Battery Inspection and Warning Method and System Based on Intelligent Data Processing

Abstract

The present application provides a battery inspection and warning method and system based on intelligent data processing. The method includes: obtaining a plurality of state data groups corresponding to each battery pack, where each state data group represents the battery state of the battery pack under any state parameter type; for the same state parameter type, determining a target type data group corresponding to the state parameter type based on all state data groups; obtaining an abnormal determination rule, and adjusting the abnormal determination rule according to the target type data group and the historical type data group to obtain a target determination rule; performing intelligent abnormal detection on the target type data group based on the target determination rule to obtain an abnormal detection result corresponding to the state parameter type; and obtaining an inspection and warning result according to the abnormal detection results corresponding to each of the multiple state parameter types, where the inspection and warning result is used for battery inspection and warning. The method of the present application improves the accuracy of the abnormal detection result by adjusting the abnormal determination rule.

Description

Technical Field

[0001] This application relates to the technical field of battery inspection, and particularly to a battery inspection and warning method and system based on intelligent data processing. Background Art

[0002] With the wide application of battery technology, especially in electric vehicles and energy storage systems, the safety and reliability of batteries have become crucial. Traditional battery inspection relies on manual inspection or simple threshold alarms, which are inefficient and prone to false alarms or missed alarms. Although intelligent battery management systems (BMS) have improved detection accuracy using big data and artificial intelligence, existing solutions still face challenges in processing multi-dimensional state parameters, especially when fixed anomaly determination rules are difficult to adapt to different working conditions and environmental changes.

[0003] Current methods mainly adopt fixed anomaly detection criteria, failing to fully consider the mutual influence between different state parameters and the importance of historical data. Therefore, in complex application scenarios, these methods often cannot provide sufficiently accurate anomaly detection results, leading to a decline in the reliability and accuracy of the warning system. Summary of the Invention

[0004] This application provides a battery inspection and warning method and system based on intelligent data processing to solve the technical problem of inaccurate battery inspection and warning.

[0005] In a first aspect, this application provides a battery inspection and warning method based on intelligent data processing, which is applied to an AC-DC integrated power supply system. The AC-DC integrated power supply system includes multiple battery packs. The method includes: obtaining multiple state data groups corresponding to each battery pack, where each state data group represents the battery state of the battery pack under any state parameter type; for the same state parameter type, based on all the state data groups, determining a target type data group corresponding to the state parameter type;

[0006] obtaining an anomaly determination rule, and adjusting the anomaly determination rule according to the target type data group and the historical type data group to obtain a target determination rule;

[0007] performing intelligent anomaly detection on the target type data group based on the target determination rule to obtain an anomaly detection result corresponding to the state parameter type;

[0008] obtaining an inspection and warning result according to the anomaly detection results corresponding to multiple state parameter types, where the inspection and warning result is used for battery inspection and warning.

[0009] Optionally, adjusting the anomaly determination rule according to the target type data group and the historical type data group to obtain a target determination rule includes:

[0010] Performing discretization processing on the target type data group to obtain discretization processing parameters and a discretized target data group, where the discretization processing parameters characterize the specific content included in the discretization processing process;

[0011] Performing discretization processing on the historical type data group according to the discretization processing parameters to obtain a discretized historical data group;

[0012] Calculating a distribution difference according to the discretized target data group and the discretized historical data group to obtain a discretized distribution difference, where the discretized distribution difference characterizes the difference in the discrete data distribution between the target type data group and the historical type data group;

[0013] Adjusting the anomaly determination rule according to the discretized distribution difference to obtain a target determination rule.

[0014] Optionally, after calculating the distribution difference according to the discretized target data group and the discretized historical data group to obtain the discretized distribution difference, it further includes:

[0015] Obtaining a continuous distribution difference, where the continuous distribution difference characterizes the distribution difference of continuous data between the target type data group and the historical type data group;

[0016] Obtaining a target distribution difference according to the discretized distribution difference and the continuous distribution difference;

[0017] Adjusting the anomaly determination rule according to the target distribution difference to obtain a new target determination rule.

[0018] Optionally, calculating the distribution difference according to the discretized target data group and the discretized historical data group to obtain the discretized distribution difference includes:

[0019] Obtaining a discretized target distribution feature according to the discretized target data group, and obtaining a discretized historical distribution feature according to the discretized historical data group;

[0020] Calculating a distribution difference between the discretized historical distribution feature and the discretized target distribution feature to obtain the discretized distribution difference.

