Battery pack differential pressure fault judgment method and system

Abstract

The invention relates to the field of battery packs, in particular to a method and a system for judging a voltage difference fault of a battery pack. The method comprises the following steps: acquiring a voltage value of any battery module in a battery pack at a target moment, constructing graph structure data for the battery pack, and clustering the graph structure data by utilizing spectral clustering to obtain a plurality of clusters; obtaining an adjacent cluster, matching the adjacent cluster with the target moment cluster, and determining a value of a judgment function; calculating a pressure difference abnormal value of the battery module according to the calculated pressure difference variable quantity; and obtaining the accumulated value of the abnormal voltage difference value of any battery module in the preset sampling period, and taking the maximum value of the accumulated value in the battery pack as the abnormality degree of the battery pack to complete the fault judgment of the battery pack. According to the technical scheme of the invention, the precision of the voltage difference fault judgment result of the battery pack can be improved, and the operation safety of the battery pack is ensured.

Description

Technical Field

[0001] The present invention relates to the field of battery packs, and more specifically, to a method and system for determining a battery pack voltage difference fault. Background Art

[0002] In modern battery management systems, battery packs are used as core components in electric vehicles, energy storage systems, and various high-end electronic products. With the advancement of battery technology and the continuous growth of demand, the reliability and safety of battery packs have received increasing attention. Fault judgment and diagnosis of battery packs, especially pressure difference faults inside battery packs, has become one of the important research directions in the field of battery management.

[0003] A battery pack is usually composed of multiple battery modules, and the total voltage of the battery pack is formed by combining these modules in series or in parallel. In practical applications, when a battery pack fails, it is often a problem with a certain battery module, which in turn affects the operation of the entire battery pack. However, since the total voltage of the battery pack is the sum of the voltages of multiple modules, when performing voltage difference detection of the battery pack, the voltage change of a single module may not directly reflect obvious abnormalities, which can easily lead to false detection or missed detection during the detection process.

[0004] The existing Chinese patent application document with publication number CN110837050A discloses a battery pack pressure difference fault judgment method, device and storage medium, including obtaining the current working state, current parameters and voltage parameters of the battery pack to be detected; judging the pressure difference fault of the battery pack to be detected based on the current working state, current parameters and voltage parameters.

[0005] However, the above application documents do not adequately consider the pressure difference variation characteristics of the battery pack under different usage cycles and aging levels, and do not specify how to dynamically adjust the judgment criteria to adapt to the fault judgment of the battery pack over a period of time, which may result in inaccurate pressure difference fault judgment results. Summary of the invention

[0006] In order to solve the problem of inaccurate pressure difference fault judgment results, the present invention proposes a battery pack pressure difference fault judgment method and system.

[0007] In a first aspect, the present invention discloses a method for judging a voltage difference fault of a battery pack, comprising: obtaining a voltage value of any battery module in a battery pack at a target time, where the target time is any sampling time, constructing graph structure data for the battery pack, clustering the graph structure data using spectral clustering to obtain a plurality of cluster clusters, wherein the voltage difference between the battery modules is approximately divided into one cluster cluster; obtaining adjacent cluster clusters, where the adjacent cluster clusters are cluster clusters at historical sampling times adjacent to the target time, matching the adjacent cluster clusters with the target time cluster clusters, and determining the value of a judgment function; taking the absolute difference between the pressure difference value of the target time cluster cluster and the pressure difference value of the adjacent cluster cluster as a pressure difference variation, and calculating the pressure difference abnormality of the battery module according to the pressure difference variation, and the pressure difference abnormality satisfies the relationship: , Indicates battery module At target time The pressure difference is abnormal, Indicates battery module At target time The pressure difference change, Represents a judgment function; obtains the accumulated value of the abnormal value of the pressure difference of any battery module within a preset sampling period, takes the maximum value of the accumulated value in the battery pack as the abnormality of the battery pack, and completes the battery pack fault judgment.

