A battery management system resource allocation method, system, device and equipment

Abstract

The application discloses a battery management system resource allocation method, system, device and equipment, and relates to the technical field of battery management. In the scheme, the abnormal state determination model is adjusted through context data, so that the adjusted abnormal state determination model is more consistent with the actual system operation environment, and then the system operation state parameters can be accurately analyzed based on the abnormal state determination model to obtain an accurate first abnormal state determination result. It can be seen that the application adjusts the abnormal state determination model based on the context model, improves the determination accuracy of the model, reduces the possibility of misjudgment in actual application, avoids the situation that the system abnormality cannot be found in time and the system is misjudged as abnormal when it is normal, that is, the system abnormality can be accurately and timely found. Further, the resource allocation of the battery management system is adjusted based on the system operation state parameters, so that the system performance can be ensured.

Description

Technical Field

[0001] This application relates to the field of battery management technology, and in particular to a battery management system resource allocation method, system, device and equipment. Background Technology

[0002] The battery management system (BMS) is a critical system for ensuring the safe and efficient operation of battery packs. During battery use, the BMS monitors various state parameters of the battery in real time, such as voltage, current, and temperature. By managing the charging and discharging of the battery appropriately, it can extend battery life, improve battery efficiency, and ensure battery safety and reliability. In practical applications, changes in workload and external events can lead to fluctuations in system resource usage and even system anomalies.

[0003] Current methods for monitoring abnormal system states cannot accurately detect anomalies in the battery management system, resulting in the inability to take timely measures when resource problems occur. Summary of the Invention

[0004] This application provides a battery management system resource allocation method, a battery management system, a battery device, and electrical equipment, which can accurately and promptly detect system anomalies, thereby ensuring system performance.

[0005] In a first aspect, this application provides a battery management system resource allocation method, including:

[0006] The system obtains at least one system operating state parameter of the battery management system, context data of the system operating state parameter, and a pre-trained abnormal state judgment model; the context data includes data that is associated with the system operating state parameter and affects the system operating state parameter.

[0007] Based on the context data, the abnormal state determination model is adjusted;

[0008] The at least one system operating status parameter is input into the adjusted abnormal state judgment model to obtain the first abnormal state judgment result;

[0009] If the first abnormal state judgment result indicates that the battery management system is in an abnormal state, the resource allocation of the battery management system is adjusted based on the at least one system operating state parameter.

[0010] In this embodiment, the abnormal state determination model is adjusted by context data so that the adjusted abnormal state determination model is more in line with the actual system operating environment. Therefore, based on the abnormal state determination model, the system operating state parameters can be accurately analyzed to obtain accurate abnormal state determination results.

[0011] Thus, this application adjusts the abnormal state judgment model based on the context model, improving the model's judgment accuracy and reducing the possibility of misjudgment in practical applications. It avoids situations where system anomalies are not detected in a timely manner or where normal systems are misjudged as abnormal, enabling accurate and timely detection of system anomalies. Furthermore, adjusting the battery management system's resource allocation based on system operating state parameters ensures system performance.

[0012] In one possible implementation, the at least one system operating state parameter is input into the adjusted abnormal state determination model to obtain a first abnormal state determination result, including:

[0013] The at least one system operating status parameter is input into the adjusted abnormal state determination model, and the following operations are performed based on the abnormal state determination model:

[0014] For each of the system operating status parameters, the parameter value of the system operating status parameter is compared with the corresponding parameter threshold to obtain the comparison result; the parameter threshold is the critical value for whether the system operating status is abnormal.

[0015] Based on the comparison results of each of the system operating status parameters, the first abnormal state judgment result is determined.

[0016] This application embodiment determines anomalies by setting thresholds. Specifically, it compares the threshold parameters set in the anomaly state determination model with the corresponding system operating state parameters, and the current state of the battery management system can be obtained based on the comparison results. This approach allows for the combination of comparison results from multiple system operating state parameters to determine anomalies, thereby improving the accuracy of the determination results.

[0017] In one possible implementation, the abnormal state determination model is adjusted based on the context data, including:

[0018] Based on the context data, the threshold values ​​of each parameter in the abnormal state determination model are adjusted.

[0019] In this embodiment, the specific method for adjusting the abnormal state determination model based on contextual data is to adjust the parameter thresholds within the model. It is evident that this embodiment combines contextual data characterizing the actual environment to adjust the parameter thresholds for abnormal state determination, thereby improving the model's accuracy and reducing the possibility of misjudgment in practical applications.

