Fuel cell stack assembly diagnosis method and device, electronic equipment and storage medium

Abstract

The invention discloses a fuel cell stack assembly diagnosis method and device, electronic equipment and a storage medium, and relates to the field of fuel cell simulation analysis, and the method comprises the following steps: constructing a physical model of a target component; simplifying local features of the physical model of the target component, and generating an optimized physical model of the target component; based on the optimized physical model of the target component, analyzing the target component in combination with the multi-physical field dimension, and generating multi-model analysis result data; obtaining preset target index data; acquiring real-time operation data of the electric pile; according to a comparison result of the multi-model analysis result data and preset target index data; judging whether the multi-model analysis result data meets preset target index data or not; if not, dynamically correcting the input parameters of the physical model of the target component in combination with the electric pile operation data collected in real time; and if the relative deviation of the analysis results of two adjacent iterations is within a preset range and all indexes meet preset target index data, outputting a diagnosis result.

Description

Technical Field

[0001] The present application relates to the field of fuel cell simulation analysis, and in particular to a fuel cell stack assembly diagnostic method, a fuel cell stack assembly diagnostic device, an electronic device, and a storage medium. Background Art

[0002] As the core power unit of commercial vehicles, the reliability and lifespan of fuel cell stacks directly impact the overall vehicle's operating efficiency and economic viability. With the widespread adoption of fuel cell commercial vehicles, the durability of stack assemblies under complex operating conditions has become increasingly prominent. However, existing diagnostic technologies primarily rely on characterization and analysis of single parameters such as voltage, temperature, and gas pressure, or on offline evaluations based on experimental testing. This results in delayed fault warnings, high maintenance costs, and even the risk of sudden failure.

[0003] While finite element analysis (FEA) is currently used for performance optimization during the fuel cell design phase, its application in real-time diagnosis still faces significant bottlenecks. First, existing methods often simulate a single physical field (such as mechanics or thermals), ignoring the interactive impact of multi-field coupling on fuel cell stack performance, resulting in insufficient model accuracy. Second, they lack an adaptive fusion mechanism for actual operating data, resulting in fixed model parameters that cannot be dynamically adjusted with fuel cell stack aging or environmental changes, reducing long-term diagnostic reliability. Furthermore, the harsh vibration, shock, and temperature fluctuations of commercial vehicles further exacerbate the dynamic uncertainty of the fuel cell stack's structural state, and existing diagnostic devices generally lack the efficient finite element modeling and real-time analysis capabilities for these operating conditions.

[0004] Therefore, developing a high-precision finite element diagnostic method and device for commercial vehicle fuel cell stack assemblies, which can achieve early warning of hidden faults and accurate assessment of health status through multi-physics field coupling modeling, real-time data-driven correction and edge computing optimization, is of great significance to improving the reliability of fuel cell systems and reducing the cost of the entire life cycle. Summary of the Invention

[0005] In view of this, the present invention aims to provide a fuel cell stack assembly diagnostic method, fuel cell stack assembly diagnostic device, electronic device, and storage medium. This solution proposes a new simulation analysis method for the fuel cell stack installed inside a fuel cell engine. This method includes analysis methods and processes for the stiffness, temperature field, strength, and random vibration of the fuel cell stack assembly, using ABAQUS / ANSA / FEMFAT software to complete simulation modeling, solution, and evaluation. The present invention provides the following solutions:

[0006] According to one aspect of the present invention, a fuel cell stack assembly diagnostic method is provided, comprising the following steps:

[0007] Build a physical model of the target component;

[0008] simplifying local features of the physical model of the target component, generating an optimized physical model of the target component based on the physical model of the target component;

[0009] analyzing the target component in multiple physical field dimensions based on the optimized physical model of the target component, and generating multi-model analysis result data;

[0010] acquiring preset target index data;

[0011] acquiring real-time data of the stack operation;

[0012] comparing the multi-model analysis result data with the preset target index data, and determining whether the multi-model analysis result data meets the preset target index data;

[0013] If not, the input parameters of the physical model of the target component are dynamically corrected in combination with the real-time collected stack operation data.

