Battery management system task detection methods, systems, storage media and products

Abstract

The embodiment of the application provides a battery management system task detection method, system, storage medium and product, the method comprises the following steps: obtaining a target execution time corresponding to a task in a battery management task execution process, and a target interval time of continuously executing the same task twice; according to the target execution time and the target interval time, determining whether there is a time anomaly in the battery management task execution process. In this way, the time anomaly is detected from two dimensions of execution time and interval time, so that the head of the time anomaly can be found in time, and the accuracy and reliability of task detection are improved.

Description

Technical Field

[0001] This application relates to the field of battery management system technology, and in particular to a task detection method, system, storage medium and product for a battery management system. Background Technology

[0002] During the execution of battery management tasks, battery management systems (BMS) often need to detect any time anomalies. Based on the detection results, interventions or appropriate measures can be taken to ensure the smooth execution of battery management tasks and improve the stability of the BMS. Therefore, improving the accuracy and reliability of task detection is crucial for enhancing the stability of the BMS. Summary of the Invention

[0003] This application provides a task detection method, system, storage medium, and product for a battery management system. It can more comprehensively detect time anomalies by considering both task execution time and interval time, so as to promptly detect any signs of time anomalies and thus improve the accuracy and reliability of task detection.

[0004] In a first aspect, embodiments of this application provide a task detection method, the method comprising:

[0005] Obtain the target execution time of the battery management task during its execution, as well as the target interval between two consecutive executions of the same task. The target interval is the difference between the start times of the two consecutive executions of the same task.

[0006] Determine whether there is a timeout anomaly based on the target execution time, and determine whether there is an interval time anomaly based on the target interval time;

[0007] In response to at least one of timeout exception and interval time exception, determine that a time exception exists during the execution of the battery management task.

[0008] In this way, by obtaining the target execution time of the battery management task during its execution process, as well as the target interval time between two consecutive executions of the same task, time anomalies can be detected more comprehensively from both the execution time and interval time dimensions. This allows for the timely detection of early signs of time anomalies, thereby improving the accuracy and reliability of task detection.

[0009] In some embodiments, determining whether a timeout exception exists based on a target execution time, and determining whether an interval time exception exists based on a target interval time, includes:

[0010] Based on the target execution time and the maximum allowed duration corresponding to the task, determine whether there is a timeout exception;

[0011] Based on the target interval time and the reference interval time for two consecutive executions of the same task, determine whether there is an interval time anomaly.

[0012] In this way, timeout anomalies can be determined based on the target execution time and the maximum allowable duration corresponding to the task, while interval time anomalies can be determined based on the target interval time and the reference interval time between two consecutive executions of the same task. This allows for the detection of time anomalies from two dimensions: timeout anomalies and interval time anomalies, so as to detect the early signs of time anomalies in a timely manner and improve the accuracy and reliability of task detection.

[0013] In some embodiments, the reference interval time includes a first time threshold and a second time threshold, and the first time threshold is less than the second time threshold;

[0014] Based on the target interval time and the reference interval time between two consecutive executions of the same task, determine whether there are any interval time anomalies, including:

[0015] The number of anomalies is accumulated when the target interval is less than the first time threshold or greater than the second time threshold.

[0016] If the number of abnormal occurrences meets the preset conditions, an abnormal interval time is determined to exist.

[0017] In this way, the number of suspected abnormalities in the target interval time can be accumulated, and the task can be judged based on the number of abnormalities to determine whether there is indeed an abnormality in the interval time. This avoids misjudging occasional abnormalities as abnormal interval times, and further improves the accuracy and reliability of task detection.

[0018] In some embodiments, determining that an interval time anomaly exists when the number of anomalies meets a preset condition includes:

[0019] If the number of consecutive anomalies reaches a preset threshold, an anomaly in the interval time is determined.

[0020] In this way, an anomaly in the interval time is only confirmed when multiple consecutive anomalies occur, further improving the accuracy and reliability of task detection.

[0021] In some embodiments, before determining whether there is an interval time anomaly based on the target interval time and the reference interval time between two consecutive executions of the same task, the method further includes:

[0022] Obtain multiple time intervals between two consecutive executions of the first task within a historical period during normal operation, where the first task is any task in the battery management task.

[0023] Determine the mean interval time and the standard deviation of the interval time based on multiple interval time data;

[0024] The reference interval for performing the first task twice consecutively is determined based on the average interval time and the standard deviation of the interval time.

[0025] In this way, the average interval and standard deviation of the interval can be calculated based on multiple interval data of two consecutive executions of the same task within a historical period under normal operating conditions. Then, the reference interval corresponding to the task can be calculated, which improves the accuracy of the reference interval and thus improves the accuracy of judging the interval anomaly.

[0026] In some embodiments, obtaining the target execution time of a task during the execution of a battery management task, and the target interval between two consecutive executions of the same task, includes:

[0027] Obtain target operating condition parameters during the execution of battery management tasks;

[0028] The target operating condition parameters are input into a pre-trained prediction model to predict the target execution time of the task and the target interval between two consecutive executions of the same task. The prediction model is trained based on multiple samples, each of which includes a corresponding operating condition parameter sample, a task execution time label, and an interval time label between two consecutive executions of the same task.

[0029] In this way, based on the target operating condition parameters and prediction models during the execution of battery management tasks, the target execution time of the task and the target interval between two consecutive executions of the same task can be predicted in advance. This allows for early detection of time anomalies and early warning when a time anomaly trend appears, giving the battery management system more time to take adjustment and intervention measures to prevent the task anomaly from worsening, thereby further improving the stability and reliability of the battery management system.

[0030] In some embodiments, obtaining target operating condition parameters during the execution of a battery management task includes:

[0031] Acquire at least one type of initial operating condition parameter during the execution of the battery management task. The types of initial operating condition parameters include the system load index of the battery management system, the environmental parameters of the battery management system, and the battery status parameters.

[0032] Determine the preset target operating parameters from the initial operating parameters; wherein, the target operating parameters cover all types of the initial operating parameters.

[0033] In this embodiment, target operating parameters that are strongly correlated with task execution time and interval time can be selected from at least one type of initial operating parameters to serve as the basis for predicting execution time and interval time, thereby improving the accuracy and reliability of prediction and laying the foundation for the accuracy of task detection.

[0034] In some embodiments, the prediction model is trained using the following methods:

[0035] Acquire raw data, which includes operating parameters and time information under multiple preset battery management task execution scenarios.

[0036] The raw data is preprocessed to obtain sample data, which includes multiple training samples. Each training sample includes a corresponding working condition parameter sample, a task execution time label, and an interval time label between two consecutive executions of the same task.

[0037] The initial model is trained using multiple training samples to obtain the prediction model.

