimensional parameters of the target battery pack, including backup power duration parameters, capacity parameters, reliability parameters, data integrity parameters, degradation rate parameters, hidden danger remediation parameters, hidden danger work order parameters, and offline parameters. The evaluation unit 220 is used to evaluate the health of the target battery pack based on the multi-dimensional parameters to obtain the target health. The control unit 230 is used to perform maintenance control on the target battery pack based on the target health status.

[0097] The device provided in this embodiment fundamentally breaks through the limitations of existing technologies that rely solely on electrochemical characteristics by acquiring eight multi-dimensional parameters covering backup power duration, capacity, reliability, data integrity, degradation rate, hazard remediation, hazard work orders, and offline status. This expands health assessment from a single physical dimension to a comprehensive system integrating equipment performance, operation and maintenance management, data quality, and risk exposure. It can accurately identify availability degradation caused by non-electrochemical factors such as data loss, hazard backlog, or communication interruptions. The target health level obtained from this multi-dimensional parameter assessment is no longer a one-sided performance indicator, but a reliable quantitative result that comprehensively and accurately reflects the actual safe operating status of the battery pack, providing a complete basis for maintenance decisions. By directly triggering differentiated maintenance control based on this target health level, an intelligent linkage mechanism from status assessment to control actions is established, enabling timely early warning and precise maintenance of high-risk battery packs. This avoids the maintenance lag or over-maintenance problems caused by incomplete information in traditional technologies, ultimately significantly reducing the operating costs of critical infrastructure and the risk of power outages.

[0098] The apparatus provided by the present invention is used to execute the above-described method embodiments. For specific processes and details, please refer to the above embodiments, which will not be repeated here.

[0099] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include a processor 310, a communications interface 320, a memory 330, and a communication bus 340, wherein the processor 310, communications interface 320, and memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a battery pack monitoring method. This method includes: acquiring multi-dimensional parameters of the target battery pack, including backup power duration parameters, capacity parameters, reliability parameters, data integrity parameters, degradation rate parameters, hazard remediation parameters, hazard work order parameters, and offline parameters; evaluating the health of the target battery pack based on the multi-dimensional parameters to obtain a target health level; and performing maintenance control on the target battery pack based on the target health level.

[0100] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0101] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the battery pack monitoring method provided by the above methods. The method includes: acquiring multi-dimensional parameters of a target battery pack, including backup power duration parameters, capacity parameters, reliability parameters, data integrity parameters, degradation rate parameters, hidden danger remediation parameters, hidden danger work order parameters, and offline parameters; evaluating the health of the target battery pack based on the multi-dimensional parameters to obtain a target health level; and performing maintenance control on the target battery pack based on the target health level.

[0102] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the battery pack monitoring method provided by the above methods. The method includes: acquiring multi-dimensional parameters of a target battery pack, including backup power duration parameters, capacity parameters, reliability parameters, data integrity parameters, degradation rate parameters, hidden danger remediation parameters, hidden danger work order parameters, and offline parameters; evaluating the health of the target battery pack based on the multi-dimensional parameters to obtain a target health level; and performing maintenance control on the target battery pack based on the target health level.

[0103] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0104] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A battery pack monitoring method, characterized in that, include: Obtain multi-dimensional parameters of the target battery pack, including backup power duration parameters, capacity parameters, reliability parameters, data integrity parameters, degradation rate parameters, hidden danger remediation parameters, hidden danger work order parameters, and offline parameters; The health of the target battery pack is evaluated based on the multi-dimensional parameters to obtain the target health. Based on the target health status, the target battery pack is maintained and controlled.

2. The battery pack monitoring method according to claim 1, characterized in that, The step of evaluating the health of the target battery pack based on the multi-dimensional parameters to obtain the target health includes: The multi-dimensional parameters are preprocessed, including outlier removal and / or missing value imputation. The processed multi-dimensional parameters are standardized to obtain the standardized values ​​of the parameters in each dimension; The health of the target battery pack is evaluated based on the standardized values ​​of the parameters in each dimension and the corresponding weight values ​​of the parameters in each dimension, thereby obtaining the target health.

3. The battery pack monitoring method according to claim 2, characterized in that, The process of evaluating the health of the target battery pack based on the standardized values ​​of the parameters in each dimension and the corresponding weight values ​​of the parameters in each dimension, to obtain the target health, includes: Calculate the membership degree of the standardized values ​​of the parameters in each dimension to each preset health level to form a fuzzy evaluation matrix; The target health score is obtained by combining the weight values ​​corresponding to the parameters of each dimension with the fuzzy evaluation matrix.

4. The battery pack monitoring method according to claim 2, characterized in that, The steps for determining the weight values ​​corresponding to the parameters of each dimension include: Analyze the impact of the parameters in each dimension on the health assessment of the target battery pack; Based on the degree of influence, determine the weight values ​​corresponding to the parameters of each dimension.

5. The battery pack monitoring method according to claim 4, characterized in that, The step of determining the weight values ​​corresponding to the parameters of each dimension based on the degree of influence includes: Based on the degree of influence, determine the initial weight values ​​corresponding to the parameters of each dimension; Based on the lifecycle node of the target battery pack and the scenario type in which the target battery pack is located, the initial weight values ​​corresponding to the parameters of each dimension are adjusted to obtain the weight values ​​corresponding to the parameters of each dimension.

6. The battery pack monitoring method according to any one of claims 1-5, characterized in that, The backup power duration parameter includes at least one of the following: discharge start time, discharge end time, and load current during the discharge process. The capacity parameters include at least one of the capacity calculation duration and the remaining capacity duration; The data integrity parameters include at least one of the following: data collection integrity rate, data reporting success rate, and inaccurate or abnormal data from the device. The hazard remediation parameters include at least one of the following: out-of-service hazard remediation work order data, hazard remediation completion rate, and hazard remediation timeliness rate; The hazard work order parameters include at least one of the following: unarchived hazard data and the number of pending hazard work orders; The offline parameters include at least one of the number of offline times and the total offline duration.

7. The battery pack monitoring method according to any one of claims 1-5, characterized in that, The maintenance control of the target battery pack based on the target health status includes: Based on the target health level, the health level of the target battery pack is determined from multiple preset health levels to obtain the target health level; the multiple preset health levels include a first health level, a second health level, a third health level, a fourth health level, and a fifth health level; the health level corresponding to the first health level is greater than or equal to a first threshold, the health level corresponding to the second health level is greater than or equal to a second threshold and less than the first threshold, the health level corresponding to the third health level is greater than or equal to a third threshold and less than the second threshold, the health level corresponding to the fourth health level is greater than or equal to a fourth threshold and less than the third threshold, and the health level corresponding to the fifth health level is less than the fourth threshold; When the target health level is the fourth health level or the fifth health level, a target warning mode is determined from multiple preset warning modes according to the target health level; each preset warning mode corresponds to a different warning object, warning method and warning content; The target battery is maintained and controlled according to the target early warning mode.

8. A battery pack monitoring device, characterized in that, include: The parameter acquisition unit is used to acquire multi-dimensional parameters of the target battery pack, including backup power duration parameters, capacity parameters, reliability parameters, data integrity parameters, degradation rate parameters, hidden danger remediation parameters, hidden danger work order parameters, and offline parameters. An evaluation unit is used to evaluate the health of the target battery pack based on the multi-dimensional parameters to obtain the target health. A control unit is used to perform maintenance control on the target battery pack based on the target health status.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the battery pack monitoring method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the battery pack monitoring method as described in any one of claims 1 to 7.

Images