Fault detection methods, systems, devices, and media

Abstract

The application provides a fault detection method, system, device and medium. The method comprises the following steps: determining fluctuation data of each type of detection data under each fault influence factor according to N types of detection data and M fault influence factors which affect the accuracy of the detection data and represent the state of the battery under the running state of the vehicle in a first time period; determining a comprehensive fault detection threshold of the battery under the M fault influence factors by means of the fluctuation data of each type of detection data under each fault influence factor; and detecting the detection data of the battery in a second time period by the fault detection threshold, so as to determine the fault detection information of the battery. The error and irrationality caused by manually setting the fault detection threshold for each detection data are effectively weakened, the accuracy of determining the fault detection threshold is improved, and the accuracy of the battery fault detection is improved.

Description

Technical Field

[0001] This application relates to the field of equipment fault detection technology, and in particular to a fault detection method, system, device and medium. Background Technology

[0002] With the rapid development of the new energy industry, new energy equipment relies on electricity as its power source, and batteries are one of the core components for storing and providing electrical energy. To ensure the normal operation of batteries and extend their service life, individual batteries or the entire battery pack of new energy equipment can be tested.

[0003] In related technologies, electrical signals such as battery voltage, resistance, and current can be detected, and the values ​​of these signals can be compared with fault detection thresholds to determine whether a battery is faulty. However, these fault detection thresholds are usually set manually, relying on human subjective judgment. Different people may set different thresholds, leading to inconsistent comparison results, misjudgments or omissions in battery fault detection, and reducing the accuracy of battery fault detection. Summary of the Invention

[0004] In view of the above problems, this application provides a fault detection method, apparatus, device, medium and program product that can solve the problem of low accuracy of battery fault detection caused by manually setting fault detection thresholds.

[0005] In a first aspect, embodiments of this application provide a fault detection method applied to a battery management system, the method comprising:

[0006] Obtain N types of detection data representing the battery state under vehicle operation conditions within the first time period, where N is a positive integer;

[0007] Based on the preset M fault influencing factors, the fluctuation data of each type of detection data is determined. The fluctuation data represents the degree of deviation of each detection value in each type of detection data from the preset center value, and M is an integer greater than 1.

[0008] Based on the fluctuation data of each type of detection data, the fault detection threshold of the battery is determined;

[0009] Based on the battery detection data and fault detection thresholds during the second time period, the battery fault detection information is determined.

[0010] In the above scheme, the threshold setting for battery fault detection can be optimized. Specifically, based on N types of detection data characterizing the battery state under vehicle operation during the first time period and M fault influencing factors affecting the accuracy of the detection data, the fluctuation data of each type of detection data under each fault influencing factor is determined. Using the fluctuation data of each type of detection data under each fault influencing factor, a comprehensive fault detection threshold for the battery under the M fault influencing factors is determined. This fault detection threshold can then be used to detect the battery's detection data during the second time period, thereby determining the battery's fault detection information. This effectively reduces the errors and irrationality caused by manually setting fault detection thresholds for each type of detection data, thus improving the accuracy of determining the fault detection threshold and consequently improving the accuracy of battery fault detection. This avoids safety accidents caused by misjudgments or omissions in battery fault detection due to manually setting fault detection thresholds.

[0011] In some embodiments, the step of "determining the fluctuation data of each type of detection data based on M preset fault influencing factors" may specifically include:

[0012] Given that M fault influencing factors may include at least one of the following: battery operating status, battery operating environment, and battery wear level, N types of detection data are divided according to each fault influencing factor to obtain at least one type of detection data under each fault influencing factor in the first time period.

[0013] Using statistical algorithms, at least one type of detection data under each fault influencing factor is statistically calculated to obtain the statistical value of each type of detection data under each fault influencing factor.

[0014] The statistical value of each type of detection data under each fault influencing factor is determined as the fluctuation data of each type of detection data.

[0015] In the above scheme, by analyzing the statistical values ​​of each type of detection data under multiple fault influencing factors, the complex interaction relationship affecting battery faults can be revealed, thereby improving the accuracy of the classification of operating data. Furthermore, the statistical values ​​of each type of detection data under each fault influencing factor can reflect the central tendency, dispersion, or distribution pattern of the detection data, which can be accurately used as the basis for overall inference of the fluctuation data of each type of detection data under each fault influencing factor, thus improving the accuracy of determining the fluctuation data of each type of detection data under each fault influencing factor.

[0016] In some embodiments, prior to the step described above of "using statistical algorithms to perform statistical calculations on at least one type of detection data under each fault influencing factor to obtain statistical values ​​for each type of detection data under each fault influencing factor," the fault detection method may further include:

[0017] Using the Kalman filter algorithm, at least one type of detection data under each fault influencing factor in the first time time is denoised to obtain at least one type of denoised detection data. The noise value in the at least one type of denoised detection data is within the preset Gaussian white noise range.

[0018] Based on this, the aforementioned steps involving "using statistical algorithms to perform statistical calculations on at least one type of detection data under each fault influencing factor to obtain the statistical value of each type of detection data under each fault influencing factor" can specifically include:

[0019] By using statistical algorithms, statistical calculations are performed on at least one type of denoised detection data to obtain the statistical values ​​of each type of detection data under each fault influencing factor.

[0020] In the above scheme, the Kalman filter algorithm can be used to remove noise introduced by sensor error and environmental interference from the detection data under the fault influencing factors, so that the detection data of each type of detection data under each fault influencing factor is closer to the real state, reducing error interference, avoiding the problem of missing or incorrect statistical values ​​of each type of detection data under the fault influencing factors due to noise, improving the reliability and consistency of statistical values, and improving the data quality and reliability of statistical values ​​of each type of detection data under the fault influencing factors.

[0021] In some embodiments, the step of "determining the battery fault detection threshold based on the fluctuation data of each type of detection data" mentioned above may specifically include:

[0022] When M is an integer greater than 1, based on the fluctuation data of each type of detection data, determine the fluctuation fault threshold of each type of detection data under each fault influencing factor;

[0023] The battery fault detection threshold is determined based on the fluctuating fault threshold under each of the M fault influencing factors.

[0024] In the above scheme, the fluctuating fault threshold of each type of detection data under each fault influencing factor can be determined first. Then, the fluctuating fault thresholds under multiple fault influencing factors are integrated to obtain the battery fault detection threshold. This allows for a detailed analysis of the accuracy of the fluctuating fault threshold under each fault influencing factor, and the summarization of the fluctuating fault thresholds under M fault influencing factors can improve the accuracy of determining the battery fault detection threshold.

[0025] In some embodiments, the step of "determining the fluctuating fault threshold for each type of detection data under each fault influencing factor based on the fluctuation data of each type of detection data" may specifically include:

[0026] Based on the weight of each fault influencing factor, the fluctuation data of each type of detection data under each fault influencing factor is weighted and calculated to obtain the fluctuation fault threshold of each type of detection data under each fault influencing factor.

[0027] In the above scheme, by setting a corresponding weight for each fault influencing factor, the characteristics of the detection data under different fault influencing factors can be accurately adapted, the accuracy of analyzing the fluctuating fault threshold of each type of detection data under each fault influencing factor can be improved, and thus the accuracy of determining the fluctuating fault threshold of each type of detection data under each fault influencing factor can be improved.

[0028] In some embodiments, the step of "determining the battery fault detection threshold based on the fluctuating fault threshold under each of the M fault influencing factors" may specifically include:

[0029] Based on each factor affecting the failure, obtain the weight of each factor affecting the failure;

[0030] Based on the weight of each fault influencing factor, the fluctuating fault threshold under each fault influencing factor is weighted and summed to obtain the battery fault detection threshold.

[0031] In the above scheme, by setting different weights for different fault influencing factors, the characteristics of the detection data under different fault influencing factors can be accurately adapted, the accuracy of analyzing the fluctuating fault threshold of each type of detection data under M fault influencing factors can be improved, and thus the accuracy of determining the fluctuating fault threshold of each type of detection data under M fault influencing factors can be improved.

[0032] In some embodiments, the step of "determining battery fault detection information based on battery detection data and fault detection thresholds within a second time period" may specifically include:

[0033] If the time in the second time period is later than the time in the first time period, and the fault detection information includes the first information used to characterize the battery fault, the detection value in the battery detection data in the second time period is matched with the fault detection threshold to obtain the matching result.

[0034] If the matching result indicates that the detected value is greater than the fault detection threshold, the first piece of information is determined.