[0014] If the relative deviation of the analysis results of the adjacent two iterations is within the preset range and all indexes meet the preset target index data, a diagnosis result is output.

[0015] Further, the method further comprises: constructing the physical model of the target component comprises: constructing a physical model including a stack assembly shell, a current collecting plate, a membrane electrode assembly, and a bipolar plate assembly, to ensure that the topological relationship of each component is consistent with the actual assembly consistency.

[0016] Further, the method further comprises:

[0017] Simplifying the local features of the physical model of the target component comprises: simplifying the local features and retaining complete geometric features for the key force transmission path.

[0018] Further, the method further comprises:

[0019] The input parameters of the physical model of the target component include: material basic parameter input, multi-field coupling parameter expansion, different component characteristic grid rule definition, and nonlinear contact pair definition.

[0020] Further, the method further comprises:

[0021] The input parameters for constructing the physical model of the target component further include: acquiring an assembly relationship file, acquiring a feature size table, determining material properties of the target component, and acquiring working condition and load data.

[0022] Further, the method further comprises:

[0023] After preprocessing the input parameters for constructing the physical model of the target component, meshing is performed.

[0024] The grid division includes geometric defect repairing, non-key part deleting, key feature retaining and strengthening, contact area grid processing and output format model file.

[0025] Further, the method comprises the following steps:

[0026] The analysis of the target component in combination with multiple physical field dimensions comprises multi-working condition boundary condition loading and solving, temperature field analysis, acceleration load analysis and random vibration analysis.

[0027] According to two aspects of the present application, a fuel cell stack assembly diagnosis device is provided, which comprises:

[0028] A model building unit is configured to build a physical model of the target component.

[0029] A model optimization unit is configured to simplify local features of the physical model of the target component based on the physical model of the target component, and generate an optimized physical model of the target component.

[0030] A model analysis unit is configured to analyze the target component in combination with multiple physical field dimensions based on the optimized physical model of the target component, and generate multi-model analysis result data.

[0031] A judgment correction unit is configured to acquire preset target index data and real-time stack operation data.

[0032] According to the comparison result of the multi-model analysis result data and the preset target index data.

[0033] The multi-model analysis result data is judged whether it meets the preset target index data.

[0034] If no, the input parameters of the physical model of the target component are dynamically corrected in combination with the real-time collected stack operation data.

[0035] An iteration execution unit is configured to repeat the above steps until the analysis result deviation of the continuous two iterations is within a preset range and all indexes meet the preset target index data.

[0036] According to three aspects of the present application, an electronic device is provided, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete mutual communication through the communication bus.

[0037] The memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of a fuel cell stack assembly diagnosis method.

[0038] According to four aspects of the present application, a computer readable storage medium is provided, which stores a computer program executable by an electronic device, when the computer program is run on the electronic device, causes the electronic device to execute the steps of a fuel cell stack assembly diagnosis method.

[0039] Through the above scheme, the following beneficial technical effects are obtained:

[0040] The present application constructs a high-fidelity parameterized model by integrating the three-dimensional geometric model of the stack assembly, the assembly relationship file, the material multi-physical field attribute and the measured working condition data, and ensures the consistency of the simulation input and the actual physical state.

[0041] The present application balances the model accuracy and the calculation efficiency by using software to realize geometric defect repair and non-key feature simplification.

[0042] The present application ensures the stress analysis accuracy and contact convergence of the key area through the grid accurate division strategy and node mapping.

[0043] The present application realizes multi-field coupling and efficient solution through multi-physical field dimension, and realizes strength evaluation under dynamic load based on stress fatigue damage calculation. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 is a flowchart of a fuel cell stack assembly diagnosis method provided by one or more embodiments of the present application.

[0045] Figure 2 is a structural diagram of a fuel cell stack assembly diagnosis device provided by one or more embodiments of the present application.

[0046] Figure 3 is a schematic diagram of a fuel cell engine assembly and stack of one specific embodiment of the present application.