[0021] Optionally, before determining the target type data group corresponding to the state parameter type based on all the state data groups for the same state parameter type, it further includes:

[0022] For each of the battery packs, based on the multiple state data groups corresponding to the battery pack and the state data groups corresponding to other battery packs, obtain the overall distribution difference corresponding to the battery pack, where the overall distribution difference characterizes the difference in battery states between the battery pack and the other battery packs, and the other battery packs are the battery packs other than the battery pack among the multiple battery packs;

[0023] Based on the overall distribution difference and the overall distribution threshold range, obtain the adjustment parameter corresponding to the battery pack, where the adjustment parameter characterizes the quantitative difference in battery states between the battery pack and the other battery packs;

[0024] Process each of the state data groups corresponding to the battery pack according to the adjustment parameter to obtain each new state data group;

[0025] Correspondingly, for the same type of state parameter, based on all the state data groups, determine the target type data group corresponding to the type of state parameter, including:

[0026] For the same type of state parameter, based on all the new state data groups, determine the target type data group corresponding to the type of state parameter.

[0027] Optionally, the abnormal detection result is in numerical form or text form.

[0028] Optionally, when the abnormal detection result is in numerical form;

[0029] The obtaining of the inspection warning result according to the abnormal detection results corresponding to multiple types of state parameters includes:

[0030] Obtain historical detection results, where the historical detection results can be determined based on the type of state parameter;

[0031] Based on the abnormal detection results corresponding to multiple types of state parameters, obtain the distribution difference of abnormal results, where the distribution difference of abnormal results characterizes the distribution difference between the multiple abnormal detection results and the multiple historical detection results;

[0032] Based on the distribution difference of abnormal results and the conventional result distribution range, obtain the inspection warning result.

[0033] Optionally, the distribution difference calculation is a divergence calculation.

[0034] In a second aspect, the present application provides a battery inspection warning system based on intelligent data processing, which is applied to the battery inspection warning method based on intelligent data processing according to any one of the first aspects, and includes:

[0035] The first acquisition module is used to acquire multiple state data groups corresponding to each of the battery packs, where each state data group characterizes the battery state of the battery pack under any state parameter type;

[0036] The first processing module is used to determine the target type data group corresponding to the state parameter type based on all the state data groups for the same state parameter type;

[0037] The second acquisition module is used to acquire an anomaly determination rule, and adjust the anomaly determination rule according to the target type data group and the historical type data group to obtain a target determination rule;

[0038] The second processing module is used to perform intelligent anomaly detection on the target type data group based on the target determination rule to obtain the anomaly detection result corresponding to the state parameter type;

[0039] The warning module is used to obtain an inspection warning result according to the anomaly detection results corresponding to multiple state parameter types, where the inspection warning result is used for battery inspection warning.

[0040] The battery inspection warning method based on intelligent data processing provided by this application can comprehensively characterize the operation conditions of each battery pack under different state parameter types by acquiring multiple state data groups of each battery pack, ensuring an accurate grasp of the battery state; for the same state parameter type, determine the target type data group from all state data, and adjust the anomaly determination rule in combination with the historical type data group, so that the rule can not only reflect the characteristics of the current state parameter, but also consider the performance under past similar conditions, enhancing the accuracy and adaptability of anomaly judgment; perform intelligent anomaly detection on the target type data group based on the optimized target determination rule, which can effectively improve the sensitivity and accuracy of anomaly recognition, reduce false alarms and missed alarms; finally, comprehensively evaluate and generate an inspection warning result according to the anomaly detection results of multi-dimensional state parameter types, providing a scientific basis for battery inspection and significantly improving the reliability and effectiveness of the battery inspection warning system. Description of the Drawings

[0041] The drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0042] Figure 1 It is a schematic diagram of the application scenario of a battery inspection warning method based on intelligent data processing provided by an embodiment of this application;

[0043] Figure 2 It is a schematic flowchart of a battery inspection warning method based on intelligent data processing provided by an embodiment of this application;

[0044] Figure 3 A structural schematic diagram of a battery inspection and warning system based on intelligent data processing provided by an embodiment of the present application;

[0045] Figure 4 A structural schematic diagram of an electronic device provided by the present application.

[0046] Through the above-mentioned drawings, specific embodiments of the present application have been shown, and more detailed descriptions will be provided later. These drawings and written descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Specific Embodiments

[0047] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0048] First, the nouns involved in the present application will be explained:

[0049] Figure 1 A schematic diagram of the application scenario of the battery inspection and warning method based on intelligent data processing provided by the present application. As Figure 1 shown, an application scenario of the prior art is as follows: The electronic device collects status data from the AC-DC integrated power supply system; the electronic device generates inspection and warning results using the status data; the electronic device uses the inspection and warning results to implement battery inspection and warning for the AC-DC integrated power supply system.