[0035] In the above scheme, battery fault detection can be performed by setting accurate fault detection thresholds, avoiding safety accidents caused by misjudgment or omission of battery fault detection due to manually setting fault detection thresholds, and improving the accuracy of battery fault detection.

[0036] In some embodiments, the fault detection method may further include:

[0037] If the fault detection information includes first information characterizing the battery fault, the first information is sent to the host computer of the battery management system through the communication module of the battery management system to issue a fault alarm to the user.

[0038] The above solution can promptly alert users while ensuring the normal operation of the battery management system, enabling risk awareness, effectively guaranteeing the safety of the battery management system, and improving operational efficiency.

[0039] In some embodiments, the fault detection method may further include:

[0040] Obtain battery-based fault detection thresholds to determine the accuracy of battery fault detection information;

[0041] Based on the accuracy information, determine the false alarm rate or false negative rate of the battery management system for battery fault detection;

[0042] If the false alarm rate is greater than or equal to the first preset threshold, or the false alarm rate is greater than or equal to the second preset threshold, update the battery fault detection threshold.

[0043] In the above scheme, the battery management system can determine whether the battery has a fault based on the battery's fault detection threshold, and determine whether to optimize the battery's fault detection threshold to improve the accuracy of fault detection and judgment, so that it can accurately judge the occurrence of faults, while minimizing false positives and false negatives.

[0044] In some embodiments, the step of "updating the battery fault detection threshold" mentioned above may specifically include:

[0045] When the fault detection information includes first information to characterize the battery fault, the fault location is determined by the fault propagation model.

[0046] Based on the fault detection data associated with the fault location, determine the cause of the fault at the fault location;

[0047] Based on the cause of the fault, the fault detection threshold of the fault detection data is adjusted to obtain the adjusted fault detection threshold of the fault detection data;

[0048] Adjust the fault detection threshold based on the fault detection data, and update the battery's fault detection threshold.

[0049] In the above scheme, correlation analysis technology is used to explore the causal relationship between fault detection data associated with fault location. Combined with the fault propagation model, the source of the fault can be quickly located, thereby providing accurate detection data to be adjusted for the repair of the battery's fault detection threshold, and realizing efficient and accurate updating of the battery's fault detection threshold.

[0050] In some embodiments, the step of "determining the fault location through a fault propagation model" mentioned above may specifically include:

[0051] By using a fault propagation model, the fault source system component that is dependent on the fault can be identified based on the dependency relationship between at least two system components in the battery management system.

[0052] The location of the fault is determined based on the location of the fault-causing system components that are dependent on the fault.

[0053] In the above scheme, by constructing a fault propagation model, the propagation path of faults in the battery management system can be simulated, the source of faults can be quickly located, and accurate detection data to be adjusted can be provided for the repair of fault detection thresholds, so as to achieve efficient and accurate updating of battery fault detection thresholds.

[0054] In some embodiments, the step of "determining the cause of the fault at the fault location based on fault detection data associated with the fault location" may specifically include:

[0055] Based on the correlation analysis information between the reference fault detection data and the reference fault causes, the fault causes corresponding to the fault detection data are determined.

[0056] In the above scheme, by performing correlation analysis on the collected fault detection data and various fault causes, the causal relationship between fault detection data and fault causes can be found, and the specific causes and paths of fault occurrence can be clarified. This provides accurate detection data to be adjusted for the repair of fault detection thresholds, and achieves efficient and accurate updating of battery fault detection thresholds.

[0057] In some embodiments, the fault detection method may further include:

[0058] Acquire N types of detection data characterizing the battery state under vehicle operation conditions during the third time period;

[0059] Based on the N types of detection data characterizing the battery state under vehicle operation conditions during the third time period, the fault detection threshold of the battery during the third time period is determined.

[0060] If the battery fault detection threshold in the third time period is different from that in the first time period, the battery fault detection information is determined based on the battery detection data in the second time period and the fault detection threshold in the third time period; wherein the time of the third time period is later than the time of the first time period but earlier than the time of the second time period.

[0061] In the above scheme, by continuously collecting N types of battery detection data and updating the fault detection threshold in real time, the real-time nature of the fault detection threshold can be guaranteed, reducing the misjudgment and missed judgment of battery fault detection caused by the failure to update the fault detection threshold in a timely manner. This improves the accuracy of determining the fault detection threshold, thereby improving the accuracy of battery fault detection and avoiding safety accidents caused by misjudgment or missed judgment of battery fault detection due to manually setting the fault detection threshold.

[0062] Secondly, embodiments of this application provide a battery management system, including: an acquisition module, configured to acquire N types of detection data characterizing the battery state during a first time period while the battery is in a vehicle operating state, where N is a positive integer;

[0063] The determination module is used to determine the fluctuation data of each type of detection data based on M preset fault influencing factors. The fluctuation data represents the degree of deviation of each detection value in each type of detection data from the preset center value, and M is an integer greater than 1.

[0064] The determination module is also used to determine the battery fault detection threshold based on the fluctuation data of each type of detection data;

[0065] The determination module is also used to determine battery fault detection information based on battery detection data and fault detection thresholds within the second time period.

[0066] In the above solution, the battery fault detection threshold setting can be optimized through the battery management system. Specifically, the battery management system determines the fluctuation data of each type of detection data under each fault influencing factor based on the detection data of N types of detection data and M fault influencing factors. Using the fluctuation data of each type of detection data under each fault influencing factor, the fluctuation fault threshold of each type of detection data under the M fault influencing factors is determined. In this way, the battery fault detection threshold can be determined by the fluctuation fault threshold of each type of detection data under the M fault influencing factors. This effectively reduces the error and irrationality caused by manually setting the fault detection threshold for each detection data, thereby improving the accuracy of determining the fault detection threshold and thus improving the accuracy of battery fault detection. This avoids safety accidents caused by misjudgment or omission of battery fault detection due to manually setting fault detection thresholds.

[0067] Thirdly, this application provides a computer device, including a processor and a memory storing computer program instructions, wherein the processor, when executing the computer program instructions, implements the fault detection method as described in the first aspect.

[0068] Fourthly, this application provides a readable storage medium storing computer program instructions, which, when executed by a processor, implement the fault detection method as described in the first aspect.

[0069] Fifthly, this application provides a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform the fault detection method as described in the first aspect.

[0070] 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

[0071] 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 these drawings without creative effort.

[0072] Figure 1 This is a schematic diagram of the structure of a fault detection system according to an embodiment of this application;

[0073] Figure 2 This is a flowchart of a fault detection method according to an embodiment of this application;

[0074] Figure 3 A flowchart illustrating the fault detection method for determining fluctuation data according to one embodiment of this application;

[0075] Figure 4 A flowchart illustrating the fault detection method for determining fluctuation data according to one embodiment of this application;

[0076] Figure 5 This is a flowchart illustrating the process of determining a battery fault detection threshold in a fault detection method according to an embodiment of this application.

[0077] Figure 6 This is a flowchart illustrating the process of determining a battery fault detection threshold in a fault detection method according to an embodiment of this application.

[0078] Figure 7 This is a flowchart illustrating the determination of matching results in a fault detection method according to an embodiment of this application;

[0079] Figure 8 This is a flowchart of a fault detection method according to an embodiment of this application;

[0080] Figure 9 This is a flowchart illustrating the fault detection threshold for updating a battery in a fault detection method according to one embodiment of this application.

[0081] Figure 10This is a flowchart illustrating the fault detection threshold for updating the battery in a fault detection method according to one embodiment of this application.

[0082] Figure 11 This is a flowchart illustrating the process of determining battery fault detection information in a fault detection method according to an embodiment of this application.

[0083] Figure 12 This is a flowchart illustrating a fault detection method according to an embodiment of this application;

[0084] Figure 13 Schematic diagrams of the structure of a fault detection device provided in some embodiments of this application;

[0085] Figure 14 A schematic diagram of the hardware structure of a computer device provided for some embodiments of this application. Detailed Implementation

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] Unless otherwise specified, all embodiments and optional embodiments of this application can be combined to form new technical solutions.

[0091] Unless otherwise specified, all technical features and optional technical features of this application may be combined to form new technical solutions.

[0092] 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.

[0093] 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.

[0094] 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).