[0008] By matching the target time cluster with the historical adjacent cluster, the changing trend of the battery module status can be captured, and the pressure difference abnormality can be calculated using the pressure difference change to further analyze the abnormal fluctuation of the battery module. The cumulative calculation of the pressure difference abnormality provides a reliable abnormality evaluation indicator for the battery pack. When the abnormality of the battery pack reaches the preset threshold, the potential failure risk of the battery pack can be judged in time.

[0009] Preferably, in the spectral clustering, one battery module is one node, and the edge weight of two nodes is the absolute value of the voltage difference between the two battery modules.

[0010] Preferably, the matching of adjacent clusters and target time clusters includes: taking the battery module in any cluster in the adjacent clusters as the original module; counting the number of original modules contained in each cluster in the target time cluster, and matching the target time cluster corresponding to the maximum number with any cluster in the adjacent clusters; traversing all clusters to complete the matching.

[0011] While ensuring the similarity of battery module attenuation characteristics, it can effectively respond to fluctuations or abnormalities in battery module status, help identify modules that may have problems and provide timely warnings.

[0012] Preferably, determining the value of the judgment function includes: for any battery module, in response to a change in the cluster where any battery module is located, the value of the judgment function is 1; in response to no change in the cluster where any battery module is located, the value of the judgment function is 0.

[0013] This method can capture fluctuations in the status of battery modules in real time, providing an important basis for health monitoring of battery packs.

[0014] Preferably, the calculation of the pressure difference constant of the battery module also includes: at the target moment, taking the absolute difference between the pressure difference value of the cluster where the battery module is located and the minimum value of the pressure difference values ​​in all clusters as the pressure difference amplitude; and taking the product of the normalized pressure difference change and the normalized pressure difference amplitude as the pressure difference constant.

[0015] It not only considers the pressure difference changes within the module, but also integrates the relative pressure difference with other modules, thereby improving the sensitivity and accuracy of outlier detection.

[0016] Preferably, the method further includes: constructing a window at the target time, constructing a pressure difference abnormal sequence, obtaining a maximum first-order difference value in the pressure difference abnormal sequence and the number of first-order difference values ​​greater than half of the maximum first-order difference value, and calculating an abnormal weight at the target time based on the maximum first-order difference value and the number, wherein the abnormal weight satisfies the relationship: , Indicates the target time The abnormal weight of Indicates the target time The number of Indicates the target time The maximum difference value of Represents an exponential function; the weighted abnormal accumulation value of the battery module in the window is calculated according to the abnormal weight.

[0017] The calculation method of abnormal weight takes into account the amplitude of the difference and the frequency of change, which can more finely reflect the intensity of the pressure difference abnormality and its changing trend. Through this calculation method, the weighted abnormal accumulation value of the battery module in the window can not only reflect the current pressure difference abnormality of the module, but also take into account the persistence and amplitude of the abnormal fluctuation, thereby helping the system to more accurately identify potential faults and respond.

[0018] Preferably, the weighted abnormal cumulative value satisfies the relationship: , Indicates battery module At target time The weighted anomaly accumulation value in the window of Indicates battery module At target time The pressure difference is abnormal, Indicates the target time The abnormal weight of Indicates the window size.

[0019] In a second aspect, the present invention discloses a battery pack pressure difference fault judgment system, comprising: a processor; and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the system executes the above-mentioned battery pack pressure difference fault judgment method.

[0020] Beneficial effects of the present invention: The present invention can effectively judge the voltage difference fault of the battery pack by combining the voltage difference of the battery modules in the battery pack with the spectral clustering technology. Through the cluster analysis of the voltage difference of the battery modules, the battery modules are divided into different clusters according to the similarity of the voltage difference, so as to identify the modules with abnormal pressure difference, and calculate the abnormal value based on the change of their pressure difference. By constructing the matching of historical clustering clusters, the pressure difference fluctuation of the battery module at different sampling times can be tracked, and then the pressure difference fault can be dynamically judged.