[0050] An embodiment of the present application provides a battery inspection and warning method based on intelligent data processing, aiming to solve the above technical problems of the prior art, which is executed by the above-mentioned electronic device.

[0051] Next, the technical solution of the present application and how the technical solution of the present application solves the above technical problems will be described in detail with specific embodiments. These several specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the drawings.

[0052] Figure 2 A flowchart of a battery inspection and warning method based on intelligent data processing provided by an embodiment of the present application. As Figure 2As shown in the figure, a battery inspection and warning method based on intelligent data processing is applied to an AC / DC integrated power supply system, and the AC / DC integrated power supply system includes multiple battery packs.

[0053] The above-mentioned battery inspection and warning method based on intelligent data processing may specifically include steps S201 to S205, where:

[0054] S201. Obtain multiple state data groups corresponding to each battery pack, where each state data group represents the battery state of the battery pack under any state parameter type.

[0055] The state parameter types are parameters such as battery temperature and internal resistance size.

[0056] S202. For the same state parameter type, based on all the state data groups, determine the target type data group corresponding to the state parameter type.

[0057] The target type data group includes the state data corresponding to each of the multiple battery packs corresponding to the state parameter type.

[0058] S203. Obtain the abnormal determination rule, and adjust the abnormal determination rule according to the target type data group and the historical type data group to obtain the target determination rule.

[0059] The abnormal determination rule is a preset numerical interval, which represents the data distribution difference degree between the target type data group and the historical type data group when the AC / DC integrated power supply system is working normally, where the historical type data group is the historical target type data group.

[0060] For example, calculate the real-time data distribution difference degree between the target type data group and the historical type data group in real time, where the data distribution difference degree can be obtained based on methods such as the KL divergence calculation formula and the k-means clustering method; use the real-time data distribution difference degree to adjust the abnormal determination rule, see S203-6, which will not be elaborated in this embodiment.

[0061] S204. Perform intelligent abnormal detection on the target type data group based on the target determination rule to obtain the abnormal detection result corresponding to the state parameter type.

[0062] When performing intelligent anomaly detection, first, based on the target determination rule obtained by pre-adjusting and optimizing, which comprehensively considers the current state parameter characteristics of the target type data group and the relevant data patterns in the historical type data group, thus ensuring high adaptability to different working conditions and environmental changes. Then, input the target type data group into the anomaly detection model constructed based on the machine learning algorithm. The model analyzes and processes the input data to identify data patterns that deviate from the normal operation mode, that is, potential anomalies. This process utilizes statistical methods, threshold comparison, and pattern recognition techniques to accurately capture abnormal behaviors and output anomaly detection results corresponding to specific state parameter types.

[0063] The above intelligent anomaly detection mechanism can significantly improve the accuracy of anomaly recognition and provide a reliable basis for subsequent warning measures.

[0064] S205. Obtain a patrol warning result according to the anomaly detection results corresponding to each of the multiple state parameter types, where the patrol warning result is used for battery patrol warning.

[0065] The battery patrol warning method based on intelligent data processing provided by the embodiments of this application can comprehensively represent the operating conditions of each battery group under different state parameter types by obtaining multiple state data groups of each battery group, ensuring accurate mastery of the battery state; for the same state parameter type, determine the target type data group from all state data and adjust the anomaly determination rule in combination with the historical type data group, so that the rule can not only reflect the characteristics of the current state parameter but also consider the performance under past similar conditions, enhancing the accuracy and adaptability of anomaly judgment; perform intelligent anomaly detection on the target type data group based on the optimized target determination rule, which can effectively improve the sensitivity and accuracy of anomaly recognition, reduce false alarms and missed alarms; finally, comprehensively evaluate and generate a patrol warning result based on the anomaly detection results of multi-dimensional state parameter types, providing a scientific basis for battery patrol and significantly improving the reliability and effectiveness of the battery patrol warning system.

[0066] In a realizable manner, the above S203 adjusts the anomaly determination rule according to the target type data group and the historical type data group to obtain the target determination rule, which can specifically include S203-1, S203-2, S203-3, and S203-6, where:

[0067] S203-1. Perform discretization processing on the target type data group to obtain discretization processing parameters and a discretized target data group, where the discretization processing parameters characterize the specific content included in the discretization processing process.

[0068] For example, in the above discretization process, the sampling interval is 1 ms. At this time, the sampling interval = 1 ms is used as the discretization parameter.

[0069] S203-2. Discretize the historical type data group according to the discretization parameter to obtain a discretized historical data group.