[0095] In the description of the embodiments of this application, the technical terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of this application and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0096] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0097] In current battery management systems (BMS), fault detection is a crucial step in ensuring the safe and efficient operation of batteries. However, existing BMS fault detection mechanisms generally face a challenge: insufficient precision in setting fault detection thresholds. Specifically, when monitoring battery data such as voltage, current, and temperature, the BMS relies on manually set fault detection thresholds to determine whether a battery has malfunctioned. However, these thresholds are often based on human experience or fixed standards, lacking sufficient consideration of the actual operating conditions and environmental factors of different batteries. Due to the imprecise nature of these thresholds, when battery data approaches the threshold, it is often difficult to accurately distinguish between normal fluctuations and the precursors to a true fault. This ambiguity leads to two problems: first, misjudgment, where normal fluctuations are incorrectly identified as faults, triggering unnecessary warnings or protective measures and affecting normal battery use; second, missed detection, where the true precursors to a fault are not detected in time, allowing the fault to develop further, potentially causing more serious damage to the battery or even leading to a safety accident.

[0098] Based on this, to address the problem of misjudgment or missed detection in battery fault detection, which reduces the accuracy of battery fault detection, this application proposes a fault detection method that optimizes the threshold setting for battery fault detection. Specifically, it involves identifying N types of detection data characterizing the battery state under vehicle operation conditions within a first time period, and M fault influencing factors affecting the accuracy of the detection data. The method determines the fluctuation data of each type of detection data under each fault influencing factor. Using this fluctuation data, a comprehensive fault detection threshold for the battery under the M fault influencing factors is determined. This threshold is then used to detect the battery's detection data within a second time period, thereby determining the battery's fault detection information. This effectively reduces the errors and irrationality caused by manually setting fault detection thresholds for each type of detection data, thus improving the accuracy of determining the fault detection threshold and consequently improving the accuracy of battery fault detection. This avoids safety accidents caused by misjudgment or missed detection of battery faults due to manually setting fault detection thresholds.

[0099] Based on this, in order to better describe the fault detection method, system, device, computer equipment, storage medium, and computer program product provided in the embodiments of this application, the following will be combined with the appendix. Figures 1 to 14 The following detailed description is provided, and it should be noted that these embodiments are not intended to limit the scope of this application.

[0100] First, this application provides a fault detection system. This fault detection system can be a battery management system, which may include an operating system, a data acquisition module, and a data transmission module corresponding to the battery management system.

[0101] In this embodiment, the in-vehicle operating system is an operating system that conforms to the Automotive Open System Architecture (AUTOSAR) standard and is mounted on the BMS system. The in-vehicle operating system can be a system running on the electronic control unit in the vehicle. In some embodiments, the in-vehicle operating system in this embodiment can be used to determine and update battery fault detection thresholds. In other embodiments, the in-vehicle operating system can be used to determine fault detection information, based on the battery management system's fault detection thresholds for individual battery cells (hereinafter referred to as batteries) and battery detection data, to determine whether a battery fault exists.

[0102] The battery management system in this application embodiment is used to perform at least one of the following functions for 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 in 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., but this application embodiment does not impose any limitations on this.

[0103] 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; the battery management system in this application can also be integrated as a controller into the power-consuming device, such as into the vehicle or vehicle chassis; the battery management system in this application can also be integrated as a controller into the charging device, such as into the charging device or battery swapping device; the battery management system in this application can also be deployed as control software on a server. The server can be an independent 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 (CDN), and big data and artificial intelligence platforms, such as vehicle networking cloud, application (APP) backend, etc.

[0104] In some embodiments, the data acquisition module can be a sensor in the electronic management system, used to collect N types of detection data characterizing the battery state when the battery is in operation, so that the battery management system can determine the battery fault detection threshold.

[0105] In some embodiments, the data transmission module can be used to send the first information to the host computer of the battery management system to provide a fault alarm to the user.

[0106] Therefore, the fault detection system in this embodiment can determine the comprehensive fault detection threshold of the battery under M fault influencing factors through the vehicle operating system, data acquisition module, and data transmission module. This fault detection threshold can then be used to analyze the collected battery detection data, thereby determining the battery's fault detection information. This effectively reduces the errors and irrationality caused by manually setting fault detection thresholds for each data point, thus improving the accuracy of determining the fault detection threshold and consequently improving the accuracy of battery fault detection. It avoids safety accidents caused by misjudgments or omissions in battery fault detection due to manually setting fault detection thresholds. Furthermore, while ensuring the normal operation of the battery management system, the data transmission module can promptly alert users, enabling risk awareness and effectively ensuring the security of the vehicle operating system and battery management system, thereby improving operational efficiency.

[0107] Secondly, combining Figure 2 The fault detection method provided in the embodiments of this application will be described in detail.

[0108] Figure 2 This is a flowchart illustrating a fault detection method provided in an embodiment of this application.

[0109] like Figure 2 As shown, this fault detection method can be applied to a battery management system, and the fault detection method specifically includes the following steps:

[0110] Step 210: Obtain N types of detection data representing the battery state under vehicle operation during the first time period, where N is a positive integer; Step 220: Determine the fluctuation data of each type of detection data based on M preset fault influencing factors, where the fluctuation data represents the degree of deviation of each detection value in each type of detection data from the preset center value, where M is an integer greater than 1; Step 230: Determine the battery fault detection threshold based on the fluctuation data of each type of detection data; Step 240: Determine the battery fault detection information based on the battery detection data and fault detection threshold during the second time period.

[0111] The detection data in this application embodiment may include at least one of the following: electrical parameters, temperature, and internal resistance. The electrical parameters include at least one of the following: voltage, resistance, and current.

[0112] The M fault influencing factors in this application embodiment may include at least one of the following: battery operating status, battery operating environment, and battery wear level.

[0113] The battery's operating states can include normal state, overcharge protection state, and short-circuit protection state. Specifically, the normal state means the battery can freely charge and discharge; all transistors (MOSFETs) in the circuit are in the conducting state, with very low on-resistance and minimal impact on circuit performance. The overcharge protection state means that when the battery voltage reaches a preset value, such as 4.28V, the protection circuit will cut off the charging circuit to prevent overcharging and thus protect the battery from damage. The short-circuit protection state means that when the circuit current is too high during battery discharge, the protection circuit will quickly cut off the discharge circuit to prevent a short circuit.

[0114] The battery operating environment may include at least one of the following: ambient temperature, electrostatic interference, electromagnetic interference, humidity and corrosion, mechanical vibration and shock of the environment in which the BMS hardware is located.

[0115] Specifically, ambient temperature is a crucial factor affecting BMS hardware performance. High temperatures can degrade or even damage electronic components, while low temperatures can impact battery charging and discharging efficiency. Therefore, monitoring battery temperature and adjusting charging power based on preset thresholds can protect the battery from overheating or overcooling. Electrostatic interference (ESI) is a transient high-voltage phenomenon that can be caused by human contact, lightning strikes, or power system fluctuations. ESI surges can affect the normal operation of the BMS through various means, leading to data transmission errors, damage to electronic components, and even system failure. Electromagnetic interference (EMI) affects BMS signal transmission and data processing, causing system instability or malfunctions. Shielding, filtering, and grounding are commonly used to reduce the impact of EMI. Humidity and corrosion refer to the fact that high humidity environments can cause BMS hardware to become damp, affecting its performance and lifespan. Chemicals in corrosive environments can erode BMS hardware, leading to malfunctions. Therefore, the impact of humidity and corrosion on BMS hardware should be considered. Mechanical vibration and shock refer to the varying degrees of vibration and shock that vehicles experience during operation, which can affect the connection and stability of the BMS hardware. Therefore, the impact of mechanical vibration and shock on BMS hardware should be considered.

[0116] Battery degradation can refer to the degree of aging of BMS hardware.

[0117] Fluctuation data characterizes the degree of deviation of each detection value in each type of detection data from the preset central value. This degree of deviation can be quantified by statistical indicators such as variance and standard deviation. Variance is the average of the squares of the differences between each data point and the mean, while standard deviation is the square root of variance, used to measure the dispersion of the data. These indicators can analyze the fluctuation of detection data within a certain period of time.

[0118] For example, voltage and temperature are used as the detection data for illustration. Voltage detection data for each battery cell in at least one battery cell is acquired between 10:00 and 11:00 AM. Based on the voltage detection data, battery operating state, battery operating environment, and battery wear level, fluctuation data 1 (voltage detection data under different battery operating states), fluctuation data 2 (voltage detection data under different battery operating environments), and fluctuation data 3 (voltage detection data under different battery wear levels) are determined. Then, based on fluctuation data 1, fluctuation data 2, and fluctuation data 3, a voltage fluctuation fault threshold under different battery operating states, different battery operating environments, and different battery wear levels is determined.