[0038] In this way, a prediction model can be trained based on multiple training samples, including corresponding working condition parameter samples, task execution time labels, and time labels of the interval between two consecutive executions of the same task. This allows the prediction model to predict the target execution time of the task and the target interval between two consecutive executions of the same task in advance, laying the foundation for early detection of time anomalies and early warning.

[0039] In some embodiments, the sample data further includes multiple test samples; the initial model is trained using multiple training samples to obtain a prediction model, including:

[0040] The initial model is trained using multiple training samples to obtain the first model;

[0041] The first model is evaluated using multiple test samples to obtain the evaluation index corresponding to the first model. The evaluation index includes at least one of mean squared error, mean absolute error, accuracy and recall.

[0042] If the evaluation index corresponding to the first model meets the preset convergence condition, the first model is determined to be the prediction model.

[0043] If the evaluation index corresponding to the first model does not meet the preset convergence condition, the first model is optimized to obtain the prediction model.

[0044] This allows for model optimization of the prediction model, improving its accuracy and thus enhancing the accuracy of target execution time and target interval time, ultimately improving the accuracy and reliability of task detection.

[0045] In some embodiments, after evaluating the first model using multiple test samples to obtain the evaluation index corresponding to the first model, the method further includes:

[0046] If the evaluation metric corresponding to the first model does not meet the preset convergence condition, multiple sub-prediction models are obtained. These multiple sub-prediction models are obtained by training multiple initial models of different model types using multiple training samples.

[0047] In this way, if model optimization still cannot meet the accuracy requirements of the prediction model, multiple sub-prediction models can be trained using different types of initial models. Subsequently, the prediction values ​​of multiple sub-prediction models can be comprehensively considered to announce the accuracy of the target execution time and target interval time.

[0048] In some embodiments, the target operating condition parameters are input into a pre-trained prediction model to predict the target execution time of the task and the target interval between two consecutive executions of the same task, including:

[0049] The target operating condition parameters are input into multiple sub-prediction models to obtain the prediction value corresponding to each sub-prediction model. The prediction value includes the execution time of the task predicted by the sub-prediction model and the interval between two consecutive executions of the same task.

[0050] Based on the predicted values ​​of multiple sub-prediction models and the preset weight values ​​of multiple sub-prediction models, the target execution time of the task and the target interval time for executing the same task twice consecutively are determined.

[0051] In this way, the prediction results of multiple sub-prediction models can be combined to obtain more accurate target execution time and target interval time, thereby improving the accuracy and reliability of task detection.

[0052] In some embodiments, obtaining the target execution time of a task during the execution of a battery management task, and the target interval between two consecutive executions of the same task, includes:

[0053] During the execution of battery management tasks, a general-purpose timer is used to record the target execution time of the task and the target interval between two consecutive executions of the same task.

[0054] In this way, a more precise general-purpose timer can be used to record the target execution time of the task and the target interval between two consecutive executions of the same task. This allows for accurate acquisition of the target execution time and target interval, thereby improving the accuracy and reliability of task detection.

[0055] In some embodiments, after determining that a time anomaly exists during the execution of the battery management task in response to at least one of a timeout anomaly and an interval time anomaly, the method further includes:

[0056] Output a prompt message.

[0057] This allows for early warnings when time anomalies occur, enabling the battery management system to take timely adjustments and interventions to prevent further deterioration of the abnormal situation, thereby further improving the stability and reliability of the battery management system.

[0058] Secondly, embodiments of this application also provide a battery management system, the device comprising:

[0059] The information acquisition unit is used to acquire the target execution time of the task during the execution of the battery management task, as well as the target interval time between two consecutive executions of the same task. The target interval time is the difference between the start times of the two consecutive executions of the same task.

[0060] Processor, used for:

[0061] Determine whether there is a timeout anomaly based on the target execution time, and determine whether there is an interval time anomaly based on the target interval time;

[0062] In response to at least one of timeout exception and interval time exception, determine that a time exception exists during the execution of the battery management task.

[0063] In this way, by obtaining the target execution time of the battery management task during its execution process, as well as the target interval time between two consecutive executions of the same task, time anomalies can be detected more comprehensively from both the execution time and interval time dimensions. This allows for the timely detection of early signs of time anomalies, thereby improving the accuracy and reliability of task detection.

[0064] Thirdly, embodiments of this application provide an electronic device, the device including: a processor and a memory storing program instructions; the processor executes the program instructions to implement the method of the first aspect.

[0065] Fourthly, embodiments of this application provide a machine-readable storage medium storing program instructions, which, when executed by a processor, implement the method of the first aspect.

[0066] Fifthly, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform the method of the first aspect.

[0067] 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

[0068] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on the drawings without creative effort.

[0069] Figure 1 One of the flowcharts of the task detection method provided in the embodiments of this application;

[0070] Figure 2 A second schematic flowchart illustrating the task detection method provided in this application embodiment;

[0071] Figure 3 The third schematic flowchart of the task detection method provided in the embodiments of this application;

[0072] Figure 4 The fourth flowchart illustrating the task detection method provided in this application embodiment;

[0073] Figure 5 Fifth flowchart illustrating the task detection method provided in this application embodiment;

[0074] Figure 6 A flowchart illustrating the task detection method provided in this application embodiment is shown in Figure 6.

[0075] Figure 7 This is a schematic diagram of the battery management system provided in an embodiment of this application;

[0076] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0077] The accompanying drawings are not drawn to scale. Detailed Implementation

[0078] The embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The detailed description of the following embodiments and the accompanying drawings are used to illustrate the principles of this application by way of example, but should not be used to limit the scope of this application, that is, this application is not limited to the described embodiments.

[0079] In the description of this application, it should be noted that, unless otherwise stated, "a plurality of" means two or more; the terms "upper," "lower," "left," "right," "inner," and "outer," etc., indicating orientation or positional relationships, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on this application. Furthermore, the terms "first," "second," and "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. "Vertical" is not vertical in the strict sense, but within the allowable tolerance range. "Parallel" is not parallel in the strict sense, but within the allowable tolerance range.

[0080] In this application, the reference to "embodiment" means that a specific 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 mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application can be combined with other embodiments.

[0081] Unless otherwise specified, all embodiments and optional embodiments of this application can be combined to form new technical solutions.

[0082] Unless otherwise specified, all technical features and optional technical features of this application may be combined to form new technical solutions.

[0083] Unless otherwise specified, all steps of this application may be performed sequentially or randomly, preferably sequentially. For example, the method includes steps (a) and (b), indicating that the method may include steps (a) and (b) performed sequentially, or it may include steps (b) and (a) performed sequentially. For example, the mention that the method may also include step (c) indicates that step (c) may be added to the method in any order; for example, the method may include steps (a), (b), and (c), or it may include steps (a), (c), and (b), or it may include steps (c), (a), and (b), etc.

