Fault analysis method and device of storage battery pack, electronic equipment and storage medium

Abstract

The invention relates to the technical field of power systems, and discloses a fault analysis method and device for a storage battery pack, electronic equipment and a storage medium, and the method comprises the steps: collecting the operation data of the storage battery pack in real time; obtaining alarm information of the monitoring device, and extracting a fault type identifier and an associated fault position number in the alarm information; based on the operation data and the alarm information, an initial fault feature set of the storage battery pack is generated, and the initial fault feature set comprises an abnormal parameter type, an abnormal storage battery distribution position and a system association state; and according to the initial fault feature set, fault reason and position analysis is carried out through a preset multi-level fault discrimination logic tree, and a fault analysis result is generated. According to the invention, accurate positioning and analysis of the storage battery pack fault can be realized, and the accuracy and efficiency of fault identification are improved.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a method, device, electronic device, and storage medium for analyzing a battery pack fault. Background Art

[0002] DC system batteries play a vital role in substation operation. As a core component of the substation's DC system, they quickly come into operation in the event of AC power failures or anomalies, providing reliable DC power to critical substation equipment such as relay protection devices, automatic control devices, and communications equipment. This ensures the continued stable operation of these devices, safeguarding the safe and stable control of the substation and preventing system failures and accidents from escalating due to power outages. Furthermore, batteries maintain DC system voltage stability during grid fluctuations or momentary power outages, preventing damage to sensitive electronic equipment. Their independent power supply makes them immune to external grid interference, providing a solid line of defense for substation power supply.

[0003] However, current DC system battery monitoring technology has several drawbacks. While existing technology can monitor basic battery parameters, fault identification and location are imprecise, and alarm messages are often vague, requiring maintenance personnel to expend considerable time and effort to further analyze and troubleshoot the actual cause of the fault. This not only requires high-level technical expertise from maintenance personnel, but also easily leads to inaccurate fault reporting, inefficient communication and resolution, and inefficient subsequent maintenance, even leading to wasted resources. In other words, existing substation DC system battery monitoring technology suffers from insufficient accuracy and inefficiency in fault identification.

[0004] The preceding description is intended to provide general background information and does not necessarily constitute prior art. Summary of the Invention

[0005] The embodiments of the present application provide a battery pack fault analysis method, device, electronic device, and storage medium, which can accurately locate and analyze battery pack faults, improve the accuracy and efficiency of fault identification, effectively avoid processing delays and resource waste caused by inaccurate fault identification, and provide reliable protection for the stable operation of battery packs in substation DC systems.

[0006] In a first aspect, an embodiment of the present application provides a battery pack fault analysis method, comprising:

[0007] Real-time collection of battery pack operating data, including voltage parameters, current parameters, temperature parameters of individual batteries, as well as DC system bus voltage status, AC system status, and charger operating mode;

[0008] Obtaining alarm information from a monitoring device, and extracting a fault type identifier and an associated fault location number from the alarm information;

[0009] generating an initial fault feature set for the battery pack based on the operating data and the alarm information, the initial fault feature set including abnormal parameter type, abnormal battery distribution location, and system association status;

[0010] According to the initial fault feature set, a fault cause and location analysis is performed through a preset multi-level fault discrimination logic tree to generate a fault analysis result.

[0011] Optionally, in some embodiments of the present application, the real-time collection of operating data of the battery pack includes:

[0012] The voltage value of each single battery is collected in real time through the voltage sensor, and the charge and discharge current of the battery pack is monitored through the current sensor;

[0013] The surface temperature of each single battery is acquired using a temperature sensor, and the bus voltage of the DC system is acquired using a bus voltage sensor.

[0014] The power supply status of the AC system and the operating mode of the charger are synchronously collected, and the operating mode includes an equalizing charge state, a floating charge state or a discharging state.

[0015] Optionally, in some embodiments of the present application, generating an initial fault feature set of the battery pack based on the operating data and the alarm information includes:

[0016] Comparing the voltage parameters, current parameters, and temperature parameters of the single battery with preset normal operating thresholds, and marking the abnormal parameter type of the abnormal battery according to the obtained comparison results, wherein the abnormal parameter type includes voltage overvoltage, voltage undervoltage, current sudden change, or temperature exceeding a limit;

[0017] Determining the physical location number and distribution characteristics of the abnormal battery according to the fault location number in the alarm information;

[0018] Based on the DC system bus voltage state, AC system state and charger operation mode, a system-level associated state tag is generated.

[0019] Optionally, in some embodiments of the present application, the multi-level fault judgment logic tree includes the following judgment logic:

[0020] If there is a single battery with abnormal voltage and it is not the first or last battery, it is determined to be a single battery failure;

[0021] If the voltage of the head-end battery or the terminal battery is abnormal, it is determined to be a single cell fault or a signal line break in combination with the polarity connection of the signal acquisition line;

[0022] If the voltages of two adjacent batteries are abnormal and the voltage at the battery pack terminal is normal, it is determined that the signal line is broken, and the position of the break is located based on the physical connection relationship of the signal acquisition line;

[0023] If the voltages of multiple non-adjacent batteries are abnormal and the DC bus voltage is abnormal, it is determined that there is a charger failure or AC power interruption based on the AC system status.

[0024] Optionally, in some embodiments of the present application, the multi-level fault judgment logic tree further includes the following judgment logic:

[0025] If the temperature of the single battery rises abnormally but the voltage is normal, it is determined that the signal collector is faulty;

[0026] If the temperature of a single battery cell rises abnormally and the voltage is abnormal, it is determined to be a battery failure.

[0027] Optionally, in some embodiments of the present application, the signal acquisition line polarity connection method includes:

[0028] Identifying a connection mode of the battery pack, wherein the connection mode includes a positive polarity connection mode or a negative polarity connection mode;

[0029] If the connection method is positive polarity connection, the voltage of the first-end battery is collected separately by the first signal line, and the voltage of the remaining batteries is collected by the adjacent positive signal lines;

[0030] If the connection method is negative polarity connection, the voltage of the first-end battery is collected separately by the second signal line, and the voltage of the remaining batteries is collected by the adjacent negative signal line;

[0031] Corrected the logic for associating signal line breakage with battery failure based on the connection type.

