Battery maintenance decision-making method and device, vehicle and storage medium
By acquiring and analyzing historical operating data of faulty batteries, and using characteristic parameters to automatically identify fault types and match maintenance strategies, the problem of blind maintenance in fuel cell systems has been solved, enabling precise and intelligent maintenance decisions and reducing costs and time.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING CAVAN NEW ENERGY AUTOMOTIVE CO LTD
- Filing Date
- 2026-01-05
- Publication Date
- 2026-05-08
AI Technical Summary
In the existing technology, fuel cell systems lack effective data support after the faulty battery is isolated, which leads to maintenance personnel relying on experience to make blind decisions, resulting in over-maintenance or under-maintenance, low efficiency and high cost.
By acquiring historical operating data of faulty batteries, performing data preprocessing and feature extraction, and utilizing parameters such as voltage recovery capability, fault duration, abnormal temperature peaks, and historical isolation frequency, the system automatically identifies the fault type and matches maintenance strategies, achieving precise and intelligent maintenance decisions.
It has enabled precise and intelligent operation and maintenance of fuel cell systems, avoiding blind repairs, reducing costs and time, improving maintenance efficiency, and forming a data-driven closed-loop decision-making system.
Smart Images
Figure CN121998613A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of new energy technology, and in particular to a battery maintenance decision-making method, device, vehicle, and storage medium. Background Technology
[0002] During fuel cell operation, the fuel cell system has the capability to isolate single-cell-level faults online. The fuel cell stack can isolate faulty units without shutting down the system, thereby achieving fault-tolerant operation and ensuring mission continuity.
[0003] In related technologies, after a faulty battery is isolated, repair personnel lack effective data and support to determine the root cause of the fault and the reversibility of the battery. As a result, they can only rely on personal experience to make blind repair decisions, which can lead to problems such as over-repair or under-repair. Ultimately, this results in low repair efficiency and high costs, which urgently need to be addressed. Summary of the Invention
[0004] This application provides a battery maintenance decision-making method, apparatus, vehicle, and storage medium to solve the problems in related technologies where battery faults can only be addressed by making blind maintenance decisions based on personal experience, resulting in over-maintenance or under-maintenance.
[0005] The first aspect of this application provides a battery maintenance decision-making method, including the following steps: Obtain historical operating data of the faulty battery; The historical operating data is preprocessed, and features are extracted from the preprocessed historical operating data to obtain the maintenance decision feature parameters of the faulty battery. The fault type of the faulty battery is determined based on the maintenance decision characteristic parameters, and the maintenance strategy for the faulty battery is determined based on the fault type. The faulty battery is then repaired according to the maintenance strategy.
[0006] According to one embodiment of this application, before obtaining the historical operating data of the faulty battery, the method further includes: Determine whether the faulty battery is in an isolated state; If the faulty battery is in the isolated state, a maintenance decision instruction for the faulty battery is triggered.
[0007] According to one embodiment of this application, the step of extracting features from the preprocessed historical operating data to obtain the maintenance decision feature parameters of the faulty battery includes: Calculate the historical operating data after data preprocessing, and determine the voltage recovery capability, fault duration, abnormal temperature peak, and historical isolation frequency of the historical operating data after data preprocessing. The maintenance decision characteristic parameters of the faulty battery are obtained based on the voltage recovery capability, the fault duration, the abnormal temperature peak, and the historical isolation frequency.
[0008] According to one embodiment of this application, determining the fault type of the faulty battery based on the maintenance decision characteristic parameters includes: Determine whether the voltage recovery capability of the faulty battery is in the target recovery state, whether the fault duration of the faulty battery is less than a preset duration threshold, whether the abnormal temperature peak of the faulty battery is less than a preset temperature peak, and whether the historical isolation frequency of the faulty battery is less than a preset cumulative isolation number. If the voltage recovery capability of the faulty battery is in the target recovery state, and the fault duration of the faulty battery is less than the preset duration threshold, and the abnormal temperature peak of the faulty battery is less than the preset temperature peak, and the historical isolation frequency of the faulty battery is less than the preset cumulative isolation number, then the fault type of the faulty battery is determined to be a recoverable fault type.
[0009] According to one embodiment of this application, determining the fault type of the faulty battery based on the maintenance decision characteristic parameters further includes: If the voltage recovery capability of the faulty battery is not in the target recovery state, or the fault duration of the faulty battery is greater than or equal to the preset duration threshold, or the abnormal temperature peak of the faulty battery is greater than or equal to the preset temperature peak, or the historical isolation frequency of the faulty battery is greater than or equal to the preset cumulative isolation count, then the fault type of the faulty battery is determined to be an unrecoverable fault type.
