Fuel cell stack membrane electrode leak identification method and related products

Abstract

The application belongs to the technical field of fuel cells. A fuel cell stack membrane electrode leakage identification method and related products are proposed. Single piece voltages under low, medium and high current densities are collected, and the specificity performance loss difference value relative to the average value of the stack is calculated. Based on the characteristics that leakage leads to significant voltage loss at low current density and less impact at high current density, a differentiated threshold is set to determine leakage and locate the faulty single piece. Further, according to the size of the low-load specificity loss value, the leakage degree is subdivided into five levels from slight to critical, and a graded alarm and maintenance strategy is generated. The application eliminates common mode interference such as temperature and aging, does not require additional sensors, and significantly improves the safety and predictive maintenance capability of the stack operation.

Description

Technical Field

[0001] This invention relates to the field of fuel cell technology, specifically to a method for identifying leaks in the membrane electrode assembly (MEA) of a fuel cell stack and related products. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Fuel cells, as efficient and clean energy conversion devices, have broad application prospects in transportation and distributed power generation. The fuel cell stack, as its core component, is composed of multiple individual cells connected in series, with the membrane electrode assembly (MEA) being the key site for electrochemical reactions. The MEA typically consists of a proton exchange membrane, a catalyst layer, and a gas diffusion layer, and its performance directly determines the output efficiency and lifespan of the fuel cell stack. In actual operation, the fuel cell stack needs to frequently switch between different load conditions, and changes in current density cause fluctuations in the voltage of individual cells. To monitor the health of the fuel cell stack, the voltage data of each individual cell is typically monitored in real time, and performance degradation is assessed by comparing it with historical benchmark data. Existing battery management systems have basic data acquisition capabilities, capable of recording voltage performance under different current densities, providing data support for subsequent state analysis. With the accelerated commercialization of fuel cells, the requirements for system safety and reliability are increasing, making the accurate identification of early failures of core components a key focus of the industry.

[0004] Existing methods for identifying membrane electrode assembly (MEA) leaks in fuel cell stacks have limitations, making it difficult to accurately distinguish leaks from other types of performance degradation under complex operating conditions. Traditional diagnostic methods often rely on single voltage threshold judgments or average voltage analysis of the entire stack, neglecting leakage losses and ignoring the differences in various loss mechanisms across different current density ranges. When a micro-perforation or leak occurs in the MEA, it manifests as a significant increase in leakage loss in low current density regions, while in medium-to-high current density regions, it may be masked by ohmic or mass transfer losses. This leads to misjudgments or omissions in identification methods based on single operating conditions or simple difference calculations. Furthermore, existing solutions fail to effectively utilize the evolution of the difference between single-cell voltage and average single-cell voltage at different current densities, and cannot construct a discrimination logic that specifically reflects MEA leak characteristics. This makes it difficult to promptly and accurately locate target cells with MEA leaks during normal operation of the fuel cell stack, thus affecting system maintenance decisions and operational safety. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a method for identifying membrane electrode leaks in fuel cell stacks and related products. This method can detect internal perforations in the membrane electrode in advance without affecting the normal operation of the system, thereby improving the safety and reliability of the fuel cell stack.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for identifying membrane electrode leakage in a fuel cell stack.

[0007] A method for identifying membrane electrode leakage in a fuel cell stack includes the following steps: During normal operation of the fuel cell stack, the first difference between the initial voltage and the current voltage of each cell under the first current density, the second current density and the third current density are obtained, as well as the second difference between the initial voltage and the current voltage of the average single cell voltage corresponding to each cell. Based on the first and second differences, the performance loss difference of each single cell at the first current density, the second current density and the third current density are calculated. If the first performance loss difference of the target single cell at the first current density is greater than the first preset threshold, and the second performance loss difference at the second current density is less than the second preset threshold, and the third performance loss difference at the third current density is less than the third preset threshold, then it is determined that the target single cell has membrane electrode leakage.

