Battery abnormal connection detection method, electronic device, storage medium and program product

Abstract

The embodiment of the invention provides a battery abnormal connection detection method, electronic equipment, a storage medium and a program product. The method comprises the steps that detection information of a battery cluster is acquired, the battery cluster comprises a plurality of temperature to-be-detected points, and the detection information is used for indicating detection temperatures and current information of the plurality of temperature to-be-detected points in a first preset time period; based on the current information, determining a state distribution condition of the battery cluster in a first preset time period, and based on the state distribution condition, determining target detection data; performing grouping processing on the target detection data, and constructing feature parameters based on multiple groups of detection data; and performing abnormal connection detection on the battery cluster based on the feature parameters corresponding to the multiple groups of detection data to obtain abnormal points in the battery cluster. According to the method, feature extraction is performed on the detection data, abnormal points are accurately positioned, and the problem of battery connection looseness of the energy storage system is recognized in advance, so that the safety and the use performance of the battery cluster of the energy storage system are improved.

Description

Technical Field

[0001] This application relates to the technical field of batteries, and in particular, to a method for detecting abnormal battery connections, an electronic device, a storage medium, and a program product. Background Art

[0002] The interior of an energy storage battery usually includes battery modules, which are the core part of the battery PACK and are responsible for storing and releasing electrical energy. It is composed of multiple single cells combined in series and parallel, and a single cell monitoring and management device is installed. However, inside the energy storage system, loose connections of the positive and negative electrodes of the battery cluster and the power lines of the manual maintenance switch (Maintenance Switch Disconnector, hereinafter simply referred to as "MSD") may lead to a series of serious safety risks.

[0003] Abnormal connections of the positive and negative electrodes and the MSD power lines may cause short circuits, overheating, and failure of the battery management system, resulting in a decline in the performance of the battery pack and a reduction in charge and discharge efficiency. In addition, the uneven distribution of current will accelerate the inconsistency inside the system. If not discovered and processed in time, these problems may not only damage the energy storage device itself, but also pose a threat to the surrounding environment and personnel safety.

[0004] To address the above problems, the prior art determines the abnormal detection results of the battery pack through a series of battery temperature abnormal judgment thresholds built from thermodynamic experimental data, or outputs the temperature abnormal alarm information of the copper busbar by collecting the temperature data of the copper busbar and the adaptive hierarchical alarm threshold in real time during the operation of the factory unit. The above prior art has high data requirements, complex implementation means, limited applicable scenarios, and the detection results are greatly affected by data, resulting in inaccurate abnormal detection. Summary of the Invention

[0005] Embodiments of this application provide a method for detecting abnormal battery connections, an electronic device, a storage medium, and a program product, which are used to solve the problems in the prior art that have high data requirements, complex implementation means, limited applicable scenarios, and the detection results are greatly affected by data, resulting in inaccurate abnormal detection.

[0006] In a first aspect, an embodiment of this application provides a method for detecting abnormal battery connections, including:

[0007] Obtain detection information of a battery cluster, where the battery cluster includes multiple temperature measurement points to be measured, and the detection information is used to indicate the detected temperatures and current information of the multiple temperature measurement points to be measured within a first preset period;

[0008] Based on the current information, determine the state distribution of the battery cluster within the first preset period, and based on the state distribution, determine the target detection data, where the target detection data is the data within the detection information that is within the second preset period;

[0009] Perform grouping processing on the target detection data, and based on multiple groups of detection data, construct characteristic parameters;

[0010] Based on the characteristic parameters corresponding to multiple groups of detection data, perform abnormal connection detection on the battery cluster to obtain the abnormal points within the battery cluster.

[0011] In a possible implementation manner, the current information includes: current values at multiple timestamps. Based on the current information, determining the operating state distribution of the battery cluster within the first preset period includes:

[0012] Based on the current values at the multiple timestamps, determine the operating state of the battery cluster within the first period and the operating period corresponding to each operating state. The operating states include: charging state, discharging state, and static state;

[0013] According to each operating state and the corresponding operating period, determine the operating state distribution of the battery cluster within the first preset period.

[0014] In a possible implementation manner, based on the operating state distribution, determining the target detection data includes:

[0015] Based on the operating state distribution, determine a third period that is greater than the first preset duration. The third period is used to indicate the period during which the battery cluster continuously remains in the same operating state;

[0016] Based on the detection information corresponding to the third period, determine a second period that is greater than the second preset duration. The second period is used to indicate the period during which the thermal management system continuously remains unstarted within the third period;

[0017] Use the data within the second period in the detection information as the target detection data.

[0018] In a possible implementation manner, the temperature measurement points to be measured include: positive electrode connection point, negative electrode connection point, first aviation plug temperature measurement point, and second aviation plug temperature measurement point. Performing grouping processing on the target detection data and constructing characteristic parameters based on multiple groups of detection data includes:

[0019] Group the target detection data according to the positive electrode connection point, negative electrode connection point, first aviation plug temperature measurement point, second aviation plug temperature measurement point, and the model information corresponding to the aviation plug temperature measurement point to obtain multiple groups of detection data sets;

[0020] Perform feature statistical processing on multiple groups of the detected data sets respectively to obtain the characteristic parameters corresponding to each group of detected data sets.

[0021] In a possible implementation manner, the performing abnormal connection detection on the battery cluster based on the characteristic parameters corresponding to multiple groups of detected data to obtain the abnormal points in the battery cluster includes:

[0022] Adopt an anomaly detection algorithm to perform anomaly determination processing on the characteristic parameters corresponding to multiple groups of the detected data to obtain the anomaly scores of the temperature points to be measured corresponding to multiple groups of the detected data;

[0023] Determine the abnormal points in the battery cluster based on the anomaly scores.