[0020] In one possible implementation, after inputting the at least one system operating state parameter into the adjusted abnormal state determination model to obtain a first abnormal state determination result, the method further includes:

[0021] Obtain the battery status data corresponding to the battery management system;

[0022] Based on the battery status data, the second abnormal state judgment result of the battery management system is determined;

[0023] If the first abnormal state judgment result is inconsistent with the second abnormal state judgment result, the threshold values ​​of each parameter in the abnormal state judgment model are adjusted according to the battery state data.

[0024] In this implementation, the abnormal state judgment model is adjusted in real time during system operation to improve the accuracy of abnormal state judgment conditions in practical applications. Specifically, a more accurate second abnormal state judgment result is determined based on battery state data. If the first and second abnormal state judgment results are inconsistent, the parameter thresholds are adjusted, thereby improving the model's judgment accuracy and reducing the possibility of misjudgment in practical applications.

[0025] In one possible implementation, adjusting the resource allocation of the battery management system based on the at least one system operating state parameter includes:

[0026] Based on the system operating status parameters, the resource allocation priority for battery management tasks is determined;

[0027] Hardware resources are allocated to the battery management task in descending order of resource allocation priority.

[0028] This application's embodiments assign different resource allocation priorities to battery management tasks, and then allocate hardware resources to each battery management task in descending order of resource allocation priority. Because in the event of system anomalies, the number of tasks that can be executed with limited resources is limited, this solution can ensure that high-critical tasks can be processed in a timely manner while maintaining system performance.

[0029] In one possible implementation, determining the resource allocation priority of the battery management task based on the system operating state parameters includes:

[0030] When the system operating status parameters indicate that the system resource utilization rate exceeds a threshold, the task type of the battery management task is obtained;

[0031] Based on each of the described task types, the resource allocation priority of the battery management task is determined.

[0032] In this implementation, the resource allocation priority is determined by the task type of the battery management task, and hardware resources are allocated to each battery management task in descending order of priority. This solution ensures that battery management tasks of important types are executed first.

[0033] In one possible implementation, adjusting the resource allocation of the battery management system based on the at least one system operating state parameter includes:

[0034] Based on the system operating status parameters, determine the resource access permissions for the battery management task;

[0035] Based on the resource access permissions, allocate hardware resources for the battery management task.

[0036] In this implementation, the resource access permissions of the battery management system are determined by the system's operating status parameters, and resource allocation is then implemented based on these permissions, thereby reducing the probability of system anomalies.

[0037] In one possible implementation, before acquiring at least one system operating state parameter of the battery management system, context data of the system operating state parameter, and a pre-trained abnormal state determination model, the method further includes:

[0038] Obtain system operating status parameter samples and corresponding status labels of the battery management system; the status labels include normal status labels and / or abnormal status labels.

[0039] The abnormal state determination model is obtained by training a machine learning model based on the system operating state parameter samples and the corresponding state labels.

[0040] In this implementation, the machine learning model is trained based on system operating state parameter samples and corresponding state labels, thereby obtaining an abnormal state judgment model that can accurately determine anomalies. Based on this model, system anomalies can be detected accurately and in a timely manner.

[0041] In one possible implementation, the system operating status parameters include any one or any combination of the following: CPU utilization data, memory utilization data, task execution time data, task response time data, system throughput data, and system energy consumption data.

[0042] This implementation provides specific examples of system operating status parameters, which can improve the accuracy of anomaly detection conditions.

[0043] The context data includes any one or any combination of the following: priorities between different battery management tasks, dependencies between different battery management tasks, and functional and requirement data of the battery management system application.

[0044] This implementation provides specific examples of context data. Through this context data, the actual situation of the system's current operation can be accurately understood. Based on this data, the abnormal state judgment conditions can be adjusted to obtain a second abnormal state judgment condition that is more in line with the actual situation.

[0045] Secondly, this application provides a battery management system, including:

[0046] An information acquisition unit is used to acquire at least one system operating status parameter of the battery management system, context data of the system operating status parameter, and a pre-trained abnormal state judgment model; the context data includes data that is associated with the system operating status parameter and affects the system operating status parameter;

[0047] A processor is configured to adjust the abnormal state determination model based on the context data;

[0048] The processor is further configured to input the at least one system operating status parameter into the adjusted abnormal state judgment model to obtain a first abnormal state judgment result.

[0049] The processor is further configured to adjust the resource allocation of the battery management system based on the at least one system operating status parameter when the first abnormal state judgment result indicates that the battery management system is in an abnormal state.

[0050] Thirdly, this application provides a battery device, including the aforementioned battery and a battery management system.

[0051] Fourthly, this application provides an electrical device including the aforementioned battery device.