[0070] It should be noted that processing the data group with the same discretization method instead of pre-processing the historical type data group in advance can ensure that the processing methods for the target type data group and the historical type data group are the same, and can avoid the high distribution difference caused by different processing methods.

[0071] S203-3. Calculate the distribution difference based on the discretized target data group and the discretized historical data group to obtain a discretized distribution difference, where the discretized distribution difference characterizes the difference in the discrete data distribution between the target type data group and the historical type data group.

[0072] S203-6. Adjust the anomaly determination rule according to the discretized distribution difference to obtain a target determination rule.

[0073] Among them, the target determination rule = the anomaly determination rule * (1 + the discretized distribution difference).

[0074] In one implementable manner, after performing the distribution difference calculation based on the discretized target data group and the discretized historical data group in S203-3 above to obtain a discretized distribution difference, S203-4 and S203-5 are further included, where:

[0075] S203-4. Obtain a continuous distribution difference, where the continuous distribution difference characterizes the distribution difference of the continuous data between the target type data group and the historical type data group.

[0076] It should be noted that the state data needs to consider not only discrete features but also continuous features. Therefore, in this embodiment, the continuous features of the state data are added by obtaining the continuous distribution difference.

[0077] Specifically, perform continuous processing on the target type data group to obtain a continuous processing parameter and a continuous target data group, where the continuous processing parameter characterizes the specific content included in the continuous processing process; perform continuous processing on the historical type data group according to the continuous processing parameter to obtain a continuous historical data group; calculate the distribution difference based on the continuous target data group and the continuous historical data group to obtain a continuous distribution difference, where the continuous distribution difference characterizes the distribution difference of the continuous data between the target type data group and the historical type data group.

[0078] S203-5. Obtain the target distribution difference based on the discretized distribution difference and the continuous distribution difference.

[0079] The target distribution difference is the mean value.

[0080] Correspondingly, in the above S203-6, the anomaly determination rule is adjusted according to the discretized distribution difference to obtain the target determination rule, including:

[0081] Adjust the anomaly determination rule according to the target distribution difference to obtain a new target determination rule.

[0082] In an implementable manner, in the above S203-3, the distribution difference calculation is performed based on the discretized target data group and the discretized historical data group to obtain the discretized distribution difference, which may specifically include S203-3-1 and S203-3-2, where:

[0083] S203-3-1. Obtain the discretized target distribution feature based on the discretized target data group, and obtain the discretized historical distribution feature based on the discretized historical data group.

[0084] S203-3-2. Perform the distribution difference calculation on the discretized historical distribution feature and the discretized target distribution feature to obtain the discretized distribution difference.

[0085] In an implementable manner, before the above S202 determines the target type data group corresponding to the state parameter type based on all state data groups for the same state parameter type, it further includes SA1 to SA3, where:

[0086] SA1. For each battery pack, obtain the overall distribution difference corresponding to the battery pack according to the multiple state data groups corresponding to the battery pack and the state data groups corresponding to other battery packs, where the overall distribution difference characterizes the difference in battery states between the battery pack and other battery packs, and other battery packs are the battery packs other than the battery pack among the multiple battery packs.

[0087] Specifically, for each battery pack, a statistical analysis method is used to calculate the difference metric between its state parameters (such as voltage, current, temperature, etc.) and the corresponding state parameters of other battery packs. This step can be achieved by calculating the mean, variance, or using more complex machine learning models to quantify these differences. Specifically, for each battery pack, its state data set is compared with the state data sets of all other battery packs. By determining the distribution of each state parameter among different battery packs, representative numerical metrics (such as standard deviation, coefficient of variation, etc.) are calculated to characterize the battery state difference of the battery pack relative to other battery packs. This process not only considers the direct comparison of a single state parameter but also combines the comprehensive analysis of multi-dimensional parameters to ensure that the overall distribution difference can comprehensively and accurately reflect the working state differences among battery packs. Finally, based on the above analysis results, an accurate evaluation of the overall distribution difference between each battery pack and the rest of the battery packs is obtained, providing strong support for the balancing control and fault diagnosis in the subsequent battery management system.

[0088] SA2. Based on the overall distribution difference and the overall distribution threshold range, obtain the adjustment parameters corresponding to the battery pack. The adjustment parameters characterize the quantitative difference between the battery state of the battery pack and that of other battery packs.

