A method and system for judging the differential pressure fault of a battery pack

Abstract

The present invention relates to the field of battery packs. More specifically, the present invention relates to a method and system for judging the differential pressure fault of a battery pack. The method includes: obtaining the voltage value of any battery module in the battery pack at the target moment, constructing graph structure data for the battery pack, and using spectral clustering to cluster the graph structure data to obtain a number of clustering clusters; obtaining adjacent clustering clusters, matching the adjacent clustering clusters and the clustering clusters at the target moment, and determining the value of the judgment function; calculating the abnormal differential pressure value of the battery module according to the calculated differential pressure change amount; obtaining the accumulated value of the abnormal differential pressure value of any battery module within a preset sampling period, and taking the maximum value of the accumulated values in the battery pack as the abnormality degree of the battery pack, thereby completing the fault judgment of the battery pack. Through the technical solution of the present invention, the accuracy of the battery pack differential pressure fault judgment result can be improved, and the operation safety of the battery pack can be ensured.

Description

Technical Field

[0001] The present invention relates to the field of battery packs. More specifically, the present invention relates to a method and system for judging the differential pressure fault of a battery pack. 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 progress of battery technology and the continuous growth of demand, the reliability and safety of battery packs have received increasing attention. The fault judgment and diagnosis of battery packs, especially the differential pressure fault inside the battery pack, have become one of the important research directions in the field of battery management.

[0003] In a battery pack, it is usually composed of multiple battery modules, and the total voltage of the battery pack is formed by the series or parallel combination of these modules. In actual applications, when a battery pack fails, it is often a certain battery module that has a problem, 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 detecting the differential pressure of the battery pack, the voltage change of a single module may not be directly reflected as an obvious abnormality, which is likely to lead to misdetection or missed detection during the detection process.

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

[0005] However, the above application document does not adequately consider the differential pressure change characteristics of the battery pack under different usage cycles and aging degrees, and does not clarify how to dynamically adjust the judgment criteria to adapt to the fault judgment of the battery pack over a period of time, resulting in inaccurate differential pressure fault judgment results. Summary of the Invention

[0006] To solve the problem of inaccurate differential pressure fault judgment results, the present invention proposes a method and system for judging the differential pressure fault of a battery pack.

[0007] In a first aspect, the present invention discloses a method for judging the differential pressure fault of a battery pack, including: obtaining the voltage value of any battery module in the battery pack at a target moment, where the target moment is any sampling moment, constructing graph structure data for the battery pack, and using spectral clustering to cluster the graph structure data to obtain several clustering clusters, wherein battery modules with approximately the same voltage difference are divided into one clustering cluster; obtaining adjacent clustering clusters, where the adjacent clustering clusters are the clustering clusters at historical sampling moments adjacent to the target moment, matching the adjacent clustering clusters and the clustering cluster at the target moment, and determining the value of the judgment function; taking the absolute difference between the differential pressure value of the clustering cluster at the target moment and the differential pressure value of the adjacent clustering cluster as the differential pressure change amount, calculating the abnormal differential pressure value of the battery module according to the differential pressure change amount, and the abnormal differential pressure value satisfies the relational expression:

[0008] , denotes the abnormal differential pressure value of the battery module at the target moment , denotes the battery module at the target moment of the differential pressure change amount, denotes the judgment function; obtaining the accumulated value of the abnormal differential pressure value of any battery module within a preset sampling period, taking the maximum value of the accumulated values in the battery pack as the abnormality degree of the battery pack, and completing the fault judgment of the battery pack.

[0009] By matching the clustering cluster at the target moment with the adjacent historical clustering clusters, the change trend of the battery module state can be captured, and the abnormal differential pressure value is calculated using the differential pressure change amount to further analyze the abnormal fluctuation of the battery module. The cumulative calculation of the abnormal differential pressure value provides a reliable abnormality degree evaluation index for the battery pack. When the abnormality degree of the battery pack reaches the preset threshold, the potential fault risk of the battery pack can be judged in time.

[0010] Preferably, in the spectral clustering, one battery module is a node, and the edge weight between two nodes is the absolute value of the voltage difference between two battery modules.