[0047] Figure 4 is a structural block diagram of an electronic device of a fuel cell stack assembly diagnosis method provided by one or more embodiments of the present application. DETAILED DESCRIPTION

[0048] The technical solutions of the present application will be described clearly and completely below with reference to the drawings, obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0049] Figure 1 is a flowchart of a fuel cell stack assembly diagnosis method provided by one or more embodiments of the present application.

[0050] like Figure 1 As shown, the following steps are included:

[0051] Step S1, constructing a physical model of the target component;

[0052] Specifically, the definition of the multi-component three-dimensional geometric model: accurately construct the three-dimensional geometric models of core components such as the stack assembly shell, current collecting plate, membrane electrode assembly, bipolar plate assembly, etc., to ensure the consistency of the topological relationship of each component with the actual assembly.

[0053] Step S2, based on the physical model of the target component, simplifying local features of the physical model of the target component to generate an optimized physical model of the target component;

[0054] Specifically, through geometric simplification and feature cleaning: local features that have little impact on the calculation results (such as tiny chamfers, process holes, and non-load-bearing threads) are simplified to eliminate redundant geometric details; the complete geometric features of key force transmission paths (such as bolt connection surfaces and longitudinal beam welding areas) are retained to avoid stress concentration distortion.

[0055] Step S3, analyzing the target component based on the optimized physical model of the target component in combination with multiple physical field dimensions to generate multi-model analysis result data;

[0056] Specifically, model correction: analyze and verify the dynamic characteristics of the model, dynamically adjust the longitudinal beam cutoff length (retain length ≥ 3 times the section height), and ensure that the model boundary conditions match the actual excitation.

[0057] Multiphysics dimensions include:

[0058] Input of basic material parameters: Determine the material properties used for the above components, including the elastic modulus, Poisson's ratio, tensile strength, yield strength, and S / N curve of the material.

[0059] Multi-field coupling parameter expansion: Define temperature material properties, including thermal expansion coefficient, wall heat transfer coefficient, and fit SN curve confidence intervals using fatigue test data.

[0060] Definition of grid rules for different component characteristics: including different grid size definitions and unit type definitions for the stack assembly shell, longitudinal beams, suspension assembly, current collecting plate, membrane electrode assembly, bipolar plate assembly, etc.

[0061] Definition of nonlinear contact pairs: Contact pairs are established in key areas such as bolt preload surface, suspension assembly, collector plate, and shell assembly surface.

[0062] Loading and solving of multiple working condition boundary conditions: Modal analysis extracts free modal calculation and constrained modal calculation respectively, and determines whether the structure needs to be improved based on the modal calculation results.

[0063] Temperature field analysis: Calculate the heat dissipation of the shell surface through the radiation model, define the convection heat transfer coefficient of the cooling channel, and build a heat generation model based on the actual situation of the fuel cell stack.

[0064] Acceleration load analysis: Apply acceleration loads in various directions to the assembly and calculate stiffness and strength.

[0065] Random vibration analysis: Convert test field data into a PSD spectrum, define the vibration duration corresponding to the target life, calculate the damage value, and evaluate whether the requirements are met.

[0066] Step S4, obtaining preset target indicator data;

[0067] Step S5, obtaining real-time data of the battery stack operation;

[0068] Step S6, comparing the multi-model analysis result data with the preset target indicator data;

[0069] Determine whether the multi-model analysis result data meets the preset target indicator data;

[0070] If not, dynamically modify the input parameters of the physical model of the target component in combination with the real-time collected stack operation data;

[0071] Step S7: If the relative deviation of the analysis results of two adjacent iterations is within a preset range and all indicators meet the preset target indicator data, the diagnosis result is output.

[0072] Specifically, the fluctuation range of the multi-field analysis results of two adjacent iterations in key performance parameters is less than the preset quantitative threshold; all performance indicators meet the requirements of the target indicator system built based on the fuel cell design specifications; through the dynamic parameter update strategy that integrates real-time operation data, the adaptive optimization of the analysis model is achieved until the two-dimensional convergence criteria are met, completing the closed-loop optimization process.