[0008] In one implementation of the first aspect of the present invention, obtaining a first difference between the initial voltage and the current voltage of each individual cell, and a second difference between the initial voltage and the current voltage of the average single-cell voltage corresponding to each individual cell, includes: Record the initial single-cell voltage value and initial average single-cell voltage value of the fuel cell stack in its factory condition or normal condition; When the fuel cell stack is detected to be operating at the first current density, the current voltage value of each cell is read and the first difference under the first current density is calculated, and the second difference under the first current density is also calculated. When the fuel cell stack is detected to be operating at the second current density, the current voltage value of each cell is read and the first difference under the second current density is calculated, and the second difference under the second current density is also calculated. When the fuel cell stack is detected to be operating at the third current density, the current voltage value of each cell is read and the first difference under the third current density is calculated, and the second difference under the third current density is also calculated.

[0009] In one implementation of the first aspect of the present invention, the performance loss difference of each single cell at a first current density, a second current density, and a third current density is calculated based on a first difference and a second difference, including: Subtracting the second difference under the first current density from the first difference under the first current density yields the first performance loss difference. Subtracting the second difference at the second current density from the first difference at the second current density yields the second performance loss difference. Subtracting the second difference at the third current density from the first difference at the third current density yields the third performance loss difference.

[0010] In one implementation of the first aspect of the present invention, after determining that the target single cell has membrane electrode leakage, the method further includes: The perforation degree of the membrane electrode is determined based on the magnitude of the first performance loss difference. The larger the first performance loss difference, the larger the internal perforation of the membrane electrode or the more severe the leakage.

[0011] In one implementation of the first aspect of the present invention, before determining that the target single cell has membrane electrode leakage, the method further includes: To determine whether the first performance loss difference mainly depends on the membrane electrode perforation size and activation loss, to determine whether the second performance loss difference mainly depends on leakage loss and ohmic loss, and to determine whether the third performance loss difference mainly depends on ohmic loss and mass transfer loss.

[0012] In one implementation of the first aspect of the present invention, if the first performance loss difference of each single cell at the first current density is less than or equal to the first preset threshold, or the second performance loss difference at the second current density is greater than or equal to the second preset threshold, or the third performance loss difference at the third current density is greater than or equal to the third preset threshold, then it is determined that the membrane electrode of the fuel cell stack has no leakage.

[0013] Secondly, the present invention provides a fuel cell stack membrane electrode leakage identification system.

[0014] A fuel cell stack membrane electrode leakage detection system includes: The difference acquisition unit is configured to: during normal operation of the fuel cell stack, acquire the first difference between the initial voltage and the current voltage of each cell under the first current density, the second current density and the third current density, and the second difference between the initial voltage and the current voltage of the average single cell voltage corresponding to each cell. The loss calculation unit is configured to calculate the performance loss difference of each single cell at the first current density, the second current density, and the third current density based on the first difference and the second difference. The leakage determination unit is configured to determine that the target single cell has membrane electrode leakage if the first performance loss difference of the target single cell at the first current density is greater than the first preset threshold, the second performance loss difference at the second current density is less than the second preset threshold, and the third performance loss difference at the third current density is less than the third preset threshold.

[0015] Thirdly, the present invention provides a computer device, comprising: a processor and a computer-readable storage medium; A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the fuel cell stack membrane electrode leakage identification method of the first aspect of the present invention.

[0016] Fourthly, the present invention provides a computer-readable storage medium storing a computer program adapted to be loaded by a processor and executed by the fuel cell stack membrane electrode leakage identification method of the first aspect of the present invention.

[0017] Fifthly, the present invention provides a vehicle including a controller configured to perform a fuel cell stack membrane electrode leakage identification method according to a first aspect of the present invention; or, a fuel cell stack membrane electrode leakage identification system according to a second aspect of the present invention; or, a computer-readable storage medium according to a third aspect of the present invention; or, a computer device according to a fourth aspect of the present invention.

[0018] Compared with the prior art, the beneficial effects of the present invention are: This invention innovatively proposes a method for identifying membrane electrode leakage in fuel cell stacks. By calculating the performance loss difference between the voltage difference of a single cell and the average voltage difference of a single cell under different current densities, and making a joint judgment based on differentiated threshold logic in three current density ranges (low, medium, and high), it effectively solves the problem that existing technologies cannot accurately distinguish membrane electrode leakage from other performance degradation under complex operating conditions.