[0011] Preferably, the matching of the adjacent clustering clusters and the clustering cluster at the target moment includes: taking the battery modules in any clustering cluster in the adjacent clustering clusters as the original modules; counting the number of original modules included in each clustering cluster in the clustering cluster at the target moment, and matching the clustering cluster at the target moment corresponding to the maximum value with any clustering cluster in the adjacent clustering clusters; traversing all clustering clusters to complete the matching.

[0012] It can effectively cope with the situation where the state of the battery module fluctuates or is abnormal while ensuring the similarity of the attenuation characteristics of the battery module, helping to identify the modules that may have problems and giving early warnings in time.

[0013] 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.

[0014] This method can capture the fluctuations in the battery module status in real time, providing an important basis for the health monitoring of the battery pack.

[0015] Preferably, calculating the abnormal pressure difference value of the battery module further 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 pressure difference value among all clusters as the pressure difference amplitude; taking the product of the normalized pressure difference change amount and the normalized pressure difference amplitude as the abnormal pressure difference value.

[0016] It not only considers the pressure difference change inside the module but also synthesizes the relative pressure difference with other modules, thus improving the sensitivity and accuracy of the outlier detection.

[0017] Preferably, it further includes: constructing a window at the target moment, constructing an abnormal pressure difference sequence, obtaining the maximum first-order difference value and the number of first-order difference values greater than half of the maximum first-order difference value in the abnormal pressure difference sequence, calculating the abnormal weight at the target moment based on the maximum first-order difference value and the number, and the abnormal weight satisfies the relational expression:

[0018] , represents the abnormal weight at the target moment of, represents the number at the target moment of, represents the number at the target moment of the maximum difference value, represents the exponential function; calculating the weighted abnormal accumulation value of the battery module in the window according to the abnormal weight.

[0019] The calculation method of the abnormal weight considers the amplitude of the difference and the frequency of the change, so that it can more precisely reflect the intensity of the abnormal pressure difference and its change trend. Through this calculation method, the weighted abnormal accumulation value of the battery module in the window can not only reflect the current abnormal pressure difference situation of the module but also consider the persistence and amplitude of the abnormal fluctuation, thus helping the system to more accurately identify potential faults and make responses.

[0020] Preferably, the weighted abnormal accumulation value satisfies the relational expression:

[0021] , represents the battery module at the target moment in the window of the weighted abnormal accumulation value, represents the battery module The pressure difference anomaly value at the target moment, represents the anomaly weight at the target moment, and represents the window size.

[0022] In a second aspect, the present invention discloses a battery pack pressure difference fault judgment system, including: a processor; and a memory, where the memory stores computer instructions, and when the computer instructions are run by the processor, the system executes the above-mentioned battery pack pressure difference fault judgment method.

[0023] Advantages of the present invention:

[0024] By combining the voltage difference between battery modules in the battery pack and spectral clustering technology, the present invention can effectively judge the pressure difference fault of the battery pack. Through the clustering analysis of the voltage differences of battery modules, the battery modules are divided into different clusters according to the similarity of voltage differences, so as to identify the modules with abnormal pressure differences, and calculate the anomaly value based on the pressure difference change amount thereof. By constructing the matching of historical clustering clusters, the pressure difference fluctuations of battery modules at different sampling moments can be tracked, and then it can be dynamically judged whether there is a pressure difference fault.

[0025] Through the calculation of anomaly weight and weighted anomaly accumulation value, the present invention further evaluates and comprehensively judges the faults of the internal modules of the battery pack, can more accurately identify the health status of the battery pack, and ensure the safety and stability of the battery pack in practical applications. Description of the Drawings

[0026] By reading the following detailed description with reference to the drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become easy to understand. In the 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:

[0027] Figure 1 is a flowchart of a method for judging the pressure difference fault of a battery pack according to an embodiment of the present invention. Detailed Embodiments

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.

[0029] It should be understood that when terms such as "first", "second", etc. are used in the claims, specification and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "comprising" and "including" used in the specification 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 combinations.

[0030] The present invention provides a method for judging the differential pressure fault of a battery pack. As Figure 1 shown, a method for judging the differential pressure fault of a battery pack includes steps S1 - S4, which are specifically described below.