[0073] Further, including:

[0074] Constructing the physical model of the target component includes: constructing a physical model of the stack assembly shell, current collecting plate, membrane electrode assembly and bipolar plate assembly to ensure the consistency of the topological relationship of each component with the actual assembly.

[0075] Specifically, by integrating the three-dimensional geometric model of the battery stack assembly, assembly relationship files, multi-physical field properties of materials and measured operating condition data, a high-fidelity parametric model is constructed to ensure the consistency between the simulation input and the actual physical state.

[0076] Further, including:

[0077] Simplifying the local features of the physical model of the target component includes simplifying the local features and retaining the complete geometric features of the key force transmission path.

[0078] Further, including:

[0079] The input parameters of the physical model of the target component include: material basic parameter input, multi-field coupling parameter expansion, grid rule definition of different component characteristics, and nonlinear contact pair definition.

[0080] Further, including:

[0081] The input parameters for constructing the physical model of the target component also include: obtaining an assembly relationship file, obtaining a feature dimension table, determining the material properties of the target component, and obtaining working condition and load data.

[0082] Further, including:

[0083] After pre-processing the input parameters of the physical model of the target component, meshing is performed;

[0084] Among them, meshing includes: geometric defect repair, non-critical parts deletion, key feature retention and enhancement, contact area mesh processing and output format model file.

[0085] Further, including:

[0086] The analysis of target components in combination with multiple physical field dimensions includes: multi-condition boundary condition loading and solution, temperature field analysis, acceleration load analysis and random vibration analysis.

[0087] Through the above features, the three-dimensional geometric models of core components such as the stack assembly shell, current collector, membrane electrode assembly, and bipolar plate assembly are accurately constructed to ensure the consistency of the topological relationship of each component with the actual assembly. Local features that have little impact on the calculation results are simplified to eliminate redundant geometric details, while retaining the complete geometric features of key force transmission paths. The material properties of each component are determined, including elastic modulus, Poisson's ratio, tensile strength, yield strength, S / N curve, and temperature-related properties such as thermal expansion coefficient and wall heat transfer coefficient. The mesh size and unit type of each component are defined, and nonlinear contact pairs are established in key areas such as bolt preload surfaces, suspension assemblies, current collectors, and shell assembly surfaces.

[0088] Perform multi-condition boundary condition loading and solution, and perform free mode and constrained mode calculations separately. Calculate shell surface heat dissipation through a radiation model, define the convection heat transfer coefficient of the cooling channel, and construct a heat generation model based on the actual fuel cell stack to complete temperature field analysis. Apply acceleration loads in various directions to the assembly and perform stiffness and strength calculations. Convert test field data into a PSD spectrum, define the vibration duration corresponding to the target life, calculate damage values, and conduct a multi-field coupling analysis integrating the mechanical field and temperature field to obtain analysis results.

[0089] The analysis result is compared with the preset target index, if any analysis result does not meet the target index, at least one of the three-dimensional geometric model, material attribute parameter, grid division rule and contact relationship is dynamically corrected according to the type of the result that does not meet the target index, combined with the real-time collected stack operation data; the corresponding analysis step is re-executed, and the comparison and correction steps are repeated until the analysis result deviation of two consecutive iterations is within the preset range and all indexes meet the target requirement; the real-time collected stack operation data includes but is not limited to temperature, vibration and stress data, which is used to update the multi-field coupling parameters and correct the S / N curve confidence interval.

[0090] Through the above technical features, the technical problems of the prior art are solved, that is, the single physical field is simulated, the interaction influence of the multi-field coupling effect on the stack performance is ignored, the model precision is insufficient, and the adaptive fusion mechanism of the actual operation data is lacking, the model parameters are fixed, and the long-term diagnosis reliability is reduced. At the same time, the research and development cycle is shortened, multiple rounds of optimization are completed in the virtual simulation stage, the physical prototype iteration cost is reduced, the reliability of the design is improved, and the simulation analysis truly serves the design iteration of the product.