[0010] According to one embodiment of this application, determining a repair strategy for the faulty battery based on the fault type, and repairing the faulty battery according to the repair strategy, includes: If the fault type of the faulty battery is the recoverable fault type, then the faulty battery is repaired online. If the fault type of the faulty battery is the unrecoverable fault type, a structured maintenance work order is generated and a maintenance instruction is sent to the maintenance personnel to remind them to replace the faulty component of the faulty battery.
[0011] The battery maintenance decision-making method according to embodiments of this application acquires historical operating data of a faulty battery and performs data preprocessing. Feature extraction is then performed on the preprocessed historical operating data to obtain maintenance decision feature parameters for the faulty battery. The fault type of the faulty battery is then determined based on these feature parameters, and a maintenance strategy is determined based on the fault type. The faulty battery is then repaired according to the maintenance strategy. This solves the problem in related technologies where battery fault assessment relies solely on personal experience for blind maintenance decisions, leading to over-maintenance or under-maintenance. By automatically analyzing the historical operating data of the faulty battery, the recoverability of the faulty battery is intelligently determined, and online maintenance or replacement of individual cells is automatically matched, thereby achieving precise and intelligent operation and maintenance of the fuel cell system.
[0012] A second aspect of this application provides a battery maintenance decision-making device, comprising: The acquisition module is used to acquire historical operating data of faulty batteries; The feature extraction module is used to preprocess the historical operating data and extract features from the preprocessed historical operating data to obtain the maintenance decision feature parameters of the faulty battery. The maintenance module is used to determine the fault type of the faulty battery based on the maintenance decision feature parameters, determine the maintenance strategy for the faulty battery based on the fault type, and perform maintenance on the faulty battery according to the maintenance strategy.
[0013] According to one embodiment of this application, before acquiring historical operating data of the faulty battery, the acquisition module further includes: The first judgment unit is used to determine whether the faulty battery is in an isolated state; The instruction triggering unit is used to trigger a maintenance decision instruction for the faulty battery if the faulty battery is in the isolated state.
[0014] According to one embodiment of this application, the feature extraction module includes: The calculation unit is used to calculate the historical operating data after data preprocessing, and to determine the voltage recovery capability, fault duration, abnormal temperature peak value, and historical isolation frequency of the historical operating data after data preprocessing. The acquisition unit is used to obtain maintenance decision characteristic parameters of the faulty battery based on the voltage recovery capability, the fault duration, the abnormal temperature peak, and the historical isolation frequency.
[0015] According to one embodiment of this application, the maintenance module includes: The second judgment unit is used to determine whether the voltage recovery capability of the faulty battery is in the target recovery state, whether the fault duration of the faulty battery is less than a preset duration threshold, whether the abnormal temperature peak of the faulty battery is less than a preset temperature peak, and whether the historical isolation frequency of the faulty battery is less than a preset cumulative isolation number. The first determination unit is configured to determine that the fault type of the fault battery is a recoverable fault type if the voltage recovery capability of the fault battery is in the target recovery state, the fault duration of the fault battery is less than the preset duration threshold, the abnormal temperature peak value of the fault battery is less than the preset temperature peak value, and the historical isolation frequency of the fault battery is less than the preset cumulative isolation number.
[0016] According to one embodiment of this application, the maintenance module includes: The second determination unit is used to determine that the fault type of the fault battery is an unrecoverable fault type if the voltage recovery capability of the fault battery is not in the target recovery state, or the fault duration of the fault battery is greater than or equal to the preset duration threshold, or the abnormal temperature peak of the fault battery is greater than or equal to the preset temperature peak, or the historical isolation frequency of the fault battery is greater than or equal to the preset cumulative isolation number.
[0017] According to one embodiment of this application, the maintenance module includes: The first maintenance unit is used to perform online maintenance on the faulty battery if the fault type of the faulty battery is the recoverable fault type. The second maintenance unit is used to generate a structured maintenance work order and send maintenance instructions to the maintenance personnel if the fault type of the faulty battery is the unrecoverable fault type, so as to remind the maintenance personnel to replace the faulty component of the faulty battery.
[0018] The battery maintenance decision-making device according to an embodiment of this application acquires historical operating data of a faulty battery and performs data preprocessing. It then extracts features from the preprocessed historical operating data to obtain maintenance decision feature parameters for the faulty battery. Based on these parameters, it determines the fault type of the battery and subsequently determines a maintenance strategy accordingly. This addresses the problems in related technologies where battery fault assessment relies solely on personal experience for blind maintenance decisions, leading to over-maintenance or under-maintenance. By automatically analyzing the historical operating data of the faulty battery, it intelligently assesses the recoverability of the faulty battery and automatically matches online maintenance or cell replacement strategies, thereby achieving precise and intelligent operation and maintenance of the fuel cell system.
[0019] A third aspect of this application provides a vehicle including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the battery maintenance decision method as described in the above embodiments.