[0024] In a possible implementation manner, the method further includes:

[0025] Obtain the historical anomaly scores of multiple groups of temperature points to be measured, and determine the anomaly change trend of the temperature points to be measured based on the anomaly scores of multiple groups of the temperature points to be measured and the historical anomaly scores;

[0026] When the anomaly change trend is abnormally increasing, determine that the corresponding temperature point to be measured is in an abnormal state and generate an anomaly warning message.

[0027] In a second aspect, an embodiment of the present application provides a battery abnormal connection detection device, including:

[0028] An acquisition module, configured to acquire the detection information of a battery cluster, where multiple temperature points to be measured are included in the battery cluster, and the detection information is used to indicate the detected temperatures and current information of multiple the temperature points to be measured within a first preset period;

[0029] A determination module, configured to determine the state distribution of the battery cluster within the first preset period based on the current information, and determine target detection data based on the state distribution, where the target detection data is the data within a second preset period in the detection information;

[0030] A grouping module, configured to perform grouping processing on the target detection data and construct characteristic parameters based on multiple groups of detected data;

[0031] A detection module, configured to perform abnormal connection detection on the battery cluster based on the characteristic parameters corresponding to multiple groups of detected data to obtain the abnormal points in the battery cluster.

[0032] In a possible implementation, the determining module is further configured to determine the operating state of the battery cluster and the corresponding operating period of each operating state within the first period based on the current values at the multiple timestamps. The operating states include: charging state, discharging state, and static state;

[0033] The determining module is further configured to determine the operating state distribution of the battery cluster within the first preset period according to each operating state and the corresponding operating period.

[0034] In a possible implementation, the determining module is further configured to determine a third period greater than a first preset duration based on the operating state distribution. The third period is used to indicate the period during which the battery cluster continuously remains in the same operating state;

[0035] The determining module is further configured to determine a second period greater than a second preset duration based on the detection information corresponding to the third period. The second period is used to indicate the period during which the thermal management system continuously does not start within the third period;

[0036] The determining module is further configured to use the data within the second period in the detection information as the target detection data.

[0037] In a possible implementation, the device further includes: a statistical module;

[0038] The grouping module is further configured to group the target detection data according to the positive connection point, negative connection point, first connector temperature measurement point, second connector temperature measurement point, and the model information corresponding to the connector temperature measurement point, to obtain multiple groups of detection data sets;

[0039] The statistical module is configured to perform feature statistical processing on multiple groups of the detection data sets respectively to obtain the feature parameters corresponding to each group of detection data sets.

[0040] In a possible implementation, the detection module is further configured to use an anomaly detection algorithm to perform anomaly determination processing on the feature parameters corresponding to multiple groups of the detection data to obtain the anomaly scores of the temperature measurement points to be measured corresponding to multiple groups of the detection data;

[0041] The determining module is further configured to determine the anomaly points within the battery cluster based on the anomaly scores.

[0042] In a possible implementation, the obtaining module is further configured to obtain the historical anomaly scores of multiple groups of temperature measurement points to be measured, and determine the anomaly change trend of the temperature measurement points to be measured based on the anomaly scores of multiple groups of the temperature measurement points to be measured and the historical anomaly scores;

[0043] The determining module is further configured to determine that the corresponding temperature measurement point is in an abnormal state and generate an abnormal alarm message when the abnormal change trend shows an abnormal increase.

[0044] In a third aspect, an embodiment of the present application provides a battery abnormal connection detection device, including: a memory and a processor;

[0045] The memory stores computer-executable instructions;

[0046] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementation manners of the first aspect.

[0047] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the above first aspect and / or various possible implementation manners of the first aspect.

[0048] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the above first aspect and / or various possible implementation manners of the first aspect.

[0049] The battery abnormal connection detection method, electronic device, storage medium and program product provided by the embodiments of the present application obtain detection information of a battery cluster, where the battery cluster includes a plurality of temperature measurement points to be measured, and the detection information is used to indicate the detected temperatures and current information of the plurality of temperature measurement points to be measured within a first preset period; based on the current information, determine the state distribution of the battery cluster within the first preset period, and based on the state distribution, determine target detection data, where the target detection data is the data within a second preset period in the detection information; perform grouping processing on the target detection data, and construct characteristic parameters based on multiple groups of detection data; perform abnormal connection detection on the battery cluster based on the characteristic parameters corresponding to multiple groups of detection data to obtain abnormal points in the battery cluster. By extracting features from the detection data, the abnormal points are accurately located, and the problem of loose battery connections in the energy storage system is identified in advance, thereby improving the safety and performance of the battery cluster in the energy storage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0051] Figure 1 It is a schematic diagram of the scenario of the battery abnormal connection detection method provided by the present application;

[0052] Figure 2Flow schematic of the battery abnormal connection detection method provided by this application Figure 1 ;

[0053] Figure 3 Flow schematic of the battery abnormal connection detection method provided by this application Figure 2 ;

[0054] Figure 4 Flow schematic of the battery abnormal connection detection method provided by this application Figure 3 ;

[0055] Figure 5 Structural schematic diagram of the battery abnormal connection detection device provided by this application;

[0056] Figure 6 Structural schematic diagram of the battery abnormal connection detection equipment provided by this application.

[0057] Through the above-mentioned drawings, specific embodiments of this application have been shown, and there will be more detailed descriptions hereinafter. These drawings and text descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments. Detailed implementation manners

[0058] 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 implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with this application. On the contrary, they are merely examples of devices and methods consistent with some aspects of this application as detailed in the appended claims.