[0119] Furthermore, temperature detection data for each battery cell in at least one battery cell is acquired. Based on the temperature detection data, battery operating state, battery operating environment, and battery wear level, fluctuation data 4 of the temperature detection data under different battery operating states, fluctuation data 5 of the temperature detection data under different battery operating environments, and fluctuation data 6 of the temperature detection data under different battery wear levels are determined. Then, based on fluctuation data 4, fluctuation data 5, and fluctuation data 6, a fault threshold for temperature fluctuation under different battery operating states, different battery operating environments, and different battery wear levels is determined.

[0120] Based on this, the fault detection thresholds for the battery are determined according to the voltage fluctuation fault thresholds under different battery operating states, different battery operating environments, and different battery wear levels, as well as the temperature fluctuation fault thresholds under different battery operating states, different battery operating environments, and different battery wear levels.

[0121] Then, after obtaining the battery voltage value at 11:05, the voltage value is compared with the battery fault detection threshold corresponding to the voltage. If the voltage value is greater than the fault detection threshold, the first information used to characterize the battery fault is determined as fault detection information; if the voltage value is less than or equal to the fault detection threshold, the second information used to characterize the battery not being faulty is determined as fault detection information.

[0122] Therefore, the threshold setting for battery fault detection can be optimized. Based on N types of detection data characterizing the battery state during the first time period under vehicle operation, and M fault influencing factors affecting the accuracy of the detection data, the fluctuation data of each type of detection data under each fault influencing factor is determined. Using the fluctuation data of each type of detection data under each fault influencing factor, a comprehensive fault detection threshold for the battery under the M fault influencing factors is determined. This fault detection threshold can then be used to detect the battery's detection data during the second time period, thereby determining the battery's fault detection information. This effectively reduces the errors and irrationality caused by manually setting fault detection thresholds for each type of detection data, thus improving the accuracy of determining the fault detection threshold and consequently improving the accuracy of battery fault detection. This avoids safety accidents caused by misjudgments or omissions in battery fault detection due to manually setting fault detection thresholds.

[0123] The steps described above are explained in detail below.

[0124] In step 210, in this embodiment of the application, the battery management system can comprehensively acquire detection data such as battery electrical parameters, temperature, internal resistance, etc., to provide a data basis for setting and optimizing fault detection thresholds. For example, by continuously monitoring the battery voltage, the range and trend of voltage changes under different fault influencing factors can be collected, which is crucial for determining the thresholds of overvoltage and undervoltage faults.

[0125] It should be noted that the detection data in this application embodiment reflects the actual changes in the battery's state, including but not limited to the aforementioned electrical parameters, temperature, and internal resistance. This detection data dynamically reflects the battery's actual operating state. These parameters will change accordingly with battery use, aging, and changes in environmental conditions. For example, battery performance varies at different temperatures; comprehensive monitoring of temperature parameters can help adjust temperature-related fault detection thresholds to adapt to different operating temperature environments.

[0126] In the embodiments of this application, various parameter changes of the battery under normal and fault conditions, such as voltage, current, and temperature, can be analyzed, and the influence of factors such as the battery's charge and discharge characteristics and aging degree on fault detection can be considered.

[0127] Based on this, step 210 may include: acquiring N types of detection data characterizing the battery state in real time through the data acquisition module of the battery management system, so as to store the acquired data in the storage space for subsequent analysis and processing, thereby determining the fault detection threshold.

[0128] Regarding step 220, in some embodiments of this application, the M fault influencing factors may include at least one of the following: battery operating state, battery operating environment, and battery wear level. Based on this, fluctuation data for each fault influencing factor can be determined using a statistical algorithm. Based on this, such as... Figure 3 As shown, step 220 may specifically include steps 2201 to 2203.

[0129] Step 2201: Divide the N types of detection data according to each fault influencing factor to obtain at least one type of detection data under each fault influencing factor in the first time period.

[0130] For example, taking voltage and temperature detection data as examples, the operating data is divided according to different battery operating states, different battery operating environments, and different battery wear levels to obtain voltage detection data under different battery operating states, voltage detection data under different battery operating environments, and voltage detection data under different battery wear levels; and, temperature detection data under different battery operating states, temperature detection data under different battery operating environments, and temperature detection data under different battery wear levels.

[0131] Step 2202: Using a statistical algorithm, perform statistical calculations on at least one type of detection data under each fault influencing factor to obtain the statistical value of each type of detection data under each fault influencing factor.

[0132] The statistical algorithms used in this application include, but are not limited to, descriptive statistical algorithms and hypothesis testing algorithms. Descriptive statistical algorithms can be used to calculate basic characteristics of data, such as mean, variance, standard deviation, and median. Hypothesis testing algorithms can be used to verify the significance of statistical hypotheses, including t-tests, chi-square tests, and F-tests.

[0133] Here, we can take the mean and variance in descriptive statistical algorithms as an example to calculate the average or variance value of each type of detection data under each fault influencing factor.

[0134] Specifically, based on the voltage detection data under different battery operating conditions, the voltage detection data under different battery operating environments, and the voltage detection data under different battery wear levels, the average value of the voltage detection data under different battery operating conditions, the average value of the voltage detection data under different battery operating environments, and the average value of the voltage detection data under different battery wear levels are calculated.

[0135] Similarly, based on the temperature detection data under different battery operating conditions, the temperature detection data under different battery operating environments, and the temperature detection data under different battery wear levels, the average values ​​of the temperature detection data under different battery operating conditions, the average values ​​of the temperature detection data under different battery operating environments, and the average values ​​of the temperature detection data under different battery wear levels are calculated.

[0136] Step 2203: Determine the statistical value of each type of detection data under each fault influencing factor as the fluctuation data of each type of detection data.

[0137] For example, the average value of the voltage detection data under different battery operating conditions can be determined as the fluctuation data of the voltage detection data under different battery operating conditions, the average value of the voltage detection data under different battery operating environments can be determined as the fluctuation data of the voltage detection data under different battery operating environments, and the average value of the voltage detection data under different battery wear levels can be determined as the fluctuation data of the voltage detection data under different battery wear levels.

[0138] It should be noted that, in addition to defining the statistical value itself as fluctuating data, the statistical value can also be updated periodically within the range of variance plus or minus a certain multiple of the mean to adapt to changes in battery status.

[0139] Therefore, by analyzing the statistical values ​​of each type of detection data under multiple fault influencing factors, the complex interactive relationships affecting battery faults can be revealed, thereby improving the accuracy of operational data classification. Furthermore, the statistical values ​​of each type of detection data under each fault influencing factor can reflect the central tendency, dispersion, or distribution pattern of the detection data, which can be accurately used as the basis for overall inference of the fluctuation data of each type of detection data under each fault influencing factor, thus improving the accuracy of determining the fluctuation data of each type of detection data under each fault influencing factor.

[0140] In some embodiments, prior to step 2202 described above, such as Figure 4 As shown, the fault detection method may further include step 2204, which uses a Kalman filter algorithm to denoise at least one type of detection data under each fault influencing factor in the first time period, to obtain at least one type of denoised detection data, wherein the noise value in the at least one type of denoised detection data is within a preset Gaussian white noise range.

[0141] Here, the preset Gaussian white noise range is used to control the noise in the denoised detection data within the standard of Gaussian white noise. The Kalman filtering algorithm can be provided by a Kalman filter. The preset Gaussian white noise range refers to noise in the denoised detection data whose probability density function follows a Gaussian distribution and whose power spectral density is uniformly distributed over any time interval.

[0142] Based on this, step 2202 may specifically include:

[0143] Statistical algorithms are used to perform statistical calculations on at least one type of denoised detection data to obtain statistical values ​​for each type of detection data under each fault influencing factor. Therefore, Kalman filtering can be used to remove noise introduced by sensor errors and environmental interference from the detection data under each fault influencing factor, making the detection data for each type of detection data under each fault influencing factor closer to the true state, reducing error interference, and avoiding missing or incorrect statistical values ​​for each type of detection data under fault influencing factors due to noise. This improves the reliability and consistency of the statistical values, and enhances the data quality and reliability of the statistical values ​​for each type of detection data under each fault influencing factor.