[0084] The Battery Management System (BMS) 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 BMS of this application can also implement 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.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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, CDN (Content Delivery Network), and big data and artificial intelligence platforms, such as vehicle networking cloud, APP backend, etc.

[0089] This application provides a task detection method, system, storage medium, and product for a battery management system to solve the aforementioned technical problems. The task detection method provided in this application is described first below.

[0090] Please refer to Figure 1 This application provides a task detection method, which may include:

[0091] Step 101: Obtain the target execution time of the battery management task during the execution process, and the target interval time between two consecutive executions of the same task. The target interval time is the difference between the start times of the two consecutive executions of the same task.

[0092] In step 101, the battery management tasks may include battery status monitoring tasks, power estimation tasks, and equalization control tasks.

[0093] It can obtain the target execution time of any task during the execution of battery management tasks. For example, it can obtain the target execution time of battery status monitoring task, battery power estimation task, and balance control task respectively.

[0094] It can also obtain the target interval between two consecutive executions of the same task during battery management task execution. For example, it can obtain the target interval between the execution of the first equalization control task and the execution of the second equalization control task.

[0095] The target execution time and target interval can be obtained by collecting the start and end times of each task and calculating them accordingly. Alternatively, they can be predicted by acquiring operating parameters during the battery management task execution. A combination of both methods is also possible: predicting the target execution time and target interval while simultaneously acquiring them in real-time using a timer. No specific limitations are specified here.

[0096] In some embodiments, obtaining the target execution time of a task during the execution of a battery management task, and the target interval between two consecutive executions of the same task, may include:

[0097] During the execution of battery management tasks, a general-purpose timer is used to record the target execution time of the task and the target interval between two consecutive executions of the same task.

[0098] It is understandable that when collecting the start and end times of task execution in real time, there may be situations such as inaccurate timestamp acquisition, insufficient timer precision, and excessive system load or resource contention that may prevent the time monitoring program from obtaining accurate time information in a timely manner. In such cases, the target execution time or target interval time may not be obtained or may be obtained incorrectly.

[0099] Therefore, in this embodiment, a general purpose timer (GPT) can be used to measure the target execution time for each task and the target interval between two consecutive executions of the same task.

[0100] In this way, a more precise general-purpose timer can be used to record the target execution time of the task and the target interval between two consecutive executions of the same task. This allows for accurate acquisition of the target execution time and target interval, thereby improving the accuracy and reliability of task detection.

[0101] Step 102: Determine whether there is a timeout exception based on the target execution time, and determine whether there is an interval time exception based on the target interval time.

[0102] In step 102, it can be determined whether there is a time anomaly during the execution of the battery management task based on the target execution time and the target interval time. On one hand, it can be determined whether the target execution time is within the specified time. For example, each task has a maximum allowed duration. If the target execution time exceeds the maximum allowed duration, the task times out, and in this case, it can be considered that there is a timeout anomaly during the execution of the battery management task.

[0103] On the other hand, it can be used to determine whether the target interval is reasonable. For example, the interval for each task should be close to the reference interval. If the target interval differs from the reference interval, the interval is unreasonable, and it can be considered that there is an interval anomaly during the execution of the battery management task.

[0104] Step 103: In response to at least one of timeout exception and interval time exception, determine that there is a time exception during the execution of the battery management task.

[0105] In step 103, if there is a timeout exception, an interval time exception, or both a timeout exception and an interval time exception, it can be determined that there is a time exception during the execution of the battery management task, which may cause problems in the execution of the task and thus cause the battery management system to freeze or even crash, affecting the stability and reliability of the battery management system.

[0106] In this way, by obtaining the target execution time of the battery management task during its execution process, as well as the target interval time between two consecutive executions of the same task, time anomalies can be detected more comprehensively from both the execution time and interval time dimensions. This allows for the timely detection of early signs of time anomalies, thereby improving the accuracy and reliability of task detection.

[0107] In some embodiments, such as Figure 2 As shown, determining whether there is a timeout exception based on the target execution time, and determining whether there is an interval time exception based on the target interval time, can include:

[0108] Step 201: Determine whether there is a timeout exception based on the target execution time and the maximum allowed duration corresponding to the task;

[0109] Step 202: Determine whether there is an interval time anomaly based on the target interval time and the reference interval time for two consecutive executions of the same task.

[0110] In this embodiment, if the target execution time is greater than the maximum allowed duration for the task, a timeout exception can be determined. If the target execution time is less than or equal to the maximum allowed duration for the task, no timeout exception can be determined.

[0111] The reference interval between two consecutive executions of the same task can be a range of time. If the target interval falls within this range, it can be determined that there is no interval anomaly. If the target interval does not fall within this range, it can be determined that there is an interval anomaly.

[0112] The reference interval can be a value preset based on experience and taking into account actual conditions. Alternatively, the reference interval can be a value determined based on historical data.

[0113] In some embodiments, such as Figure 3 As shown, before determining whether there is an interval time anomaly based on the target interval time and the reference interval time between two consecutive executions of the same task, the method may further include:

[0114] Step 301: Obtain multiple time intervals between two consecutive executions of the first task within a historical time period during normal operation. The first task is any task in the battery management task.

[0115] Step 302: Determine the average interval time and the standard deviation of the interval time based on multiple interval time data;

[0116] Step 303: Determine the reference interval for two consecutive executions of the first task based on the average interval time and the standard deviation of the interval time.

[0117] In this embodiment, taking the balance control task as an example, multiple interval time data of two consecutive executions of the balance control task can be collected within a historical time period under normal operating conditions. For example, the interval time between each execution of the balance control task within the past month can be collected.

[0118] Statistical analysis can be performed on multiple interval time data to calculate the average interval time and the standard deviation of the interval time. Then, a reference interval time can be determined based on the average interval time and the standard deviation of the interval time. For example, considering the characteristics of the battery management system and the actual application scenario, a reasonable reference interval time can be determined by adding or subtracting a certain multiple of the standard deviation of the interval time from the average interval time as the boundary of the reference interval time. For instance, the reference interval time could be [T_avg-2T_std, T_avg+2T_std], where T_avg is the average interval time and T_std is the standard deviation of the interval time.

[0119] In this way, the average interval and standard deviation of the interval can be calculated based on multiple interval data of two consecutive executions of the same task within a historical period under normal operating conditions. Then, the reference interval corresponding to the task can be calculated, which improves the accuracy of the reference interval and thus improves the accuracy of judging the interval anomaly.