[0059] Terms such as "first", "second", "third", "fourth", etc. (if any) in the specification, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can be implemented in an order different from those illustrated or described here, for example.

[0060] In the embodiments of this application, words such as "exemplary" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in this application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0061] First, the nouns involved in this application are explained:

[0062] Manual Maintenance Switch MSD: Msd (Maintenance Switch Disconnector) is the abbreviation of the manual maintenance switch, which is installed and used in the power battery system Pack to ensure the safety of the power battery pack during use and maintenance.

[0063] Downsampling: It is a technique in digital signal processing used to reduce the sampling rate of a signal, usually for reducing data transmission rate or data size. A filter is used during downsampling to reduce the distortion caused by aliasing, as downsampling can lead to aliasing.

[0064] Figure 1 The following is a schematic diagram of the scenario of the battery abnormal connection detection method provided by this application. As Figure 1 shown, the main body of the detection involved in this application is the battery cluster 1. There are multiple Packs in the battery cluster 1. Each Pack includes a positive connection point 2 and a negative connection point 3. To connect multiple battery cells together, the positive connection point 2 and the negative connection point 3 of the Pack can be connected through the two aviation plug interfaces 41 and 42 of the MSD power line respectively. To ensure the normal operation of the battery cluster, it is necessary to ensure that the connection of the MSD power line is firm and reliable, ensuring that there is no loosening or detachment under high-voltage conditions.

[0065] Combined with the above scenario, within the energy storage system, loose connections of the positive and negative poles of the battery cluster and the MSD power line may lead to a series of serious safety risks. In the prior art, a series of battery temperature abnormal judgment thresholds built through thermodynamic experimental data are used to determine the abnormal detection result of the battery pack, or the temperature data of the copper busbar collected in real time during the operation of the factory unit and the adaptive hierarchical alarm threshold are used to output the temperature abnormal alarm information of the copper busbar. The above prior art has high data requirements, complex implementation means, limited applicable scenarios, and the detection result is greatly affected by data, resulting in inaccurate abnormal detection.

[0066] The battery abnormal connection detection method provided by this application identifies connection points with loosening risks by performing outlier detection on the temperature points at the power lines of the positive and negative poles of the battery cluster and the MSD aviation plug connection. It can adaptively identify the loosening problems of the power lines of the positive and negative poles of the energy storage system battery cluster and the MSD aviation plug connection in advance, thereby improving the safety and performance of the energy storage system battery cluster. It solves the problems of the prior art, such as high data requirements, complex implementation means, limited applicable scenarios, and the detection result being greatly affected by data, resulting in inaccurate abnormal detection.

[0067] 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 below 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 accompanying drawings.

[0068] Figure 2 Flow schematic of the battery abnormal connection detection method provided by the present application Figure 1 , such as Figure 2 shown, the method includes:

[0069] S101. Obtain the detection information of the battery cluster.

[0070] Among them, the battery cluster contains multiple temperature measurement points to be measured, and the detection information is used to indicate the detected temperatures and current information of the multiple temperature measurement points to be measured within the first preset period. The current information may include, for example: timestamp, total battery cluster current information, etc.

[0071] It can be understood that the temperature data can be provided by temperature sensors installed near the aviation plugs. These sensors will convert the temperature signals into electrical signals and transmit them to the data acquisition device or the BMS system. By connecting to the interface of the data acquisition device or the BMS system, the temperature data of each aviation plug temperature point can be obtained, or dedicated data acquisition software or API interfaces can be used to extract the temperature data from the device or system and associate it with the corresponding aviation plug position. Through the management system inside the battery cluster, the corresponding temperature information can be obtained. Within the first preset period, the system will record and store the detected temperatures of each temperature measurement point to be measured. These temperature data can be used to analyze the heat dissipation performance, thermal management effect of the battery cluster, and whether there is abnormal temperature rise, etc.

[0072] Optionally, according to the data preprocessing principle, some abnormal data temperatures (exceeding the normal range, such as less than or greater than ) data can be cleaned, or the temperature jump data caused by abnormal acquisition communication can be filtered and filled.

[0073] Through the current information in the detection information, it is determined that the magnitude and change of the current directly reflect the charge and discharge state and power output situation of the battery cluster. By analyzing the current information, the energy conversion efficiency of the battery cluster under different working conditions can be understood, and whether the charge and discharge performance of the battery is normal can be evaluated. At the same time, by comprehensively analyzing the temperature information and the current information, the operating characteristics of the battery cluster can be more comprehensively understood, providing strong data support for optimizing the battery management strategy.

[0074] Timestamps are usually automatically generated by data acquisition devices or BMS systems. For example, by connecting to the interfaces of data acquisition devices or BMS systems, frame data containing timestamps can be obtained, or dedicated data acquisition software or API interfaces can be used to extract timestamp information from the devices or systems.

[0075] S102. Based on the current information, determine the state distribution of the battery cluster within the first preset time period, and based on the state distribution, determine the target detection data.

[0076] Among them, the target detection data is the data within the second preset time period in the detection information.

[0077] It can be understood that the current data of the battery cluster within the first preset time period is obtained through the battery management system (BMS) or dedicated data acquisition devices. The collected current data is cleaned to remove invalid data such as outliers and missing values. The data is smoothed to reduce the impact of noise and fluctuations on subsequent analysis.

[0078] According to the working characteristics of the battery cluster and the actual application requirements, different state categories are defined. The states of the battery cluster can be classified into the following categories, for example:

[0079] Charging state: When the current is positive and within a certain range, it can indicate that the battery cluster is charging. For example, it is stipulated that when the current is greater than 0A and less than 120% of the charging rated current, it is in the charging state.