[0020] A fourth aspect of this application provides a computer-readable storage medium storing computer instructions for causing the computer to perform a battery maintenance decision-making method as described in the above embodiments.
[0021] A fifth aspect of this application provides a computer program product, including a computer program that is executed to implement the battery maintenance decision method described in the above embodiments.
[0022] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description
[0023] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a battery maintenance decision-making method according to an embodiment of this application; Figure 2 This is a flowchart of a maintenance decision control strategy according to an embodiment of this application; Figure 3 This is an example diagram of a battery maintenance decision device according to an embodiment of this application; Figure 4 This is a structural schematic diagram of a vehicle according to an embodiment of this application. Detailed Implementation
[0024] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0025] The following description, with reference to the accompanying drawings, illustrates a battery maintenance decision-making method, apparatus, vehicle, and storage medium according to embodiments of this application. Addressing the problem mentioned in the background art where battery fault assessment relies solely on personal experience for blind maintenance decisions, leading to over-maintenance or under-maintenance, this application provides a battery maintenance decision-making method. This method acquires and preprocesses historical operating data of the faulty battery, extracts features from the preprocessed historical operating data to obtain maintenance decision-making feature parameters for the faulty battery, determines the fault type based on these feature parameters, and then determines a maintenance strategy based on the fault type. This allows for maintenance of the faulty battery according to the established strategy. This solves the problem of over-maintenance or under-maintenance arising from relying solely on personal experience for battery fault assessment in related technologies. By automatically analyzing the historical operating data of the faulty battery, the recoverability of the faulty battery is intelligently determined, and online maintenance or replacement of individual cells is automatically matched, thereby achieving precise and intelligent operation and maintenance of the fuel cell system.
[0026] Specifically, before introducing the embodiments of this application, we will first introduce the problems existing in the related technologies of this application. In the current fuel cell system, the ability to isolate single-cell-level faults online is already available (e.g., cutting off the hydrogen supply to the cell and short-circuiting it). The stack can isolate faulty units without shutting down, thereby achieving fault-tolerant operation and significantly improving mission reliability. However, when a cell fails, the system will continue to operate in degraded mode, postponing the cell repair decision until a planned shutdown. After shutdown, maintenance personnel are faced with an isolated cell, thus lacking effective data and support to determine the root cause of the cell failure and the reversibility of cell repair. Consequently, it is impossible to determine whether the faulty cell is a reversible failure (e.g., slight water flooding, temporary gas blockage) or an irreversible failure (e.g., catalyst layer corrosion, membrane perforation).
[0027] In this situation, maintenance personnel can only rely on their personal experience to make blind decisions about repairing faulty batteries, which may lead to over-repair and under-repair. Over-repair, which means directly performing "replacement on the entire stack", is costly, time-consuming, and may cause secondary damage to healthy batteries. Under-repair, on the other hand, refers to performing only a simple system-level purging. If the fault is permanent, it cannot cure the problem, which will lead to repeated faults and eventually require re-repair, thus increasing the total maintenance cost and time.
[0028] Therefore, maintenance personnel, fearing recurrence of faults, choose to directly "replace the entire battery pack" regardless of the problem's severity, resulting in extremely high spare parts and labor costs, and causing unnecessary long-term equipment downtime. Furthermore, in an effort to save costs and time, maintenance personnel may assume the fault is minor and perform only a simple system-level purge of the faulty battery. If the diagnosis is incorrect (in reality, irreversible damage), the fault will quickly recur, leading to a second downtime. This significantly increases the total maintenance cost and may delay production. Ultimately, this results in low maintenance efficiency and high costs, preventing battery faults from being resolved scientifically and rationally.
[0029] To address the aforementioned problems, this application proposes a fault maintenance decision-making method based on operational data, aiming to eliminate decision-making blind spots for battery faults, resolve issues such as over-maintenance and under-maintenance of battery faults, and heavy reliance on expert experience.
[0030] Specifically, Figure 1 This is a schematic flowchart illustrating a battery maintenance decision-making method provided in an embodiment of this application.
[0031] like Figure 1 As shown, the battery repair decision-making method includes the following steps: In step S101, historical operating data of the faulty battery is obtained.
[0032] According to one embodiment of this application, before obtaining the historical operating data of the faulty battery, the method further includes: determining whether the faulty battery is in an isolated state; if the faulty battery is in an isolated state, triggering a maintenance decision instruction for the faulty battery.
[0033] Specifically, before initiating the maintenance decision-making process, this application embodiment first needs to perform isolation status identification and decision trigger judgment of the faulty battery to ensure that subsequent diagnosis and maintenance analysis are carried out only for faulty batteries that have implemented online fault tolerance processing.