[0089] Based on the determined overall distribution difference of each battery pack, first set an overall distribution threshold range. This threshold range is predefined according to the system design requirements and the safety standards for the operation of the battery pack to determine whether the state difference between battery packs is within an acceptable range. Next, for each battery pack, compare and analyze its calculated overall distribution difference with the overall distribution threshold range. If the overall distribution difference of a certain battery pack exceeds the preset threshold range, it indicates that there is a significant working state difference between this battery pack and other battery packs, and it needs to be adjusted to restore consistency. At this time, according to the specific value and characteristics exceeding the threshold, the corresponding adjustment parameters are calculated through a predetermined algorithm (such as proportional-integral-derivative control algorithm, fuzzy logic control, or other adaptive adjustment mechanisms). These adjustment parameters not only quantify the degree of state difference of the battery pack relative to other battery packs but also provide clear guidance for specific adjustment operations, such as adjusting the charging rate, limiting the depth of discharge, etc., so as to ensure that all battery packs can maintain the best working state. Finally, use the above adjustment parameters to execute the corresponding adjustment measures to effectively reduce or eliminate the state difference between battery packs and improve the performance and safety of the entire battery system.

[0090] SA3. Process each state data set corresponding to the battery pack according to the adjustment parameters to obtain each new state data set.

[0091] According to the calculated adjustment parameters, corresponding processing steps are performed on each state data group in the battery pack. First, key parameters in each state data group are identified, including but not limited to indicators such as voltage, current, temperature, etc. Then, based on the determined adjustment parameters, appropriate mathematical operations or algorithm models (such as linear transformation, non - linear mapping, or other specific correction algorithms) are used to precisely adjust these key parameters. Through such an adjustment process, updated state data groups are generated to ensure that they reflect the actual state of the battery pack under new working conditions. This process aims to eliminate or minimize performance deviations caused by initial inconsistencies, thereby ensuring that all battery packs can operate under optimized conditions and improving the stability and efficiency of the entire battery system. Finally, the newly processed state data groups are applied to subsequent monitoring and management systems to achieve more precise control and management of the battery pack.

[0092] Correspondingly, S203 determines the target type data group corresponding to the state parameter type based on all the state data groups for the same state parameter type, including:

[0093] For the same state parameter type, based on all the new state data groups, the target type data group corresponding to the state parameter type is determined.

[0094] It should be noted that the anomaly detection result is in numerical form or text form.

[0095] In one implementable manner, the anomaly detection result is in text form. The above - mentioned S205 obtains the inspection warning result according to the anomaly detection results corresponding to multiple state parameter types, which may specifically include: after receiving the anomaly detection results of multiple state parameter types presented in text form, first, these results are parsed and classified to identify the state parameters that exceed the preset safety range and determine their anomaly levels. Then, according to the importance and correlation between each state parameter type, combined with historical data and predefined logic rules or algorithm models, all the anomaly detection results are comprehensively analyzed. By evaluating the possible impact of each abnormal state on the overall system, the corresponding inspection warning result is generated. This process not only considers the deviation of a single parameter but also analyzes the possible synergistic effects among multiple parameters, thereby ensuring that the inspection warning result can accurately reflect the actual operating condition of the system and providing a scientific basis for subsequent targeted maintenance measures. The finally output inspection warning result will clearly indicate the specific problems that need attention and their urgency, guiding the operation and maintenance personnel to respond in a timely and effective manner.

[0096] In another implementable manner, the anomaly detection result is in numerical form. The above - mentioned S205 obtains the inspection warning result according to the anomaly detection results corresponding to multiple state parameter types, which may specifically include S205 - 1 to S205 - 3, where:

[0097] S205-1. Obtain historical detection results, where the historical detection results can be determined based on the type of status parameter.

[0098] First, determine the type of status parameter corresponding to the historical detection results to be obtained, ensuring that these types are associated with the current detection requirements. Then, retrieve historical records that match the type of status parameter from a storage medium or database, where each record contains the detection value of the status parameter and its background information at a specific time point or time period. Subsequently, screen and organize the retrieved data, removing irrelevant or redundant information and retaining the valid data that can reflect the change trend and abnormal conditions of the status parameter. Based on this, construct a clear and orderly set of historical detection results, which can not only display the past performance of each status parameter but also provide a reference basis for analyzing the current detection data. Finally, present these historical detection results classified by the type of status parameter to facilitate further analysis of its change law over time and its impact on system operation.

[0099] S205-2. Obtain the distribution difference of abnormal results based on the abnormal detection results corresponding to each type of status parameter, where the distribution difference of abnormal results characterizes the distribution difference between multiple abnormal detection results and multiple historical detection results.