[0052] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0053] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiments below. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0054] Figure 1 A flowchart illustrating a battery management system resource allocation method provided in an embodiment of this application;

[0055] Figure 2 A schematic flowchart of step S103 provided in an embodiment of this application;

[0056] Figure 3 A flowchart illustrating an abnormal state determination model adjustment method provided in an embodiment of this application;

[0057] Figure 4 A flowchart illustrating step S104 provided in an embodiment of this application;

[0058] Figure 5 A schematic diagram of another S104 provided for an embodiment of this application;

[0059] Figure 6 A flowchart illustrating a training abnormal state determination model provided in an embodiment of this application;

[0060] Figure 7 This is a schematic diagram of the structure of a battery management system provided in some embodiments of this application. Detailed Implementation

[0061] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0063] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0064] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0065] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0066] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0067] The battery management system of this application is used to perform at least one of the following functions for individual battery cells: state monitoring, state analysis, charge / discharge control, safety protection, information management, thermal management, and high-voltage power distribution. In addition, the battery management system of this application can also perform the functions of a controller in an electrical device, such as a vehicle control unit (VCU) or a motor control unit (MCU), etc., and this application does not impose any limitations on this.

[0068] It should be noted that the battery management system in this application can be integrated as a controller into the battery device, such as into the battery pack or energy storage box.

[0069] The battery management system in this application can also be integrated as a controller into electrical devices, such as in a vehicle or vehicle chassis.

[0070] The battery management system in this application can also be integrated into the charging device as a controller, such as into the charging device or the battery swapping device.

[0071] The battery management system in this application can also be deployed as control software on a server. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, such as vehicle networking cloud, application backends, etc.

[0072] Battery management systems (BMS) may experience anomalies during operation, thus requiring monitoring of the system status to take timely measures to ensure system performance. However, the specific operating conditions of BMS vary under different operating environments, making accurate status monitoring of the BMS impossible.

[0073] For example, in some situations, when a batch of related tasks are executed simultaneously, the load, energy consumption, CPU utilization, and memory usage of the battery management system may all increase. However, this does not necessarily indicate that the system is in an abnormal state. Therefore, traditional solutions cannot accurately detect anomalies in the battery management system, leading to misjudgments and an inability to take timely measures when anomalies occur, resulting in system performance degradation, malfunctions, or even crashes.

[0074] To address the aforementioned issues, this application considers that the various system operating state parameters of the battery management system will change accordingly under different operating environments. Contextual data based on these system operating state parameters can be used to infer the current operating environment, thereby achieving more accurate judgment. Furthermore, to achieve accurate anomaly detection, this application proposes using an anomaly detection model. In practical applications, this model can be adjusted based on the contextual data of the system operating state parameters, resulting in a more accurate determination of system anomalies.

[0075] Based on this, this application provides a resource allocation method for a battery management system. Figure 1 This is a flowchart illustrating a battery management system resource allocation method provided in an embodiment of this application. Figure 1 As shown, the method may include the following steps: S101 to S104.

[0076] S101: Obtain at least one system operating state parameter of the battery management system, context data of the system operating state parameter, and a pre-trained abnormal state judgment model.

[0077] This application does not limit the specific content of the system operating status parameters. As an optional implementation, the system operating status parameters may include CPU utilization data, memory utilization data, task execution time data, task response time data, system throughput data, and system energy consumption data, etc. Based on the above data, the current state of the system can be determined relatively accurately. In practical applications, the system operating status parameters can be adjusted in real time according to specific circumstances to ensure the accuracy of anomaly detection.

[0078] Contextual data primarily includes data that is related to and affects system operating status parameters. Examples include the priorities of different tasks, dependencies between tasks, functional data and requirement data of system applications, etc. Based on this data, the current actual operating environment of the system can be determined, providing a basis for subsequent judgments about the system's status.

[0079] The method for obtaining the above data is not specifically limited here. As an optional implementation method, the required system operating status parameters and context data can be obtained through the relevant interfaces of the operating system in the battery management system (such as API, hardware monitoring interface, etc.).

[0080] The abnormal state determination model is used to judge the system state based on system operating state parameters and output an abnormal state judgment result to determine whether the battery management system is in an abnormal state. The abnormal state determination model can judge the system abnormality by comparing the system operating state parameters with the corresponding parameter thresholds, and then determining the abnormal state judgment result based on the comparison result.

[0081] In practical applications, the anomaly detection model can be a pre-trained machine learning model. The specific model type is not limited and can include, but is not limited to, regression models for predicting resource demand, classification models for classifying task types, or more complex deep learning models. In implementation, the anomaly detection model can be continuously updated by learning from new data, improving its adaptability to the real-world environment and the accuracy of anomaly detection.

[0082] S102: Adjust the abnormal state determination model based on context data.