[0120] In this way, timeout anomalies can be determined based on the target execution time and the maximum allowable duration corresponding to the task, while interval time anomalies can be determined based on the target interval time and the reference interval time between two consecutive executions of the same task. This allows for the detection of time anomalies from two dimensions: timeout anomalies and interval time anomalies, so as to detect the early signs of time anomalies in a timely manner and improve the accuracy and reliability of task detection.

[0121] In some embodiments, such as Figure 4 As shown, the reference interval time includes a first time threshold and a second time threshold, and the first time threshold is less than the second time threshold;

[0122] Based on the target interval time and the reference interval time between two consecutive executions of the same task, determine whether there is an interval time anomaly, which may include:

[0123] Step 401: If the target interval is less than the first time threshold or greater than the second time threshold, accumulate the number of anomalies.

[0124] Step 402: If the number of abnormalities meets the preset conditions, it is determined that there is an abnormal interval time.

[0125] In this embodiment, the reference interval may include a first time threshold and a second time threshold, wherein the first time threshold is less than the second time threshold. For example, the first time threshold may be T_avg-2T_std, and the second time threshold may be T_avg+2T_std.

[0126] If the target interval time is less than the first time threshold or greater than the second time threshold, it can be considered that the target interval time is not within the range of the reference interval time. In this case, it can be considered that there may be an interval time abnormality in the battery management system during the execution of the battery management task.

[0127] It is understandable that a single abnormal interval may be caused by accidental factors and may not necessarily indicate a problem. Therefore, we can simply accumulate the number of abnormalities and temporarily not classify them as abnormal intervals.

[0128] An interval time anomaly can be determined if the number of anomalies meets preset conditions. For example, if the cumulative number of anomalies is greater than or equal to a certain threshold, an interval time anomaly can be determined.

[0129] In this way, the number of suspected abnormalities in the target interval time can be accumulated, and the task can be judged based on the number of abnormalities to determine whether there is indeed an abnormality in the interval time. This avoids misjudging occasional abnormalities as abnormal interval times, and further improves the accuracy and reliability of task detection.

[0130] In some embodiments, determining that an interval time anomaly exists when the number of anomalies meets a preset condition may include:

[0131] If the number of consecutive anomalies reaches a preset threshold, an anomaly in the interval time is determined.

[0132] In this embodiment, an interval time anomaly is determined only when a series of suspected anomalies occur and the number of consecutive anomalies reaches a preset threshold. For example, if three consecutive target interval times are all less than a first time threshold or greater than a second time threshold, then an interval time anomaly can be determined.

[0133] In this way, an anomaly in the interval time is only confirmed when multiple consecutive anomalies occur, further improving the accuracy and reliability of task detection.

[0134] In some embodiments, such as Figure 5 As shown, obtaining the target execution time of a battery management task and the target interval between two consecutive executions of the same task can include:

[0135] Step 501: Obtain the target operating condition parameters during the execution of the battery management task;

[0136] Step 502: Input the target operating condition parameters into the pre-trained prediction model to predict the target execution time of the task and the target interval time between two consecutive executions of the same task; wherein, the prediction model is trained based on multiple samples, each sample including the corresponding operating condition parameter sample, the task execution time label and the interval time label between two consecutive executions of the same task.

[0137] In this embodiment, target operating condition parameters can be obtained during the execution of the battery management task. These target operating condition parameters may include system load indicators such as CPU utilization, memory usage, and bus communication load; environmental parameters such as electromagnetic interference intensity, temperature change, and humidity change; and one or more of battery status parameters such as battery voltage, current, temperature, remaining charge, and number of charge / discharge cycles.

[0138] For example, target operating condition parameters may include CPU utilization and battery voltage. Target operating condition parameters may also include CPU utilization, battery voltage and temperature changes. Target operating condition parameters may also include memory usage and battery voltage, etc. The specific settings can be combined with the actual scenario, and no specific limitations are made here.

[0139] A prediction model can be pre-trained using multiple samples. Each sample can include a corresponding set of operating parameters, a task execution time label, and a time interval label between two consecutive executions of the same task. It is understood that the operating parameter samples can correspond to the aforementioned target operating parameters.

[0140] The target operating condition parameters can be input into the prediction model to predict the target execution time of the task and the target interval between two consecutive executions of the same task.

[0141] In this way, based on the target operating condition parameters and prediction models during the execution of battery management tasks, the target execution time of the task and the target interval between two consecutive executions of the same task can be predicted in advance. This allows for early detection of time anomalies and early warning when a time anomaly trend appears, giving the battery management system more time to take adjustment and intervention measures to prevent the task anomaly from worsening, thereby further improving the stability and reliability of the battery management system.

[0142] In some embodiments, obtaining target operating condition parameters during the execution of a battery management task may include:

[0143] Acquire at least one type of initial operating condition parameter during the execution of the battery management task. The types of initial operating condition parameters include the system load index of the battery management system, the environmental parameters of the battery management system, and the battery status parameters.

[0144] Determine the preset target operating parameters from the initial operating parameters; wherein, the target operating parameters cover all types of the initial operating parameters.

[0145] In this embodiment, at least one type of initial operating condition parameter can be obtained during the execution of the battery management task. The type of initial operating condition parameter may include the system load index of the battery management system, the environmental parameters of the battery management system, and the battery status parameters.

[0146] Taking the initial operating condition parameters as an example, which include system load indicators and battery status parameters, the initial operating condition parameters can include CPU utilization, memory usage, bus communication load, battery voltage, battery current, battery temperature, remaining battery capacity, and battery charge / discharge cycles.

[0147] Preset target operating parameters, encompassing all types of initial operating parameters, can be determined from the initial operating parameters. It is understood that these preset target operating parameters can be strongly correlated with task execution.

[0148] For example, changes in battery voltage may affect task complexity, and CPU utilization can reflect system load. Therefore, CPU utilization and battery voltage can be determined as target operating condition parameters.

[0149] In some examples, predicting task execution time and interval time can also refer to predicting the execution time and interval time of a specific task within the battery management task. For instance, the balancing control task is directly related to the judgment of time anomalies, so it can be used as a criterion for judgment. The prediction model can be used to predict the execution time of the balancing control task, as well as the interval time between two consecutive executions of the balancing control task.

[0150] In this embodiment, target operating parameters that are strongly correlated with task execution time and interval time can be selected from at least one type of initial operating parameters to serve as the basis for predicting execution time and interval time, thereby improving the accuracy and reliability of prediction and laying the foundation for the accuracy of task detection.

[0151] In some embodiments, such as Figure 6 As shown, the prediction model is trained using the following method:

[0152] Step 601: Obtain raw data, which includes operating condition parameter information and time information under multiple preset battery management task execution scenarios;

[0153] Step 602: Preprocess the raw data to obtain sample data. The sample data includes multiple training samples. Each training sample includes a corresponding working condition parameter sample, a task execution time label, and an interval time label between two consecutive executions of the same task.