[0080] Discharging state: When the current is negative and within a certain range, it can indicate that the battery cluster is discharging. For example, it is stipulated that when the current is less than 0A and greater than -120% of the discharging rated current, it is in the discharging state.

[0081] Static state: When the absolute value of the current is less than a certain threshold (such as 0.1A), it can be considered that the battery cluster is in the static state, and at this time the battery is neither significantly charging nor discharging.

[0082] According to the above-defined state classification criteria, judge the current information at each time point within the first preset time period to determine the state of the battery cluster at that moment. Then count the time proportion or the number of occurrences of different states within the entire time period to obtain the state distribution.

[0083] According to the state distribution, in the case of continuously being in a single state for more than a certain period of time, obtain the characteristic data within the time period of this single state, and then determine the target detection data.

[0084] S103. Group the target detection data and construct characteristic parameters based on multiple groups of detection data.

[0085] Among them, through the above process, it can be known that the target monitoring data is the data within a preset time period under a certain single state. Therefore, the data corresponding to multiple temperature measurement points is included in such data. In order to separate the data of each type of temperature measurement point, it is necessary to perform grouping processing on it to obtain the characteristic parameters corresponding to each type of temperature measurement point, so as to obtain a more accurate detection result.

[0086] It can be understood that all the temperature points to be measured can be identified. Each temperature point may be associated with a specific physical location or state, such as different modules of a battery pack, connection points, cooling systems, etc. The identification method can be, for example, through sensor numbers, position numbers, etc. Subsequently, the data is grouped according to the type and position of the temperature measurement points, or according to their performance within a certain preset time period.

[0087] Secondly, after grouping the target detection data, the next step is to extract useful characteristic parameters from each group of data, and these characteristics will help with subsequent analysis and judgment. The extracted characteristic parameters can include, for example:

[0088] Mean: The average temperature of each group of data can be used as the basic characteristic of the group.

[0089] Standard Deviation: Measures the degree of temperature fluctuation and can reveal the stability and consistency of the data.

[0090] Max / Min: By observing the maximum and minimum values of the data, the areas or moments of abnormal temperature fluctuations can be identified.

[0091] Peak: Can represent the sudden or extreme situations that occur in the data, usually appearing when the battery temperature fluctuates abnormally.

[0092] Data Variation: Can reflect the degree of temperature change within a certain time period and help analyze whether there are abnormalities.

[0093] Time Series Trend: Perform time series analysis on the data to extract the trend information of rising, falling, or remaining stable, which is crucial for judging the battery state.

[0094] By grouping the target detection data and extracting key characteristic parameters within each group, the ability to process and analyze complex monitoring data can be effectively improved. This method not only helps to accurately identify abnormal situations but also provides a scientific basis for battery management systems, temperature control, and energy optimization.

[0095] S104. Based on the characteristic parameters corresponding to multiple groups of detection data, perform abnormal connection detection on the battery cluster to obtain the abnormal points within the battery cluster.

[0096] Among them, according to the change of characteristic parameters, anomaly detection can be carried out on each battery point in the battery cluster by methods such as anomaly detection algorithms or threshold judgment.

[0097] It can be understood that the anomaly detection methods can be divided into multiple data forms, specifically including: statistical anomaly detection, clustering anomaly detection, machine learning anomaly detection, and time series anomaly detection.

[0098] Specifically, for example, it can be statistical-based anomaly detection, which can include: setting a temperature threshold, and when the temperature of a certain battery in the battery cluster exceeds the set threshold, it is determined as an anomaly. For example, if the temperature of a certain battery exceeds the set maximum allowable value, it is considered that the battery may have an abnormal connection; or for each battery point, calculate the mean and standard deviation of its temperature. If the temperature of a certain battery point deviates from the mean by more than multiple standard deviations, it is considered that the battery is abnormal.

[0099] Clustering-based anomaly detection can include clustering all the data of the battery cluster and gathering similar temperature patterns together. If the characteristic parameters of a certain battery point deviate significantly from most of the data clusters, it may be an anomaly point; or perform density-based clustering on the data points, and the points with lower density may be anomaly points, representing battery points with abnormal connections or states.

[0100] Machine learning-based anomaly detection can include training an SVM model, using the data of the battery cluster in the normal state to train the model, and then detecting those battery points with temperature characteristics significantly different from the normal pattern through the model and determining them as anomalies; or by constructing multiple trees to isolate the data, and the points with higher isolation usually indicate anomalies.

[0101] Optionally, the data of the battery cluster usually contains a time dimension, and the detection method can also use time series models (such as ARIMA, LSTM, etc.) to detect abnormal fluctuations in temperature or state. If the temperature data of the battery cluster shows a change trend that does not conform to the normal pattern, it can be determined as an anomaly point.

[0102] According to the foregoing detection method, input the detection points of each battery cluster and their characteristic parameters into the model to obtain the anomaly score of each battery point. If the score of a certain battery point is higher than the set threshold, it is marked as an anomaly point. Perform anomaly classification on each battery point through temperature data or other sensor data, and mark the battery cells or connections with problems. Once an anomaly point is found, the system can report and arrange for maintenance in a timely manner through alarms, notifications, etc.

[0103] Optionally, to better understand the anomalies in the battery cluster, the detection results can be visualized. Common visualization methods include: plotting the temperature distribution of each battery in the battery cluster as a heatmap to help discover temperature anomaly regions; plotting the curves of each temperature point in the battery cluster over time to facilitate trend analysis; or displaying the clusters to which each battery point belongs to help identify abnormal clusters.