[0032] Optionally, in some embodiments of the present application, the method further includes:

[0033] Establish a historical fault case library to record fault characteristics, analysis results and treatment effects;

[0034] Using a machine learning algorithm and the historical fault case library to train a multi-level fault discrimination logic tree, adjusting branch weights, discrimination thresholds, and priorities of the multi-level fault discrimination logic tree, and obtaining an optimized multi-level fault discrimination logic tree;

[0035] The optimized multi-level fault discrimination logic tree is deployed in real time to the online analysis system to analyze the cause and location of the fault of the battery pack based on the optimized multi-level fault discrimination logic tree.

[0036] In a second aspect, an embodiment of the present application provides a battery pack fault analysis device, comprising:

[0037] A data acquisition module is used to collect real-time operating data of the battery pack, including voltage parameters, current parameters, and temperature parameters of the individual batteries, as well as the DC system bus voltage status, AC system status, and charger operating mode;

[0038] An alarm extraction module is used to obtain alarm information from the monitoring device and extract the fault type identifier and the associated fault location number in the alarm information;

[0039] a fault characteristic module, configured to generate an initial fault characteristic set of the battery pack based on the operating data and the alarm information, wherein the initial fault characteristic set includes abnormal parameter type, abnormal battery distribution location, and system association status;

[0040] The fault analysis module is used to analyze the cause and location of the fault according to the initial fault feature set through a preset multi-level fault judgment logic tree to generate a fault analysis result.

[0041] In a third aspect, an embodiment of the present application further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the battery pack fault analysis method as described in the first aspect are implemented.

[0042] In a fourth aspect, an embodiment of the present application further provides a readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the battery pack fault analysis method as described in the first aspect.

[0043] The present application provides a fault analysis method, device, electronic device and storage medium for a battery pack. First, operating data of the battery pack is collected in real time. The operating data includes voltage parameters, current parameters, temperature parameters of individual batteries, as well as the DC system bus voltage status, AC system status and charger operating mode. Then, alarm information from a monitoring device is obtained, and the fault type identifier and associated fault location number in the alarm information are extracted. Then, based on the operating data and the alarm information, an initial fault feature set of the battery pack is generated. The initial fault feature set includes abnormal parameter types, abnormal battery distribution locations and system-related status. Finally, based on the initial fault feature set, a preset multi-level fault discrimination logic tree is used to perform fault cause and location analysis to generate a fault analysis result. The battery pack fault analysis solution provided in this application generates an initial fault feature set by comprehensively collecting various operating data and monitoring alarm information of the battery pack, and uses a multi-level fault judgment logic tree for analysis. It can more comprehensively and accurately determine the cause and location of the fault, avoiding the misjudgment and missed judgment of faults caused by single data and vague alarm information in the existing technology, thereby improving the efficiency and accuracy of fault judgment, avoiding the processing delays and resource waste caused by inaccurate fault identification in the existing technology, and effectively improving the maintenance efficiency and reliability of the battery pack of the substation DC system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 This is an application environment diagram of the battery pack fault analysis method provided by an embodiment of the present application;

[0046] Figure 2 1 is a flow chart of a battery pack fault analysis method provided in an embodiment of the present application;

[0047] Figure 3 This is another flowchart of the battery pack fault analysis method provided by an embodiment of the present application;

[0048] Figure 4 This is a schematic diagram of the structure of a battery pack fault analysis device provided in an embodiment of the present application;

[0049] Figure 5 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of systems and methods consistent with aspects of the present application, as detailed in the appended claims.

[0051] It should be noted that, in this document, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive descriptions such as inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0052] It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0053] In the subsequent description, the use of suffixes such as "module", "component" or "unit" to represent elements is only for the purpose of facilitating the description of the present application and has no specific meaning. Therefore, "module", "component" or "unit" can be used interchangeably.

[0054] At present, the typical dual-set DC system commonly used in substations with voltage levels of 110kV and above has corresponding monitoring points at basic electrical nodes to monitor the system operation status. However, the monitoring system only provides a rough information analysis and intuitive judgment of the monitoring points, and cannot accurately reflect fault information and accurately locate the fault. For example, if the monitoring system alarm displays "single battery No. X is over / under voltage", the actual fault may not be a fault of the battery itself. The operation and maintenance personnel need to further determine the true cause of the fault based on other information. This places higher requirements on the skill level of patrol personnel and maintenance personnel. At the same time, it may also cause inaccurate fault reporting and the need for maintenance personnel to re-locate the fault after arriving at the site, resulting in inefficiency in communication and problem handling between the two parties, and repeated inspections cause a certain amount of resource waste.

[0055] In order to solve the above technical problems, the embodiments of the present application provide a battery pack fault analysis method, device, electronic device and storage medium, which can accurately locate and analyze battery pack faults, improve the accuracy and efficiency of fault identification, effectively avoid processing delays and resource waste caused by inaccurate fault identification, and provide reliable protection for the stable operation of the battery pack of the substation DC system.

[0056] Figure 1 FIG. 1 is an application environment diagram of a battery pack failure analysis method in one embodiment. Figure 1 The battery pack fault analysis method is applied to a battery pack fault analysis system. The battery pack fault analysis system includes a terminal 110 and a server 120. Terminal 110 and server 120 are connected via a network. Terminal 110 can be a desktop terminal or a mobile terminal. The mobile terminal can be at least one of a mobile phone, a tablet computer, a laptop computer, etc. Server 120 can be implemented as a standalone server or a server cluster consisting of multiple servers. Server 120 is used to collect real-time operating data of the battery pack. The operating data includes voltage parameters, current parameters, and temperature parameters of individual batteries, as well as the DC system bus voltage status, AC system status, and charger operating mode. Server 120 also acquires alarm information from monitoring devices and extracts the fault type identifier and associated fault location number from the alarm information. Based on the operating data and alarm information, an initial fault feature set for the battery pack is generated. The initial fault feature set includes the abnormal parameter type, the distribution location of abnormal batteries, and the system-related status. Based on the initial fault feature set, a fault cause and location analysis is performed using a preset multi-level fault judgment logic tree to generate a fault analysis result.