[0031] S1, obtain the voltage value of any battery module in the battery pack at the target moment, construct graph structure data for the battery pack, and use spectral clustering to cluster the graph structure data to obtain several clustering clusters.

[0032] In one embodiment, inside the battery pack, a high-precision voltage sensor is installed for each battery module to collect the sequential voltage values 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 fluctuations of the battery modules and transmit the data to the central monitoring system.

[0033] Obtain the voltage value of any battery module in the battery pack at the target moment. 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.

[0034] By constructing the graph structure data of the battery pack, the edge weight between nodes represents the absolute value of the voltage difference between battery modules. Then, use the spectral clustering algorithm to cluster the graph structure data, aiming to group battery modules with similar voltage differences into the same clustering cluster. The spectral clustering algorithm can divide 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., smaller voltage differences) will be grouped into the same cluster, which helps to discover groups of modules with consistent performance and normal states in the battery pack. While battery modules with larger voltage differences will be assigned to different clusters, facilitating further monitoring of potential fault risks.

[0035] S2, obtain adjacent clustering clusters. The adjacent clustering clusters are the clustering clusters at the historical sampling moments adjacent to the target moment. Match the adjacent clustering clusters and the clustering clusters at the target moment to determine the value of the judgment function.

[0036] It should be noted that the battery modules within each clustering cluster should have similar attenuation rates because they are within the same battery pack and are in the same working environment (such as temperature, humidity, charge-discharge mode, etc.). Therefore, the attenuation process of the battery is less affected by environmental factors. The attenuation of the battery module is mainly determined by factors within the battery itself, such as the production quality and chemical characteristics of the battery, and these factors are usually relatively consistent among the battery modules within the same cluster.

[0037] In one embodiment, in the clustering analysis of the battery pack, in order to achieve the matching and tracking of different clustering clusters, first, the battery modules within any one of the adjacent clustering clusters are used as the original modules.

[0038] Statistically count the number of original modules included in each clustering cluster at the target moment. Match the clustering cluster at the target moment corresponding to the maximum value with any one of the adjacent clustering clusters to ensure that the attribution relationship of the modules can be accurately tracked. Traverse all clustering clusters and complete the matching process between clustering clusters one by one according to the above method.

[0039] By using the battery modules in adjacent clustering clusters as the original modules and statistically counting the number of original modules included in each clustering cluster at the target moment, the change in the attribution relationship of the battery modules at different time points can be identified, thereby achieving the matching of clustering clusters between different time periods. In this way, while ensuring the similarity of the attenuation characteristics of the battery modules, it can effectively cope with the situation where the state of the battery modules fluctuates or is abnormal, helping to identify the modules that may have problems and giving early warnings in a timely manner.

[0040] For any battery module, in response to a change in the clustering cluster where the battery module is located, the value of the judgment function is 1; in response to no change in the clustering cluster where the battery module is located, the value of the judgment function is 0.

[0041] When the clustering cluster where the battery module is located 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 abnormal attenuation; while when the clustering cluster where the battery module is located has not changed, the value of the judgment function is 0, indicating that the state of the module remains stable and no abnormality has occurred. This method can capture the fluctuations in the state of the battery module in real time and provides an important basis for the health monitoring of the battery pack.

[0042] S3. Take the absolute difference between the pressure difference value of the clustering cluster at the target moment and the pressure difference value of the adjacent clustering cluster as the pressure difference change amount, and calculate the pressure difference abnormality value of the battery module according to the pressure difference change amount.

[0043] In one embodiment, the pressure difference abnormality value satisfies the relational expression:

[0044] , represents the battery module at the target moment The abnormal pressure difference value represents the battery module at the target moment of the pressure difference change amount, represents the judgment function.

[0045] When the pressure difference change amount of the battery module changes significantly at the target moment, under 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 abnormal pressure difference value will take the normalized value of the pressure difference change amount, indicating that there is an abnormal pressure difference change in this battery module, the battery performance has declined or there is a fault. On the contrary, when the judgment function value is 0, the abnormal pressure difference value is 0, indicating that the state of this battery module has not changed significantly. In this way, the abnormal fluctuations of the battery module during operation can be captured in a timely manner, avoiding system damage or efficiency decline caused by the failure to detect abnormal pressure differences in a timely manner.