[0019] This invention utilizes the physical characteristics of membrane electrode leakage, where leakage loss increases significantly at low current densities but is less pronounced at medium and high current densities due to ohmic and mass transfer losses. A specific fault identification model is constructed to address this issue. By comparing the significant performance loss difference of a target single cell at the first current density with the slight performance loss difference at the second and third current densities, voltage fluctuation interference caused by non-leakage factors can be accurately isolated. This enables early and accurate identification of micro-perforations or leaks in the membrane electrode during normal operation of the fuel cell stack, significantly reducing false positives and false negatives, and improving the safety and maintenance efficiency of the fuel cell system.

[0020] Advantages of additional aspects of the invention 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 the invention. Attached Figure Description

[0021] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0022] Figure 1 A schematic flowchart of a fuel cell stack membrane electrode leakage identification method provided as an exemplary embodiment of the present invention; Figure 2 A schematic diagram of the framework of a fuel cell stack membrane electrode leakage identification system provided as an exemplary embodiment of the present invention; Figure 3 A schematic diagram of a computer device provided for an exemplary embodiment of the present invention. Detailed Implementation

[0023] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0024] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0025] This implementation proposes a method for identifying membrane electrode leakage in fuel cell stacks, which does not require a pressure difference and does not affect the normal operation of the system. Leakage in the membrane electrode can be identified in advance using data from normal stack operation. Accurate identification of membrane electrode leakage is achieved by analyzing the performance loss of individual cell voltage at different current densities. Specifically, at low current densities, membrane electrode leakage leads to significant voltage loss, while at high current densities, the voltage loss is relatively small. Therefore, by analyzing the performance loss of individual cell voltage at different current densities, membrane electrode leakage problems can be identified.

[0026] This invention utilizes the difference in sensitivity to leakage loss caused by changes in current density to improve the sensitivity and accuracy of leakage identification without affecting the normal operation of the system. By analyzing the performance loss of individual cell voltage under different current densities, the location of the leaking cell can be accurately pinpointed, improving the safety and reliability of the fuel cell stack. By comparing with the average individual cell voltage, misjudgments due to performance degradation caused by other factors are prevented. Online leakage identification can be achieved using existing voltage monitoring data without the need for additional sensors or engine disassembly, reducing identification costs and complexity.

[0027] The present invention will now be described in further detail with reference to the accompanying drawings. This embodiment takes a hydrogen fuel cell stack as an application scenario, aiming to achieve accurate identification of internal perforations or leaks in the membrane electrode assembly (MEA) through daily operating data, without affecting the normal operation of the system.

[0028] S101: System initialization and baseline data recording.

[0029] like Figure 1 As shown, when the fuel cell stack is in its factory condition or a confirmed healthy and normal state, the control system first performs the operation of "reading the voltage values ​​of each individual cell in the initial state".

[0030] At this point, the system records a set of baseline data, including: The initial single-cell voltage value of each cell (denoted as ) ,in, Indicates the first (Single battery); The initial average single-cell voltage of the entire fuel cell stack (denoted as ) ).

[0031] These initial values ​​will serve as a reference for subsequent calculations of voltage differences throughout the entire monitoring period.

[0032] Through the above methods, this invention establishes a high-precision personalized health baseline profile, eliminates the initial difference interference caused by individual manufacturing tolerances, and provides a reliable reference system for subsequent dynamic monitoring by recording the initial values ​​of all individual chips and the average voltage, ensuring that any slight performance degradation can be keenly detected, thus laying the data foundation for long-term accurate diagnosis.

[0033] S102: Data acquisition and difference calculation under multiple operating conditions.

[0034] During normal operation of the fuel cell stack, the control system continuously monitors the current current density and collects data based on three preset characteristic current density points (corresponding to current density A, current density B, and current density C, respectively).

[0035] Step 1: Monitoring of low current density conditions (i.e., the first current density, or current density A).

[0036] Real-time determination of whether the current current density has reached current density A (e.g.) (low-load interval); if determined to be yes, the system immediately performs a data recording operation: Read the current voltage value of each individual cell and calculate the voltage difference between each individual cell. : (1); Simultaneously calculate the current average voltage of a single chip and obtain the average voltage difference. : (2); in, and These are the first and second differences under the first current density, respectively; If the condition is not met, the system controls the fuel cell stack to continue operating normally until the condition is met.