[0034] Specifically, the control system first iterates through the status flag bits of all faulty cells in the fuel cell stack to check if there are any faulty cells marked as isolated. This involves closing the independent hydrogen shut-off valve on the anode side of the corresponding faulty cell to cut off its fuel supply and closing the electronic short-circuit switch connected in parallel with it. Then, the status register of the faulty cell is set to the isolated state. After performing the above operations, the system status is updated and the output power is adjusted. If the cell is short-circuited, the total voltage of the fuel cell stack and the maximum allowable output power are recalculated. After completing all operations, the system enters the degraded fault-tolerant operation mode.
[0035] Secondly, since maintenance decisions are not executed in real time, but are triggered by software after the fuel cell system is safely shut down or switched to maintenance mode, sufficient computing resources and time are ensured for in-depth data analysis without affecting the normal operation of the stack. Therefore, after the fuel cell system is safely shut down or switched to maintenance mode, the maintenance decision main program first scans the status registers of all faulty cells. Only when at least one faulty cell is detected to be in an isolated state will the maintenance decision engine be activated, and a maintenance decision instruction will be sent to the data module associated with the faulty cell. The maintenance decision instruction may include the faulty cell ID (Identifier), isolation event number, and trigger priority, etc., for subsequent accurate retrieval of the historical operating data of the faulty cell.
[0036] Finally, the system retrieves the historical operating data of the faulty battery that has been isolated online from the vehicle operation database or remote cloud platform, covering the entire lifecycle before, during, and after the isolation event. This historical operating data is collected and stored in real time by the data acquisition module during normal operation and mainly includes time-series data such as voltage, temperature, and current density of the faulty battery.
[0037] Among them, the full lifecycle historical operation data usually covers 30 seconds before the fault occurs to 10 seconds after the isolation is completed, so as to ensure that the entire process of fault initiation, development and system response is fully captured.
[0038] In step S102, the historical operating data is preprocessed, and features are extracted from the preprocessed historical operating data to obtain the maintenance decision feature parameters of the faulty battery.
[0039] According to one embodiment of this application, feature extraction is performed on the preprocessed historical operating data to obtain the maintenance decision feature parameters of the faulty battery, including: calculating the preprocessed historical operating data and determining the voltage recovery capability, fault duration, abnormal temperature peak, and historical isolation frequency of the preprocessed historical operating data; and obtaining the maintenance decision feature parameters of the faulty battery based on the voltage recovery capability, fault duration, abnormal temperature peak, and historical isolation frequency.
[0040] Specifically, after obtaining the historical operating data of the faulty battery, in order to ensure the accuracy and robustness of subsequent feature extraction of the faulty battery, and in order to eliminate noise interference, repair outliers, and unify the time reference, this application needs to further preprocess the historical operating data. This mainly includes filtering, alignment, and other preprocessing of the historical operating data, so as to transform the original historical operating data into a high-quality time series dataset with clear structure, controllable noise, time synchronization, and focus on the fault process, thus laying a reliable foundation for the feature extraction of the historical operating data in the next step.
[0041] Furthermore, in this embodiment of the application, after preprocessing the historical operating data, the key feature extraction stage is entered, which aims to quantify several core indicators that reflect the nature of the fault from high-quality time series data, and form maintenance decision feature parameters that can be used for rule judgment.
[0042] like Figure 2 As shown, the maintenance decision characteristic parameters in this application embodiment are criteria designed based on the electrochemical mechanism and engineering experience of fuel cells. These criteria can effectively distinguish between reversible faults (such as instantaneous flooding and membrane drying) and irreversible damage (such as membrane perforation, catalyst degradation, and bipolar plate corrosion). They mainly include voltage recovery capability V. recovery Fault duration T fault Temperature anomaly peak T max (or the maximum deviation of the average temperature of the fuel cell stack, ΔT) max ) and historical isolation frequency N isolations Four parts, then through voltage recovery capability V recovery Fault duration T fault Temperature anomaly peak T max and historical isolation frequency N isolations The weights of each component are determined, and the final recommendations are output based on the experience of those skilled in the art.
[0043] Among them, voltage recovery capability V recovery This refers to the voltage timing data within a window of time preceding the fault, measured by the voltage recovery capability V. recovery Analyze whether there are spontaneous rebound fluctuations during the voltage drop process. If multiple fluctuations in voltage can be observed before it drops to the threshold, it indicates that the fault may be intermittent (such as slight water flooding) and reversible. Conversely, a continuous low voltage indicates that the battery may have suffered permanent damage.
[0044] Fault duration T fault This refers to the total time from the first voltage anomaly (e.g., multiple consecutive drops below the warning threshold of 0.3V) to the final isolation (hydrogen gas cutoff + electronic short circuit). If the fault duration T... fault The longer the duration (e.g., greater than a preset duration threshold) is, the longer the battery operates in a fault state, and the greater the risk of irreversible damage (such as reverse polarity corrosion).