[0046] In another embodiment, at the target moment, the absolute difference between the pressure difference value of the clustering cluster where the battery module is located and the minimum value of the pressure difference values in all clustering clusters is used as the pressure difference amplitude; the product of the normalized pressure difference change amount and the normalized pressure difference amplitude is used as the abnormal pressure difference value.

[0047] This calculation method can more comprehensively reflect the abnormal pressure difference situation of the battery module, taking into account both the pressure difference change inside the module and the relative pressure difference with other modules, thus 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 a precise basis for the state monitoring and fault warning of the battery pack.

[0048] S4. Obtain the accumulated value of the abnormal pressure difference value of any battery module within the preset sampling period, and take the maximum value of the accumulated values in the battery pack as the abnormality degree of the battery pack to complete the fault judgment of the battery pack.

[0049] In one embodiment, in order to more accurately monitor the abnormal pressure difference of the battery module, first calculate the accumulated value of the abnormal pressure difference value of each battery module within the preset sampling period, which reflects the abnormal degree of the module within this period.

[0050] Then, take the maximum value of all the module accumulated values as the abnormality degree of the battery pack, which is used as a key indicator to judge the health status of the battery pack. If a certain battery module continuously shows high abnormal values in multiple sampling periods, or the growth rate of its abnormal values is relatively fast, it indicates that there may be a persistent abnormality in the pressure difference of this module, suggesting that this module may have a fault or performance decline.

[0051] In one embodiment, it further includes: constructing a window based on a target time, using the target window as the end sampling time in the window, and constructing a window with a preset length as the window size.

[0052] Construct a differential pressure anomaly sequence of the window, obtain the maximum first-order difference value in the differential pressure anomaly sequence and the number of first-order difference values greater than half of the maximum first-order difference value, and calculate the anomaly weight at the target time based on the maximum first-order difference value and the number. The anomaly weight satisfies the relational expression:

[0053] , represents the anomaly weight at the target time , represents the target time , represents the target time of the maximum difference value, represents the exponential function.

[0054] The calculation method of the anomaly weight takes into account the amplitude of the difference and the frequency of the change, so that it can more precisely reflect the intensity of the differential pressure anomaly and its change trend. Through this calculation method, the weighted anomaly cumulative value of the battery module in the window can not only reflect the current differential pressure anomaly situation of the module, but also take into account the persistence and amplitude of the anomaly fluctuation, thereby helping the system to more accurately identify potential faults and make responses.

[0055] This method enhances the dynamic monitoring ability of the battery module state, effectively avoids misjudgment caused by local anomaly fluctuations, and at the same time provides a more sensitive and stable fault warning.

[0056] Calculate the weighted anomaly cumulative value of the battery module in the window according to the anomaly weight. The weighted anomaly cumulative value satisfies the relational expression:

[0057] , represents the battery module at the target time in the window of, represents the battery module at the target time of the differential pressure anomaly value, represents the target time of the anomaly weight, represents the window size.

[0058] For the same battery pack, traverse to obtain the weighted abnormal accumulation value of each battery module, and use the maximum value of the weighted abnormal accumulation value as the abnormality degree of the battery pack. When the abnormality degree of the battery pack is greater than the preset battery threshold, generate and send an alarm signal. When the abnormality degree of the battery pack is not greater than the preset battery threshold, continue to monitor the battery pack. The battery threshold can be set by those skilled in the art according to the battery modules included in the battery pack.

[0059] An embodiment of the present invention also discloses a battery pack differential pressure fault judgment system, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, a battery pack differential pressure fault judgment method according to the present invention is implemented.

[0060] The above system further includes other components well-known to those skilled in the art such as a communication bus and a communication interface. Their settings and functions are known in the art, so they will not be elaborated here.

[0061] In the present invention, the aforementioned memory can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or component. For example, a computer-readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory (RRAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), an enhanced dynamic random access memory (EDRAM), a high-bandwidth memory (HBM), a hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application program, module, or both. Any such computer storage medium can be part of the device or accessible or connectable to the device.