[0091] Figure 2 is a structural diagram of a fuel cell stack assembly diagnosis device provided by one or more embodiments of the present application.

[0092] As shown in Figure 2 , the device comprises:

[0093] The model building unit is configured to build a physical model of the target component.

[0094] The model optimization unit is configured to simplify the local features of the physical model of the target component based on the physical model of the target component, and generate an optimized physical model of the target component.

[0095] The model analysis unit is configured to analyze the target component based on the optimized physical model of the target component and in combination with multiple physical field dimensions, and generate multi-model analysis result data.

[0096] The judgment and correction unit is configured to obtain preset target index data and stack operation real-time data.

[0097] According to the comparison result of the multi-model analysis result data and the preset target index data;

[0098] Whether the multi-model analysis result data meets the preset target index data is judged.

[0099] If not, the input parameters of the physical model of the target component are dynamically corrected in combination with the real-time collected stack operation data.

[0100] The iterative execution unit is used to repeat the above steps until the deviation of the analysis results of two consecutive iterations is within a preset range and all indicators meet the preset target indicator data.

[0101] Specifically, physical models lack accuracy: Traditional fuel cell stack assembly physical models often contain redundant details, affecting computational efficiency and accuracy, and fail to fully consider the effects of multi-physics coupling. This device, through model building and optimization units, addresses the issues of redundant local features in physical models and the lack of comprehensive multi-physics analysis, ensuring a simplified and efficient model that accurately reflects actual conditions.

[0102] Lack of dynamic adaptability: Existing diagnostic technologies struggle to dynamically adjust model parameters based on the actual operating status of the fuel cell stack, resulting in reduced reliability of diagnostic results as the stack ages or the environment changes. The judgment and correction unit dynamically adjusts model input parameters based on real-time collected fuel cell operating data, resolving the issue of fixed model parameters and the inability to adapt adaptively.

[0103] Low reliability of analysis results: A single analysis process cannot guarantee the accuracy and reliability of the model, making misdiagnosis or missed diagnosis prone. The iterative execution unit solves the problem of unreliable analysis results by continuously optimizing the analysis results to ensure that the deviation is within the preset range and meets the preset target indicators.

[0104] The above technical features improve model accuracy and computational efficiency: the model building unit and the model optimization unit construct and simplify the physical model, removing redundant details while retaining key features. This not only improves model accuracy, but also reduces unnecessary calculations, speeds up calculations, makes the model more in line with actual operating conditions, and provides a reliable foundation for subsequent analysis.

[0105] Enhanced diagnostic adaptability and accuracy: The judgment and correction unit dynamically corrects model parameters based on real-time stack operation data. Combined with multi-physical field dimensional analysis, the diagnostic device can adapt to different operation stages of the stack and complex environmental changes, significantly improving the accuracy and reliability of diagnostic results and avoiding misdiagnosis due to fixed model parameters.

[0106] Achieving closed-loop optimization and continuous improvement: The iterative execution unit continuously iterates to ensure that the deviation of the analysis results is controlled within the preset range and that all indicators meet the target requirements, forming a closed-loop optimization mechanism. This mechanism enables continuous improvement of the diagnostic device, continuously enhancing the diagnostic capabilities of the fuel cell stack assembly and ensuring stable and efficient operation of the stack.

[0107] It is worth noting that, although the device only discloses the model building unit, the model optimization unit, the model analysis unit, the judgment correction unit and the iterative execution unit, but does not mean that the device is limited to the above basic function modules, relatively, the meaning expressed by the present application is that on the basis of the above basic function modules, the person skilled in the art can add one or more function modules according to the prior art to form infinite embodiments or technical solutions, that is, the system is open rather than closed, and the protection scope of the present application claimed cannot be limited to the above disclosed basic function modules because the present embodiment only discloses individual basic function modules.