[0083] In this implementation, the context data of the system's operating status parameters is incorporated into the considerations for abnormal state determination. Since the corresponding abnormal parameter values ​​may differ under different operating environments, in order to accurately monitor abnormalities in the battery management system, this embodiment adjusts the abnormal state determination model based on the context data, thereby obtaining an abnormal state determination model that is more suitable for the actual operating environment of the current battery management system.

[0084] This implementation does not limit how the abnormal state determination model should be adjusted. As mentioned above, the abnormal state determination model can determine anomalies by having system operating status parameters exceed threshold values. Alternatively, as an optional implementation, the parameter thresholds in the abnormal state determination model can be adjusted based on context data.

[0085] For example, if a batch of related tasks are executed at the same time, the load, energy consumption, CPU utilization, and memory usage of the battery management system will inevitably increase. In this case, the parameter thresholds used to determine anomalies can be increased to avoid misjudging anomalies in the battery management system, thereby avoiding the situation where incorrect handling measures are taken after misjudgment, which would lead to a decrease in system performance.

[0086] S103: Input at least one system operating status parameter into the adjusted abnormal state judgment model to obtain the first abnormal state judgment result.

[0087] After adjusting the abnormal state judgment model, at least one system operating state parameter is input into the adjusted abnormal state judgment model. Then, the at least one system operating state parameter is analyzed based on the abnormal state judgment model to determine the first abnormal state judgment result of the battery management system.

[0088] The initial anomaly assessment result indicates whether the battery management system is in an abnormal state, but the specific assessment method is not limited. In practical applications, threshold comparison, statistical analysis, machine learning, and other methods can be used to determine whether the system usage is abnormal. For example, threshold parameters for CPU usage and memory occupancy can be set, and an anomaly alarm can be triggered when these thresholds are exceeded; or statistical models can be used to analyze the distribution of task execution time to identify abnormal values ​​in the execution time that exceed the parameter thresholds.

[0089] As mentioned above, the determination of system anomalies can usually be achieved by checking whether the system operating status parameters exceed a threshold. However, in this embodiment, the system operating status parameters can include multiple types, thus allowing for multiple corresponding parameter thresholds. As an optional implementation, each system operating status parameter can be compared with its corresponding parameter threshold to obtain multiple comparison results.

[0090] In addition, the determination of anomalies in the battery management system can be based on the presence of at least one system operating status parameter that exceeds the corresponding parameter threshold; or multiple system operating status parameters that exceed the corresponding parameter threshold; or a specific combination of system operating status parameters that exceed the corresponding parameter threshold.

[0091] As an optional implementation, each system operating status parameter can correspond to multiple parameter thresholds with different values. For example, two parameter thresholds can be set for each system operating parameter. If a single system operating status parameter exceeds the larger parameter threshold, the system is determined to be abnormal; or if multiple system operating status parameters exceed the smaller parameter threshold, the system is determined to be abnormal. It is worth noting that the above are some specific embodiments provided in this application and do not limit the specific implementation of this solution.

[0092] S104: If the first abnormal state judgment result indicates that the battery management system is in an abnormal state, adjust the resource allocation of the battery management system based on at least one system operating state parameter.

[0093] Finally, if the first abnormal state judgment result indicates that the battery management system is in an abnormal state, the resource allocation of the battery management system needs to be adjusted to ensure that the system does not malfunction or crash.

[0094] Specifically, based on the trained policy model, corresponding resource policies can be formulated according to the abnormal state conditions. Resource policies may include task scheduling algorithms, memory management strategies, etc. These policies are then tested through simulation or in a real system to evaluate their effectiveness and optimize them based on feedback.

[0095] Specifically, the resource allocation of the battery management system can be adjusted based on the system's operating status parameters. For example, if the system's hardware resources (such as the central processing unit and memory) are over-utilized, corresponding measures can be taken to reduce the resource utilization or ensure that important and critical tasks are executed first.

[0096] As some alternative implementation methods, the resource allocation of the battery management system can be adjusted in the following ways: setting corresponding resource allocation priorities for battery management tasks, adjusting the system working mode, and restricting the task's access permissions to memory, etc.

[0097] In this embodiment, the abnormal state determination model is adjusted by context data so that the adjusted abnormal state determination model is more in line with the actual system operating environment. Therefore, based on the abnormal state determination model, the system operating state parameters can be accurately analyzed to obtain accurate abnormal state determination results.

[0098] Thus, this application adjusts the abnormal state judgment model based on the context model, improving the model's judgment accuracy and reducing the possibility of misjudgment in practical applications. It avoids situations where system anomalies are not detected in a timely manner or where normal systems are misjudged as abnormal, enabling accurate and timely detection of system anomalies. Furthermore, adjusting the battery management system's resource allocation based on system operating state parameters ensures system performance.