[0144] In step 230, in some embodiments of this application, M is an integer greater than 1, such as... Figure 5 As shown, step 230 may specifically include steps 2301 and 2302.

[0145] Step 2301: Based on the fluctuation data of each type of detection data, determine the fluctuation fault threshold of each type of detection data under each fault influencing factor.

[0146] For example, if the detected data is voltage detection data, the fluctuation data can be represented by an average value. In this case, based on the average value of the voltage detection data, the fluctuation fault threshold of the voltage detection data under at least two fault influencing factors can be determined. These at least two fault influencing factors include: battery operating state, battery operating environment, and battery wear level. That is, the fluctuation fault threshold 1 for the voltage detection data under battery operating state and the fluctuation fault threshold 2 for the voltage detection data under battery operating environment.

[0147] Step 2302: Determine the battery's fault detection threshold based on the fluctuating fault threshold under each of the M fault influencing factors.

[0148] For example, a fault detection threshold related to battery voltage is determined based on fluctuation fault threshold 1 and fluctuation fault threshold 2.

[0149] In the above scheme, the fluctuating fault threshold of each type of detection data under each fault influencing factor can be determined first. Then, the fluctuating fault thresholds under multiple fault influencing factors are integrated to obtain the battery fault detection threshold. This allows for a detailed analysis of the accuracy of the fluctuating fault threshold under each fault influencing factor, and the summarization of the fluctuating fault thresholds under M fault influencing factors can improve the accuracy of determining the battery fault detection threshold.

[0150] In some embodiments of this application, step 2301 may specifically include:

[0151] Based on the weight of each fault influencing factor, the fluctuation data of each type of detection data under each fault influencing factor is weighted and calculated to obtain the fluctuation fault threshold of each type of detection data under each fault influencing factor.

[0152] For example, since the battery operating state and battery operating environment have a significant impact on battery failure, the weights for the battery operating state, battery operating environment, and battery wear level can be set to 0.4 and 0.2 respectively. Using the example from step 220 above as an example, based on the weight of 0.4 for the battery operating state, the fluctuation data of the voltage detection data under the battery operating state are weighted and calculated to obtain voltage fluctuation failure threshold 1 under the battery operating state; and based on the weight of 0.4 for the battery operating environment, the fluctuation data of the voltage detection data under the battery operating state are weighted and calculated to obtain voltage fluctuation failure threshold 2 under the battery operating state.

[0153] Therefore, by setting a corresponding weight for each fault influencing factor, the characteristics of the detection data under different fault influencing factors can be accurately adapted, improving the accuracy of analyzing the fluctuating fault threshold of each type of detection data under each fault influencing factor, and thus improving the accuracy of determining the fluctuating fault threshold of each type of detection data under each fault influencing factor.

[0154] In some embodiments of this application, such as Figure 6 As shown, step 2302 can specifically include steps 23021 and 23022, as detailed below.

[0155] Step 23021: Obtain the weight of each fault influencing factor based on each fault influencing factor.

[0156] Step 23022: Based on the weight of each fault influencing factor, the fluctuating fault threshold under each fault influencing factor is weighted and summed to obtain the battery fault detection threshold.

[0157] For example, since the battery operating state and battery operating environment have a significant impact on battery failure, the weights for the battery operating state, battery operating environment, and battery wear level can be set to 0.4 and 0.4 respectively. Using the example from step 220 above as an example, the weights for the battery operating state (0.4), battery operating environment (0.4), and battery wear level (0.2), along with the average values ​​of voltage detection data under different battery operating states, different battery operating environments, and different battery wear levels, are weighted and summed to obtain the voltage fluctuation failure threshold under the three failure influencing factors.

[0158] Therefore, by setting different weights for different fault influencing factors, it is possible to accurately adapt the characteristics of the detection data under different fault influencing factors, improve the accuracy of analyzing the fluctuating fault threshold of each type of detection data under M fault influencing factors, and thus improve the accuracy of determining the fluctuating fault threshold of each type of detection data under M fault influencing factors.

[0159] In some embodiments of this application, the fluctuating fault threshold of each type of detection data under M fault influencing factors can be determined as the fault detection threshold of the battery.

[0160] For example, taking the embodiment in step 230 above as an example, the voltage fluctuation fault threshold under the three fault influencing factors can be determined as the battery fault detection threshold. Alternatively, the voltage fluctuation fault threshold under the three fault influencing factors and the temperature fluctuation fault threshold under the three fault influencing factors can be determined as the battery fault detection threshold.

[0161] In step 240, in some embodiments of this application, the time in the second time period is later than the time in the first time period, and the fault detection information includes first information for characterizing battery faults. Based on this, such as Figure 7 As shown, step 240 can specifically be steps 2401 to 2403.

[0162] Step 2401: Match the detection values ​​in the battery detection data during the second time period with the fault detection threshold to obtain the matching result.

[0163] Step 2402: If the matching result indicates that the detected value is greater than the fault detection threshold, determine the first information.

[0164] For example, if the fault detection threshold is determined based on N types of detection data representing the battery state during vehicle operation from 10:00 to 11:00, then when the battery voltage value at 11:05 is obtained, the voltage value is compared with the battery fault detection threshold corresponding to the voltage. If the voltage value is greater than the fault detection threshold, then the first information used to represent the battery fault is determined as the fault detection information.

[0165] In some embodiments of this application, the fault detection information includes second information to characterize that the battery is not faulty. Based on this, after step 2401, the fault detection method may further include step 2403, determining the second information if the matching result indicates that the detection value is less than or equal to the fault detection threshold.

[0166] For example, if the voltage value is less than or equal to the fault detection threshold, the second information used to characterize that the battery is not faulty is determined as fault detection information.

[0167] Therefore, battery fault detection can be performed by setting accurate fault detection thresholds, avoiding safety accidents caused by misjudgment or omission of battery fault detection due to manually setting fault detection thresholds, and improving the accuracy of battery fault detection.

[0168] In addition, in some embodiments of this application, if steps 210 to 230 are executed by the vehicle operating system in the battery management system, after step 240, the fault detection method can also be combined with the BMS to verify whether the battery fault detection threshold is applicable to actual fault detection. Based on this, after step 240, the fault detection method can also include step 250, transmitting a verification instruction to the battery management system. The verification instruction carries the battery fault detection threshold and is used to instruct the battery management system to determine whether the battery has a fault based on the battery fault detection threshold.

[0169] Therefore, by optimizing the fault detection thresholds used for battery fault detection in the battery management system through the vehicle operating system, the coordinated cooperation between the two systems can ensure the accuracy of determining the fault detection thresholds and enable the battery management system to accurately determine the occurrence of faults, reducing false positives and false negatives, and avoiding safety accidents caused by false positives or false negatives in battery fault detection due to manually setting fault detection thresholds.

[0170] Based on this, the verification instruction in this embodiment is also used to instruct the battery management system to send a fault alarm message to the vehicle operating system when the battery fault detection threshold is determined to be faulty. Therefore, after step 240, as follows... Figure 8 As shown, the fault detection method may further include step 260:

[0171] If the fault detection information includes first information characterizing the battery fault, the first information is sent to the host computer of the battery management system through the communication module of the battery management system to issue a fault alarm to the user.

[0172] In this embodiment of the application, the BMS host computer is the human-machine interface for controlling and displaying the BMS. The BMS host computer provides an intuitive interaction method to display fault alarm information to the user.

[0173] Therefore, while ensuring the normal operation of the battery management system, timely alarms can be sent to users, enabling risk awareness, effectively ensuring the safety of the battery management system, and improving operation and maintenance efficiency.

[0174] In some embodiments of this application, the battery management system can detect the judgment result of determining whether the battery has a fault based on the battery's fault detection threshold, and determine whether to trigger the adjustment of the battery's fault detection threshold involved in step 240 above.

[0175] Based on this, after step 250, the effectiveness of the fault detection threshold can be further verified. Based on this, such as... Figure 9 As shown, the fault detection method may further include steps 2701 to 2703, as detailed below.

[0176] Step 2701: Obtain the judgment result based on the battery-based fault detection threshold to determine whether a battery fault exists. Step 2702: Based on the judgment result and a reference judgment result, determine the false alarm rate or false negative rate of the battery management system for battery fault detection.

[0177] Step 2703: If the false alarm rate is greater than or equal to the first preset threshold, or the false alarm rate is greater than or equal to the second preset threshold, update the battery fault detection threshold.