[0154] Step 603: Train the initial model using multiple training samples to obtain the prediction model.

[0155] In this embodiment, raw data can be acquired, including operating condition parameters and time information under multiple preset battery management task execution scenarios. For example, system load indicators of the battery management system, such as CPU utilization, memory usage, and bus communication load, can be collected, as these factors may affect the execution time of battery management tasks. Environmental parameters of the battery management system, such as electromagnetic interference intensity, temperature changes, and humidity changes, can also be collected, as these environmental parameters may interfere with the electronic components of the battery management system, thus affecting the execution time of battery management tasks. Battery state parameters, such as battery voltage, battery current, battery temperature, remaining battery capacity, and number of charge / discharge cycles, can also be collected, as changes in battery state may alter the complexity of battery management tasks, thereby affecting their execution time. Furthermore, the execution time and interval time corresponding to each task under different operating condition parameters can also be collected.

[0156] The raw data can be preprocessed to obtain sample data. For example, preprocessing may include data cleaning, data normalization, time series processing, etc.

[0157] For example, outliers and erroneous data can be removed from the original data. For instance, if battery voltage data at a certain point in time significantly exceeds a reasonable range, it can be identified as an outlier and processed. Methods such as mean substitution and interpolation can be used for correction, or the data point can be directly deleted. Data with different dimensions can also be standardized to the same scale. For example, physical quantities such as battery voltage and current, as well as CPU usage and memory occupancy, can be normalized to a range between 0 and 1, making them easier for the model to process. If the data is time series data, differencing and seasonal adjustments can be performed to eliminate trends, making it more stable and easier for the model to predict.

[0158] The processed data can then be used for feature selection. As mentioned above, battery voltage, CPU utilization, and the execution time and interval of the equalization control task can be used as the main features. That is, each training sample can include corresponding operating condition parameter samples (battery voltage samples and CPU utilization samples), task execution time labels (execution time labels of equalization control tasks), and interval time labels between two consecutive executions of the same task (interval time labels between two consecutive executions of equalization control tasks).

[0159] Several preset model types can be included, such as linear regression models, decision tree models, random forest models, support vector machine models, and deep learning models. Among them, linear regression models are suitable for predicting simple linear relationships. Decision tree models can handle non-linear relationships and are easy to interpret. Random forest models have high accuracy and robustness. Support vector machine models perform well on small sample sizes and high-dimensional data. Deep learning models are effective for predicting time series data.

[0160] The initial model can be selected based on actual needs; for example, a random forest model can be used. Multiple training samples are then used to train the initial model. For a random forest model, parameters such as the number of trees in the forest, the depth of the trees, and the selection method for splitting features can be adjusted to obtain a prediction model with better accuracy and generalization ability.

[0161] In some examples, the sample data may also include multiple validation samples. After the prediction model is trained, multiple validation samples can be used to monitor the performance of the prediction model and avoid overfitting.

[0162] In this way, a prediction model can be trained based on multiple training samples, including corresponding working condition parameter samples, task execution time labels, and time labels of the interval between two consecutive executions of the same task. This allows the prediction model to predict the target execution time of the task and the target interval between two consecutive executions of the same task in advance, laying the foundation for early detection of time anomalies and early warning.

[0163] In some embodiments, the sample data further includes multiple test samples; training the initial model using multiple training samples to obtain a prediction model may include:

[0164] The initial model is trained using multiple training samples to obtain the first model;

[0165] The first model was evaluated using multiple test samples to obtain the evaluation index corresponding to the first model;

[0166] If the evaluation index corresponding to the first model meets the preset convergence condition, the first model is determined to be the prediction model.

[0167] If the evaluation index corresponding to the first model does not meet the preset convergence condition, the first model is optimized to obtain the prediction model.

[0168] In this embodiment, after training the initial model with multiple training samples to obtain the first model, the first model can be evaluated with multiple test samples to obtain the evaluation index corresponding to the first model. For example, the operating condition parameter samples corresponding to multiple test samples can be input into the first model to obtain the execution time prediction value and interval time prediction value output by the first model. By comparing the execution time labels and execution time prediction values ​​corresponding to multiple test samples, and by comparing the interval time labels and interval time prediction values ​​corresponding to multiple test samples, the evaluation index corresponding to the first model is obtained.

[0169] The evaluation metrics can include at least one of the following: mean squared error, mean absolute error, precision, and recall. Appropriate evaluation metrics can be selected based on the specific prediction task. Lower mean squared error and mean absolute error indicate better predictive performance of the model. Simultaneously, precision and recall can be observed to evaluate the model's accuracy in identifying time anomalies.

[0170] If the evaluation index corresponding to the first model meets the preset convergence condition, then the first model can be considered to meet the prediction accuracy requirements, and the first model can be determined as the prediction model.

[0171] If the evaluation metric corresponding to the first model does not meet the preset convergence condition, then the first model can be considered as not meeting the prediction accuracy requirements, and optimization of the first model is necessary. Optimization methods may include adjusting model parameters, adding data features, replacing the initial model, or using ensemble learning methods.

[0172] For example, if the model's accuracy is found to be low, you can try adding new features, such as the number of battery charge / discharge cycles or the degree of battery aging. Alternatively, you can adjust the model's hyperparameters, such as increasing the number of trees in the random forest. If performance still cannot be improved, you can consider replacing the initial model with a new prediction model.

[0173] This allows for model optimization of the prediction model, improving its accuracy and thus enhancing the accuracy of target execution time and target interval time, ultimately improving the accuracy and reliability of task detection.

[0174] In some embodiments, after evaluating the first model using multiple test samples to obtain the evaluation index corresponding to the first model, the method may further include:

[0175] If the evaluation metric corresponding to the first model does not meet the preset convergence condition, multiple sub-prediction models are obtained. These multiple sub-prediction models are obtained by training multiple initial models of different model types using multiple training samples.

[0176] In this embodiment, model optimization can also involve training multiple sub-prediction models using initial models of different model types. The model training method is the same as described above and will not be repeated here.

[0177] A more accurate target execution time and target interval time can be determined based on the predicted values ​​corresponding to multiple sub-prediction models. For example, the execution time and interval time prediction values ​​with high similarity among multiple sub-prediction models can be used to determine the target execution time and target interval time.

[0178] In this way, if model optimization still cannot meet the accuracy requirements of the prediction model, multiple sub-prediction models can be trained using different types of initial models. Subsequently, the prediction values ​​of multiple sub-prediction models can be comprehensively considered to announce the accuracy of the target execution time and target interval time.