[0045] Temperature anomaly peak T max The absolute temperature peak T reached by the faulty battery before it was isolated refers to the peak value of the abnormal temperature. max and its maximum deviation from the average temperature of the fuel cell stack, ΔT max Since temperature is a key indicator of internal damage, therefore, when T max Greater than the preset absolute peak temperature and ΔT maxWhen the maximum deviation from the preset average temperature is greater than the maximum value, extremely high temperatures (such as T) max >85°C) or extremely large temperature differences (such as ΔT) max >15°C usually indicates severe local overheating, at which point the faulty battery may have suffered physical damage such as membrane dehydration, catalyst layer sintering, or sealing ring aging.
[0046] Historical isolation frequency N isolations N refers to the cumulative number of times the battery is isolated throughout the entire lifespan of the battery pack. isolations If a battery repeatedly fails (i.e., is frequently isolated and then restored by maintenance), and the cumulative number of failures exceeds the preset isolation count, it indicates that the battery itself may be a "weak unit" in the battery stack. The fundamental problem has not been resolved and simple maintenance cannot cure it. Replacement is recommended.
[0047] Therefore, by using the maintenance decision feature parameters of the above four faulty batteries as input to the rule engine of this application embodiment, the subsequent fault type determination and maintenance strategy generation are directly determined. All features have clear physical interpretability, engineering measurability and discriminative validity, thereby avoiding the credibility problem caused by the black box model and meeting the stringent requirements of vehicle fuel cell systems for safety, traceability and maintainability.
[0048] In step S103, the fault type of the faulty battery is determined based on the maintenance decision characteristic parameters, the maintenance strategy for the faulty battery is determined based on the fault type, and the faulty battery is repaired according to the maintenance strategy.
[0049] According to one embodiment of this application, determining the fault type of a faulty battery based on maintenance decision characteristic parameters includes: determining whether the voltage recovery capability of the faulty battery is in a target recovery state, whether the fault duration of the faulty battery is less than a preset duration threshold, whether the abnormal temperature peak of the faulty battery is less than a preset temperature peak, and whether the historical isolation frequency of the faulty battery is less than a preset cumulative isolation count; if the voltage recovery capability of the faulty battery is in a target recovery state, the fault duration of the faulty battery is less than the preset duration threshold, the abnormal temperature peak of the faulty battery is less than the preset temperature peak, and the historical isolation frequency of the faulty battery is less than the preset cumulative isolation count, then the fault type of the faulty battery is determined to be a recoverable fault type.
[0050] The target recovery status, preset duration threshold, preset temperature peak, and preset cumulative isolation count can all be dynamically adjusted by those skilled in the art based on the fuel cell stack model, application scenario, operating environment, and historical maintenance feedback data, and stored in the system configuration file or cloud database. Furthermore, they can support OTA (Over-The-Air) remote updates to ensure continuous optimization of decision-making strategies.
[0051] Specifically, after obtaining the maintenance decision characteristic parameters of the faulty battery, the system inputs the maintenance decision characteristic parameters into the preset rule engine and performs multi-condition joint judgment to determine the fault type of the faulty battery.
[0052] Specifically, if the voltage recovery capability V of the faulty battery recovery The battery is in the target recovery state, meaning the faulty battery exhibits spontaneous recovery, and the fault duration T of the faulty battery... fault The duration is less than a preset time threshold (e.g., the fault duration of the faulty battery is less than 10 seconds), and the abnormal temperature peak T of the faulty battery is... max Less than the preset peak temperature (and ΔT) max (less than the maximum deviation of the preset average temperature), and the historical isolation frequency N of the faulty battery. isolations Less than the preset cumulative number of isolations, for example, the historical isolation frequency N. isolations Less than 2 (i.e., N) isolations =1, first failure), the rule engine determines the failure type of the faulty battery as a recoverable failure type only when all four conditions above are met.
[0053] According to one embodiment of this application, determining the fault type of a faulty battery based on maintenance decision characteristic parameters further includes: if the voltage recovery capability of the faulty battery is not in the target recovery state, or the fault duration of the faulty battery is greater than or equal to a preset duration threshold, or the abnormal temperature peak of the faulty battery is greater than or equal to a preset temperature peak, or the historical isolation frequency of the faulty battery is greater than or equal to a preset cumulative isolation number, then the fault type of the faulty battery is determined to be an unrecoverable fault type.
[0054] Specifically, if the voltage recovery capability V of the faulty battery recovery Not in the target recovery state, that is, during the development of the fault, the single cell voltage does not show a significant upward trend, which may be due to irreversible electrochemical damage such as membrane perforation, severe catalyst poisoning or internal short circuit, and the performance cannot be restored by purging or drying.