[0037] Step 2: Monitoring of medium current density operating conditions (i.e., the second current density, or current density B).

[0038] Continue monitoring to determine whether the current current density has reached current density B (e.g., ...). If the specified interval is determined to be yes, perform a similar recording operation: Read the current voltage value of each individual cell; Calculate the voltage difference of each individual cell. : (3); Calculate the average voltage difference : (4); in, and These are the first and second differences under the second current density, respectively; If the determination is negative, the system controls the fuel cell stack to continue operating normally.

[0039] Step 3: Monitoring of high current density operating conditions (i.e., the third current density, or current density C).

[0040] Continue monitoring to determine whether the current current density has reached the current density C (e.g., ...). (High load or rated range), if determined to be yes, perform a recording operation: Read the current voltage value of each individual cell; Calculate the voltage difference of each individual cell. : (5); Calculate the average voltage difference : (6); in, and These are the first and second differences under the third current density, respectively; If the condition is not met, the system controls the fuel cell stack to continue operating normally, waiting for the next condition to meet the requirements.

[0041] This invention constructs a multi-dimensional voltage evolution spectrum by automatically acquiring data covering the low, medium and high operating conditions. By using real-time difference calculations under different loads, common-mode interference is effectively removed, and abnormal characteristics under specific operating conditions are highlighted. This provides rich and high-quality dynamic input data for subsequent leakage mechanism analysis based on electrochemical principles.

[0042] S103: Calculation of performance loss difference and leakage determination.

[0043] After the system successfully collects all the necessary data at current densities A, B, and C (i.e.) , , , , , (All have been acquired), and the core calculation and judgment stage has begun.

[0044] S103-1: Calculate the performance loss difference under different current densities.

[0045] For each single cell (the first) (i.e., slices), calculate the difference in specific performance loss at three current densities (i.e., slices). Figure 1 As shown , , ): First performance loss difference ( ): (7); This reflects the additional voltage drop of a single cell relative to the average level of the entire stack at low current densities. According to electrochemical principles, this value depends primarily on the perforation size of the membrane electrode and activation losses. If micropore leakage exists, the mixed potential effect caused by hydrogen permeation is most significant at low current densities.

[0046] Second performance loss difference ( ): (8); This reflects the specific losses at medium current densities, which mainly depend on leakage losses and ohmic losses.

[0047] Third performance loss difference ( ): (9); This reflects the specific losses at high current densities, which mainly depend on ohmic losses and mass transfer losses.

[0048] This invention uses a differential algorithm to accurately extract the specific loss of a single cell relative to the system average level, effectively isolating the effects of environmental fluctuations and common-mode decay. Combined with electrochemical mechanisms, the mixed potential effect under low current is quantified as a key indicator, enabling the clear identification of even minute membrane electrode perforations in complex operating environments, greatly improving the identification accuracy of fault characteristics.

[0049] S103-2: Leakage detection logic.

[0050] Set three preset thresholds, respectively , and (For example , , ).

[0051] Regarding the first For a single-cell battery, the system executes the following logical judgment: If all three of the following conditions are met: Condition 1: (Significant loss of specificity at low current densities). Condition 2: (The specificity loss is small at medium current densities). Condition 3: (The specificity loss is small at high current densities). Then determine: the first Single-cell batteries exhibit membrane electrode leakage; Otherwise (i.e., not all of the above conditions are met, for example, the loss is not significant at low current density, or the loss is significant at high current density): Therefore, it is determined that there is no leakage in the membrane electrode.

[0052] This invention constructs a logic decision model based on multi-feature fusion, utilizing the unique response curves of leakage under different current densities to effectively eliminate interference from other fault modes such as catalyst poisoning and water flooding. This "low-sensitivity, high-suppression" decision strategy significantly reduces the false alarm rate and false negative rate, ensuring the high reliability and robustness of the leakage identification results.

[0053] S104: Leakage assessment and maintenance recommendations.

[0054] Once a certain single cell is identified (such as the first one) The present invention can further address the issue of membrane electrode leakage in the wafer. The magnitude of the value is used to assess the severity of the leak.