[0108] In another specific embodiment, a fuel cell stack analysis system is provided, comprising:

[0109] A modeling module for performing multi-component three-dimensional geometric model definition, geometric simplification and feature cleaning, material parameter input, mesh rule definition, nonlinear contact pair definition;

[0110] An analysis module for multi-condition boundary condition loading and solving, modal analysis, temperature field analysis, acceleration load analysis, random vibration analysis and multi-field coupling analysis;

[0111] A data fusion and closed-loop control module for real-time acquisition of stack operation data, comparison of analysis results with preset target indicators, triggering of corresponding feedback paths when the analysis results do not meet the target indicators, dynamic correction of the modeling module to the model, parameters, rules or contact pairs, and re-calling of the analysis module to perform corresponding analysis steps until the analysis results of two consecutive iterations are within the preset range and all indicators meet the design requirements.

[0112] Further, comprising: the data fusion and closed-loop control module is further used to set quantitative target indicator thresholds for each analysis link, the target indicator thresholds including modal frequency safety margin ≥20%, temperature deviation ≤5℃, damage value ≤1.

[0113] Further, comprising: the data fusion and closed-loop control module is further used to establish a parameter change log and an operation data archive, record the parameter change information of each model correction and the stack operation data at the corresponding time, for tracing the optimization process and the influence of parameter adjustment on the results.

[0114] Figure 3 is a schematic diagram of a fuel cell engine assembly and a stack of one specific embodiment of the present application.

[0115] The specific implementation process is as follows:

[0116] First, the fuel cell stack assembly parameters and the model need to be collected to prepare for simulation analysis, and the data to be collected includes:

[0117] 3D models of the stack assembly housing, current collector, membrane electrode assembly, bipolar plate assembly and related accessories

[0118] Assembly relationship files, including bolt preload, contact relationship, welding relationship, etc.

[0119] Key feature dimensions, such as bipolar plate channel width, membrane electrode active area, and cooling channel cross-sectional dimensions

[0120] Determine the material properties of the above components, including the elastic modulus, Poisson's ratio, tensile strength, yield strength, S / N curve, thermophysical properties, and contact characteristics of the material. Each component needs to be set with the correct density, and the total mass of the simplified model of the battery stack assembly should be equal to the actual mass.

[0121] Working condition and load data: test field vibration acceleration spectrum, stack operating temperature field data, cooling system parameters flow, temperature, pressure, etc.

[0122] After the above data is ready, pre-processing is performed and meshing is performed. The mesh model requirements are as follows:

[0123] Geometric defect repair: Use pre-processing software to repair model gaps and interferences, manually repair complex surfaces, eliminate non-load-bearing features such as tiny chamfers and process holes, and smooth burrs on the edges of membrane electrodes.

[0124] Deletion of non-critical parts: Remove components such as brackets and decorative covers that contribute less than 1% to the overall stiffness; perform mass point equivalence on the retained components to ensure conservation of inertia parameters.

[0125] Key features are retained and enhanced: solid bolt modeling is used, the mesh nodes in the membrane electrode-bipolar plate contact area correspond, and the inlet and outlet structures of the cooling channel are completely retained to ensure smooth and accurate calculations.

[0126] Contact area mesh processing: Node mapping is used on the bolt connection surface to ensure consistent mesh density between the master and slave surfaces; the membrane electrode-bipolar plate interface is offset to avoid initial penetration.

[0127] After the mesh is divided, it is output as a .inp format model file.

[0128] Based on test data and flow field calculations, temperature and acceleration loads are applied to the assembly to perform temperature field, stiffness, and strength calculations. After loading, the loads are imported into ABAQUS software for solution calculations. The resulting .odb file is then generated, and displacement data is read to evaluate assembly stiffness. Evaluation criteria are determined based on actual space and displacement requirements.

[0129] The .odb file is input into the femfat software to calculate the safety factor, and the stack assembly strength is evaluated based on the safety factor. The safety factor evaluation standard is formed by accumulated experience.

[0130] If there is no accumulated empirical data or evaluation criteria, strength evaluation can be performed based on the stress calculation results. The evaluation criterion is that the maximum stress value is less than the tensile strength limit of the material.

[0131] Figure 4 This is a block diagram of an electronic device structure of a fuel cell stack assembly diagnostic method provided by one or more embodiments of the present invention.