[0057] See also Figure 2 , Figure 2 1 is a flow chart of a battery pack fault analysis method provided in one embodiment of the present application. This embodiment mainly uses the battery pack fault analysis method applied to a computer device as an example for illustration. The battery pack fault analysis method provided in one embodiment of the present application may specifically include the following steps:

[0058] S1. Real-time collection of battery pack operating data, including single battery voltage parameters, current parameters, temperature parameters, as well as the DC system bus voltage status, AC system status and charger operating mode;

[0059] Specifically, step S1 primarily involves collecting real-time operating data from the battery pack. This can be accomplished, for example, by installing sensors at key locations within the battery pack, such as voltage sensors on each individual battery cell, current sensors in the battery pack's charge and discharge circuits, temperature sensors on the surface of each individual battery cell, and bus voltage sensors on the DC system busbars. These sensors are then connected to the monitoring interfaces of the AC system and charger to obtain real-time information on the AC system's power supply status and the charger's operating mode. Furthermore, high-precision, high-reliability sensors can be used to ensure the accuracy and stability of the collected data. Furthermore, to achieve real-time data transmission, wired or wireless communication technologies can be used to transmit the data collected by the sensors to a data processing center. For example, 4G / 5G communication modules can be used for long-distance wireless data transmission, or industrial Ethernet can be used for high-speed, stable data transmission.

[0060] S2 obtains the alarm information of the monitoring device, extracts the fault type identification and the associated fault location number in the alarm information;

[0061] Specifically, for step S2, communication is carried out with the monitoring system of the substation to receive the alarm information issued by it. The alarm information usually contains a fault type identifier (such as "single battery overvoltage", "single battery undervoltage", etc.) and an associated fault location number (such as "battery X"). By parsing the alarm information, these key information are extracted. By developing a special alarm information parsing module, it is possible to be compatible with the alarm information formats sent by monitoring devices of different manufacturers and models. In addition, in order to improve the processing efficiency of the alarm information, real-time data processing technology can be used to quickly parse and extract the alarm information.

[0062] S3 based on the operating data and alarm information, generates the initial fault feature set of the battery pack, the initial fault feature set includes abnormal parameter type, abnormal battery distribution location and system association status;

[0063] Specifically, in step S3, the collected voltage, current, and temperature parameters of the individual batteries are compared with preset normal operating thresholds, and the abnormal parameter types of the abnormal batteries are marked. Simultaneously, the physical location number and distribution characteristics of the abnormal batteries are determined based on the fault location number in the alarm information. Furthermore, system-level associated status labels are generated based on the DC system bus voltage status, AC system status, and charger operating mode. Data fusion technology can also be used to integrate different types of operating data and alarm information to improve the accuracy and reliability of the initial fault feature set. Furthermore, big data analysis techniques can be used to mine and analyze historical fault data to optimize the setting of normal operating thresholds.

[0064] S4. Based on the initial fault feature set, the fault cause and location are analyzed through a preset multi-level fault discrimination logic tree to generate a fault analysis result;

[0065] Specifically, in step S4, a step-by-step analysis is performed according to a preset multi-level fault discrimination logic tree based on the abnormal parameter types, abnormal battery distribution locations, and system-related status in the initial fault feature set. For example, a determination is first made as to whether a single battery voltage abnormality exists and is not located at the first or last battery. If so, a single battery fault is determined. If the voltage of the first or last battery is abnormal, the fault is determined to be a single battery fault or a broken signal line, based on the polarity of the signal acquisition line. Artificial intelligence techniques, such as decision tree algorithms in machine learning, can also be used to optimize and train the multi-level fault discrimination logic tree, improving the accuracy and adaptability of fault discrimination. Furthermore, to increase the efficiency of fault analysis, parallel computing techniques can be used to process multiple fault discrimination logics in parallel.

[0066] This embodiment comprehensively collects various operating data and monitoring alarm information from the battery pack to generate an initial set of fault characteristics, and uses a multi-level fault identification logic tree for analysis. This allows for a more comprehensive and accurate determination of the cause and location of the fault, avoiding the misjudgment and omission of faults caused by the single data and vague alarm information in the prior art, significantly improving the accuracy and efficiency of fault identification. Accurate fault location and cause analysis enable maintenance personnel to quickly take targeted measures to address the problem, reducing the time and effort spent on on-site troubleshooting, lowering maintenance costs and workload, and also reducing the risk of equipment damage and resource waste caused by improper fault handling. By promptly and accurately detecting and handling battery pack faults, the stable operation of the substation's DC system is guaranteed, ensuring that the battery pack can reliably provide DC power to key equipment in the event of an AC power supply failure or abnormality, enhancing the overall reliability of the substation, and having important significance for ensuring the stable operation and reliable power supply of the power system.

[0067] Optionally, in some embodiments, step S1 of “real-time collection of operating data of the battery pack” may specifically include:

[0068] S11 real-time acquisition of the voltage value of each single battery through the voltage sensor, and the current sensor monitors the charge and discharge current of the battery pack;

[0069] Specifically, high-precision voltage sensors installed on each battery cell monitor voltage changes in real time and transmit the data to a data processing center. Self-calibration voltage sensors can be used to ensure long-term monitoring accuracy. Wireless sensor network technology can also be utilized to reduce wiring costs and complexity. Current sensors are installed in the battery pack's charge and discharge circuits to monitor the magnitude and direction of current flowing through the pack. For example, Hall-effect current sensors can be used to achieve contactless current measurement, improving safety and reliability.

[0070] S12 uses a temperature sensor to obtain the surface temperature of each single battery, and collects the bus voltage of the DC system through the bus voltage sensor;

[0071] Specifically, a temperature sensor is installed on the surface of each battery cell to monitor temperature changes in real time. An infrared temperature sensor can be used for non-contact measurement of battery surface temperature, avoiding data errors caused by poor sensor contact. A bus voltage sensor is installed on the DC system busbar to monitor bus voltage stability in real time. The bus voltage sensor should have high insulation performance and anti-interference capabilities to ensure stable operation in strong electromagnetic environments.

[0072] S13 synchronously collects the power supply status of the AC system and the operating mode of the charger, the operating mode includes equalizing charge state, floating charge state or discharge state;

[0073] Specifically, by connecting to the communication interfaces of the AC system and charger, the system's power supply status (such as voltage and frequency) and the charger's operating mode (equalizing charge, floating charge, or discharging state) can be obtained in real time. Furthermore, the intelligent monitoring module can monitor the status of the AC system and charger in real time, and transmit data via communication protocols (such as Modbus and CAN bus).

[0074] This embodiment implements comprehensive monitoring of the operating status of the battery pack and its related systems through the deployment of multiple sensors, ensuring data integrity and accuracy. The application of high-precision sensors and real-time data transmission technology enables the system to promptly capture subtle changes in the battery pack, providing the possibility of early warning of faults.