[0055] Specifically A larger perforation area indicates a larger internal perforation area of ​​the membrane electrode, or a higher hydrogen leakage rate, indicating a more severe leak. This can be used to generate tiered alarm signals, guiding maintenance personnel to perform targeted replacements or repairs to prevent the fault from escalating. Assume the system is set with a basic judgment threshold. (That is, only values ​​exceeding this value are considered to pose a leakage risk), and one possible grading logic is as follows: Level L0: Normal fluctuation range (no leakage); Numerical range: ; Alarm status: Green (normal) (no alarm); Fault characteristics: The voltage fluctuation of a single chip is completely within the normal common-mode interference range, and no obvious signs of membrane electrode perforation or sealing failure were detected. The voltage difference at this time is mainly caused by manufacturing tolerances or minor temperature distribution variations. Operation and maintenance recommendation: Continuous monitoring without any intervention, automatic data recording to update the health baseline curve, and maintenance of regular inspection cycles.

[0056] Through L0-level routine monitoring and baseline self-updating mechanism, the system can dynamically adapt to the aging process of the fuel cell stack, ensuring no fault interference while accumulating valuable data for long-term health trend analysis and optimizing the whole life cycle management strategy.

[0057] Level L1: Minor leakage area (early warning); Numerical range: ; Alarm status: Yellow alert (Level 1 alarm); Fault characteristics: The membrane electrode may have micropores at the micrometer scale, or there may be very slight localized loosening of the end plate / sealing gasket, leading to trace hydrogen permeation. Under low load conditions, a measurable additional voltage drop begins to appear on this single electrode, but it has not yet affected the overall output performance of the fuel cell stack.

[0058] Maintenance recommendations: Observe closely and mark this unit as a "key observation object". Automatically shorten the data sampling and analysis cycle of this unit (e.g., from once every 100 hours to once every 10 hours). It is recommended that during the next routine maintenance of the vehicle / equipment, technicians conduct a visual inspection or airtightness retest of this area, and there is no need to immediately shut down the machine for replacement.

[0059] This invention establishes an L1-level early warning mechanism, capable of identifying micron-level leaks at the nascent stage of a fault, preventing potential hazards from escalating into major accidents. Through adaptive encrypted sampling and key marking strategies, it achieves precise allocation of maintenance resources, avoiding downtime losses caused by excessive maintenance while ensuring that potential risks are under close monitoring.

[0060] Level L2: Moderate leak area (planned maintenance); Numerical range: ; Alarm status: Orange alarm (Level 2 alarm); Fault characteristics: The membrane electrode exhibits significant perforation or an expanded area of ​​sealing failure, leading to increased hydrogen leakage. At low current densities, voltage stability deteriorates, and due to hydrogen-oxygen mixing, there is a potential risk of slight chemical degradation of the catalyst in adjacent cells, resulting in a deterioration in the overall consistency of the fuel cell stack. Maintenance recommendations: Planned maintenance, automatically generate "planned maintenance work orders" that require on-site visits in the near future (e.g., within 7 days), control strategies can be fine-tuned, and efforts should be made to avoid the fuel cell stack operating in extremely low current density ranges for extended periods to slow down leakage deterioration. Spare parts should be prepared in advance with corresponding single cells or short stack components for quick replacement during maintenance windows.

[0061] By setting up Level 2, a proactive planned maintenance process is triggered. Through the generation of work orders and pre-positioning of spare parts, unplanned downtime is transformed into controllable planned maintenance. Combined with fine-tuning of control strategies to avoid worsening operating conditions, the rate of fault propagation is effectively slowed, adjacent catalytic converters are protected, maintenance costs are minimized, and the operational efficiency of the fleet is ensured.

[0062] Level L3: Severe leakage zone (power-limited operation); Numerical range: ; Alarm status: Red fault (Level 3 alarm); Fault characteristics: The membrane electrode rupture area is large, or there is a through crack, allowing a large amount of hydrogen gas to enter the cathode side. Under low load conditions, the voltage of a single electrode drops severely, which can easily trigger the low voltage protection of the single electrode, leading to an unexpected shutdown. This poses a high safety hazard, and in high temperature and humidity environments, it may cause local hot spots or even thermal runaway.