[0132] like Figure 4 As shown, the present application provides an electronic device, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0133] A computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of a fuel cell stack assembly diagnosis method.

[0134] The present application also provides a computer-readable storage medium storing a computer program executable by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of a fuel cell stack assembly diagnostic method.

[0135] For simplicity of description, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because certain steps can be performed in other orders or simultaneously according to the embodiments of the present invention. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0136] Through the description of the above embodiments, it can be seen that those skilled in the art can clearly understand that the present application can be implemented by means of software plus the necessary general hardware platform. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present application or certain parts of the embodiments.

[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A fuel cell stack assembly diagnostic method, characterized in that: include: Build a physical model of the target component; Based on the physical model of the target component, simplify the local features of the physical model of the target component to generate an optimized physical model of the target component; Based on the optimized physical model of the target component, the target component is analyzed in combination with multiple physical field dimensions to generate multi-model analysis result data; Obtain preset target indicator data; Obtain real-time data on the operation of the fuel cell stack; According to the comparison results of the multi-model analysis result data and the preset target indicator data, it is judged whether the multi-model analysis result data meets the preset target indicator data; If not, dynamically modify the input parameters of the physical model of the target component in combination with the real-time collected stack operation data; If the relative deviation of the analysis results of two adjacent iterations is within the preset range and all indicators meet the preset target indicator data, the diagnosis result is output.

2. A fuel cell stack assembly diagnostic method according to claim 1, characterized in that: Constructing the physical model of the target component includes: constructing a physical model of the stack assembly shell, current collecting plate, membrane electrode assembly and bipolar plate assembly to ensure the consistency of the topological relationship of each component with the actual assembly.

3. A fuel cell stack assembly diagnostic method according to claim 1, characterized in that: Simplifying the local features of the physical model of the target component includes simplifying the local features and retaining the complete geometric features of the key force transmission path.

4. A fuel cell stack assembly diagnostic method according to claim 1, characterized in that: The input parameters of the physical model of the target component include: material basic parameter input, multi-field coupling parameter expansion, different component characteristic grid rule definition and nonlinear contact pair definition.

5. A fuel cell stack assembly diagnostic method according to claim 4, characterized in that: The input parameters for constructing the physical model of the target component also include: obtaining an assembly relationship file, obtaining a feature dimension table, determining the material properties of the target component, and obtaining working condition and load data.

6. A fuel cell stack assembly diagnostic method according to claim 5, characterized in that: include: After pre-processing the input parameters of the physical model of the target component, meshing is performed; The meshing process includes: repairing geometric defects, deleting non-critical parts, retaining and strengthening key features, processing contact area meshes, and outputting format model files.

7. A fuel cell stack assembly diagnostic method according to claim 1, characterized in that: The target component is analyzed in combination with multiple physical field dimensions, including: multi-condition boundary condition loading and solution, temperature field analysis, acceleration load analysis and random vibration analysis.

8. A fuel cell stack assembly diagnostic device, characterized in that: include: A model building unit, used to build a physical model of the target component; A model optimization unit, configured to simplify local features of the physical model of the target component based on the physical model of the target component, and generate an optimized physical model of the target component; A model analysis unit, configured to analyze the target component based on an optimized physical model of the target component in combination with multiple physical field dimensions, and generate multi-model analysis result data; A judgment and correction unit is used to obtain preset target indicator data and real-time data of the fuel cell stack operation; Comparison results based on multi-model analysis results and preset target indicator data; Determine whether the multi-model analysis result data meets the preset target indicator data; If not, dynamically modify the input parameters of the physical model of the target component in combination with the real-time collected stack operation data; The iterative execution unit is used to repeat the above steps until the deviation of the analysis results of two consecutive iterations is within a preset range and all indicators meet the preset target indicator data.

9. An electronic device, characterized in that: include: A processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; A computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of a fuel cell stack assembly diagnostic method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that It stores a computer program that can be executed by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of a fuel cell stack assembly diagnostic method as described in any one of claims 1-7.

Images