[0055] Or the duration T of the faulty battery fault If the duration is greater than or equal to a preset duration threshold (e.g., the fault duration of a faulty battery is greater than or equal to 10 seconds), the faulty battery may be subjected to reverse current due to prolonged abnormal operating conditions, leading to carbon carrier corrosion or proton exchange membrane thermal degradation. Such damage is cumulative and irreversible.
[0056] Or the abnormal temperature peak T of the faulty battery max Greater than or equal to the preset peak temperature (and ΔT) max(The maximum deviation value of the preset average temperature is greater than or equal to the maximum value of the preset average temperature. Since a significant local temperature rise usually reflects the formation of internal hot spots, it may be caused by local combustion due to membrane drying or flow channel blockage, or microscale membrane perforation has occurred, leading to a direct reaction between hydrogen and oxygen. This is a high-risk physical failure sign.)
[0057] Or the historical isolation frequency N of the faulty battery isolations Greater than or equal to the preset cumulative number of isolations, such as the historical isolation frequency N. isolations Two or more repeated failures indicate that the faulty battery has inherent weaknesses such as manufacturing defects, poor assembly, or material aging. Even if it currently exhibits minor abnormalities, its long-term reliability has been severely degraded, and continued use will significantly increase the risk of system downtime.
[0058] Therefore, as long as any one of the above four conditions is met, the rule engine can determine that the faulty battery is an unrecoverable fault.
[0059] According to one embodiment of this application, a maintenance strategy for a faulty battery is determined based on the fault type, and the faulty battery is maintained according to the maintenance strategy. This includes: if the fault type of the faulty battery is a recoverable fault, then the faulty battery is maintained online; if the fault type of the faulty battery is an unrecoverable fault, then a structured maintenance work order is generated, and a maintenance instruction is sent to the maintenance personnel to remind them to replace the faulty component of the faulty battery.
[0060] Specifically, this application proposes that after the rule engine completes the fault type determination, the system automatically executes the matching maintenance strategy based on the determination result, thereby realizing a fault operation and maintenance process from intelligent diagnosis to precise execution.
[0061] Specifically, such as Figure 2 As shown, if the faulty battery is classified as a recoverable fault, a simple maintenance procedure is executed, i.e., an online repair procedure is initiated. The system automatically performs an online recovery procedure for the repair personnel. For example, a targeted high-pressure hydrogen circulation purging procedure is initiated, or nitrogen is injected for drying, attempting to remove accumulated water or contaminants from the battery. After the recovery procedure is completed, the system can attempt to automatically restart the battery's hydrogen valve and monitor whether its performance has been restored. This involves repowering the battery and monitoring its open-circuit voltage and the operating voltage after loading. If the voltage is stable within the normal range (e.g., ≥0.65V), the repair is considered successful, its "isolation status" flag is cleared, and it is allowed to be put back into operation. This event is recorded as a "recoverable fault." If the fault is not recovered, it is upgraded to an unrecoverable fault and the manual repair procedure is initiated.
[0062] Optionally, if the faulty battery is an unrecoverable fault, the single-cell replacement process is executed, i.e., the manual maintenance process is initiated. At this time, the system will automatically generate a structured maintenance work order and push it to the maintenance personnel through the vehicle-mounted human-machine interface terminal or remote operation and maintenance platform to notify the maintenance personnel to prepare spare parts and tools and arrange a planned shutdown for stack replacement. For example, based on the operating status of vehicles, ships, etc., a shutdown can be selected during the off-peak operating time to wait for maintenance. At this time, the maintenance personnel will carry out stack replacement according to the detailed maintenance work order. After all isolated batteries have been repaired, the system will briefly shut off the hydrogen cut-off valve and connect the current to the battery and monitor whether its voltage has recovered to verify the maintenance effect. At the same time, the system will record all data of this decision, the execution process and the final result in the maintenance log database and generate a digital maintenance report. This data can be used to optimize and adjust the parameters of the decision rules in the future, so that the system has the ability to continuously learn. When all isolated batteries have been repaired, the entire process ends, and the system waits to be triggered again or enters the ready state.
[0063] The structured maintenance work order must include the battery number (ID) to be replaced, a summary of fault data (such as peak temperature and duration), and the basis for decision-making. After the maintenance is completed, the system will archive all data of the fault, operation records, and performance data after replacement to update the health status model of the battery stack and form a knowledge loop.
[0064] Therefore, based on the above specific embodiments, this application transforms maintenance decision-making from "experience-driven" to "data-driven," achieving standardization and automation, reducing reliance on senior technicians, and avoiding unnecessary open-chain replacements, saving significant costs and time. Simultaneously, it can decisively recommend replacing irreparable batteries, preventing ineffective maintenance, significantly reducing total lifecycle costs, and forming a closed loop of "data-decision-feedback." Each maintenance becomes a data point for optimizing the decision-making model, making the system increasingly "intelligent" with use. Furthermore, it seamlessly integrates with the underlying fault isolation system, constituting a complete "online monitoring-real-time isolation-intelligent diagnosis-maintenance decision" fuel cell intelligent health management system, greatly enhancing the product's core competitiveness.