[0179] In some embodiments, the target operating condition parameters are input into a pre-trained prediction model to predict the target execution time of the task and the target interval between two consecutive executions of the same task, including:

[0180] The target operating condition parameters are input into multiple sub-prediction models to obtain the prediction value corresponding to each sub-prediction model. The prediction value includes the execution time of the task predicted by the sub-prediction model and the interval between two consecutive executions of the same task.

[0181] Based on the predicted values ​​of multiple sub-prediction models and the preset weight values ​​of multiple sub-prediction models, the target execution time of the task and the target interval time for executing the same task twice consecutively are determined.

[0182] In this embodiment, the target operating condition parameters can be input into multiple sub-prediction models to obtain the prediction value corresponding to each sub-prediction model. The prediction value may include the execution time of the task predicted by the sub-prediction model, and the interval between two consecutive executions of the same task. For example, sub-prediction model A corresponds to the predicted execution time A and the predicted interval time A; sub-prediction model B corresponds to the predicted execution time B and the predicted interval time B; and sub-prediction model C corresponds to the predicted execution time C and the predicted interval time C.

[0183] The target execution time of a task and the target interval between two consecutive executions of the same task can be determined based on the predicted values ​​of multiple sub-prediction models and the preset weight values ​​of multiple sub-prediction models.

[0184] For example, the target execution time = predicted execution time A*a + predicted execution time B*b + predicted execution time C*c. The target interval time = predicted interval time A*a + predicted interval time B*b + predicted interval time C*c. Where a is the weight value corresponding to sub-prediction model A, b is the weight value corresponding to sub-prediction model B, and c is the weight value corresponding to sub-prediction model C.

[0185] In some examples, the preset weight values ​​corresponding to multiple sub-prediction models can be pre-set based on empirical values, or the preset weight values ​​corresponding to multiple sub-prediction models can be determined based on the accuracy of each sub-prediction model.

[0186] In this way, if model optimization still cannot meet the accuracy requirements of the prediction model, multiple sub-prediction models can be trained using different types of initial models. The prediction results of multiple sub-prediction models can be combined to obtain a more accurate target execution time and target interval time, thereby improving the accuracy and reliability of task detection.

[0187] In some examples, multiple initial models of different types that meet the requirements can be selected and trained directly at the beginning of the prediction model training to obtain multiple prediction sub-models. In other words, the prediction model can include multiple sub-prediction models, which are obtained by training multiple initial models of different model types using multiple training samples. The target operating condition parameters are then input into the multiple sub-prediction models to obtain the prediction value corresponding to each sub-prediction model. The prediction value includes the execution time of the task predicted by the sub-prediction model, as well as the interval between two consecutive executions of the same task. In order to determine the target execution time of the task and the target interval between two consecutive executions of the same task based on the prediction values ​​of the multiple sub-prediction models and the preset weight values ​​of the multiple sub-prediction models.

[0188] In some embodiments, after determining that a time anomaly exists during the execution of the battery management task in response to at least one of a timeout anomaly and an interval time anomaly, the method may further include:

[0189] Output a prompt message.

[0190] In this embodiment, if a time anomaly occurs during the execution of a battery management task, a prompt message can be output so that the battery management system can be managed and intervened in a timely manner based on the prompt message. For example, task reset or task balancing adjustment can be used to eliminate the problem of task time anomaly, so as to ensure the stability and reliability of the battery management system.

[0191] In some examples, predictive models can be used to anticipate potential time-related anomalies. Then, hook functions can be used to customize the sending method and receiving recipients of alert signals according to specific needs. The hook mechanism enables alert signals to be quickly delivered to the appropriate processing modules, improving the system's response speed.

[0192] This allows for early warnings when time anomalies occur, enabling the battery management system to take timely adjustments and interventions to prevent further deterioration of the abnormal situation, thereby further improving the stability and reliability of the battery management system.

[0193] Based on the task detection method provided in the above embodiments, this application can also provide a corresponding embodiment of a battery management system.

[0194] like Figure 7As shown, the battery management system 900 may include:

[0195] The information acquisition unit 901 is used to acquire the target execution time of the task during the execution of the battery management task, as well as the target interval time between two consecutive executions of the same task.

[0196] Processor 902, used for:

[0197] Determine whether there is a timeout anomaly based on the target execution time, and determine whether there is an interval time anomaly based on the target interval time;

[0198] In response to at least one of timeout exception and interval time exception, determine that a time exception exists during the execution of the battery management task.

[0199] In this way, by obtaining the target execution time of the battery management task during its execution process, as well as the target interval time between two consecutive executions of the same task, time anomalies can be detected more comprehensively from both the execution time and interval time dimensions. This allows for the timely detection of early signs of time anomalies, thereby improving the accuracy and reliability of task detection.

[0200] In some embodiments, the processor 902 can also be used for:

[0201] Based on the target execution time and the maximum allowed duration corresponding to the task, determine whether there is a timeout exception;

[0202] Based on the target interval time and the reference interval time for two consecutive executions of the same task, determine whether there is an interval time anomaly.

[0203] In this way, timeout anomalies can be determined based on the target execution time and the maximum allowable duration corresponding to the task, while interval time anomalies can be determined based on the target interval time and the reference interval time between two consecutive executions of the same task. This allows for the detection of time anomalies from two dimensions: timeout anomalies and interval time anomalies, so as to detect the early signs of time anomalies in a timely manner and improve the accuracy and reliability of task detection.

[0204] In some embodiments, the reference interval time includes a first time threshold and a second time threshold, and the first time threshold is less than the second time threshold;

[0205] The processor 902 can also be used for:

[0206] The number of anomalies is accumulated when the target interval is less than the first time threshold or greater than the second time threshold.

[0207] If the number of abnormal occurrences meets the preset conditions, an abnormal interval time is determined to exist.

[0208] In this way, the number of suspected abnormalities in the target interval time can be accumulated, and the task can be judged based on the number of abnormalities to determine whether there is indeed an abnormality in the interval time. This avoids misjudging occasional abnormalities as abnormal interval times, and further improves the accuracy and reliability of task detection.

[0209] In some embodiments, the processor 902 can also be used for:

[0210] If the number of consecutive anomalies reaches a preset threshold, an anomaly in the interval time is determined.

[0211] In this way, an anomaly in the interval time is only confirmed when multiple consecutive anomalies occur, further improving the accuracy and reliability of task detection.

[0212] In some embodiments, the information acquisition unit 901 can also be used for:

[0213] Obtain multiple time intervals between two consecutive executions of the first task within a historical period during normal operation, where the first task is any task in the battery management task.

[0214] The processor 902 can also be used for:

[0215] Determine the mean interval time and the standard deviation of the interval time based on multiple interval time data;

[0216] The reference interval for performing the first task twice consecutively is determined based on the average interval time and the standard deviation of the interval time.