[0075] Optionally, in some embodiments, step S3 of “generating an initial fault feature set of the battery pack based on the operating data and the alarm information” may specifically include:

[0076] S31. The voltage parameters, current parameters, and temperature parameters of the single battery are compared with the preset normal operating thresholds. The abnormal parameter type of the abnormal battery is marked according to the comparison results. The abnormal parameter types include overvoltage, undervoltage, current mutation or temperature limit;

[0077] Specifically, the system has built-in threshold ranges for the normal operation of individual batteries, including the normal voltage range (such as the specific numerical limits for overvoltage and undervoltage), the current variation range, and the safe temperature range. The voltage, current, and temperature data collected in real time for each individual battery are compared against these preset thresholds. The thresholds can be flexibly adjusted and set based on factors such as battery model, age, and environmental conditions. At the same time, machine learning algorithms are used to automatically optimize and update thresholds based on historical operating data to better reflect actual operating conditions.

[0078] S32. According to the fault location number in the alarm information, determine the physical location number and distribution characteristics of the abnormal battery;

[0079] Specifically, if a single battery's voltage exceeds the preset overvoltage or undervoltage threshold, it is flagged as a voltage anomaly; if the current changes beyond the normal range, it is flagged as a current anomaly; and if the temperature exceeds the safe range, it is flagged as a temperature anomaly. Anomaly types can be categorized as overvoltage, undervoltage, sudden current change, or temperature overlimit. Different types of anomalies are identified using codes or tags to facilitate subsequent logical judgment and analysis. The time and duration of the anomaly are also recorded to provide data support for fault development trend analysis.

[0080] S33. Generate system-level associated status tags based on the DC system bus voltage status, AC system status, and charger operation mode;

[0081] Specifically, the alarm information issued by the monitoring device contains a fault location number, which corresponds to the physical location of the individual batteries in the battery pack. By analyzing the alarm information, it is determined which individual batteries have abnormalities and the distribution of these abnormal batteries in the battery pack is analyzed, such as whether they are concentrated in a certain area, distributed discretely, or have other specific distribution patterns. A physical location database of the battery pack is established to store the location information of each individual battery and associate it with the location number in the alarm information. At the same time, Geographic Information System (GIS) technology can be combined to visualize the layout of the battery pack and the distribution of abnormalities.

[0082] A system-level correlation status tag is generated by comprehensively considering factors such as the stability of the DC system bus voltage, the normality of the AC system power supply, and whether the charger is in equalizing, floating, or discharging mode. For example, "normal bus voltage, normal AC power supply, and charger in floating charging mode" corresponds to a normal operation correlation status tag; while "low bus voltage, AC power supply failure, and charger in discharging mode" corresponds to a fault status tag. Using a rule engine or state machine technology, the corresponding system-level correlation status tag is automatically matched and generated based on pre-set rules and logic. Furthermore, the system-level correlation status tag can be correlated with historical fault cases for analysis, uncovering potential relationships between system state changes and fault occurrences.

[0083] This embodiment achieves refined extraction and comprehensive description of battery pack fault characteristics by comparing operating data with thresholds, marking abnormal parameter types, determining the location and distribution characteristics of abnormal batteries, and generating system-level associated status labels. This provides accurate and rich information support for subsequent fault diagnosis, effectively improving the accuracy and efficiency of fault diagnosis, helping to quickly locate the cause and location of the fault, and taking targeted maintenance measures in a timely manner to ensure the stable operation of the substation DC system.

[0084] Optionally, in some embodiments, the multi-level fault judgment logic tree in step S4 includes the following judgment logic:

[0085] If there is a single battery with abnormal voltage and it is not the first or last battery, it is determined to be a single battery failure;

[0086] Specifically, if monitoring data indicates that only a single battery voltage, not at the head or tail, is outside the normal range, while other relevant parameters (such as current and temperature) show no significant anomalies and the rest of the system (such as bus voltage and AC system) is operating normally, the battery itself can be directly identified as faulty. Combined with information such as the battery's age and charge and discharge history, the cause of the battery failure can be further analyzed, such as whether it is caused by long-term overcharge, overdischarge, internal short circuit, or other factors, and its remaining service life can be predicted.

[0087] If the voltage of the head-end battery or the terminal battery is abnormal, it is determined to be a single cell fault or a signal line break in combination with the polarity connection of the signal acquisition line;

[0088] Specifically, given the unique wiring configuration of the head-end or tail-end batteries, abnormal voltage could indicate a fault in the battery itself or a disconnection in the signal acquisition line. These two situations can be distinguished by analyzing the polarity of the signal acquisition line and combining it with voltage data from adjacent batteries. A health monitoring mechanism for the signal acquisition line is established, monitoring parameters such as insulation resistance and contact status in real time to provide early warning of potential disconnection risks.

[0089] If the voltages of two adjacent batteries are abnormal and the voltage at the battery pack terminal is normal, it is determined that the signal line is broken, and the position of the break is located based on the physical connection relationship of the signal acquisition line;

[0090] Specifically, abnormal voltages between two adjacent batteries, while normal voltage across the entire battery pack, indicate a fault not with the batteries themselves but rather a break in the signal acquisition line connecting the two batteries. Based on the specific connection path of the signal acquisition line, the physical location of the break can be precisely determined. The redundant signal acquisition circuit automatically switches to a backup line if the primary line breaks, and records the break location for easy repair.

[0091] If the voltages of multiple non-adjacent batteries are abnormal and the DC bus voltage is abnormal, it is determined that there is a charger failure or AC power interruption based on the AC system status;

[0092] Specifically, when multiple non-adjacent battery voltages and the DC bus voltage are abnormal, the problem may lie with the charger or the AC power supply. Further analysis of the AC system's power supply status, such as voltage and frequency, can be performed to determine if the fault lies with the charger or the AC power supply. Backup power supplies or uninterruptible power supplies (UPS) are installed at key points between the charger and AC power supply to ensure temporary system operation in the event of a fault. Detailed parameter records at the time of the fault are also provided to assist in fault analysis.

[0093] This embodiment performs detailed analysis and logical judgment of voltage anomalies under different fault scenarios, combined with the physical connection relationship of the signal acquisition lines and the overall operating status of the system, to accurately identify the cause and location of battery pack and related system faults, effectively improving the accuracy and efficiency of fault diagnosis and ensuring the stable and reliable operation of the substation DC system.