[0062] Although this specification has shown and described multiple embodiments of the present invention, it is obvious to those skilled in the art that such embodiments are provided only by way of example. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and idea of the present invention. It should be understood that various alternative solutions of the embodiments of the present invention described herein can be adopted in the process of practicing the present invention.

[0063] The above are all preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby. Therefore, all equivalent changes made according to the structure, shape and principle of the present invention shall be covered within the protection scope of the present invention.

Claims

1. A method for judging the differential pressure fault of a battery pack, characterized in that Including: Obtain the voltage value of any battery module in the battery pack at the target moment. The target moment is any sampling moment. Construct graph structure data for the battery pack, and use spectral clustering to cluster the graph structure data to obtain several clustering clusters. Among them, battery modules with approximately the same voltage difference are divided into one clustering cluster; Obtain adjacent clustering clusters. The adjacent clustering clusters are the clustering clusters at historical sampling moments adjacent to the target moment. Take the battery modules in any clustering cluster in the adjacent clustering clusters as the original modules, count the number of original modules included in each clustering cluster in the clustering clusters at the target moment, match the clustering cluster at the target moment corresponding to the maximum value with any clustering cluster in the adjacent clustering clusters, traverse all clustering clusters, and complete the matching of adjacent clustering clusters and clustering clusters at the target moment. For any battery module, in response to the change of the clustering cluster where any battery module is located, the value of the judgment function is 1; In response to the clustering cluster where any battery module is located not changing, the value of the judgment function is 0; Take the absolute difference between the pressure difference value of the clustering cluster at the target moment and the pressure difference value of the adjacent clustering cluster as the pressure difference change amount, and calculate the abnormal pressure difference value of the battery module according to the pressure difference change amount. The abnormal pressure difference value satisfies the relationship: , represents a battery module at the target time of the abnormal pressure difference value, represents a battery module at the target time of the pressure difference change amount, represents a judgment function; represents a standard normalization function; Obtain the accumulated value of the abnormal pressure difference value of any battery module within the preset sampling period, and take the maximum value of the accumulated values in the battery pack as the abnormality degree of the battery pack to complete the fault judgment of the battery pack.

2. The method for judging the differential pressure fault of a battery pack according to claim 1, wherein In the spectral clustering, one battery module is a node, and the edge weight of two nodes is the absolute value of the voltage difference between the two battery modules.

3. The method for judging the differential pressure fault of a battery pack according to claim 1, characterized in that, The abnormal pressure difference value of the battery module is calculated in another way: At the target moment, take the absolute difference between the pressure difference value of the clustering cluster where the battery module is located and the minimum value of the pressure difference values in all clustering clusters as the pressure difference amplitude; Take the product of the normalized pressure difference change amount and the normalized pressure difference amplitude as the abnormal pressure difference value.

4. A method for judging the differential pressure fault of a battery pack according to claim 1, characterized in that, Obtaining the accumulated value of the abnormal pressure difference value of any battery module within the preset sampling period, and taking the maximum value of the accumulated values in the battery pack as the abnormality degree of the battery pack includes: Construct a window at the target moment, construct an abnormal pressure difference sequence, obtain the maximum first-order difference value in the abnormal pressure difference sequence and the number of first-order difference values greater than half of the maximum first-order difference value, and calculate the abnormal weight at the target moment based on the maximum first-order difference value and the number. The abnormal weight satisfies the relationship: , represents the target moment of the abnormal weight, represents the target moment of the number, represents the target moment of the maximum first-order difference value, represents the exponential function; Calculate the weighted abnormal accumulated value of the battery module in the window according to the abnormal weight.

5. The method for judging the differential pressure fault of a battery pack according to claim 4, wherein The weighted abnormal accumulated value satisfies the relationship: , represents the battery module at the target time of the weighted anomaly accumulation value in the window, represents the battery module at the target time of the pressure difference anomaly value, represents the anomaly weight at the target time and represents the window size.

6. A battery pack differential pressure fault judgment system, characterized in that, Including: A processor; and A memory that stores computer instructions. When the computer instructions are run by the processor, the system executes a method for judging the pressure difference fault of a battery pack according to any one of claims 1-5.

Images