[0021] The present invention further evaluates and comprehensively judges the faults of the internal modules of the battery pack by calculating the abnormal weights and weighted abnormal cumulative values, and can more accurately identify the health status of the battery pack to ensure the safety and stability of the battery pack in practical applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 It is a flow chart of a method for judging a battery pack pressure difference fault according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0024] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0025] The present invention provides a method for determining a battery pack voltage difference fault. Figure 1 As shown, a method for judging a battery pack pressure difference fault includes steps S1 to S4, which are described in detail below.

[0026] S1, obtaining the voltage value of any battery module in the battery pack at the target time, constructing graph structure data for the battery pack, and clustering the graph structure data using spectral clustering to obtain a number of clusters.

[0027] In one embodiment, a high-precision voltage sensor is installed for each battery module inside the battery pack to collect the time-series voltage value of each battery module in the battery pack in real time. A battery pack contains several battery modules. These sensors can accurately monitor the voltage fluctuation of the battery module and transmit the data to the central monitoring system.

[0028] The voltage value of any battery module in the battery pack at the target time is obtained. In order to perform more effective fault detection and performance evaluation on the battery pack, each battery module in the battery pack can be regarded as a node in the graph.

[0029] By constructing the graph structure data of the battery pack, the edge weights between nodes represent the absolute values ​​of the voltage differences between battery modules. Then, the spectral clustering algorithm is used to cluster the graph structure data, with the goal of grouping battery modules with similar voltage differences into the same cluster. The spectral clustering algorithm can partition the graph according to the voltage differences between battery modules, thereby identifying groups of modules with similar voltage behaviors. During the clustering process, battery modules with smaller edge weights (i.e., modules with smaller voltage differences) are clustered in the same cluster, which helps to find groups of modules with consistent performance and normal status in the battery pack. Battery modules with larger voltage differences are assigned to different clusters to facilitate further monitoring of potential failure risks.

[0030] S2, obtaining adjacent clusters, where the adjacent clusters are clusters of historical sampling moments adjacent to the target moment, matching the adjacent clusters with the target moment clusters, and determining the value of the judgment function.

[0031] It should be noted that the battery modules in each cluster should have similar attenuation rates, because they are in the same battery pack and are in the same working environment (such as temperature, humidity, charge and discharge mode, etc.), so the battery attenuation process is less affected by environmental factors. The attenuation of the battery module is mainly determined by factors of the battery itself, such as the production quality and chemical properties of the battery, which are usually consistent between battery modules in the same cluster.

[0032] In one embodiment, in cluster analysis of battery packs, in order to achieve matching and tracking of different clusters, firstly, a battery module in any cluster of adjacent clusters is taken as an original module.

[0033] Count the number of original modules contained in each cluster in the target time cluster, and match the target time cluster corresponding to the maximum number with any cluster in the adjacent cluster to ensure that the module's ownership relationship can be accurately tracked. Traverse all clusters and complete the matching process between clusters one by one according to the above method.

[0034] By taking the battery modules in adjacent clusters as the original modules and counting the number of original modules in each cluster at the target time, the changes in the ownership of battery modules at different time points can be identified, thereby achieving cluster matching between different time periods. In this way, while ensuring the similarity of battery module attenuation characteristics, it is possible to effectively respond to fluctuations or abnormalities in the battery module status, help identify modules that may have problems, and issue early warnings in a timely manner.

[0035] For any battery module, in response to a change in the cluster where any battery module is located, the value of the judgment function is 1; in response to no change in the cluster where any battery module is located, the value of the judgment function is 0.

[0036] When the cluster of the battery module changes, the value of the judgment function is 1, indicating that the state of the module has changed significantly, and there may be a fault or attenuation abnormality; when the cluster of the battery module does not change, the value of the judgment function is 0, indicating that the state of the module remains stable and there is no abnormality. This method can capture the fluctuation of the battery module state in real time, providing an important basis for the health monitoring of the battery pack.

[0037] S3, taking the absolute difference between the pressure difference value of the cluster at the target time and the pressure difference value of the adjacent cluster as the pressure difference variation, and calculating the pressure difference constant of the battery module according to the pressure difference variation.