[0094] Optionally, in some embodiments, the multi-level fault judgment logic tree in step S4 further includes the following judgment logic:

[0095] If the temperature of the single battery rises abnormally but the voltage is normal, it is determined that the signal collector is faulty;

[0096] Specifically, if monitoring data indicates an abnormally high temperature for a single battery cell while its voltage parameters remain within normal range, the fault is likely with the signal collector. This could be due to a malfunctioning temperature sensor or a problem with the signal transmission line. A backup signal collector or redundant sensor design can be implemented to automatically switch to the backup device when the primary signal collector fails, ensuring data continuity and reliability. Furthermore, data fusion technology can be used to comprehensively analyze data from multiple sensors to improve the accuracy of identifying signal collector failures.

[0097] If the temperature of a single battery rises abnormally and the voltage is abnormal, it is determined to be a battery failure;

[0098] Specifically, if both the temperature and voltage of a single battery cell are abnormal, this typically indicates a fault within the battery itself. This could be due to an abnormal chemical reaction within the battery, a short circuit, or other internal failure. By combining information such as battery usage history and charge and discharge records, machine learning algorithms can predict and assess the battery's health status, providing early warning of potential failure risks. Furthermore, intelligent diagnostic systems can be used to further analyze the cause of the battery failure and provide detailed repair recommendations.

[0099] This embodiment can effectively distinguish between signal collector failure and battery failure by analyzing the temperature and voltage parameters of single batteries, which not only improves the accuracy of fault diagnosis, but also reduces maintenance costs and system downtime, ensuring the reliable operation of the substation DC system.

[0100] In a specific embodiment, the following fault identification methods are included but not limited to:

[0101] 1. "DC system fault" & "single battery voltage abnormality" & "not the first or last two batteries" to determine "single battery fault";

[0102] 2. "DC system fault" & "single battery voltage abnormality" & "first / last battery voltage abnormality" to identify "single battery fault" / "first or last battery signal line disconnection";

[0103] 3. If "two batteries have abnormal voltages" & "faulty batteries are adjacent" & "battery terminal voltage is normal", it is determined that "the signal line of battery X1 or X2 is broken". The specific number of cells is determined based on the polarity of the connecting wires.

[0104] 4. "Two batteries have abnormal voltages" & "faulty batteries are not adjacent", judging "battery X1 and battery X2 are faulty";

[0105] 5. "Single battery over / under voltage" & "Multiple consecutive battery voltages are abnormal or absent" & "Faulty batteries are adjacent" & "Battery bank terminal voltage is normal" & "Module failure" to identify "Battery No. X signal collector failure" / "Battery failure";

[0106] 6. "Single battery over / under voltage" & "Multiple battery voltages abnormal / high" & "Battery terminal voltage high" & "DC bus voltage abnormal" & "System charging mode - equalization charging" to determine "normal system equalization charging status";

[0107] 7. "Single battery over / under voltage" & "all battery voltages are abnormal or absent" & "DC system bus voltage is abnormal or absent" & "AC data is abnormal or absent" & "the system is actually operating normally" & "module failure" to determine "system DC / AC acquisition module failure";

[0108] 8. "Single battery over / under voltage" & "all battery voltages are abnormal or absent" & "DC system bus voltage is abnormal or absent" & "the system is actually operating normally" & "communication abnormality" to identify "system communication failure";

[0109] 9. "Single battery over / undervoltage" & "All battery voltages abnormal (low)" & "DC system bus voltage abnormal (low)" & "AC system fault" & "Charger (rectifier module) fault" can be identified as "AC fault, battery pack discharge";

[0110] 10. "DC system failure" & "Battery X overtemperature" & "Module failure" & "Battery X voltage is normal" can be used to determine "Battery signal collector failure";

[0111] 11. "DC system failure" & "Battery X overtemperature" & "Battery X voltage abnormality" are identified as "Battery X failure".

[0112] Optionally, in some embodiments, the signal acquisition line polarity connection method in step S4 may specifically include the following steps:

[0113] Identify the connection method of the battery pack, including positive polarity connection or negative polarity connection;

[0114] Specifically, it determines whether the battery pack is connected with positive or negative polarity. This can be achieved by monitoring the connection position and polarity of the signal acquisition line. An automatic recognition algorithm has been developed to automatically determine the connection type by analyzing the voltage distribution and connection relationship of the signal acquisition line, reducing manual configuration steps and improving the intelligence and flexibility of the system.

[0115] If the connection method is positive polarity connection, the voltage of the first-end battery is collected separately by the first signal line, and the voltage of the remaining batteries is collected by the adjacent positive signal lines;

[0116] Specifically, in the positive polarity connection method, the voltage of the first battery (such as battery 1) is collected separately via its positive signal line, while the voltages of subsequent batteries are collected via adjacent positive signal lines. A dedicated signal acquisition circuit is designed to optimize the layout and connection of signal acquisition lines to reduce signal interference and improve acquisition accuracy.

[0117] If the connection method is negative polarity, the voltage of the first-end battery is collected separately by the second signal line, and the voltage of the remaining batteries is collected by the adjacent negative signal line;

[0118] Specifically, in the negative polarity connection method, the voltage of the first battery (such as battery No. 1) is collected separately via its negative signal line, and the voltages of subsequent batteries are collected via adjacent negative signal lines. Adaptive signal acquisition technology automatically adjusts the acquisition method based on the connection type, ensuring accurate voltage data collection in all connection methods.

[0119] Corrected the logic of associating signal line disconnection with battery failure according to the connection type;

[0120] Specifically, the system adjusts the logical relationship between signal line breaks and battery faults based on the identified connection type. For example, if the broken area matches the fault location determined by the logic tree, a high-confidence repair instruction is generated. If not, manual review is triggered and the logic tree's judgment rules are revised. Using machine learning algorithms, historical fault data is analyzed to continuously optimize the logic tree's judgment rules, improving the system's ability to identify faults under different connection methods.

[0121] This embodiment automatically identifies the connection method of the battery pack and adjusts the signal acquisition method and fault association logic according to different connection methods. This effectively improves the accuracy of fault location, reduces the risk of misjudgment due to differences in connection methods, and provides maintenance personnel with more reliable fault information, thereby ensuring the stable operation of the substation DC system.