[0063] Maintenance recommendations: Immediately limit power / restrict operation. The control system should automatically implement power limiting policies (Derating), prohibit the equipment from outputting high power, forcibly reduce the operating load, issue an emergency notice to the user, requiring them to come to the station for maintenance within 24-48 hours, prohibit vehicles / equipment from performing long-distance, high-load or complex operating tasks, and only allow them to travel to the maintenance station at low speed.

[0064] By implementing L3-level settings, proactive safety defenses are achieved. Automatic power limiting and forced load reduction prevent systemic shutdowns or thermal runaway risks caused by single-chip voltage collapse. Clearly defined, timely maintenance instructions and operational restrictions ensure minimal-risk operation of the equipment even when it is malfunctioning, buying valuable time for personnel evacuation and safe relocation.

[0065] Level L4: Critical Failure Zone (Emergency Shutdown); Numerical range: ; Alarm status: Purple Emergency (highest level alarm); Fault characteristics: The membrane electrode is completely broken down or torn over a large area, resulting in a severe internal short circuit or gas leakage. The voltage of a single cell may approach 0V or reverse polarity may occur, which may cause the fuel cell stack to catch fire, explode, or suffer irreversible physical damage at any time. Maintenance recommendations: In case of emergency shutdown and rescue, immediately execute the emergency shutdown procedure, instantly cut off the hydrogen supply, start the purging procedure, disconnect the high-voltage circuit, lock the system and equipment, and prohibit any form of restart attempt. Immediately notify a professional rescue team or towing service to transport the equipment to a repair center with explosion-proof conditions for disassembly and replacement. Do not attempt to handle the equipment on-site.

[0066] By implementing Level 4 safety measures, an ultimate safety barrier was constructed, capable of responding within milliseconds to catastrophic failures. Through multiple interlocking actions, including cutting off the hydrogen source, purging, and power outages, the fire and explosion chain was completely broken. Strict prohibition against restarting and professional rescue guidelines maximized the protection of personnel and surrounding assets, preventing secondary disasters.

[0067] In summary, the method of this invention enables online non-destructive testing, utilizing the low, medium, and high load conditions (current densities A / B / C) naturally encountered during the daily operation of vehicles or equipment for diagnosis. Unlike traditional methods, it eliminates the need for deliberately constructing hydrogen-air pressure differentials or shutdown tests, thus not affecting normal user operation. It also possesses high anti-interference capabilities by introducing a calculation method that subtracts the average difference from the single-chip difference (i.e.,... This effectively eliminates common-mode interference caused by temperature fluctuations, humidity changes, and overall aging of the fuel cell stack, and accurately extracts the specific voltage drop of a single cell caused by membrane electrode perforation; it can achieve precise positioning and characterization, not only determining whether there is a leak, but also accurately locating the specific single cell number. ), and through The numerical quantification of leakage levels provides strong data support for predictive maintenance, significantly improving the safety and lifespan management capabilities of the fuel cell stack.

[0068] Figure 2 A fuel cell stack membrane electrode leakage detection system is shown, comprising: The difference acquisition unit 201 is configured to: during the normal operation of the fuel cell stack, acquire the first difference between the initial voltage and the current voltage of each cell under the first current density, the second current density and the third current density, and the second difference between the initial voltage and the current voltage of the average single cell voltage corresponding to each cell. The loss calculation unit 202 is configured to calculate the performance loss difference of each single cell at the first current density, the second current density and the third current density based on the first difference and the second difference. The leakage determination unit 203 is configured to determine that the target single cell has membrane electrode leakage if the first performance loss difference of the target single cell at the first current density is greater than the first preset threshold, the second performance loss difference at the second current density is less than the second preset threshold, and the third performance loss difference at the third current density is less than the third preset threshold.

[0069] It is understood that the aforementioned units can be individually or entirely merged into one or more other units, or some of the units can be further divided into multiple functionally smaller units. This achieves the same operation without affecting the technical effects of the embodiments of the present invention. The aforementioned units are based on logical functional division. In practical applications, the function of one unit can be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of the present invention, the system may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented collaboratively by multiple units.