[0038] In one embodiment, the pressure difference abnormal value satisfies the relationship: , Indicates battery module At target time The pressure difference is abnormal, Indicates battery module At target time The pressure difference change, Represents the judgment function.

[0039] When the pressure difference change of the battery module at the target time changes significantly, through the guidance of the judgment function, if the judgment function value is 1, it means that the state of the battery module has changed. At this time, the pressure difference abnormal value will take the normalized value of the pressure difference change, indicating that the battery module has an abnormal pressure difference change, the battery performance has declined, or there is a fault. Conversely, when the judgment function value is 0, the pressure difference abnormal value is 0, indicating that the state of the battery module has not changed significantly. In this way, abnormal fluctuations of the battery module during operation can be captured in time, avoiding system damage or efficiency reduction caused by the failure to discover the pressure difference abnormality in time.

[0040] In another embodiment, at the target moment, the absolute difference between the pressure difference value of the cluster where the battery module is located and the minimum pressure difference value in all clusters is taken as the pressure difference amplitude; the product of the normalized pressure difference change and the normalized pressure difference amplitude is taken as the pressure difference constant.

[0041] This calculation method can more comprehensively reflect the abnormal pressure difference of the battery module, taking into account the pressure difference change inside the module and the relative pressure difference with other modules, thereby improving the sensitivity and accuracy of abnormal value detection. In this way, the system can effectively identify those battery modules with large pressure difference changes and abnormal performance compared with other modules, providing an accurate basis for battery pack status monitoring and fault warning.

[0042] S4, obtaining the accumulated value of the abnormal value of the pressure difference of any battery module within a preset sampling period, taking the maximum value of the accumulated value in the battery pack as the abnormality of the battery pack, and completing the battery pack fault judgment.

[0043] In one embodiment, in order to more accurately monitor the voltage difference abnormality of the battery module, the accumulated value of the voltage difference abnormality value of each battery module in a preset sampling period is first calculated, which reflects the abnormality degree of the module in the period.

[0044] Next, the maximum value of the accumulated values ​​of all modules is used as the abnormality of the battery pack, which is used as a key indicator to judge the health of the battery pack. If a battery module has high abnormal values ​​continuously in multiple sampling cycles, or its abnormal value increases rapidly, it indicates that the pressure difference of the module may be continuously abnormal, indicating that the module may be faulty or its performance may be degraded.

[0045] In one embodiment, it also includes: constructing a window with a target time, constructing a window with the target window as the terminal sampling time in the window and with a preset length as the window size.

[0046] Construct the window's compression difference abnormal sequence, obtain the maximum first-order difference value in the compression difference abnormal sequence and the number of first-order difference values ​​greater than half of the maximum first-order difference value, and calculate the abnormal weight of the target time based on the maximum first-order difference value and the number. The abnormal weight satisfies the relationship: , Indicates the target time The abnormal weight of Indicates the target time The number of Indicates the target time The maximum difference value of Represents an exponential function.

[0047] The calculation method of abnormal weight takes into account the amplitude of the difference and the frequency of change, which can more finely reflect the intensity of the pressure difference abnormality and its changing trend. Through this calculation method, the weighted abnormal accumulation value of the battery module in the window can not only reflect the current pressure difference abnormality of the module, but also take into account the persistence and amplitude of the abnormal fluctuation, thereby helping the system to more accurately identify potential faults and respond.

[0048] This method enhances the dynamic monitoring capability of the battery module status, effectively avoids misjudgment due to local abnormal fluctuations, and provides more sensitive and stable fault warnings.

[0049] The weighted abnormal accumulation value of the battery module in the window is calculated according to the abnormal weight, and the weighted abnormal accumulation value satisfies the relationship: , Indicates battery module At target time The weighted anomaly accumulation value in the window of Indicates battery module At target time The pressure difference is abnormal, Indicates the target time The abnormal weight of Indicates the window size.