[0122] Optionally, in some embodiments, the battery pack fault analysis method provided in this embodiment may further include:

[0123] Establish a historical fault case library to record fault characteristics, analysis results and treatment effects;

[0124] Specifically, a historical fault case library is created to store past failure cases. Each case includes detailed characteristics of the failure (such as abnormalities in parameters such as voltage, current, and temperature), system-generated analysis results (such as the determined cause and location of the failure), and the actual remediation measures taken and their effects (such as replacing a battery or repairing a signal line). Blockchain technology is used to ensure the data security and immutability of the historical fault case library. Distributed storage and encryption technologies ensure data integrity and reliability, facilitating future queries and analysis.

[0125] The multi-level fault discrimination logic tree is trained using a machine learning algorithm and a historical fault case library. The branch weights, discrimination thresholds, and priorities of the multi-level fault discrimination logic tree are adjusted to obtain an optimized multi-level fault discrimination logic tree.

[0126] Specifically, machine learning algorithms such as decision trees, random forests, or neural networks are employed, using data from a historical fault case library as a training set to train a pre-set, multi-level fault discrimination logic tree. By adjusting the branch weights, discrimination thresholds, and priorities of the logic tree, its ability to identify fault features and classification accuracy can be optimized. For example, supervised learning methods can be employed, using known fault features and corresponding correct analysis results as input and output, and the model trained to learn the mapping relationship. Deep learning techniques are introduced to build more complex neural network models to process large amounts of historical fault data and uncover deeper fault characteristics and patterns. Furthermore, online learning mechanisms are employed to enable real-time model updates and optimizations to adapt to changes in system operating conditions and new fault types.

[0127] The optimized multi-level fault discrimination logic tree is deployed in real time to the online analysis system to analyze the cause and location of the battery pack fault based on the optimized multi-level fault discrimination logic tree;

[0128] Specifically, adjustments are made to the various branches of the logic tree based on the training results of the machine learning algorithm. For example, the weights of branches with fault characteristics that frequently appear in historical cases are increased to improve their priority in fault identification. At the same time, the identification threshold is optimized to make it more consistent with the actual fault distribution. This allows the logic tree to more accurately match new fault characteristics and improve the accuracy of fault analysis. Visualization tools are developed to intuitively display the logic tree's structural adjustment process and effect evaluation. Through a graphical interface, engineers can easily observe the changes in the logic tree's branches, weight distribution, and threshold settings, as well as verify and adjust the training results. At the same time, an automated testing framework is used to conduct comprehensive performance testing and verification of the optimized logic tree to ensure its reliability and stability in various fault scenarios.

[0129] The optimized multi-level fault discrimination logic tree is deployed in real time to an online analysis system to analyze the cause and location of the fault of the battery pack based on the optimized multi-level fault discrimination logic tree;

[0130] The optimized logic tree model is integrated into the online analysis system, enabling it to receive and process operating data and alarm information from the battery pack in real time. When a new fault occurs, the system uses the optimized logic tree to quickly analyze the cause and location of the fault and generate corresponding fault analysis results. The online analysis system is deployed using containerization technologies (such as Docker and Kubernetes) to improve the system's scalability and fault tolerance. By dynamically scaling container instances, the system's processing power is automatically adjusted based on real-time data traffic, ensuring stable system operation under high concurrency and large data volumes. Furthermore, a microservices architecture is used to decouple the system's different functional modules (such as data acquisition, fault analysis, and result presentation), facilitating system maintenance and upgrades.

[0131] This embodiment effectively improves the accuracy and adaptability of fault analysis by establishing a historical fault case library and incorporating machine learning algorithms to train and optimize a multi-level fault diagnosis logic tree. The optimized logic tree more accurately identifies and locates the cause and location of battery pack failures, reducing the risk of misdiagnosis and missed detections. Deployed in real time to the online analysis system, it enables rapid and intelligent analysis of battery pack failures, improving overall system reliability and maintenance efficiency.

[0132] Optionally, in some embodiments, the battery pack fault analysis method provided in this embodiment may further include:

[0133] If the specific fault cause is a single battery failure, an instruction to replace the battery with the specified number is generated;

[0134] Specifically, once the system identifies a single battery failure, it automatically identifies the faulty battery number and sends a replacement instruction to the maintenance terminal. Using AR technology, maintenance personnel are provided with the precise location of the faulty battery and replacement instructions, improving replacement efficiency.

[0135] If the specific fault cause is a broken signal acquisition line, an instruction to check and repair the corresponding signal acquisition line is generated;

[0136] Specifically, when the system determines a signal acquisition line is broken, it generates instructions containing the break's location and repair requirements. Combined with real-time monitoring data, it provides detailed guidance on repairing the break, including line routing and connection methods.

[0137] If the specific cause of the fault is a collector module failure, an instruction to replace the collector module is generated;

[0138] Specifically, after the system determines that the collector module is faulty, it generates a replacement instruction and sends it to the maintenance terminal. Developing a modular collector facilitates quick replacement and provides real-time operation guidance.

[0139] Output the above targeted maintenance instructions to the maintenance terminal;

[0140] Specifically, the generated maintenance instructions are sent to the terminal equipment of the maintenance personnel through the network or communication interface. A maintenance task management system is established to track the execution of instructions and provide execution feedback function.

[0141] This embodiment achieves automated and intelligent fault handling by automatically generating and outputting targeted maintenance instructions. Maintenance personnel can quickly obtain fault handling solutions, reducing troubleshooting and processing time, improving efficiency, reducing difficulty and risks, and ensuring the stable operation of the substation DC system.

[0142] Optionally, in some embodiments, the battery pack fault analysis method provided in this embodiment may further include:

[0143] During the fault location analysis process, cross-verify the telemetry data collected by redundant sensors to eliminate single-point collection errors;

[0144] Specifically, during fault location analysis, data collected by multiple sensors for the same parameter, such as the temperature measurements of the same battery from multiple temperature sensors, is compared to determine if any discrepancies exceed the allowable error range. If the data from a particular sensor significantly deviates from that of the others, it is determined that the sensor may be faulty or experiencing an acquisition error. Data fusion algorithms are used to perform weighted averaging or other fusion processing on the data from multiple sensors to improve data accuracy and reliability. Furthermore, a sensor self-diagnosis mechanism is established to monitor sensor operating status in real time, such as whether the supply voltage and signal output are normal, to promptly identify and flag potentially faulty sensors.

[0145] This embodiment introduces a cross-validation mechanism for redundant sensor data during the fault location analysis process, effectively eliminating single-point acquisition errors and improving the accuracy and reliability of fault location. This not only enhances the system's fault tolerance but also provides more reliable fault diagnosis support for the stable operation of the substation DC system.