[0178] For example, if a large number of false alarms or missed alarms are detected, it indicates that the fault detection threshold needs to be adjusted. Specifically, if comparing the judgment result with the reference judgment result reveals that the fault detection threshold does not trigger a fault alarm, it means that the fault detection threshold is set too high and needs to be lowered to improve the sensitivity of battery fault detection. If the fault detection threshold frequently triggers a fault alarm, it means that the fault detection threshold is set too low and needs to be increased to avoid frequent false alarms.

[0179] Therefore, the battery management system can determine whether a battery is faulty based on the battery's fault detection threshold, and determine whether to optimize the battery's fault detection threshold to improve the accuracy of fault detection and judgment, so that it can accurately judge the occurrence of faults while minimizing false positives and false negatives.

[0180] In some embodiments, the battery fault detection threshold can be updated through the following steps, based on which, such as Figure 10 As shown, step 2703 can specifically include steps 27031 to 27034, as detailed below.

[0181] Step 27031: In the event of a battery malfunction, determine the location of the malfunction using a fault propagation model.

[0182] Step 27032: Determine the cause of the fault at the fault location based on the fault detection data associated with the fault location.

[0183] Step 27033: Adjust the fault detection threshold of the fault detection data according to the cause of the fault, and obtain the adjusted fault detection threshold of the fault detection data.

[0184] For example, targeted threshold adjustment directions are provided. Once the specific fault location and cause are determined through fault diagnosis and location correlation analysis, the thresholds of the corresponding parameters can be adjusted accordingly. For instance, if an internal short-circuit fault is diagnosed in a battery cell, the fault detection threshold can be lowered based on the voltage and current parameters of that battery to detect the recurrence of similar faults earlier.

[0185] Step 27034: Adjust the fault detection threshold based on the fault detection data and update the battery's fault detection threshold.

[0186] Therefore, by using correlation analysis technology, the causal relationship between fault detection data related to fault location can be explored. Combined with the fault propagation model, the source of the fault can be quickly located, thereby providing accurate detection data to be adjusted for the repair of the battery's fault detection threshold, and realizing efficient and accurate updating of the battery's fault detection threshold.

[0187] Specifically, in some embodiments, step 27031 above may include:

[0188] By using a fault propagation model, the fault source system component that is dependent on the fault can be identified based on the dependency relationship between at least two system components in the battery management system.

[0189] The location of the fault is determined based on the location of the fault-causing system components that are dependent on the fault.

[0190] For example, in this embodiment of the application, a fault propagation model can be established between steps 27031. This fault propagation model can be a model used to describe how a fault propagates and affects the system. This model is typically built based on the dependencies and interactions between system components. Through the fault propagation model, the propagation path of a fault in the system can be simulated, and potentially affected tasks and other system components can be inferred. Specifically, when a system component fails, the fault propagation model calculates other system components and tasks that may be affected by the fault based on the dependencies between system components, thereby helping to quickly locate the source of the fault, predict the possible scope of the fault, and take corresponding measures for repair and prevention.

[0191] Therefore, by constructing a fault propagation model, it is possible to simulate the propagation path of faults in the battery management system, quickly locate the source of the fault, provide accurate detection data to be adjusted for the repair of fault detection thresholds, and achieve efficient and accurate updating of battery fault detection thresholds.

[0192] In some embodiments, step 27032 above may specifically include:

[0193] Based on the correlation analysis information between the reference fault detection data and the reference fault causes, the fault causes corresponding to the fault detection data are determined.

[0194] Therefore, by performing correlation analysis on the collected fault detection data and various fault causes, the causal relationship between fault detection data and fault causes can be found, and the specific causes and paths of fault occurrence can be clarified. This provides accurate detection data to be adjusted for the repair of fault detection thresholds, enabling efficient and accurate updating of battery fault detection thresholds.

[0195] Furthermore, the fault detection method provided in this application embodiment can continuously monitor and adjust the fault detection threshold. Based on this, the battery's operating data is the operating data within the first time window. Thus, if... Figure 11 As shown, the fault detection method provided in this application embodiment may further include steps 2801 to 2803, as detailed below.

[0196] Step 2801: Obtain N types of detection data representing the battery state under vehicle operation conditions during the third time period.

[0197] For example, the BMS fault detection target is clearly defined, and the types of faults to be detected are determined, such as overvoltage, undervoltage, overcurrent, and overheating, to understand the impact of different faults on battery performance and safety. Based on the detected fault types, N types of detection data characterizing the battery state under vehicle operation conditions are obtained within a third time period, such as from 11:00 to 11:04.

[0198] Step 2802: Based on the N types of detection data representing the battery status under vehicle operation during the third time period, the fault detection threshold of the battery during the third time period is determined through the steps involved in steps 210 to 230 above.

[0199] For example, the fault detection threshold 2 corresponding to the battery voltage in the third time period is determined by the steps involved in steps 210 to 230 above.

[0200] Step 2803: If the battery fault detection threshold in the third time period is different from the battery fault detection threshold in the first time period, determine the battery fault detection information based on the battery detection data in the second time period and the fault detection threshold in the third time period; wherein, the time of the third time period is later than the time of the first time period but earlier than the time of the second time period.

[0201] For example, if the fault detection threshold 1 corresponding to the battery voltage during the period from 10:00 to 11:00 is different from the fault detection threshold 2 corresponding to the battery voltage during the third time period, the fault detection threshold 2 corresponding to the battery voltage during the period from 11:00 to 11:04 is compared with the battery voltage value at 11:05. If the voltage value is greater than the fault detection threshold, the first information used to characterize the battery fault is determined as fault detection information; if the voltage value is less than or equal to the fault detection threshold, the second information used to characterize the battery not being faulty is determined as fault detection information.

[0202] In this way, the optimized fault detection threshold is applied to the actual BMS for long-term operation testing, real-world operation data is collected, the effectiveness of fault detection is analyzed, and the fault detection threshold is further adjusted and optimized.

[0203] Therefore, by continuously collecting N types of battery detection data and updating the fault detection threshold, the real-time nature of the fault detection threshold can be guaranteed, reducing misjudgments and missed detections of battery faults caused by untimely updates of the fault detection threshold. This improves the accuracy of determining the fault detection threshold, thereby improving the accuracy of battery fault detection and avoiding safety accidents caused by misjudgments or missed detections of battery faults due to manually setting fault detection thresholds.

[0204] To better illustrate the fault detection method provided in the embodiments of this application, such as Figure 12 As shown below, the determination and updating of the battery fault detection threshold are explained in detail below with reference to steps 1 to 10.

[0205] Step 1: Using the built-in data acquisition module, acquire N types of detection data characterizing the battery status during the first time period while the vehicle is in operation. The sensors in the data acquisition module are distributed at various key locations within the BMS, such as the battery cells, modules, and the entire battery pack.

[0206] Step 2: The detection data collected by the vehicle operating system may contain noise caused by sensor errors or external interference. Therefore, the vehicle operating system can use filtering algorithms such as Kalman filtering to denoise the detection data, obtaining denoised detection data.

[0207] Step 3: The vehicle operating system can determine the battery fault detection threshold based on the noise-reduced detection data through the steps involved in steps 210 to 230 above.

[0208] Step 4: The vehicle operating system determines the battery detection data within the second time period based on the battery fault detection threshold to determine whether the battery has a fault.

[0209] Step 5: The vehicle operating system determines whether the battery is faulty based on the battery's fault detection threshold.

[0210] Step 6: The vehicle operating system obtains the battery-based fault detection threshold to determine whether the battery has a fault; based on the judgment result and the reference judgment result, the false alarm rate or false alarm rate of the battery management system for battery fault detection is determined.

[0211] Step 7: If the false alarm rate is greater than or equal to the first preset threshold, or the false alarm rate is greater than or equal to the second preset threshold, the vehicle operating system determines the fault location through the fault propagation model.

[0212] Step 8: The vehicle's operating system determines the cause of the fault at the location of the fault based on the fault detection data associated with that location. For example, if a simultaneous drop in battery temperature and voltage is detected, this may indicate a problem with the cooling system.

[0213] Step 9: The vehicle operating system adjusts the fault detection threshold of the fault detection data according to the cause of the fault, and obtains the adjusted fault detection threshold of the fault detection data.

[0214] Step 10: The vehicle operating system adjusts the fault detection threshold based on the fault detection data and updates the battery's fault detection threshold.