[0065] The battery maintenance decision-making method according to embodiments of this application acquires historical operating data of a faulty battery and performs data preprocessing. Feature extraction is then performed on the preprocessed historical operating data to obtain maintenance decision feature parameters for the faulty battery. The fault type of the faulty battery is then determined based on these feature parameters, and a maintenance strategy is determined based on the fault type. The faulty battery is then repaired according to the maintenance strategy. This solves the problem in related technologies where battery fault assessment relies solely on personal experience for blind maintenance decisions, leading to over-maintenance or under-maintenance. By automatically analyzing the historical operating data of the faulty battery, the recoverability of the faulty battery is intelligently determined, and online maintenance or replacement of individual cells is automatically matched, thereby achieving precise and intelligent operation and maintenance of the fuel cell system.
[0066] Next, a battery maintenance decision-making device according to an embodiment of this application is described with reference to the accompanying drawings.
[0067] Figure 3 This is a block diagram of a battery maintenance decision device according to an embodiment of this application.
[0068] like Figure 3 As shown, the battery maintenance decision-making device 10 includes: an acquisition module 100, a feature extraction module 200, and a maintenance module 300.
[0069] Among them, the acquisition module 100 is used to acquire historical operating data of the faulty battery; The feature extraction module 200 is used to preprocess historical operating data and extract features from the preprocessed historical operating data to obtain the maintenance decision feature parameters of the faulty battery. The maintenance module 300 is used to determine the fault type of the faulty battery based on maintenance decision characteristic parameters, determine the maintenance strategy for the faulty battery based on the fault type, and perform maintenance on the faulty battery according to the maintenance strategy.
[0070] According to one embodiment of this application, before acquiring historical operating data of the faulty battery, the acquisition module 100 further includes: The first judgment unit is used to determine whether the faulty battery is in an isolated state; The instruction triggering unit is used to trigger a maintenance decision instruction for the faulty battery if the faulty battery is in an isolated state.
[0071] According to one embodiment of this application, the feature extraction module 200 includes: The calculation unit is used to calculate the historical operating data after data preprocessing, and to determine the voltage recovery capability, fault duration, abnormal temperature peak, and historical isolation frequency of the historical operating data after data preprocessing. The acquisition unit is used to obtain maintenance decision characteristic parameters of the faulty battery based on voltage recovery capability, fault duration, abnormal temperature peak, and historical isolation frequency.
[0072] According to one embodiment of this application, the repair module 300 includes: The second judgment unit is used to judge whether the voltage recovery capability of the faulty battery is in the target recovery state, whether the fault duration of the faulty battery is less than the preset duration threshold, whether the abnormal temperature peak of the faulty battery is less than the preset temperature peak, and whether the historical isolation frequency of the faulty battery is less than the preset cumulative isolation number. The first determination unit is used to determine the fault type of the fault battery as a recoverable fault type if the voltage recovery capability of the fault battery is in the target recovery state, the fault duration of the fault battery is less than a preset duration threshold, the abnormal temperature peak of the fault battery is less than a preset temperature peak, and the historical isolation frequency of the fault battery is less than a preset cumulative isolation number.
[0073] According to one embodiment of this application, the repair module 300 includes: The second determination unit is used to determine the fault type of the faulty battery as an unrecoverable fault type if the voltage recovery capability of the faulty battery is not in the target recovery state, or the fault duration of the faulty battery is greater than or equal to a preset duration threshold, or the abnormal temperature peak of the faulty battery is greater than or equal to a preset temperature peak, or the historical isolation frequency of the faulty battery is greater than or equal to a preset cumulative isolation number.
[0074] According to one embodiment of this application, the repair module 300 includes: The first maintenance unit is used to perform online maintenance on the faulty battery if the fault type is a recoverable fault type. The second maintenance unit is used to generate a structured maintenance work order and send maintenance instructions to maintenance personnel if the faulty battery is an unrecoverable fault, so as to remind the maintenance personnel to replace the faulty component of the faulty battery.
[0075] The battery maintenance decision-making device according to an embodiment of this application acquires historical operating data of a faulty battery and performs data preprocessing. It then extracts features from the preprocessed historical operating data to obtain maintenance decision feature parameters for the faulty battery. Based on these parameters, it determines the fault type of the battery and subsequently determines a maintenance strategy accordingly. This addresses the problems in related technologies where battery fault assessment relies solely on personal experience for blind maintenance decisions, leading to over-maintenance or under-maintenance. By automatically analyzing the historical operating data of the faulty battery, it intelligently assesses the recoverability of the faulty battery and automatically matches online maintenance or cell replacement strategies, thereby achieving precise and intelligent operation and maintenance of the fuel cell system.