[0146] In order to facilitate understanding of the battery pack fault analysis method provided in this application, as shown in Figure 3As shown, this embodiment also provides a specific implementation for battery pack fault analysis. The specific process includes: First, the system extracts fault information based on telemetry data from source monitoring. The extracted data covers key parameters such as the voltage and current information of the entire battery pack, temperature, and the voltage of individual batteries. Next, the system conducts in-depth analysis of the extracted data, making a comprehensive judgment based on multiple factors such as the status of the acquisition module, the polarity of the signal acquisition line, and the voltage at the pack end. The analysis results are then presented as probability values. The higher the probability value, the higher the priority of the result, facilitating the correct selection and restoration of the signal during human intervention. Finally, the system performs statistical analysis on each analysis and confirmation result to continuously train and optimize the system, improve the analysis logic, and thus enhance the accuracy of fault location.

[0147] Compared to existing technologies, the battery pack fault analysis method provided in this embodiment collects relevant telemetry information, including basic reference information such as voltage, current, and temperature. These parameters can intuitively represent the operating status of the battery pack. For example, a voltage abnormality may be caused by overvoltage or undervoltage in a single battery. Overvoltage can shorten the battery life or even damage it, while undervoltage can affect the power supply capacity of the entire battery pack. Furthermore, an open circuit in a battery pack is a relatively common fault type. Once an open circuit occurs, a stable DC power supply cannot be provided to critical substation equipment, posing a serious threat to system safety. However, in actual operation, existing monitoring systems may generate false alarms, requiring the system to have accurate judgment capabilities to eliminate interference factors. By combining the alarm information from existing monitoring devices, the present invention can more comprehensively analyze the cause of the fault. This fault identification method and system can quickly identify the cause of the fault and accurately locate it, allowing maintenance personnel to quickly take targeted measures to address it, avoiding the situation where "major problems are underestimated and minor problems are exaggerated" due to inaccurate fault identification. At the same time, it reduces the waste of resources in the troubleshooting process to a certain extent, improves maintenance efficiency, and provides a strong guarantee for the reliable operation of the substation.

[0148] It should be understood that although Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 2At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0149] To facilitate better implementation of the battery pack fault analysis method of the present application, the present invention also provides a battery pack fault analysis device based on the aforementioned battery pack fault analysis method. The meanings of the terms herein are the same as those in the aforementioned battery pack fault analysis method. For specific implementation details, please refer to the description in the method embodiment.

[0150] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of a battery pack fault analysis device provided in an embodiment of the present application. The battery pack fault analysis device may include a data acquisition module 201, an alarm extraction module 202, a fault feature module 203, and a fault analysis module 204. Specifically, it may be as follows:

[0151] The data acquisition module 201 is used to collect real-time operating data of the battery pack, including voltage parameters, current parameters, and temperature parameters of the individual batteries, as well as the DC system bus voltage status, AC system status, and charger operation mode;

[0152] The alarm extraction module 202 is used to obtain the alarm information of the monitoring device and extract the fault type identifier and the associated fault location number in the alarm information;

[0153] The fault feature module 203 is used to generate an initial fault feature set of the battery pack based on the operating data and alarm information. The initial fault feature set includes abnormal parameter type, abnormal battery distribution location and system association status;

[0154] The fault analysis module 204 is configured to analyze the cause and location of the fault based on the initial fault feature set using a preset multi-level fault discrimination logic tree to generate a fault analysis result.

[0155] The specific definitions of the battery pack fault analysis device can be found in the definitions of the battery pack fault analysis method described above and will not be further elaborated here. Each module in the battery pack fault analysis device described above may be implemented in whole or in part via software, hardware, or a combination thereof. Each of these modules may be embedded in or independent of a processor in a computer device in hardware form, or may be stored in a computer device memory in software form, allowing the processor to invoke and execute the corresponding operations of each module.

[0156] The battery pack fault analysis device provided in this embodiment generates an initial fault feature set by comprehensively collecting various operating data and monitoring alarm information of the battery pack, and uses a multi-level fault judgment logic tree for analysis. This device can more comprehensively and accurately determine the cause and location of the fault, avoiding the misjudgment and missed judgment of faults caused by single data and vague alarm information in the prior art, thereby improving the efficiency and accuracy of fault judgment, avoiding the problems of processing delays and resource waste caused by inaccurate fault identification in the prior art, and effectively improving the maintenance efficiency and reliability of the battery pack of the substation DC system.

[0157] In addition, the present invention also provides an electronic device, such as Figure 5 , which shows a schematic structural diagram of an electronic device involved in an embodiment of the present application, specifically:

[0158] The electronic device may include one or more processors 301 of processing cores, one or more computer-readable storage media memories 302, a power supply 303, an input unit 304 and other components. Those skilled in the art will appreciate that Figure 5 The electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently.

[0159] The processor 301 is the control center of the electronic device. It connects all parts of the electronic device using various interfaces and lines. By running or executing software programs and / or modules stored in the memory 302 and accessing data stored in the memory 302, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor primarily processes the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into the processor 301.

[0160] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and battery pack fault analysis methods by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created based on the use of the electronic device. In addition, the memory 302 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0161] The electronic device also includes a power supply 303 for supplying power to various components. Preferably, the power supply 303 can be logically connected to the processor 301 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 303 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0162] The electronic device may further include an input unit 304, which may be configured to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0163] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 301 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302 to implement various functions as follows:

[0164] Collect the operating data of the battery pack in real time. The operating data includes the voltage parameters, current parameters, temperature parameters of the single battery, as well as the DC system bus voltage status, AC system status and charger operation mode. Obtain the alarm information of the monitoring device and extract the fault type identification and associated fault location number in the alarm information. Generate the initial fault feature set of the battery pack based on the operating data and alarm information. The initial fault feature set includes the abnormal parameter type, abnormal battery distribution location and system association status. Based on the initial fault feature set, perform fault cause and location analysis through a preset multi-level fault judgment logic tree to generate a fault analysis result.

[0165] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0166] The embodiment of the present application comprehensively collects various operating data and monitoring alarm information of the battery pack to generate an initial fault feature set, and uses a multi-level fault judgment logic tree for analysis. This can more comprehensively and accurately determine the cause and location of the fault, avoiding the misjudgment and missed judgment of faults caused by single data and vague alarm information in the existing technology, thereby improving the efficiency and accuracy of fault judgment, avoiding the processing delays and resource waste caused by inaccurate fault identification in the existing technology, and effectively improving the maintenance efficiency and reliability of the battery pack of the substation DC system.