[0215] Therefore, in this embodiment, the battery fault detection threshold can be determined by the fluctuation fault threshold of each type of detection data under M fault influencing factors. This effectively reduces the error and irrationality caused by manually setting fault detection thresholds for each detection data, thereby improving the accuracy of determining the fault detection threshold and thus improving the accuracy of battery fault detection. This avoids safety accidents caused by misjudgment or omission of battery fault detection due to manually setting fault detection thresholds. Furthermore, by optimizing the fault detection thresholds used for battery fault detection in the battery management system through the vehicle operating system, the collaborative cooperation between the two systems can ensure the accuracy of determining the fault detection threshold and enable the battery management system to accurately judge the occurrence of faults, reducing misjudgment and omission, and avoiding safety accidents caused by misjudgment or omission of battery fault detection due to manually setting fault detection thresholds. In addition, by using correlation analysis technology, the causal relationship between fault detection data related to fault location is mined. Combined with the fault propagation model, the source of the fault can be quickly located, thereby providing accurate detection data to be adjusted for the repair of the battery fault detection threshold, achieving efficient and accurate updating of the battery fault detection threshold.

[0216] This application also provides a fault detection device, specifically combined with... Figure 13 Please provide a detailed explanation.

[0217] Figure 13This is a schematic diagram of the structure of a fault detection device provided in one embodiment of this application.

[0218] In some embodiments of this application, Figure 13 The fault detection device shown can be installed in the computer equipment provided in the embodiments of this application.

[0219] Based on this, such as Figure 13 As shown, the fault detection device 130 may specifically include:

[0220] The acquisition module 1301 is used to acquire N types of detection data representing the battery state under the vehicle's operating state during the first time period, where N is a positive integer.

[0221] The determination module 1302 is used to determine the fluctuation data of each type of detection data according to the preset M fault influencing factors, wherein the fluctuation data represents the degree of deviation of each detection value in each type of detection data from the preset center value, and M is an integer greater than 1;

[0222] The determination module 1302 is also used to determine the battery fault detection threshold based on the fluctuation data of each type of detection data;

[0223] The determination module 1302 is also used to determine the battery fault detection information based on the battery detection data and fault detection threshold during the second time period.

[0224] In this embodiment, the fault detection device 130 can optimize the threshold setting for battery fault detection. Specifically, based on N types of detection data representing the battery state under vehicle operation during the first time period and M fault influencing factors affecting the accuracy of the detection data, the fluctuation data of each type of detection data under each fault influencing factor is determined. Using the fluctuation data of each type of detection data under each fault influencing factor, the comprehensive fault detection threshold of the battery under the M fault influencing factors is determined. Thus, the detection data of the battery during the second time period can be detected using this fault detection threshold, thereby determining the battery fault detection information. This effectively reduces the errors and irrationality caused by manually setting the fault detection threshold for each detection data, thereby improving the accuracy of determining the fault detection threshold and thus improving the accuracy of battery fault detection. It also avoids safety accidents caused by misjudgment or omission of battery fault detection due to manually setting the fault detection threshold.

[0225] The fault detection device 130 in the embodiments of this application will be described in detail below.

[0226] In some embodiments of this application, the determining module 1302 can be specifically used to divide N types of detection data according to each fault influencing factor, in the case that M fault influencing factors may include at least one of the following: battery operating state, battery operating environment, and battery wear level, to obtain at least one type of detection data under each fault influencing factor in the first time period.

[0227] Using statistical algorithms, at least one type of detection data under each fault influencing factor is statistically calculated to obtain the statistical value of each type of detection data under each fault influencing factor.

[0228] The statistical value of each type of detection data under each fault influencing factor is determined as the fluctuation data of each type of detection data.

[0229] In some embodiments of this application, the fault detection device 130 in this application embodiment may further include a processing module, which is used to perform noise reduction processing on at least one type of detection data under each fault influencing factor in the first time time through Kalman filtering algorithm, to obtain at least one type of detection data after noise reduction, wherein the noise value in the at least one type of detection data after noise reduction is within a preset Gaussian white noise range.

[0230] Specifically, module 1302 can be used to perform statistical calculations on at least one type of denoised detection data using a statistical algorithm to obtain the statistical value of each type of detection data under each fault influencing factor.

[0231] In some embodiments of this application, the determining module 1302 may specifically be used to determine the fluctuation fault threshold of each type of detection data under each fault influencing factor, based on the fluctuation data of each type of detection data, when M is an integer greater than 1.

[0232] The battery fault detection threshold is determined based on the fluctuating fault threshold under each of the M fault influencing factors.

[0233] In some embodiments of this application, the determining module 1302 may be specifically used to perform weighted calculation on the fluctuation data of each type of detection data under each fault influencing factor according to the weight of each fault influencing factor, so as to obtain the fluctuation fault threshold of each type of detection data under each fault influencing factor.

[0234] In some embodiments of this application, the acquisition module 1301 may also be used to acquire the weight of each fault influencing factor based on each fault influencing factor.

[0235] Specifically, module 1302 can be used to perform a weighted summation of the fluctuating fault threshold under each fault influencing factor based on the weight of each fault influencing factor, so as to obtain the battery fault detection threshold.

[0236] In some embodiments of this application, the determining module 1302 may be specifically used to match the detection value in the battery detection data in the second time period with the fault detection threshold to obtain a matching result when the time in the second time period is later than the time in the first time period and the fault detection information includes first information for characterizing battery fault.

[0237] If the matching result indicates that the detected value is greater than the fault detection threshold, the first piece of information is determined.

[0238] In some embodiments of this application, the fault detection device 130 may further include a transmission module, which is used to send the first information to the host computer of the battery management system through the communication module of the battery management system when the fault detection information includes the first information for characterizing the battery fault, so as to issue a fault alarm to the user.

[0239] In some embodiments of this application, the acquisition module 1301 may also be used to acquire a judgment result based on the battery fault detection threshold to determine whether the battery has a fault.

[0240] Specifically, module 1302 can be used to determine the false alarm rate or false alarm rate of battery fault detection by the battery management system based on the judgment result and the reference judgment result.

[0241] In this embodiment, the fault detection device 130 may further include an update module, used to update the battery fault detection threshold when the false alarm rate is greater than or equal to a first preset threshold or the false alarm rate is greater than or equal to a second preset threshold.

[0242] In some embodiments of this application, the determining module 1302 can also be used to determine the fault location by means of a fault propagation model, when the fault detection information includes first information for characterizing the battery fault.

[0243] The determination module 1302 can also be used to determine the cause of the fault at the fault location based on the fault detection data associated with the fault location;

[0244] In this embodiment, the fault detection device 130 may further include an adjustment module, which is used to adjust the fault detection threshold of the fault detection data according to the cause of the fault, so as to obtain the adjusted fault detection threshold of the fault detection data.

[0245] In this embodiment, the fault detection device 130 may further include an update module for adjusting the fault detection threshold based on the fault detection data and updating the battery's fault detection threshold.

[0246] In some embodiments of this application, the determining module 1302 can be specifically used to determine the fault source system component that is dependent on the fault, based on the dependency relationship between at least two system components in the battery management system, through a fault propagation model.

[0247] The location of the fault is determined by the location of the fault-causing system components that are dependent on the fault.

[0248] In some embodiments of this application, the determining module 1302 may be specifically used to determine the fault cause corresponding to the fault detection data based on the correlation analysis information between the reference fault detection data and the reference fault cause.

[0249] In some embodiments of this application, the fault detection device 130 in this application embodiment may further include an acquisition module 1301, which may also be used to acquire N types of detection data characterizing the battery state under vehicle operating conditions during a third time period.

[0250] The determination module 1302 can also be used to determine the battery fault detection threshold in the third time period based on N types of detection data that characterize the battery state under the vehicle's operating state in the third time period.

[0251] The determining module 1302 can also be used to determine the battery fault detection information based on the battery detection data in the second time period and the fault detection threshold in the third time period when the battery fault detection threshold in the third time period is different from that in the first time period; wherein the time of the third time period is later than the time of the first time period but earlier than the time of the second time period.

[0252] This application also provides a computer device. (Specifically combined with...) Figure 14 Please provide a detailed explanation.

[0253] Figure 14 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application.

[0254] like Figure 14 As shown, the computer device may include the computer device for performing the fault detection method involved in the embodiments of this application. The computer device may include a processor 1401 and a memory 1402 storing computer program instructions.