[0076] Figure 4 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include: The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.
[0077] When the processor 402 executes the program, it implements the battery maintenance decision method provided in the above embodiments.
[0078] Furthermore, the vehicle also includes: Communication interface 403 is used for communication between memory 401 and processor 402.
[0079] The memory 401 is used to store computer programs that can run on the processor 402.
[0080] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.
[0081] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 4The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0082] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.
[0083] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.
[0084] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the battery maintenance decision-making method described above.
[0085] This embodiment also provides a computer program product, including a computer program that is executed to implement the battery maintenance decision method of the above embodiment.
[0086] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0087] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0088] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.
[0089] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.
[0090] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0091] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.
[0092] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
[0093] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.
Claims
1. A battery maintenance decision-making method, characterized in that, Includes the following steps: Obtain historical operating data of the faulty battery; The historical operating data is preprocessed, and features are extracted from the preprocessed historical operating data to obtain the maintenance decision feature parameters of the faulty battery. The fault type of the faulty battery is determined based on the maintenance decision characteristic parameters, and the maintenance strategy for the faulty battery is determined based on the fault type. The faulty battery is then repaired according to the maintenance strategy.
2. The method according to claim 1, characterized in that, Before obtaining historical operational data for the faulty battery, the following steps are also included: Determine whether the faulty battery is in an isolated state; If the faulty battery is in the isolated state, a maintenance decision instruction for the faulty battery is triggered.
3. The method according to claim 1, characterized in that, The process of extracting features from the preprocessed historical operating data to obtain the maintenance decision feature parameters of the faulty battery includes: Calculate the historical operating data after data preprocessing, and determine the voltage recovery capability, fault duration, abnormal temperature peak, and historical isolation frequency of the historical operating data after data preprocessing. The maintenance decision characteristic parameters of the faulty battery are obtained based on the voltage recovery capability, the fault duration, the abnormal temperature peak, and the historical isolation frequency.
4. The method according to claim 1 or 3, characterized in that, Determining the fault type of the faulty battery based on the maintenance decision characteristic parameters includes: Determine whether the voltage recovery capability of the faulty battery is in the target recovery state, whether the fault duration of the faulty battery is less than a preset duration threshold, whether the abnormal temperature peak of the faulty battery is less than a preset temperature peak, and whether the historical isolation frequency of the faulty battery is less than a preset cumulative isolation number. If the voltage recovery capability of the faulty battery is in the target recovery state, and the fault duration of the faulty battery is less than the preset duration threshold, and the abnormal temperature peak of the faulty battery is less than the preset temperature peak, and the historical isolation frequency of the faulty battery is less than the preset cumulative isolation number, then the fault type of the faulty battery is determined to be a recoverable fault type.
5. The method according to claim 4, characterized in that, The step of determining the fault type of the faulty battery based on the maintenance decision characteristic parameters further includes: If the voltage recovery capability of the faulty battery is not in the target recovery state, or the fault duration of the faulty battery is greater than or equal to the preset duration threshold, or the abnormal temperature peak of the faulty battery is greater than or equal to the preset temperature peak, or the historical isolation frequency of the faulty battery is greater than or equal to the preset cumulative isolation count, then the fault type of the faulty battery is determined to be an unrecoverable fault type.
6. The method according to claim 5, characterized in that, The step of determining a repair strategy for the faulty battery based on the fault type, and repairing the faulty battery according to the repair strategy, includes: If the fault type of the faulty battery is the recoverable fault type, then the faulty battery is repaired online. If the fault type of the faulty battery is the unrecoverable fault type, a structured maintenance work order is generated and a maintenance instruction is sent to the maintenance personnel to remind them to replace the faulty component of the faulty battery.
7. A battery maintenance decision-making device, characterized in that, include: The acquisition module is used to acquire historical operating data of faulty batteries; The feature extraction module is used to preprocess the historical operating data and extract features from the preprocessed historical operating data to obtain the maintenance decision feature parameters of the faulty battery. The maintenance module is used to determine the fault type of the faulty battery based on the maintenance decision feature parameters, determine the maintenance strategy for the faulty battery based on the fault type, and perform maintenance on the faulty battery according to the maintenance strategy.
8. The apparatus according to claim 7, characterized in that, Before acquiring historical operating data of the faulty battery, the acquisition module further includes: The judgment unit is used to determine whether the faulty battery is in an isolated state; The instruction triggering unit is used to trigger a maintenance decision instruction for the faulty battery if the faulty battery is in the isolated state.
9. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and capable of running on the processor, the processor executing the program to implement the battery maintenance decision method as described in any one of claims 1-6.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the battery maintenance decision method as described in any one of claims 1-6.