[0217] In this way, the average interval and standard deviation of the interval can be calculated based on multiple interval data of two consecutive executions of the same task within a historical period under normal operating conditions. Then, the reference interval corresponding to the task can be calculated, which improves the accuracy of the reference interval and thus improves the accuracy of judging the interval anomaly.

[0218] In some embodiments, the information acquisition unit 901 can also be used for:

[0219] Obtain target operating condition parameters during the execution of battery management tasks;

[0220] The target operating condition parameters are input into a pre-trained prediction model to predict the target execution time of the task and the target interval between two consecutive executions of the same task. The prediction model is trained based on multiple samples, each of which includes a corresponding operating condition parameter sample, a task execution time label, and an interval time label between two consecutive executions of the same task.

[0221] In this way, based on the target operating condition parameters and prediction models during the execution of battery management tasks, the target execution time of the task and the target interval between two consecutive executions of the same task can be predicted in advance. This allows for early detection of time anomalies and early warning when a time anomaly trend appears, giving the battery management system more time to take adjustment and intervention measures to prevent the task anomaly from worsening, thereby further improving the stability and reliability of the battery management system.

[0222] In some embodiments, the information acquisition unit 901 can also be used for:

[0223] Acquire at least one type of initial operating condition parameter during the execution of the battery management task. The types of initial operating condition parameters include the system load index of the battery management system, the environmental parameters of the battery management system, and the battery status parameters.

[0224] Determine the preset target operating parameters from the initial operating parameters; wherein, the target operating parameters cover all types of the initial operating parameters.

[0225] In this embodiment, target operating parameters that are strongly correlated with task execution time and interval time can be selected from at least one type of initial operating parameters to serve as the basis for predicting execution time and interval time, thereby improving the accuracy and reliability of prediction and laying the foundation for the accuracy of task detection.

[0226] In some embodiments, the information acquisition unit 901 can also be used for:

[0227] Acquire raw data, which includes operating parameters and time information under multiple preset battery management task execution scenarios.

[0228] The processor 902 can also be used for:

[0229] The raw data is preprocessed to obtain sample data, which includes multiple training samples. Each training sample includes a corresponding working condition parameter sample, a task execution time label, and an interval time label between two consecutive executions of the same task.

[0230] The initial model is trained using multiple training samples to obtain the prediction model.

[0231] In this way, a prediction model can be trained based on multiple training samples, including corresponding working condition parameter samples, task execution time labels, and time labels of the interval between two consecutive executions of the same task. This allows the prediction model to predict the target execution time of the task and the target interval between two consecutive executions of the same task in advance, laying the foundation for early detection of time anomalies and early warning.

[0232] In some embodiments, the sample data further includes multiple test samples; the processor 902 can also be used for:

[0233] The initial model is trained using multiple training samples to obtain the first model;

[0234] The first model was evaluated using multiple test samples to obtain the evaluation index corresponding to the first model;

[0235] If the evaluation index corresponding to the first model meets the preset convergence condition, the first model is determined to be the prediction model.

[0236] If the evaluation index corresponding to the first model does not meet the preset convergence condition, the first model is optimized to obtain the prediction model.

[0237] This allows for model optimization of the prediction model, improving its accuracy and thus enhancing the accuracy of target execution time and target interval time, ultimately improving the accuracy and reliability of task detection.

[0238] In some embodiments, the processor 902 can also be used for:

[0239] If the evaluation metric corresponding to the first model does not meet the preset convergence condition, multiple sub-prediction models are obtained. These multiple sub-prediction models are obtained by training multiple initial models of different model types using multiple training samples.

[0240] In this way, if model optimization still cannot meet the accuracy requirements of the prediction model, multiple sub-prediction models can be trained using different types of initial models. Subsequently, the prediction values ​​of multiple sub-prediction models can be comprehensively considered to announce the accuracy of the target execution time and target interval time.

[0241] In some embodiments, the processor 902 can also be used for:

[0242] The target operating condition parameters are input into multiple sub-prediction models to obtain the prediction value corresponding to each sub-prediction model. The prediction value includes the execution time of the task predicted by the sub-prediction model and the interval between two consecutive executions of the same task.

[0243] Based on the predicted values ​​of multiple sub-prediction models and the preset weight values ​​of multiple sub-prediction models, the target execution time of the task and the target interval time for executing the same task twice consecutively are determined.

[0244] In this way, if model optimization still cannot meet the accuracy requirements of the prediction model, multiple sub-prediction models can be trained using different types of initial models. The prediction results of multiple sub-prediction models can be combined to obtain a more accurate target execution time and target interval time, thereby improving the accuracy and reliability of task detection.

[0245] In some embodiments, the information acquisition unit 901 can also be used for:

[0246] During the execution of battery management tasks, a general-purpose timer is used to record the target execution time of the task and the target interval between two consecutive executions of the same task.

[0247] In this way, a more precise general-purpose timer can be used to record the target execution time of the task and the target interval between two consecutive executions of the same task. This allows for accurate acquisition of the target execution time and target interval, thereby improving the accuracy and reliability of task detection.

[0248] In some embodiments, the processor 902 can also be used for:

[0249] Output a prompt message.

[0250] This allows for early warnings when time anomalies occur, enabling the battery management system to take timely adjustments and interventions to prevent further deterioration of the abnormal situation, thereby further improving the stability and reliability of the battery management system.

[0251] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. They are devices corresponding to the detection method of the above-mentioned battery cell baking equipment. All implementation methods in the above-mentioned method embodiments are applicable to the embodiments of this device. For details on its specific functions and the technical effects it brings, please refer to the method embodiment section. It will not be repeated here.

[0252] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0253] Reference Figure 8 The electronic device 1000 may include a processor 1001 and a memory 1002 storing programs or instructions. When the processor 1001 executes the program, it implements the steps in any of the above method embodiments.

[0254] For example, the program can be divided into one or more modules / units, one or more of which are stored in memory 1002 and executed by processor 1001 to complete this application. The one or more modules / units can be a series of program instruction segments capable of performing a specific function, which describe the execution process of the program in the device.

[0255] Specifically, the processor 1001 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0256] Memory 1002 may include mass storage for data or instructions. For example, and not limitingly, memory 1002 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 1002 may include removable or non-removable (or fixed) media. Where appropriate, memory 1002 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 1002 is non-volatile solid-state memory.

[0257] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to one aspect of this disclosure.

[0258] The processor 1001 implements any of the methods described above by reading and executing programs or instructions stored in the memory 1002.

[0259] In one example, the electronic device may also include a communication interface 1003 and a bus 1004. The processor 1001, memory 1002, and communication interface 1003 are connected via the bus 1004 and communicate with each other.