[0099] To improve the accuracy of the first abnormal state judgment result, this application provides a feasible implementation method. Figure 2 This is a schematic flowchart of step S103 provided in an embodiment of this application. Figure 2 As shown, S103 may include: inputting at least one system operating status parameter into the adjusted abnormal state determination model, so as to execute S1031 and S1032 based on the abnormal state determination model.

[0100] S1031: For each system operating status parameter, compare the parameter value of the system operating status parameter with the corresponding parameter threshold to obtain the comparison result.

[0101] As mentioned above, system operating status parameters include any one or any combination of the following: CPU utilization data, memory utilization data, task execution time data, task response time data, system throughput data, and system energy consumption data. These system operating status parameters can improve the accuracy of anomaly detection conditions.

[0102] The parameter threshold is the critical value for whether the system's operating state is abnormal. In practical applications, one or more corresponding parameter thresholds can be set for each system operating state parameter, and then the parameter values ​​of the system operating state parameters can be compared with the corresponding parameter thresholds to obtain the comparison results.

[0103] S1032: Based on the comparison results of the operating status parameters of each system, determine the first abnormal state judgment result.

[0104] As mentioned above, this application can include multiple system operating status parameters. Therefore, for each system operating status parameter, a comparison result can be obtained. Thus, when determining the first abnormal state judgment result, the final judgment result can be obtained simultaneously based on multiple comparison results.

[0105] As some feasible implementation methods, multiple corresponding parameter thresholds can be set for each system operating status parameter. For example, two corresponding parameter thresholds can be set for each system operating status parameter. This means that a system anomaly can be determined when a single system operating status parameter exceeds the larger parameter threshold, or a system anomaly can be determined when multiple system operating status parameters are detected to simultaneously exceed their corresponding smaller parameter thresholds.

[0106] This application embodiment determines anomalies by setting thresholds. Specifically, it compares the threshold parameters set in the anomaly state determination model with the corresponding system operating state parameters, and the current state of the battery management system can be obtained based on the comparison results. This approach allows for the combination of comparison results from multiple system operating state parameters to determine anomalies, thereby improving the accuracy of the determination results.

[0107] To further improve the accuracy of the abnormal state determination model, this application provides a possible implementation method. Specifically, the abnormal state determination model is adjusted based on context data, including: adjusting the threshold values ​​of each parameter in the abnormal state determination model based on context data.

[0108] In this embodiment, the context data includes any one or any combination of the following: priorities between different battery management tasks, dependencies between different battery management tasks, and functional and requirement data of the battery management system application. This context data allows for an accurate understanding of the system's current operational status. Adjusting the abnormal state determination criteria based on this data yields a second abnormal state determination condition that better reflects the actual situation.

[0109] For example, if a batch of related tasks are executed at the same time, some system operating status parameters will inevitably rise. In this case, the parameter thresholds used to determine anomalies can be appropriately increased to avoid misjudging anomalies in the battery management system, and thus avoid system performance degradation caused by taking incorrect handling measures after misjudgment.

[0110] In this embodiment, the specific method for adjusting the abnormal state determination model based on contextual data is to adjust the parameter thresholds within the model. It is evident that this embodiment combines contextual data characterizing the actual environment to adjust the parameter thresholds for abnormal state determination, thereby improving the model's accuracy and reducing the possibility of misjudgment in practical applications.

[0111] In practical applications, the pre-trained abnormal state judgment model may not be accurate. Therefore, as a feasible implementation method, the abnormal state judgment model can be verified by the battery state data corresponding to the battery management system. If the abnormal state judgment results determined by the two methods are inconsistent, the abnormal state judgment model can be adjusted to improve the accuracy of the model.

[0112] Figure 3 This is a flowchart illustrating an abnormal state determination model adjustment method provided in an embodiment of this application. Figure 3 As shown, after S103, this method may further include: S301 to S303.

[0113] S105: Obtain battery status data corresponding to the battery management system.

[0114] As an optional implementation, the battery status data corresponding to the battery management system may include data such as battery temperature, voltage, and current.

[0115] S106: Based on battery status data, determine the second abnormal state judgment result of the battery management system.

[0116] By acquiring battery status data, the second abnormal state judgment result of the battery management system can be determined. The determined second abnormal state judgment result is one of the two states: normal state and abnormal state. In other words, the abnormality of the battery management system is detected again in this way.

[0117] S107: If the results of the first abnormal state judgment and the second abnormal state judgment are inconsistent, the threshold values ​​of each parameter in the abnormal state judgment model shall be adjusted according to the battery state data.