[0104] In addition, based on the detection results, the detection model is continuously optimized. By adding more features, adjusting algorithm parameters, or combining new data sources, the accuracy and efficiency of anomaly detection can be improved. Through feature parameter extraction and anomaly detection algorithms based on multiple sets of detection data, abnormal connection points in the battery cluster can be effectively identified. The detected abnormal points can help identify potential problems in the battery cluster, such as overheating, loose connections, poor cooling, etc., providing important decision-making support for the battery management system to ensure the stable operation of the battery cluster.

[0105] The battery abnormal connection detection method provided by the embodiments of the present application obtains detection information of a battery cluster, where the battery cluster includes multiple temperature measurement points to be measured, and the detection information is used to indicate the detected temperatures and current information of the multiple temperature measurement points to be measured within a first preset period; based on the current information, determine the state distribution of the battery cluster within the first preset period, and based on the state distribution, determine target detection data, where the target detection data is the data within a second preset period in the detection information; perform grouping processing on the target detection data, and based on multiple sets of detection data, construct feature parameters; based on the feature parameters corresponding to the multiple sets of detection data, perform abnormal connection detection on the battery cluster to obtain abnormal points within the battery cluster. By extracting features from the detection data, accurately locate the abnormal points, and identify in advance the problem of loose connections in the energy storage system battery, thereby improving the safety and performance of the energy storage system battery cluster.

[0106] Figure 3 Schematic flow of the battery abnormal connection detection method provided by the present application Figure 2 , as Figure 3 shown, based on the Figure 2 embodiment, the battery abnormal connection detection method is described in detail. The method includes:

[0107] S201. Obtain the detection information of the battery cluster.

[0108] Among them, step S201 is similar to the above step S101, and the present application will not elaborate here.

[0109] S202. Based on the current values at multiple timestamps, determine the operating state of the battery cluster within a first period and the operating period corresponding to each operating state.

[0110] Among them, the operating state of the battery cluster and the corresponding operating time periods for each operating state. The operating states include: charging state, discharging state, and static state. Collect the current value data of the battery cluster at multiple timestamps within the first time period. These data should have sufficient time resolution to accurately reflect the changes in the operating state of the battery cluster. And preprocess the collected data, including removing noise, filling in missing values, etc., to ensure the accuracy and integrity of the data.

[0111] It can be understood that the determination of the operating state can be based on the current value. For example, when the current value is positive and greater than a certain set threshold, it can be determined that the battery cluster is in the charging state; when the current value is negative and less than a certain set threshold, it can be determined that the battery cluster is in the discharging state; when the current value is close to zero, it can be determined that the battery cluster is in the static state, and the static state means that the battery cluster is neither charging nor discharging.

[0112] At this time, if the current value remains within a certain range (charging, discharging, or static) for a long time, the operating state of the current time period can be determined. If the current value changes little over a long period of time, it can be considered a stable operating state.

[0113] It should be noted that the current value during the charging process may vary with different charging stages, but generally should remain within the positive value range; correspondingly, the current value during the discharging process will also vary with different discharging stages, but generally should remain within the negative value range. In addition, the set threshold for charging, the set threshold for discharging, and the set error range for static can all be set according to the specifications and charge-discharge characteristics of the battery cluster, and this application does not limit them here.

[0114] Specifically, for example, it can be that the operating state of the battery cluster is judged according to the current information. When the current is greater than 5A, it is considered that the current is in the discharging state; when the current is less than -5A, it is considered that the current is in the charging state; when the current is between -5A and 5A, it is considered that the current is in the static state.

[0115] Based on the current values at multiple timestamps, the operating state (charging, discharging, static) of the battery cluster at each time point can be determined by setting reasonable current thresholds. By traversing the time series and combining state classification and continuous state detection, the time periods corresponding to each operating state can be effectively divided and further analyzed and visualized.

[0116] S203. Determine the operating state distribution of the battery cluster within the first preset time period according to each operating state and the corresponding operating time periods.

[0117] S204. Based on the operating state distribution, determine the third time period that is greater than the first preset duration.

[0118] Among them, the third time period is used to indicate the time period during which the battery cluster continuously remains in the same operating state. That is, according to the duration of each state within the first preset time period, the situation where the battery cluster maintains the same state for a relatively long period of time is determined.

[0119] It can be understood that by obtaining the current value data of the battery cluster at all timestamps within the first preset time period and judging the operating state (charging, discharging, standing still) at each timestamp according to the current value data. The timestamps with the same continuous operating state can be divided into an operating time period, and the start time, end time, and corresponding operating state of each operating time period are recorded. Thereafter, the total duration of each operating state within the first preset time period can be counted, and the proportion of each operating state in the total duration can be calculated to understand the operating state distribution.

[0120] The setting of the first preset duration can be determined, for example, according to the charge and discharge characteristics of the battery, and is used to judge the third time period. Among all the operating time periods, the operating time periods with a duration longer than the first preset duration are screened out, and the screened operating time periods are used as the third time period. These time periods indicate that the battery cluster continuously remains in the same operating state for more than the first preset duration.

[0121] Specifically, for example, at this time the first preset time period is 10 minutes. Within a certain time stamp, a certain charging state lasts for 15 minutes; a certain discharging state lasts for 8 minutes; a certain standing still state lasts for 5 minutes. At this time, this charging time period is recorded as the third time period.

[0122] S205. Based on the detection information corresponding to the third time period, determine a second time period longer than the second preset duration.

[0123] Among them, the second time period is used to indicate the time period during which the thermal management system continuously does not start within the third time period. The start of the thermal management system is based on temperature monitoring. When the temperature of the battery cluster exceeds a certain predetermined threshold, the thermal management system will start. The non-start state means that the thermal management system is not activated within a period of time, and the temperature of the battery cluster remains at a relatively low level.