[0100] First, collect the corresponding abnormal detection results for each type of status parameter and standardize these results for easy comparison. Next, extract records of the same type of status parameter from the historical detection results, ensuring the consistency of the time range and data quality. Then, use statistical methods or algorithms to analyze the distribution difference between the abnormal detection results and historical data of each type of status parameter, and identify the parameters that show significantly different abnormal patterns in different time periods. Subsequently, represent these analysis results in the form of charts or other visualizations to display the distribution difference of abnormal results and its change trend relative to historical records. Finally, by comprehensively evaluating these distribution differences, determine the types of status parameters with abnormal changes as those that need further attention, providing data support for subsequent risk assessment and system optimization. This can not only help understand the abnormal points in the current system operation status but also predict possible future abnormal situations based on historical data.

[0101] It should be noted that not storing the historical result distribution status first and then using it is to ensure the accuracy of the distribution difference.

[0102] S205-3. Obtain the patrol inspection warning result based on the distribution difference of abnormal results and the normal result distribution range.

[0103] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0104] Furthermore, it should be noted that although the steps in the flowchart are displayed in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0105] Figure 3 FIG. is a schematic structural diagram of a battery inspection and warning system based on intelligent data processing provided by an embodiment of the present application, as Figure 3 shown, the battery inspection and warning system 40 based on intelligent data processing provided by the embodiment of the present application includes:

[0106] A first acquisition module 401, configured to acquire a plurality of state data groups corresponding to each battery pack, wherein each state data group represents the battery state of the battery pack under any state parameter type;

[0107] A first processing module 402, configured to determine a target type data group corresponding to the state parameter type based on all state data groups for the same state parameter type;

[0108] A second acquisition module 403, configured to acquire an anomaly determination rule, and adjust the anomaly determination rule according to the target type data group and the historical type data group to obtain a target determination rule;

[0109] A second processing module 404, configured to perform intelligent anomaly detection on the target type data group based on the target determination rule to obtain an anomaly detection result corresponding to the state parameter type;

[0110] A warning module 405, configured to obtain an inspection warning result according to the anomaly detection results corresponding to each of the multiple state parameter types, wherein the inspection warning result is used for battery inspection and warning.

[0111] In a possible implementation manner, when the second obtaining module 403 executes to adjust the anomaly determination rule according to the target type data group and the historical type data group to obtain the target determination rule, it is used for:

[0112] Perform discretization processing on the target type data group to obtain discretization processing parameters and a discretized target data group, where the discretization processing parameters represent the specific content included in the discretization processing process;

[0113] Perform discretization processing on the historical type data group according to the discretization processing parameters to obtain a discretized historical data group;

[0114] Perform distribution difference calculation according to the discretized target data group and the discretized historical data group to obtain a discretized distribution difference, where the discretized distribution difference represents the difference in the discrete data distribution between the target type data group and the historical type data group;

[0115] Adjust the anomaly determination rule according to the discretized distribution difference to obtain the target determination rule.

[0116] In a possible implementation manner, the above system 40 further includes a determination module;

[0117] The determination module is used for:

[0118] Obtain a continuous distribution difference, where the continuous distribution difference represents the difference in the continuous data distribution between the target type data group and the historical type data group;

[0119] Obtain a target distribution difference according to the discretized distribution difference and the continuous distribution difference;

[0120] Correspondingly, when the second obtaining module 403 executes to adjust the anomaly determination rule according to the discretized distribution difference to obtain the target determination rule, it is used for:

[0121] Adjust the anomaly determination rule according to the target distribution difference to obtain a new target determination rule.

[0122] In a possible implementation manner, when the second obtaining module 403 executes to perform distribution difference calculation according to the discretized target data group and the discretized historical data group to obtain the discretized distribution difference, it is used for:

[0123] Obtain a discretized target distribution feature according to the discretized target data group, and obtain a discretized historical distribution feature according to the discretized historical data group;

[0124] Perform distribution difference calculation on the discretized historical distribution feature and the discretized target distribution feature to obtain the discretized distribution difference.

[0125] In a possible implementation, the above-mentioned system 40 further includes an adjustment module;

[0126] The adjustment module is configured to:

[0127] For each battery pack, based on the multiple state data groups corresponding to the battery pack and the state data groups corresponding to other battery packs, obtain the overall distribution difference corresponding to the battery pack, where the overall distribution difference characterizes the difference in battery states between the battery pack and other battery packs, and other battery packs are the battery packs other than the battery pack among the multiple battery packs;

[0128] Based on the overall distribution difference and the overall distribution threshold range, obtain the adjustment parameter corresponding to the battery pack, where the adjustment parameter characterizes the quantitative difference in battery states between the battery pack and other battery packs;

[0129] Process each state data group corresponding to the battery pack according to the adjustment parameter to obtain each new state data group;

[0130] Correspondingly, when the above-mentioned first processing module 402 executes to determine the target type data group corresponding to the state parameter type based on all state data groups for the same state parameter type, it is configured to:

[0131] For the same state parameter type, based on all the new state data groups, determine the target type data group corresponding to the state parameter type.