[0118] If the results of the first and second abnormal state determinations are inconsistent, the characterization based on the abnormal state determination model may be inaccurate. Therefore, this implementation adjusts the abnormal state determination model based on battery state data to ensure the accuracy of the abnormal state determination conditions. The specific adjustment method is not limited; it can involve adjusting the parameter thresholds in the abnormal state determination model.

[0119] The battery management system (BMS) evaluates the accuracy and applicability of the current anomaly detection model based on real-time battery status data. If a discrepancy is detected between the model's predicted state and the actual state, the system triggers a model adjustment mechanism. Based on the evaluation results, the BMS automatically adjusts the parameters of the anomaly detection model, such as the filtering coefficients and threshold settings in the remaining battery capacity estimation algorithm, to improve the model's accuracy and response speed.

[0120] While adjusting the model, the battery management system will also update the control strategies for charging, discharging, and balancing based on the actual usage and resource requirements of the battery, in order to optimize the battery's performance and lifespan.

[0121] In this implementation, the abnormal state judgment model is adjusted in real time during system operation to improve the accuracy of abnormal state judgment conditions in practical applications. Specifically, a more accurate second abnormal state judgment result is determined based on battery state data. If the first and second abnormal state judgment results are inconsistent, the parameter thresholds are adjusted, thereby improving the model's judgment accuracy and reducing the possibility of misjudgment in practical applications.

[0122] When a system malfunctions, it is necessary to take appropriate measures in a timely manner to avoid system performance degradation, failure, or even crash; therefore, this application provides a feasible implementation method. Figure 4 This is a schematic flowchart of step S104 provided in an embodiment of this application. Figure 4 As shown, S104 may include S1041 and S1042.

[0123] S1041: Determine the resource allocation priority for battery management tasks based on system operating status parameters.

[0124] As one possible implementation, when the system's operating status parameters indicate that the system resource utilization exceeds a threshold, the task type of the battery management task can be obtained; then, the resource allocation priority of the battery management task can be determined based on each task type.

[0125] In this implementation, the resource allocation priority is determined by the task type of the battery management task, and hardware resources are allocated to each battery management task in descending order of priority. This solution ensures that battery management tasks of important types are executed first.

[0126] S1042: Allocate hardware resources to the battery management task in descending order of resource allocation priority.

[0127] Generally, battery management tasks with higher resource allocation priority need to be executed first. Therefore, in this embodiment, hardware resources are allocated to battery management tasks in descending order of resource allocation priority.

[0128] This application's embodiments assign different resource allocation priorities to battery management tasks, and then allocate hardware resources to each battery management task in descending order of resource allocation priority. Because in the event of system anomalies, the number of tasks that can be executed with limited resources is limited, this solution can ensure that high-critical tasks can be processed in a timely manner while maintaining system performance.

[0129] In addition, this application provides another possible implementation. Figure 5 This is a schematic diagram of another S104 provided in an embodiment of this application. Figure 5 As shown, S104 may also include S1043 and S1044.

[0130] S1043: Determine the resource access permissions for battery management tasks based on system operating status parameters.

[0131] For example, in practical applications, if the memory usage exceeds the corresponding parameter threshold, the resource access permissions of the battery management task can be restricted, thereby reducing the number of memory accesses.

[0132] S1044: Allocate hardware resources for battery management tasks based on resource access permissions.

[0133] In this implementation, the resource access permissions of the battery management system are determined by the system's operating status parameters, and resource allocation is then implemented based on these permissions, thereby reducing the probability of system anomalies.

[0134] As mentioned above, the battery management system needs to be anomaly detected based on the adjusted anomaly detection model, which requires the model to have sufficiently high accuracy. Therefore, a relatively accurate anomaly detection model needs to be pre-trained before it can be adjusted based on context data to achieve accurate state monitoring.

[0135] This application provides one possible implementation method. Figure 6 This is a flowchart illustrating a training process for an abnormal state determination model provided in an embodiment of this application. Figure 6 As shown, before S101, this method may also include S601 and S602.

[0136] Before acquiring at least one system operating state parameter of the battery management system, the context data of the system operating state parameter, and the pre-trained abnormal state judgment model, the method further includes:

[0137] S601: Obtain system operating status parameter samples and corresponding status labels of the battery management system.

[0138] System operating status parameter samples and status labels can be constructed based on historical operating data in the battery management system. Specifically, system operating status parameter samples may include historical data such as CPU utilization, memory utilization, task execution time, task response time, system throughput, and system energy consumption. Status labels, on the other hand, indicate the state of the battery management system under the corresponding system operating status parameter sample; that is, status labels include normal status labels and / or abnormal status labels.

[0139] Before training the model, the collected raw data can be preprocessed using a host computer, including cleaning, filtering, and normalization, to ensure data quality and consistency. Preprocessing steps may also include converting the data into a format suitable for machine learning models.