[0260] The communication interface 1003 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0261] Bus 1004 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 1004 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0262] Furthermore, in conjunction with the methods in the above embodiments, this application embodiment can provide a machine-readable storage medium for implementation. This machine-readable storage medium stores a program or instructions; when executed by a processor, the program or instructions implement any of the methods in the above embodiments. This machine-readable storage medium can be read by a machine such as a computer.

[0263] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0264] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0265] This application provides a computer program product stored in a machine-readable storage medium. The program product is executed by at least one processor to implement the various processes of the above method embodiments and achieve the same technical effects. To avoid repetition, it will not be described again here.

[0266] 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.

[0267] The functional modules 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, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer grids such as the Internet, intranets, etc.

[0268] 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.

[0269] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by a computer program or instructions. These programs or instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce 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 flowchart illustrations 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 special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0270] 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 task detection method for a battery management system, characterized in that, The method includes: Obtain the target execution time of the battery management task during the execution process, and the target interval time between two consecutive executions of the same task. The target interval time is the difference between the start times of the two consecutive executions of the same task. Determine whether there is a timeout exception based on the target execution time, and determine whether there is an interval time exception based on the target interval time; In response to at least one of timeout exception and interval time exception, it is determined that a time exception exists during the execution of the battery management task.

2. The method according to claim 1, characterized in that, The steps of determining whether a timeout exception exists based on the target execution time and determining whether an interval time exception exists based on the target interval time include: Based on the target execution time and the maximum allowed duration corresponding to the task, determine whether there is a timeout exception; Based on the target interval time and the reference interval time for two consecutive executions of the same task, determine whether there is an interval time anomaly.

3. The method according to claim 2, characterized in that, The reference interval time includes a first time threshold and a second time threshold, and the first time threshold is less than the second time threshold; The step of determining whether there is an interval time anomaly based on the target interval time and the reference interval time for two consecutive executions of the same task includes: If the target interval is less than the first time threshold or greater than the second time threshold, the number of abnormalities is accumulated. If the number of abnormal occurrences meets a preset condition, an abnormal interval time is determined to exist.

4. The method according to claim 3, characterized in that, The step of determining that there is an interval time anomaly when the number of anomalies meets a preset condition includes: If the number of consecutive anomalies reaches a preset threshold, an anomaly in the interval time is determined.

5. The method according to any one of claims 2 to 4, characterized in that, Before determining whether there is an interval time anomaly based on the target interval time and the reference interval time between two consecutive executions of the same task, the method further includes: Obtain multiple interval time data of two consecutive executions of the first task within a historical time period under normal operating conditions, wherein the first task is any one of the battery management tasks; Based on the multiple interval time data, determine the average interval time and the standard deviation of the interval time; Based on the average interval time and the standard deviation of the interval time, a reference interval time for performing the first task twice consecutively is determined.

6. The method according to any one of claims 1-5, characterized in that, The acquisition of the target execution time of the battery management task and the target interval between two consecutive executions of the same task includes: Obtain target operating condition parameters during the execution of battery management tasks; The target operating condition parameters are input into a pre-trained prediction model to predict the target execution time of the task and the target interval between two consecutive executions of the same task. The prediction model is trained based on multiple samples, each of which includes a corresponding operating condition parameter sample, a task execution time label, and an interval time label between two consecutive executions of the same task.

7. The method according to claim 6, characterized in that, The acquisition of target operating condition parameters during the execution of the battery management task includes: Acquire at least one type of initial operating condition parameter during the execution of the battery management task. The types of the initial operating condition parameters include the system load index of the battery management system, the environmental parameters of the battery management system, and the battery status parameters. Determine preset target operating parameters from the initial operating parameters; wherein, the target operating parameters cover all types of the initial operating parameters.

8. The method according to claim 6, characterized in that, The prediction model was trained using the following method: Acquire raw data, which includes operating condition parameter information and time information under multiple preset battery management task execution scenarios; The raw data is preprocessed to obtain sample data, which includes multiple training samples. Each training sample includes a corresponding working condition parameter sample, a task execution time label, and an interval time label between two consecutive executions of the same task. The initial model is trained using the multiple training samples to obtain the prediction model.

9. The method according to claim 8, characterized in that, The sample data also includes multiple test samples; the step of training the initial model using the multiple training samples to obtain the prediction model includes: The initial model is trained using the multiple training samples to obtain the first model; The first model is evaluated using the multiple test samples to obtain the evaluation index corresponding to the first model; If the evaluation index corresponding to the first model meets the preset convergence condition, the first model is determined to be the prediction model; If the evaluation index corresponding to the first model does not meet the preset convergence condition, the first model is optimized to obtain the prediction model.

10. The method according to claim 9, characterized in that, After evaluating the first model using the multiple test samples to obtain the evaluation index corresponding to the first model, the method further includes: If the evaluation index corresponding to the first model does not meet the preset convergence condition, multiple sub-prediction models are obtained. The multiple sub-prediction models are obtained by training multiple initial models of different model types using the multiple training samples respectively.

11. The method according to claim 10, characterized in that, The step of inputting the target operating condition parameters into a pre-trained prediction model to predict the target execution time of the task and the target interval time between two consecutive executions of the same task includes: The target operating condition parameters are input into the multiple sub-prediction models respectively to obtain the prediction value corresponding to each sub-prediction model. The prediction value includes the execution time of the task predicted by the sub-prediction model and the interval between two consecutive executions of the same task. Based on the predicted values ​​corresponding to the multiple sub-prediction models and the preset weight values ​​corresponding to the multiple sub-prediction models, the target execution time of the task and the target interval time for executing the same task twice consecutively are determined.

12. The method according to any one of claims 1 to 5, characterized in that, The acquisition of the target execution time of the battery management task and the target interval between two consecutive executions of the same task includes: During the execution of battery management tasks, a general-purpose timer is used to record the target execution time of the task and the target interval between two consecutive executions of the same task.

13. The method according to any one of claims 1 to 12, characterized in that, After determining that a timeout exception exists during the execution of the battery management task in response to at least one of a timeout exception and an interval time exception, the method further includes: Output a prompt message.

14. A battery management system, characterized in that, The system includes: The information acquisition unit is used to acquire the target execution time of the task during the execution of the battery management task, and the target interval time between two consecutive executions of the same task. The target interval time is the difference between the start times of the two consecutive executions of the same task. Processor, used for: Determine whether there is a timeout exception based on the target execution time, and determine whether there is an interval time exception based on the target interval time; In response to at least one of timeout exception and interval time exception, it is determined that a time exception exists during the execution of the battery management task.

15. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores a program or instructions that, when executed by a processor, implement the method as described in any one of claims 1-13.

16. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device causes the electronic device to perform the method as described in any one of claims 1-13.

Images