[0124] It can be understood that for multiple determined third time periods, collect the corresponding thermal management system status data, which can include information such as the start / stop state of the thermal management system, temperature readings, and the flow rate of the fan or coolant. Within each third time period, check the start state of the thermal management system. If the thermal management system does not start within a certain continuous time period (that is, the state is "stopped" or "not activated"), then record this time period. For each recorded non-start time period, calculate its duration.

[0125] Specifically, a second preset duration can be determined as the threshold for judging the second time period. This duration can be reasonably set according to the thermal management requirements, safety standards, and actual operating conditions of the battery cluster, and this application does not limit it here. Among all the recorded unstarted time periods, the time periods with a duration longer than the second preset duration are screened out. These time periods are the second time periods, indicating that within the third time period, the thermal management system continuously fails to start for more than the second preset duration. Record the start time, end time, and corresponding third time period information of the second time period.

[0126] Optionally, the occurrence frequency, duration, and corresponding operating status of the battery cluster of the second time period can also be analyzed to evaluate the impact of the non-start of the thermal management system on the performance and safety of the battery cluster, which will not be elaborated in this application.

[0127] S206. Use the data within the second time period in the detection information as the target detection data.

[0128] Among them, for the data within the second time period obtained through the above steps of analysis, downsampling can be performed on it. The goal of downsampling is to reduce the data density by reducing the number of data points, thereby saving storage space or reducing the computational amount in target detection. An appropriate downsampling method can be selected according to the characteristics of the data and the analysis requirements. For example, uniform downsampling can be used, that is, data points are selected according to a certain time interval; or threshold-based downsampling can be used, that is, downsampling is performed according to the amplitude of data change. If the continuous numerical change is small, some data points are skipped; if the change is large, the data points are retained.

[0129] It can be understood that the downsampling rate can be determined according to the time resolution and analysis requirements of the data. The downsampling rate refers to the ratio between the original data points and the downsampled data points.

[0130] S207. Group the target detection data according to the positive connection point, negative connection point, first aviation plug temperature measurement point, second aviation plug temperature measurement point, and the corresponding model information of the aviation plug to obtain multiple groups of detection data sets.

[0131] Among them, since the aviation plug temperature is affected by different connection points and different MSD models, grouping needs to be performed for different positions before anomaly detection. For example, the positive connection point is one group, the negative connection point is one group, and each of the 2 aviation plug temperature measurement points corresponding to the MSD is one group. In addition, since the MSD models of different battery packs in the battery cluster may be inconsistent, the aviation plug temperature measurement points are further grouped according to different models.

[0132] It is understandable that the temperature data of the positive connection points are grouped into one set; the temperature data of the negative connection points are grouped into another set. For each MSD model, the temperature data of its corresponding two connector temperature measurement points are respectively grouped into two sets. If there are multiple MSD models in the battery cluster, each model needs to be grouped separately.

[0133] S208. Respectively perform feature statistical processing on multiple groups of detection data sets to obtain the feature parameters corresponding to each group of detection data sets.

[0134] Among them, based on the above steps, it is confirmed that the detection data have been grouped according to the connection point type (positive, negative), MSD model, and connector temperature measurement points, forming multiple data sets. According to the analysis requirements and data characteristics, determine the feature parameters to be calculated. The feature parameters can include, for example, mean, standard deviation, maximum value, minimum value, median, interquartile range, skewness, kurtosis, etc.

[0135] S209. Adopt an anomaly detection algorithm to perform anomaly determination processing on the feature parameters corresponding to multiple groups of detection data to obtain the anomaly scores of the temperature measurement points to be measured corresponding to multiple groups of detection data.

[0136] S210. Based on the anomaly scores, determine the anomaly points in the battery cluster.

[0137] Among them, one or more thresholds can be set according to actual requirements and data characteristics to determine whether a data point is abnormal. The selection of the threshold should be able to balance the false alarm rate and the miss rate to ensure that both real anomaly points can be detected and not too many normal points are falsely reported. Compare the anomaly score of each data point with the set threshold. If the anomaly score exceeds the threshold, it is determined that the temperature measurement point corresponding to the data point is an anomaly point.

[0138] Specifically, the above anomaly point detection process can be, for example, taking the connector temperatures of different groups as the sample set to construct a feature data set, such as statistical features like the median and mean of the connector temperature; then randomly select a feature value and a cut-off value from the feature data set within the group, and divide the sample data set into two subsets.

[0139] For the data in the feature data set, recursively repeat the random selection steps of the feature value and the cut-off value until each subset contains only one sample or reaches the predetermined height of the tree; and continuously repeat the above steps to construct multiple random binary trees (i.e., a forest). For a new sample, judge whether it is abnormal by calculating the average value of the path lengths in each tree corresponding to the anomaly score.

[0140] It is understandable that abnormal points usually deviate from the normal point distribution to a certain extent and are independently distributed points. Therefore, the path length of abnormal points is much lower than that of normal points. Thus, abnormal points can be quickly identified by calculating the path length score.

[0141] By extracting the features of the data and performing normalization processing; using an anomaly detection algorithm to calculate the anomaly score of each data point, and then judging whether each data point is an abnormal point based on the anomaly score. In this way, the abnormal points are classified according to the battery cluster (i.e., the connection point of the positive and negative electrodes), and the abnormal points within each cluster are found. Through the above method, potential problems and anomalies in the battery cluster can be identified, which helps to discover abnormal patterns in actual monitoring and fault detection.