[0140] S602: Based on the system operating status parameter samples and corresponding status labels, a machine learning model is trained to obtain an abnormal state judgment model.

[0141] By training a machine learning model based on the acquired system operating state parameter samples and corresponding state labels, an abnormal state determination model can be obtained. The abnormal state determination model can learn the correspondence between the system operating state parameter samples and state labels, and can determine under which system operating state parameters the battery management system belongs to an abnormal state, thus making an accurate determination in practical applications.

[0142] In practical applications, the abnormal state detection model can be updated periodically to adapt to the latest system environment. This can be achieved through incremental learning, online learning, or periodically retraining the entire model.

[0143] In this implementation, the machine learning model is trained based on system operating state parameter samples and corresponding state labels, thereby obtaining an abnormal state judgment model that can accurately determine anomalies. Based on this model, system anomalies can be detected accurately and in a timely manner.

[0144] To better illustrate the resource allocation method of the battery management system provided in this application, a specific implementation method is provided here.

[0145] First, before actually performing state monitoring based on the abnormal state determination model, samples of system operating state parameters and corresponding state labels of the battery management system can be obtained. Then, a machine learning model is trained based on these samples and the corresponding state labels to obtain the abnormal state determination model.

[0146] Then, at least one system operating state parameter of the battery management system and its context data are obtained, and the abnormal state judgment model is adjusted based on the context data. The at least one system operating state parameter is then input into the adjusted abnormal state judgment model to obtain the first abnormal state judgment result. Specifically, for each system operating state parameter, the parameter value is compared with the corresponding parameter threshold to obtain the comparison result, and then the first abnormal state judgment result is determined based on the comparison results of each system operating state parameter.

[0147] Finally, if the first abnormal state determination result indicates that the battery management system is in an abnormal state, the resource allocation of the battery management system is adjusted based on at least one system operating state parameter. As some feasible implementations, the resource allocation priority of battery management tasks can be determined, and resource access permissions for battery management tasks can be restricted.

[0148] In addition, the abnormal state judgment model can be verified by the battery status data corresponding to the battery management system. If the abnormal state judgment results determined by the two methods are inconsistent, the abnormal state judgment model can be adjusted to improve the accuracy of the model.

[0149] In practical applications, ensuring the normal operation of the battery management system is crucial for electrical equipment. As an optional implementation, after determining the first state of the battery management system based on system operating status parameters and second abnormal state judgment conditions, an abnormal system status alarm can be output if the first state is abnormal. This alarm can include a notification of the abnormality and specific details of the abnormality. This promptly alerts staff to take appropriate corrective measures, thereby ensuring the system's normal operation.

[0150] The above embodiments provide a resource allocation method for a battery management system. Correspondingly, the embodiments of this application provide a battery management system. Figure 7 This is a schematic diagram of the structure of a battery management system provided in some embodiments of this application. For example... Figure 7 As shown, the battery management system includes:

[0151] The information acquisition unit 701 is used to acquire at least one system operating state parameter of the battery management system, context data of the system operating state parameter, and a pre-trained abnormal state judgment model; the context data includes data that is associated with the system operating state parameter and affects the system operating state parameter;

[0152] Processor 702 is used to adjust the abnormal state determination model based on context data;

[0153] The processor 702 is also used to input at least one system operating status parameter into the adjusted abnormal state judgment model to obtain a first abnormal state judgment result;

[0154] The processor 702 is also configured to adjust the resource allocation of the battery management system based on at least one system operating state parameter when the first abnormal state judgment result indicates that the battery management system is in an abnormal state.

[0155] This solution can accurately and promptly detect system anomalies, and then adjust the resource allocation of the battery management system to ensure system performance, while also effectively preventing system failures and crashes.

[0156] The battery management system provided in this application has the same embodiments and beneficial effects as the battery health status determination method provided above, and will not be repeated here.

[0157] To address the aforementioned technical problems, this application also provides a battery device, which includes the battery and battery management system mentioned in the above embodiments. The battery device provided in this application has the same embodiments and beneficial effects as the battery management system described above, and will not be repeated here.

[0158] To address the aforementioned technical problems, this application also provides an electrical device, including the battery device mentioned above. The electrical device provided in this application has the same embodiments and beneficial effects as the battery device described above, and will not be repeated here.