[0167] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0168] To this end, an embodiment of the present application provides a storage medium storing a plurality of instructions that can be loaded by a processor to execute the steps of any of the battery pack fault analysis methods provided in the embodiments of the present application. For example, the instructions can execute the following steps:

[0169] Collect the operating data of the battery pack in real time. The operating data includes the voltage parameters, current parameters, temperature parameters of the single battery, as well as the DC system bus voltage status, AC system status and charger operation mode. Obtain the alarm information of the monitoring device and extract the fault type identification and associated fault location number in the alarm information. Generate the initial fault feature set of the battery pack based on the operating data and alarm information. The initial fault feature set includes the abnormal parameter type, abnormal battery distribution location and system association status. Based on the initial fault feature set, perform fault cause and location analysis through a preset multi-level fault judgment logic tree to generate a fault analysis result.

[0170] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0171] The storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0172] Since the instructions stored in the storage medium can execute the steps of any battery pack fault analysis method provided in the embodiments of the present application, the beneficial effects that can be achieved by any battery pack fault analysis method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0173] The above is a detailed introduction to a battery pack fault analysis method, device, electronic device and storage medium provided in the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application. At the same time, for those skilled in the art, based on the ideas of the present application, there may be changes in the specific implementation methods and application scope. In summary, the contents of this specification should not be understood as limiting the present application.

Claims

1. A method for analyzing a battery pack failure, characterized in that: The steps include: Real-time collection of battery pack operating data, including voltage parameters, current parameters, temperature parameters of individual batteries, as well as DC system bus voltage status, AC system status, and charger operating mode; Obtaining alarm information from a monitoring device, and extracting a fault type identifier and an associated fault location number from the alarm information; generating an initial fault feature set for the battery pack based on the operating data and the alarm information, the initial fault feature set including abnormal parameter type, abnormal battery distribution location, and system association status; According to the initial fault feature set, a fault cause and location analysis is performed through a preset multi-level fault discrimination logic tree to generate a fault analysis result.

2. The battery pack failure analysis method according to claim 1, characterized in that: The real-time collection of battery pack operating data includes: The voltage value of each single battery is collected in real time through the voltage sensor, and the charge and discharge current of the battery pack is monitored through the current sensor; The surface temperature of each single battery is acquired using a temperature sensor, and the bus voltage of the DC system is acquired using a bus voltage sensor. The power supply status of the AC system and the operating mode of the charger are synchronously collected, and the operating mode includes an equalizing charge state, a floating charge state or a discharging state.

3. The battery pack failure analysis method according to claim 1, characterized in that: The generating an initial fault feature set of the battery pack based on the operating data and the alarm information includes: Comparing the voltage parameters, current parameters, and temperature parameters of the single battery with preset normal operating thresholds, and marking the abnormal parameter type of the abnormal battery according to the obtained comparison results, wherein the abnormal parameter type includes voltage overvoltage, voltage undervoltage, current sudden change, or temperature exceeding a limit; Determining the physical location number and distribution characteristics of the abnormal battery according to the fault location number in the alarm information; Based on the DC system bus voltage state, AC system state and charger operation mode, a system-level associated state tag is generated.

4. The battery pack failure analysis method according to claim 1, characterized in that: The multi-level fault judgment logic tree includes the following judgment logic: If there is a single battery with abnormal voltage and it is not the first or last battery, it is determined to be a single battery failure; If the voltage of the head-end battery or the terminal battery is abnormal, it is determined to be a single cell fault or a signal line break in combination with the polarity connection of the signal acquisition line; If the voltages of two adjacent batteries are abnormal and the voltage at the battery pack terminal is normal, it is determined that the signal line is broken, and the position of the break is located based on the physical connection relationship of the signal acquisition line; If the voltages of multiple non-adjacent batteries are abnormal and the DC bus voltage is abnormal, it is determined that there is a charger failure or AC power interruption based on the AC system status.

5. The battery pack failure analysis method according to claim 4, characterized in that: The multi-level fault judgment logic tree also includes the following judgment logic: If the temperature of the single battery rises abnormally but the voltage is normal, it is determined that the signal collector is faulty; If the temperature of a single battery cell rises abnormally and the voltage is abnormal, it is determined to be a battery failure.

6. The battery pack failure analysis method according to claim 4, characterized in that: The signal acquisition line polarity connection method includes: Identifying a connection mode of the battery pack, wherein the connection mode includes a positive polarity connection mode or a negative polarity connection mode; If the connection method is positive polarity connection, the voltage of the first-end battery is collected separately by the first signal line, and the voltage of the remaining batteries is collected by the adjacent positive signal lines; If the connection method is negative polarity connection, the voltage of the first-end battery is collected separately by the second signal line, and the voltage of the remaining batteries is collected by the adjacent negative signal line; Corrected the logic for associating signal line breakage with battery failure based on the connection type.

7. The battery pack failure analysis method according to claim 1, characterized in that: The method further comprises: Establish a historical fault case library to record fault characteristics, analysis results and treatment effects; Using a machine learning algorithm and the historical fault case library to train a multi-level fault discrimination logic tree, adjusting branch weights, discrimination thresholds, and priorities of the multi-level fault discrimination logic tree, and obtaining an optimized multi-level fault discrimination logic tree; The optimized multi-level fault discrimination logic tree is deployed in real time to the online analysis system to analyze the cause and location of the fault of the battery pack based on the optimized multi-level fault discrimination logic tree.

8. A battery pack fault analysis device, characterized in that: include: A data acquisition module is used to collect real-time operating data of the battery pack, including voltage parameters, current parameters, and temperature parameters of the individual batteries, as well as the DC system bus voltage status, AC system status, and charger operating mode; An alarm extraction module is used to obtain alarm information from the monitoring device and extract the fault type identifier and the associated fault location number in the alarm information; a fault characteristic module, configured to generate an initial fault characteristic set of the battery pack based on the operating data and the alarm information, wherein the initial fault characteristic set includes abnormal parameter type, abnormal battery distribution location, and system association status; The fault analysis module is used to analyze the cause and location of the fault according to the initial fault feature set through a preset multi-level fault judgment logic tree to generate a fault analysis result.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the battery pack fault analysis method according to any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: A computer program is stored which can be loaded by a processor and executes the battery pack fault analysis method according to any one of claims 1 to 7.

Images