[0070] According to another embodiment of the present invention, the system of this embodiment can be constructed by running a computer program (including program code) capable of performing the steps involved in the corresponding method of the present invention on a general-purpose computing device, such as a computer, which includes processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). The computer program can be recorded on, for example, a computer-readable recording medium, loaded into the aforementioned computing device through the computer-readable recording medium, and run therein.

[0071] Figure 3 A computer device is shown, which includes a processor 301, a communication interface 302, and a computer-readable storage medium 303. The processor 301, communication interface 302, and computer-readable storage medium 303 can be connected via a bus or other means.

[0072] The communication interface 302 is used to receive and send data. The computer-readable storage medium 303 can be stored in the memory of the electronic device. The computer-readable storage medium 303 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the computer-readable storage medium 303.

[0073] The processor 301 is the computing and control core of the electronic device. It is suitable for implementing one or more instructions, specifically for loading and executing one or more instructions to achieve the corresponding method flow or corresponding function.

[0074] Processor 301 is configured to perform the following procedure: During normal operation of the fuel cell stack, the first difference between the initial voltage and the current voltage of each cell under the first current density, the second current density and the third current density are obtained, as well as the second difference between the initial voltage and the current voltage of the average single cell voltage corresponding to each cell. Based on the first and second differences, the performance loss difference of each single cell at the first current density, the second current density and the third current density are calculated. If the first performance loss difference of the target single cell at the first current density is greater than the first preset threshold, and the second performance loss difference at the second current density is less than the second preset threshold, and the third performance loss difference at the third current density is less than the third preset threshold, then it is determined that the target single cell has membrane electrode leakage.

[0075] This invention also provides a computer-readable storage medium, which is a memory device in an electronic device for storing programs and data. It is understood that the computer-readable storage medium here may include both built-in storage media in the electronic device and extended storage media supported by the electronic device. The computer-readable storage medium provides storage space for storing the processing system of the electronic device.

[0076] Furthermore, this storage space also contains one or more instructions suitable for loading and execution by the processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory; alternatively, it can also be at least one computer-readable storage medium located remotely from the aforementioned processor.

[0077] In one embodiment, the computer-readable storage medium stores one or more instructions; the processor loads and executes the one or more instructions stored in the computer-readable storage medium to perform the following process: During normal operation of the fuel cell stack, the first difference between the initial voltage and the current voltage of each cell under the first current density, the second current density and the third current density are obtained, as well as the second difference between the initial voltage and the current voltage of the average single cell voltage corresponding to each cell. Based on the first and second differences, the performance loss difference of each single cell at the first current density, the second current density and the third current density are calculated. If the first performance loss difference of the target single cell at the first current density is greater than the first preset threshold, and the second performance loss difference at the second current density is less than the second preset threshold, and the third performance loss difference at the third current density is less than the third preset threshold, then it is determined that the target single cell has membrane electrode leakage.

[0078] The present invention also provides a vehicle including a controller configured to perform the following processes: During normal operation of the fuel cell stack, the first difference between the initial voltage and the current voltage of each cell under the first current density, the second current density and the third current density are obtained, as well as the second difference between the initial voltage and the current voltage of the average single cell voltage corresponding to each cell. Based on the first and second differences, the performance loss difference of each single cell at the first current density, the second current density and the third current density are calculated. If the first performance loss difference of the target single cell at the first current density is greater than the first preset threshold, and the second performance loss difference at the second current density is less than the second preset threshold, and the third performance loss difference at the third current density is less than the third preset threshold, then it is determined that the target single cell has membrane electrode leakage.

[0079] Optionally, in some other implementations, the vehicle includes the aforementioned fuel cell temperature control dynamic adjustment system; or, the vehicle includes the aforementioned computer-readable storage medium; or, the vehicle includes the aforementioned computer equipment.

[0080] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can implement the described functions using different methods for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0081] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic cable, digital cable) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data processing device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0082] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for identifying membrane electrode leakage in a fuel cell stack, characterized in that, The process includes the following: During normal operation of the fuel cell stack, the first difference between the initial voltage and the current voltage of each cell under the first current density, the second current density and the third current density are obtained respectively, as well as the second difference between the initial voltage and the current voltage of the average single cell voltage corresponding to each cell. Based on the first and second differences, the performance loss difference of each single cell at the first current density, the second current density and the third current density are calculated. If the first performance loss difference of the target single cell at the first current density is greater than the first preset threshold, and the second performance loss difference at the second current density is less than the second preset threshold, and the third performance loss difference at the third current density is less than the third preset threshold, then it is determined that the target single cell has membrane electrode leakage.