[0159] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0160] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (ROM), flash memory, erasable-ROM (E-ROM), floppy disks, compact disc-ROMs (CD-ROMs), optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0161] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0162] The foregoing flowcharts and / or block diagrams of methods, apparatus (systems) according to embodiments of this application have described various aspects of the present application. It should be understood that each block in the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to create a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowcharts and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0163] Although this application has been described with reference to preferred embodiments, various modifications can be made thereto and components can be replaced with equivalents without departing from the scope of this application. In particular, the technical features mentioned in the various embodiments can be combined in any manner, provided there is no structural conflict. This application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A resource allocation method for a battery management system, characterized in that, include: The system obtains at least one system operating state parameter of the battery management system, context data of the system operating state parameter, and a pre-trained abnormal state judgment model; the context data includes data that is associated with and affects the system operating state parameter. Based on the context data, the abnormal state determination model is adjusted; The at least one system operating status parameter is input into the adjusted abnormal state judgment model to obtain the first abnormal state judgment result; If the first abnormal state judgment result indicates that the battery management system is in an abnormal state, the resource allocation of the battery management system is adjusted based on the at least one system operating state parameter.

2. The battery management system resource allocation method according to claim 1, characterized in that, The at least one system operating state parameter is input into the adjusted abnormal state determination model to obtain a first abnormal state determination result, including: The at least one system operating status parameter is input into the adjusted abnormal state determination model, and the following operations are performed based on the abnormal state determination model: For each of the system operating status parameters, the parameter value of the system operating status parameter is compared with the corresponding parameter threshold to obtain the comparison result; the parameter threshold is the critical value for whether the system operating status is abnormal. Based on the comparison results of each of the system operating status parameters, the first abnormal state judgment result is determined.

3. The battery management system resource allocation method according to claim 2, characterized in that, Based on the context data, the abnormal state determination model is adjusted, including: Based on the context data, the threshold values ​​of each parameter in the abnormal state determination model are adjusted.

4. The battery management system resource allocation method according to claim 2, characterized in that, After inputting the at least one system operating state parameter into the adjusted abnormal state determination model to obtain the first abnormal state determination result, the method further includes: Obtain the battery status data corresponding to the battery management system; Based on the battery status data, the second abnormal state judgment result of the battery management system is determined; If the first abnormal state judgment result is inconsistent with the second abnormal state judgment result, the threshold values ​​of each parameter in the abnormal state judgment model are adjusted according to the battery state data.

5. The battery management system resource allocation method according to any one of claims 1 to 4, characterized in that, Based on the at least one system operating status parameter, adjust the resource allocation of the battery management system, including: Based on the system operating status parameters, the resource allocation priority for battery management tasks is determined; Hardware resources are allocated to the battery management task in descending order of resource allocation priority.

6. The battery management system resource allocation method according to claim 5, characterized in that, Determining the resource allocation priority of the battery management task based on the system operating status parameters includes: When the system operating status parameters indicate that the system resource utilization rate exceeds a threshold, the task type of the battery management task is obtained; Based on each of the described task types, the resource allocation priority of the battery management task is determined.

7. The battery management system resource allocation method according to any one of claims 1 to 6, characterized in that, Based on the at least one system operating status parameter, adjust the resource allocation of the battery management system, including: Based on the system operating status parameters, determine the resource access permissions for the battery management task; Based on the resource access permissions, allocate hardware resources for the battery management task.

8. The battery management system resource allocation method according to any one of claims 1 to 7, characterized in that, Before acquiring at least one system operating state parameter of the battery management system, context data of the system operating state parameter, and a pre-trained abnormal state judgment model, the method further includes: Obtain system operating status parameter samples and corresponding status labels of the battery management system; the status labels include normal status labels and / or abnormal status labels. The abnormal state determination model is obtained by training a machine learning model based on the system operating state parameter samples and the corresponding state labels.

9. The battery management system resource allocation method according to any one of claims 1 to 8, characterized in that, The system operating status parameters include any one or any combination of the following: CPU utilization data, memory utilization data, task execution time data, task response time data, system throughput data, and system energy consumption data.

10. The battery management system resource allocation method according to any one of claims 1 to 9, characterized in that, The context data includes any one or any combination of the following: priorities between different battery management tasks, dependencies between different battery management tasks, and functional and requirement data of the battery management system application.

11. A battery management system, characterized in that, include: An information acquisition unit is used to acquire at least one system operating status parameter of the battery management system, context data of the system operating status parameter, and a pre-trained abnormal state judgment model; the context data includes data that is associated with the system operating status parameter and affects the system operating status parameter; A processor is configured to adjust the abnormal state determination model based on the context data; The processor is further configured to input the at least one system operating status parameter into the adjusted abnormal state judgment model to obtain a first abnormal state judgment result. The processor is further configured to adjust the resource allocation of the battery management system based on the at least one system operating status parameter when the first abnormal state judgment result indicates that the battery management system is in an abnormal state.

12. A battery device, characterized in that, Includes the battery and battery management system as described in claim 11.

13. An electrical appliance, characterized in that, Includes the battery device as described in claim 12.

Images