[0132] In a possible implementation, the anomaly detection result is in numerical form;

[0133] When the above-mentioned warning module 405 executes to obtain the inspection warning result according to the anomaly detection results corresponding to multiple state parameter types, it is configured to:

[0134] Obtain the historical detection result, where the historical detection result can be determined based on the state parameter type;

[0135] Based on the anomaly detection results corresponding to multiple state parameter types, obtain the anomaly result distribution difference, where the anomaly result distribution difference characterizes the distribution difference between the multiple anomaly detection results and the multiple historical detection results;

[0136] Based on the anomaly result distribution difference and the normal result distribution range, obtain the inspection warning result.

[0137] In a possible implementation, the distribution difference calculation is a divergence calculation.

[0138] In a possible implementation, the anomaly detection result is in numerical form or text form.

[0139] The battery inspection and warning system based on intelligent data processing provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effects are similar. Details are not described here in this embodiment.

[0140] It should be understood that the above device embodiments are illustrative, and the devices of the present application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0141] In addition, without special instructions, in each embodiment of the present application, each functional unit / module can be integrated in one unit / module, or each unit / module can exist physically alone, or two or more units / modules can be integrated together. The above integrated unit / module can be implemented in the form of hardware or in the form of a software program module.

[0142] When the integrated unit / module is implemented in the form of hardware, the hardware can be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc.

[0143] Figure 4 It is a schematic structural diagram of the electronic device provided in the present application. As Figure 4 shown, the electronic device 50 provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the electronic device 50 further includes a communication component 503. Among them, the processor 501, the memory 502, and the communication component 503 are connected through a bus 504.

[0144] In the specific implementation process, at least one processor 501 executes the computer execution instructions stored in the memory 502, so that at least one processor 501 executes the above method.

[0145] The specific implementation process of the processor 501 can refer to the above method embodiment, and its implementation principle and technical effects are similar. Details are not described here in this embodiment.

[0146] Unless otherwise specified, the processor 501 can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, ASIC, etc. Unless otherwise specified, the memory 502 can be any suitable magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc.

[0147] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. The aforementioned memory includes: USB flash drive, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk, or optical disc, etc., all of which can store program codes.

[0148] The embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium stores computer-executable instructions. When the processor executes the computer-executable instructions, the redundant field update method for a distributed system as described above is implemented.

[0149] The embodiments of the present application also provide a computer program product, including a computer program. When the computer program is executed by the processor, the redundant field update method for a distributed system as described above is implemented.

[0150] In the above embodiments, the descriptions of the respective embodiments each have their own focuses. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as falling within the scope described in this specification.

[0151] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include known common general knowledge or conventional technical means in the technical field not disclosed in the present application. The specification and examples are only to be considered as exemplary, and the true scope and spirit of the present application are pointed out by the following claims.

[0152] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

Claims

1. A battery inspection and warning method based on intelligent data processing, characterized in that, Applied to an AC / DC integrated power supply system, the AC / DC integrated power supply system includes a plurality of battery packs; The method includes: Obtaining a plurality of state data groups corresponding to each of the battery packs, where each state data group characterizes the battery state of the battery pack under any state parameter type; For each of the battery packs, according to the plurality of state data groups corresponding to the battery pack and the state data groups corresponding to other battery packs, obtaining the overall distribution difference corresponding to the battery pack, where the overall distribution difference characterizes the difference in battery state between the battery pack and the other battery packs, and the other battery packs are the battery packs other than the battery pack among the plurality of battery packs; According to the overall distribution difference and the overall distribution threshold range, obtaining an adjustment parameter corresponding to the battery pack, where the adjustment parameter characterizes the quantitative difference in battery state between the battery pack and the other battery packs; Processing each state data group corresponding to the battery pack according to the adjustment parameter to obtain each new state data group; For the same state parameter type, based on all the new state data groups, determining a target type data group corresponding to the state parameter type; Obtaining an anomaly determination rule, and adjusting the anomaly determination rule according to the target type data group and the historical type data group to obtain a target determination rule; Performing intelligent anomaly detection on the target type data group based on the target determination rule to obtain an anomaly detection result corresponding to the state parameter type; According to the anomaly detection results corresponding to each of the multiple state parameter types, obtaining an inspection warning result, where the inspection warning result is used for battery inspection warning.