[0050] For the same battery pack, the weighted abnormal cumulative value of each battery module is traversed and obtained, and the maximum value of the weighted abnormal cumulative value is used as the abnormality of the battery pack. When the abnormality of the battery pack is greater than the preset battery threshold, an alarm signal is generated and sent. When the abnormality of the battery pack is not greater than the preset battery threshold, the battery pack continues to be monitored. The battery threshold can be set by those skilled in the art according to the battery modules included in the battery pack.

[0051] An embodiment of the present invention further discloses a battery pack pressure difference fault judgment system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a battery pack pressure difference fault judgment method according to the present invention is implemented.

[0052] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0053] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0054] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0055] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for judging a battery pack voltage difference fault, characterized in that: include: Obtain the voltage value of any battery module in the battery pack at the target time, where the target time is any sampling time, construct graph structure data for the battery pack, and use spectral clustering to cluster the graph structure data to obtain several clusters, among which the voltage difference between battery modules is approximately divided into one cluster; Obtain adjacent clusters, which are clusters at historical sampling moments adjacent to the target moment. Take the battery modules in any cluster in the adjacent clusters as the original modules. Count the number of original modules contained in each cluster in the target moment cluster. Match the target moment cluster corresponding to the maximum number with any cluster in the adjacent clusters. Traverse all clusters to complete the matching of adjacent clusters and target moment clusters, and determine the value of the judgment function. The absolute difference between the pressure difference value of the cluster at the target time and the pressure difference value of the adjacent cluster is taken as the pressure difference change. The pressure difference abnormal value of the battery module is calculated according to the pressure difference change. The pressure difference abnormal value satisfies the relationship: , Indicates battery module At target time The pressure difference is abnormal, Indicates battery module At target time The pressure difference change, represents the judgment function; Obtain the accumulated value of the abnormal pressure difference of any battery module within a preset sampling period, take the maximum value of the accumulated value in the battery pack as the abnormality of the battery pack, and complete the battery pack fault judgment.

2. A battery pack pressure difference fault judgment method according to claim 1, characterized in that: In the spectral clustering, one battery module is one node, and the edge weight of two nodes is the absolute value of the voltage difference between the two battery modules.

3. A battery pack pressure difference fault judgment method according to claim 1, characterized in that: Determining the value of the judgment function includes: For any battery module, in response to a change in the cluster where any battery module is located, the value of the judgment function is 1; In response to the fact that the cluster to which any battery module belongs does not change, the value of the judgment function is 0.

4. A battery pack pressure difference fault judgment method according to claim 1, characterized in that: The calculating the voltage difference abnormal value of the battery module also includes: At the target time, the absolute difference between the pressure difference value of the cluster where the battery module is located and the minimum pressure difference value of all clusters is taken as the pressure difference amplitude; The product of the normalized pressure difference change and the normalized pressure difference amplitude is taken as the pressure difference constant.

5. A battery pack pressure difference fault judgment method according to claim 1, characterized in that: Also includes: Build a window at the target time, build a compression difference abnormal sequence, obtain the maximum first-order difference value in the compression difference abnormal sequence and the number of first-order difference values ​​greater than half of the maximum first-order difference value, and calculate the abnormal weight of the target time based on the maximum first-order difference value and the number. The abnormal weight satisfies the relationship: , Indicates the target time The abnormal weight of Indicates the target time The number of Indicates the target time The maximum difference value of represents the exponential function; The weighted abnormal accumulation value of the battery module in the window is calculated according to the abnormal weight.

6. A battery pack pressure difference fault judgment method according to claim 5, characterized in that: The weighted abnormal cumulative value satisfies the relationship: , Indicates battery module At target time The weighted anomaly accumulation value in the window of Indicates battery module At target time The pressure difference is abnormal, Indicates the target time The abnormal weight of Indicates the window size.

7. A battery pack pressure difference fault judgment system, characterized in that: include: Processor; and A memory storing computer instructions, wherein when the computer instructions are executed by a processor, the system executes a battery pack pressure difference fault judgment method according to any one of claims 1 to 6.

Images