2. The fuel cell stack membrane electrode leakage identification method as described in claim 1, characterized in that, Obtain the first difference between the initial voltage and the current voltage of each individual cell, and the second difference between the initial voltage and the current voltage of the average individual cell voltage corresponding to each individual cell, including: Record the initial single-cell voltage value and initial average single-cell voltage value of the fuel cell stack in its factory condition or normal condition; When the fuel cell stack is detected to be operating at the first current density, the current voltage value of each cell is read and the first difference under the first current density is calculated, and the second difference under the first current density is also calculated. When the fuel cell stack is detected to be operating at the second current density, the current voltage value of each cell is read and the first difference under the second current density is calculated, and the second difference under the second current density is also calculated. When the fuel cell stack is detected to be operating at the third current density, the current voltage value of each cell is read and the first difference under the third current density is calculated, and the second difference under the third current density is also calculated.

3. The fuel cell stack membrane electrode leakage identification method as described in claim 1, characterized in that, Based on the first and second differences, the performance loss differences of each single cell at the first, second, and third current densities are calculated, including: Subtracting the second difference under the first current density from the first difference under the first current density yields the first performance loss difference. Subtracting the second difference at the second current density from the first difference at the second current density yields the second performance loss difference. Subtracting the second difference at the third current density from the first difference at the third current density yields the third performance loss difference.

4. The fuel cell stack membrane electrode leakage identification method as described in claim 1, characterized in that, After confirming that the target single cell has membrane electrode leakage, the following steps are also included: The perforation degree of the membrane electrode is determined based on the magnitude of the first performance loss difference. The larger the first performance loss difference, the larger the internal perforation of the membrane electrode or the more severe the leakage.

5. The fuel cell stack membrane electrode leakage identification method as described in claim 1, characterized in that, Before determining that the target single cell has membrane electrode leakage, the following steps are also included: To determine whether the first performance loss difference mainly depends on the membrane electrode perforation size and activation loss, to determine whether the second performance loss difference mainly depends on leakage loss and ohmic loss, and to determine whether the third performance loss difference mainly depends on ohmic loss and mass transfer loss.

6. The fuel cell stack membrane electrode leakage identification method as described in claim 1, characterized in that, If the first performance loss difference of each cell at the first current density is less than or equal to the first preset threshold, or the second performance loss difference at the second current density is greater than or equal to the second preset threshold, or the third performance loss difference at the third current density is greater than or equal to the third preset threshold, then the membrane electrode of the fuel cell stack is determined to have no leakage.

7. A fuel cell stack membrane electrode leakage identification system, characterized in that, include: The difference acquisition unit is configured to: during normal operation of the fuel cell stack, acquire the first difference between the initial voltage and the current voltage of each cell under the first current density, the second current density and the third current density, and the second difference between the initial voltage and the current voltage of the average single cell voltage corresponding to each cell. The loss calculation unit is configured to calculate the performance loss difference of each single cell at the first current density, the second current density, and the third current density based on the first difference and the second difference. The leakage determination unit is configured to determine that the target single cell has membrane electrode leakage if the first performance loss difference of the target single cell at the first current density is greater than the first preset threshold, the second performance loss difference at the second current density is less than the second preset threshold, and the third performance loss difference at the third current density is less than the third preset threshold.

8. A computer device, characterized in that, include: Processor and computer-readable storage media; A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the fuel cell stack membrane electrode leakage identification method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted to be loaded by a processor and executed as described in any one of claims 1 to 6 for identifying membrane electrode leaks in a fuel cell stack.

10. A vehicle, characterized in that, The vehicle includes a controller configured to perform the fuel cell stack membrane electrode leakage identification method according to any one of claims 1-6; or, the vehicle includes the fuel cell stack membrane electrode leakage identification system according to claim 7; or, the vehicle includes the computer-readable storage medium according to claim 8; or, the vehicle includes the computer device according to claim 9.

Images