2. The battery inspection and warning method based on intelligent data processing according to claim 1, wherein, The adjusting the anomaly determination rule according to the target type data group and the historical type data group to obtain a target determination rule includes: Performing discretization processing on the target type data group to obtain a discretization processing parameter and a discretized target data group, where the discretization processing parameter characterizes the specific content included in the discretization processing process; Performing discretization processing on the historical type data group according to the discretization processing parameter to obtain a discretized historical data group; Performing distribution difference calculation according to the discretized target data group and the discretized historical data group to obtain a discretized distribution difference, where the discretized distribution difference characterizes the difference in discrete data distribution between the target type data group and the historical type data group; Adjusting the anomaly determination rule according to the discretized distribution difference to obtain a target determination rule.

3. The battery inspection and warning method based on intelligent data processing according to claim 2, wherein, After performing the distribution difference calculation according to the discretized target data group and the discretized historical data group to obtain a discretized distribution difference, it further includes: Obtaining a continuous distribution difference, where the continuous distribution difference characterizes the difference in continuous data distribution between the target type data group and the historical type data group; According to the discretized distribution difference and the continuous distribution difference, obtaining a target distribution difference; Correspondingly, adjusting the anomaly determination rule according to the discretized distribution difference to obtain a target determination rule includes: Adjusting the anomaly determination rule according to the target distribution difference to obtain a new target determination rule.

4. The battery inspection and warning method based on intelligent data processing according to claim 2, wherein Calculating the discretized distribution difference according to the discretized target data group and the discretized historical data group includes: Obtaining the discretized target distribution feature according to the discretized target data group, and obtaining the discretized historical distribution feature according to the discretized historical data group; Calculating the distribution difference between the discretized historical distribution feature and the discretized target distribution feature to obtain the discretized distribution difference.

5. The battery inspection and warning method based on intelligent data processing according to claim 1, characterized in that The anomaly detection result is in numerical form or text form.

6. The battery inspection and warning method based on intelligent data processing according to claim 5, wherein, When the anomaly detection result is in numerical form; Obtaining the inspection warning result according to the anomaly detection results corresponding to multiple state parameter types includes: Obtaining the historical detection result, where the historical detection result can be determined based on the state parameter type; Obtaining the anomaly result distribution difference according to the anomaly detection results corresponding to multiple state parameter types, where the anomaly result distribution difference characterizes the distribution difference between the multiple anomaly detection results and the multiple historical detection results; Obtaining the inspection warning result according to the anomaly result distribution difference and the conventional result distribution range.

7. The battery inspection and warning method based on intelligent data processing according to claim 2, wherein, The distribution difference calculation is divergence calculation.

8. A battery inspection and warning system based on intelligent data processing, which is applied to the battery inspection and warning method based on intelligent data processing according to any one of claims 1-7, characterized in that Including: A first acquisition module, configured to acquire a plurality of state data groups corresponding to each battery pack, where each state data group characterizes the battery state of the battery pack under any state parameter type; A first processing module, configured to, for each battery pack, obtain the overall distribution difference corresponding to the battery pack according to the plurality of state data groups corresponding to the battery pack and the state data groups corresponding to other battery packs, where the overall distribution difference characterizes the difference between the battery state of the battery pack and the battery state of the other battery packs, and the other battery packs are the battery packs other than the battery pack among the plurality of battery packs. Obtaining the adjustment parameter corresponding to the battery pack according to the overall distribution difference and the overall distribution threshold range, where the adjustment parameter characterizes the quantitative difference between the battery state of the battery pack and the battery state of the other battery packs; processing each state data group corresponding to the battery pack according to the adjustment parameter to obtain each new state data group; for the same state parameter type, determining the target type data group corresponding to the state parameter type based on all the new state data groups; A second acquisition module, configured to acquire an anomaly determination rule, and adjust the anomaly determination rule according to the target type data group and the historical type data group to obtain a target determination rule; A second processing module, configured to perform intelligent anomaly detection on the target type data group based on the target determination rule to obtain the anomaly detection result corresponding to the state parameter type; A warning module, configured to obtain the inspection warning result according to the anomaly detection results corresponding to multiple state parameter types, where the inspection warning result is used for battery inspection warning.

9. An electronic device, characterized in that, Including: A memory and a processor; The memory is used for storing program instructions; The processor is used for calling the program instructions in the memory to execute the battery inspection and warning method based on intelligent data processing according to any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the battery inspection and warning method based on intelligent data processing according to any one of claims 1-7.

Images