[0142] The battery abnormal connection detection method provided by the embodiments of the present application performs anomaly determination processing on the characteristic parameters of multiple groups of detection data by using an anomaly detection algorithm, and determines the abnormal points within the battery cluster based on the anomaly score. This helps to timely discover and handle potential problems in the battery cluster, ensuring the safe and stable operation of the battery system.

[0143] Figure 4 is a flow schematic of the battery abnormal connection detection method provided by the present application Figure 3 , as Figure 4 shown, based on the embodiments of Figure 2 and Figure 3 this embodiment, the continuous monitoring and abnormal alarm process of battery abnormal connection are described in detail. The method includes:

[0144] S301. Obtain the historical anomaly scores of multiple groups of temperature points to be measured.

[0145] Among them, the system or database storing the historical data of the temperature points to be measured can be identified and determined to ensure that the data source contains the required anomaly score information, or at least contains the original data that can be used to calculate the anomaly score.

[0146] S302. Determine the abnormal change trend of the temperature points to be measured based on the anomaly scores and historical anomaly scores of multiple groups of temperature points to be measured.

[0147] Among them, data analysis tools can be used according to the anomaly scores and historical anomaly scores of multiple groups of temperature points to be measured to analyze the historical anomaly score trend of the temperature points to be measured, observe the change of the anomaly scores, and identify any potential abnormal patterns or trends.

[0148] S303. When the abnormal change trend is abnormally increasing, determine that the corresponding temperature point to be measured is in an abnormal state and generate an abnormal alarm message.

[0149] Among them, it is possible to comprehensively evaluate the status of the temperature measurement point by combining the increasing trend of the anomaly score, historical anomaly records, temperature readings and other relevant information. If multiple indicators point to anomalies, it is more likely to determine that the temperature measurement point is in an abnormal state.

[0150] It can be understood that since there may be a long-term deterioration trend in the connection points of the energy storage system, the anomaly score of the sample points calculated according to each working condition is used to identify the potential anomaly trend. If it is found that the anomaly score of the sample points shows an upward trend, an early warning can be given for the abnormal situation. Abnormal alarm information can be generated to inform the operation and maintenance personnel so that the operation and maintenance personnel can handle the abnormal event in time.

[0151] The battery abnormal connection detection method provided by the embodiment of the present application, through the detection of the anomaly score and the historical anomaly score, when the anomaly change trend is abnormally increasing, determines that the corresponding temperature measurement point is in an abnormal state and generates abnormal alarm information, which helps to respond to and process potential failures or problems in time, ensure the safe and stable operation of the system, and further improve the safety and performance of the battery cluster of the energy storage system.

[0152] Figure 5 It is a schematic structural diagram of the battery abnormal connection detection device provided by the present application, as Figure 4 shown, the battery abnormal connection detection device 400 provided in this embodiment includes:

[0153] An acquisition module 401, configured to acquire detection information of the battery cluster, where the battery cluster includes a plurality of temperature measurement points, and the detection information is used to indicate the detected temperatures and current information of the plurality of temperature measurement points within a first preset period;

[0154] A determination module 402, configured to determine the state distribution of the battery cluster within the first preset period based on the current information, and determine target detection data based on the state distribution, where the target detection data is the data within a second preset period in the detection information;

[0155] A grouping module 403, configured to perform grouping processing on the target detection data and construct characteristic parameters based on multiple groups of detection data;

[0156] A detection module 404, configured to perform abnormal connection detection on the battery cluster based on the characteristic parameters corresponding to multiple groups of detection data to obtain abnormal points in the battery cluster.

[0157] In a possible implementation manner, the determination module 402 is further configured to determine the operating state of the battery cluster within a first period and the operating period corresponding to each operating state based on the current values at multiple timestamps, where the operating states include: charging state, discharging state, and static state;

[0158] The determination module 402 is further configured to determine the operating state distribution of the battery cluster within the first preset time period according to each operating state and the corresponding operating time period.

[0159] In a possible implementation manner, the determination module 402 is further configured to determine a third time period greater than the first preset duration based on the operating state distribution, where the third time period is used to indicate the time period during which the battery cluster continuously maintains the same operating state;

[0160] The determination module 402 is further configured to determine a second time period greater than the second preset duration based on the detection information corresponding to the third time period, where the second time period is used to indicate the time period during which the thermal management system continuously does not start within the third time period;

[0161] The determination module 402 is further configured to use the data within the second time period in the detection information as the target detection data.

[0162] In a possible implementation manner, the device further includes: a statistics module 405;

[0163] The grouping module 403 is further configured to group the target detection data according to the positive connection point, negative connection point, first aviation plug temperature measurement point, second aviation plug temperature measurement point, and the model information corresponding to the aviation plug temperature measurement point, to obtain multiple groups of detection data sets;

[0164] The statistics module 405 is configured to perform feature statistics processing on each group of detection data sets respectively to obtain the feature parameters corresponding to each group of detection data sets.

[0165] In a possible implementation manner, the detection module 404 is further configured to use an anomaly detection algorithm to perform anomaly determination processing on the feature parameters corresponding to multiple groups of detection data to obtain the anomaly scores of the temperature measurement points to be measured corresponding to the multiple groups of detection data;

[0166] The determination module 402 is further configured to determine the anomaly points within the battery cluster based on the anomaly scores.

[0167] In a possible implementation manner, the acquisition module 401 is further configured to acquire the historical anomaly scores of multiple groups of temperature measurement points to be measured, and determine the anomaly change trend of the temperature measurement points to be measured based on the anomaly scores and historical anomaly scores of the multiple groups of temperature measurement points to be measured;

[0168] The determination module 402 is further configured to determine that the corresponding temperature measurement point to be measured is in an abnormal state and generate an anomaly warning message when the anomaly change trend is abnormally increasing.