[0255] Specifically, the processor 1401 may include a central processing unit (CPU), an application-specific integrated circuit (ASTC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0256] Memory 1402 may include a large-capacity memory for data or instructions. For example, and not limitingly, memory 1402 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 1402 may include removable or non-removable (or fixed) media. Where appropriate, memory 1402 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 1402 is non-volatile solid-state memory. In a particular embodiment, memory 1402 includes solid-state storage (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0257] The processor 1401 implements any of the fault detection methods described in the above embodiments by reading and executing computer program instructions stored in the memory 1402.

[0258] In one example, the computer device may also include a communication interface 14014 and a bus 1410. Wherein, as... Figure 14 As shown, the processor 1401, memory 1402, and communication interface 1403 are connected through bus 1410 and complete communication with each other.

[0259] The communication interface 1403 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0260] Bus 1410 includes hardware, software, or both, that couples components of a flow control device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard System (ETSA) bus, a Front Side Bus (FSB), an HyperTransport (HT) interconnect, an Industry Standard System (TSA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel System (MCA) bus, a Peripheral Component Interconnect (PCT) bus, a PCT-Express (PCT-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 1410 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.

[0261] The data processing device can execute the fault detection method in the embodiments of this application, thereby achieving a combination Figures 1 to 14 The fault detection method and apparatus described.

[0262] Furthermore, in conjunction with the fault detection methods in the above embodiments, this application embodiment can provide a computer-readable storage medium for implementation. This computer-readable storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the fault detection methods in the above embodiments.

[0263] 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.

[0264] The functional blocks shown in the above 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 (ASTCs), 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 networks such as the Internet, intranets, etc.

[0265] 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.

[0266] The above are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

[0267] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and not to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and they should all be covered within the scope of the claims and specification of this application. In particular, as long as there is no structural conflict, the various technical features mentioned in the embodiments can be combined in any way. 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 fault detection method, characterized in that, Applications in battery management systems include: Obtain N types of detection data representing the battery state under vehicle operating conditions within a first time period, where N is a positive integer; Based on M preset fault influencing factors, the fluctuation data of each type of detection data is determined, wherein the fluctuation data characterizes the degree of deviation of each detection value in each type of detection data from the preset center value, and M is an integer greater than 1; Based on the fluctuation data of each type of detection data, the fault detection threshold of the battery is determined; Based on the battery's detection data and the fault detection threshold during the second time period, the battery's fault detection information is determined.

2. The method according to claim 1, characterized in that, The M fault influencing factors may include at least one of the following: battery operating status, battery operating environment, and battery wear level; the step of determining the fluctuation data of each type of detection data based on the preset M fault influencing factors includes: Based on each of the fault influencing factors, the N types of detection data are divided to obtain at least one type of detection data under each of the fault influencing factors in the first time period; By using a statistical algorithm, at least one type of detection data under each of the aforementioned fault influencing factors is statistically calculated to obtain the statistical value of each type of detection data under each of the aforementioned fault influencing factors. The statistical value of each type of detection data under each of the aforementioned fault influencing factors is determined as the fluctuation data of each type of detection data.

3. The method according to claim 2, characterized in that, Before obtaining the statistical value of each type of detection data under each fault influencing factor by performing statistical calculations on at least one type of detection data using a statistical algorithm, the method further includes: The Kalman filter algorithm is used to denoise at least one type of detection data under each of the fault influencing factors in the first time period to obtain the denoised detection data of the at least one type of detection data. The noise value in the denoised detection data of the at least one type of detection data is within the preset Gaussian white noise range. The step involves using a statistical algorithm to perform statistical calculations on at least one type of detection data under each of the aforementioned fault influencing factors, obtaining statistical values ​​for each type of detection data under each of the aforementioned fault influencing factors, including: By using a statistical algorithm, statistical calculations are performed on the denoised detection data of at least one type of detection data to obtain the statistical value of each type of detection data under each of the fault influencing factors.

4. The method according to any one of claims 1 to 3, characterized in that, M is an integer greater than 1; determining the battery fault detection threshold based on the fluctuation data of each type of detection data includes: Based on the fluctuation data of each type of detection data, determine the fluctuation fault threshold of each type of detection data under each of the fault influencing factors; The fault detection threshold of the battery is determined based on the fluctuating fault threshold under each of the M fault influencing factors.

5. The method according to any one of claims 1 to 4, characterized in that, The step of determining the fluctuation fault threshold for each type of detection data under each fault influencing factor based on the fluctuation data of each type of detection data includes: Based on the weight of each fault influencing factor, the fluctuation data of each type of detection data under each fault influencing factor is weighted and calculated to obtain the fluctuation fault threshold of each type of detection data under each fault influencing factor.

6. The method according to any one of claims 1 to 5, characterized in that, The step of determining the battery's fault detection threshold based on the fluctuating fault threshold under each of the M fault influencing factors includes: Based on each of the fault influencing factors, obtain the weight of each of the fault influencing factors; Based on the weight of each fault influencing factor, the fluctuating fault threshold under each fault influencing factor is weighted and summed to obtain the fault detection threshold of the battery.

7. The method according to any one of claims 1 to 6, characterized in that, The time in the second time period is later than the time in the first time period, and the fault detection information includes first information for characterizing the battery fault; The determination of battery fault detection information based on battery detection data within the second time period and the fault detection threshold includes: The detection values ​​in the battery detection data during the second time period are matched with the fault detection threshold to obtain a matching result; If the matching result indicates that the detected value is greater than the fault detection threshold, the first information is determined.

8. The method according to any one of claims 1 to 6, characterized in that, The method further includes: When the fault detection information includes first information characterizing the battery fault, the first information is sent to the host computer of the battery management system through the communication module of the battery management system to issue a fault alarm to the user.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: Obtain a judgment result based on the fault detection threshold of the battery to determine whether the battery has a fault; Based on the judgment results and reference judgment results, the false alarm rate or false alarm rate of the battery management system for detecting battery faults is determined. If the false alarm rate is greater than or equal to a first preset threshold, or the false negative rate is greater than or equal to a second preset threshold, the fault detection threshold of the battery is updated.

10. The method according to any one of claims 1-9, characterized in that, The updating of the battery fault detection threshold includes: When the fault detection information includes first information characterizing the battery fault, the fault location is determined using a fault propagation model. Based on the fault detection data associated with the fault location, determine the cause of the fault at the fault location; Based on the cause of the fault, the fault detection threshold of the fault detection data is adjusted to obtain the adjusted fault detection threshold of the fault detection data. The fault detection threshold is adjusted based on the fault detection data, and the fault detection threshold of the battery is updated.

11. The method according to any one of claims 1-10, characterized in that, The process of determining the fault location using a fault propagation model includes: By using a fault propagation model, the fault source system component that is dependent on the fault is determined based on the dependency relationship between at least two system components in the battery management system. The location of the fault is determined based on the location of the fault-source system components that are dependent on the fault.

12. The method according to any one of claims 1-11, characterized in that, Determining the cause of the fault at the fault location based on fault detection data associated with the fault location includes: Based on the correlation analysis information between the reference fault detection data and the reference fault cause, the fault cause corresponding to the fault detection data is determined.

13. The method according to any one of claims 1-12, wherein the method is characterized in that, The method further includes: Obtain N types of detection data characterizing the battery state under vehicle operating conditions during the third time period; Based on the N types of detection data characterizing the battery state under vehicle operation conditions during the third time period, the fault detection threshold of the battery during the third time period is determined. If the battery fault detection threshold during the third time period is different from the battery fault detection threshold during the first time period, the battery fault detection information is determined based on the battery detection data during the second time period and the fault detection threshold during the third time period; wherein the third time period is later than the first time period but earlier than the second time period.

14. A battery management system, characterized in that, include: The acquisition module is used to acquire N types of detection data representing the state of the battery under vehicle operation during a first time period, where N is a positive integer; The determination module is used to determine the fluctuation data of each type of detection data according to M preset fault influencing factors, wherein the fluctuation data represents the degree of deviation of each detection value in each type of detection data from the preset center value, and M is an integer greater than 1; The determining module is further configured to determine the fault detection threshold of the battery based on the fluctuation data of each type of detection data; The determining module is further configured to determine the fault detection information of the battery based on the detection data of the battery within the second time period and the fault detection threshold.

15. A computer device, characterized in that, include: The processor and the memory storing computer program instructions, wherein the processor, when executing the computer program instructions, implements the steps of the fault detection method as described in any one of claims 1-13.

16. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the steps of the fault detection method as described in any one of claims 1-13.

Images