[0169] The battery anomaly connection detection device provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here in this embodiment.

[0170] Figure 6 This is a schematic structural diagram of the battery abnormal connection detection device provided by this application. As Figure 5 shown, the battery abnormal connection detection device 500 provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the device 500 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.

[0171] In the specific implementation process, at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that at least one processor 501 executes the above-mentioned method.

[0172] For the specific implementation process of the processor 501, reference can be made to the above method embodiment, and its implementation principle and technical effects are similar, so they will not be elaborated here in this embodiment.

[0173] In the above embodiment, it should be understood that the processor may be a central processing unit (English: Central Processing Unit, abbreviated: CPU), or other general-purpose processors, digital signal processors (English: Digital Signal Processor, abbreviated: DSP), application-specific integrated circuits (English: Application Specific Integrated Circuit, abbreviated: ASIC), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0174] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0175] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0176] The present application also provides a computer program product, including a computer program which, when executed by a processor, implements the above-mentioned method.

[0177] The present application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-mentioned method.

[0178] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk or an optical disc. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0179] An exemplary readable storage medium is coupled to the processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0180] The division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.

[0181] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0182] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0183] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, and other various media that can store program codes.

[0184] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When this program is executed, it executes the steps including the above method embodiments; and the aforementioned storage medium includes: ROMs, RAMs, magnetic disks, or optical discs, and other various media that can store program codes.

[0185] Finally, it should be noted that: After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily think of other implementation manners of the present invention. The present invention is intended to cover any variations, uses, or adaptive changes of the present invention. These variations, uses, or adaptive changes follow the general principles of the present invention and include the common general knowledge or conventional technical means in the technical field of the present invention that are not disclosed in the present invention. It 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 invention is only limited by the appended claims.

Claims

1. A method for detecting abnormal battery connection, characterized in that: include: Acquire detection information of a battery cluster, wherein the battery cluster includes a plurality of temperature test points, and the detection information is used to indicate the detected temperatures and current information of the plurality of temperature test points within a first preset time period; Based on the current information, determining the state distribution of the battery cluster within the first preset time period, and based on the state distribution, determining target detection data, the target detection data being data in the detection information within a second preset time period; The target detection data is processed in groups, and feature parameters are constructed based on multiple groups of detection data; Based on characteristic parameters corresponding to the multiple groups of detection data, abnormal connection detection is performed on the battery cluster to obtain abnormal points in the battery cluster.

2. The method according to claim 1, characterized in that The current information includes: current values ​​at multiple timestamps, and determining the distribution of the operating states of the battery cluster within the first preset time period based on the current information includes: Based on the current values ​​at the multiple time stamps, determining the operating state of the battery cluster and the operating time period corresponding to each operating state within the first time period, the operating state including: charging state, discharging state and static state; According to each operating state and the corresponding operating time period, the operating state distribution of the battery cluster within the first preset time period is determined.

3. The method according to claim 2, characterized in that Determining target detection data based on the running state distribution includes: Based on the distribution of the operating states, determining a third time period greater than a first preset time period, wherein the third time period is used to indicate a time period during which the battery cluster is continuously in the same operating state; Based on the detection information corresponding to the third time period, determining a second time period greater than a second preset time period, wherein the second time period is used to indicate a time period during which the thermal management system is continuously not started within the third time period; The data in the second time period in the detection information is used as the target detection data.

4. The method according to claim 1, characterized in that: The temperature points to be measured include: a positive connection point, a negative connection point, a first aerial plug temperature measurement point, and a second aerial plug temperature measurement point. The target detection data is grouped and processed, and characteristic parameters are constructed based on multiple groups of detection data, including: According to the positive connection point, the negative connection point, the first aerial plug temperature measurement point, the second aerial plug temperature measurement point, and the model information corresponding to the aerial plug temperature measurement point, the target detection data is grouped and processed to obtain multiple groups of detection data sets; Perform feature statistical processing on the multiple groups of detection data sets respectively to obtain feature parameters corresponding to each group of detection data sets.

5. The method according to claim 4, characterized in that The abnormal connection detection is performed on the battery cluster based on the characteristic parameters corresponding to the multiple groups of detection data to obtain the abnormal points in the battery cluster, including: Using an abnormality detection algorithm, the characteristic parameters corresponding to the multiple groups of detection data are processed for abnormality determination, and the abnormality scores of the temperature test points corresponding to the multiple groups of detection data are obtained; Based on the anomaly score, an abnormal point within the battery cluster is determined.

6. The method according to claim 5, characterized in that The method further comprises: Acquire historical anomaly scores of multiple groups of temperature test points, and determine an abnormal change trend of the temperature test points based on the anomaly scores of the multiple groups of temperature test points and the historical anomaly scores; When the abnormal change trend is abnormally increasing, it is determined that the corresponding temperature test point is in an abnormal state, and abnormal alarm information is generated.

7. A battery abnormal connection detection device, characterized in that: include: An acquisition module, used for acquiring detection information of a battery cluster, wherein the battery cluster includes a plurality of temperature test points, and the detection information is used for indicating the detection temperature and current information of the plurality of temperature test points within a first preset time period; a determination module, configured to determine, based on the current information, a state distribution of the battery cluster within the first preset time period, and determine target detection data based on the state distribution, wherein the target detection data is data in the detection information within a second preset time period; A grouping module, used for grouping the target detection data and constructing feature parameters based on multiple groups of detection data; The detection module is used to perform abnormal connection detection on the battery cluster based on characteristic parameters corresponding to multiple groups of detection data to obtain abnormal points in the battery cluster.

8. A battery abnormal connection detection device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when being executed by a processor.

Images