Fault diagnosis method, device and equipment of fuel cell and storage medium

Abstract

The invention discloses a fault diagnosis method, device and equipment for a fuel cell and a storage medium. The fault diagnosis method of the fuel cell comprises the following steps: analyzing fusion fault data according to an alternating current impedance spectrum of a newly added fuel cell; analyzing the reliability of the fused fault data; when the reliability of the fused fault data reaches a preset fusion threshold value, using the fused fault data to train a preset fault diagnosis model; and diagnosing the fault type of the fuel cell through the trained fault diagnosis model. According to the technical scheme of the invention, the fault diagnosis model can be continuously adjusted according to the fused fault data, so that the fault diagnosis model can be adaptively adjusted according to the aging of the fuel cell and the change of the operation environment, and the accuracy of a fault diagnosis result is ensured.

Description

Technical Field

[0001] The present invention relates to the field of fuel cells, and particularly to a method, device, equipment and storage medium for fault diagnosis of a fuel cell. Background Art

[0002] Fault diagnosis of a fuel cell is carried out by collecting the voltage of the fuel cell and judging whether there is a fault in the fuel cell by comparing the deviation between the collected voltage value and the normal voltage value. In the prior art, the existing technical solutions for fault diagnosis cannot adapt to the changes in the operating environment and the aging of the fuel cell itself, resulting in a large error in the fault diagnosis model, and thus more misjudgments in the fault diagnosis of the fuel cell. How to properly self-adapt to the changing operating environment and the aging fuel cell has become an urgent issue in the industry. Summary of the Invention

[0003] The present invention provides a method, device, equipment and storage medium for fault diagnosis of a fuel cell, which is used to dynamically adjust a fault diagnosis model according to newly added fault data to ensure the accuracy of the fault diagnosis result.

[0004] According to a first aspect of the present invention, there is provided a method for fault diagnosis of a fuel cell, the fault diagnosis method including: Analyzing out fusion fault data according to the newly added AC impedance spectrum of the fuel cell; Analyzing the reliability of the fusion fault data; When the reliability of the fusion fault data reaches a preset fusion threshold, training a preset fault diagnosis model using the fusion fault data; Diagnosing the fault type of the fuel cell through the trained fault diagnosis model.

[0005] In one embodiment, the analyzing out fusion fault data according to the newly added AC impedance spectrum of the fuel cell includes: When the data volume of the newly added AC impedance spectrum of the fuel cell and the data volume of the existing AC impedance spectrum of the fuel cell reach a preset ratio, acquiring the newly added AC impedance spectrum of the fuel cell; Classifying the fault types of the newly added AC impedance spectrum of the fuel cell through a clustering analysis algorithm; Associating the newly added AC impedance spectrum of the fuel cell with the fault types to form newly added fault data, and the fusion fault data is composed of the newly added fault data and the existing fault data.

[0006] In one embodiment, the classifying the fault types of the newly added AC impedance spectrum of the fuel cell through a clustering analysis algorithm includes: Calculate the distance between the AC impedance spectrum of the newly added fuel cell and the center points of the AC impedance spectra of each fault type; Determine the fault type corresponding to the center point with the closest distance as the fault type of the AC impedance spectrum of the newly added fuel cell.

[0007] In one embodiment, before analyzing the reliability of the fused fault data, it includes: Calculate the fusion center points of each fault type of the fused fault data; Perform clustering analysis on the existing fault data using the fusion center points to obtain the fused fault types of the existing fault data.

[0008] In one embodiment, the analysis of the reliability of the fused fault data includes: Calculate the coincidence rate between the fused fault types of the existing fault data and the original fault types; When the coincidence rate is greater than the preset fusion threshold, confirm that the fused fault data has reached the preset fusion threshold; When the coincidence rate is less than or equal to the preset fusion threshold, confirm that the fused fault data has not reached the preset fusion threshold.

[0009] In one embodiment, the diagnosis of the fault type of the fuel cell by the trained fault diagnosis model includes: Obtain the AC impedance spectrum of the fuel cell to be diagnosed; Calculate the distance between the AC impedance spectrum of the fuel cell to be diagnosed and the center points of each fault type through the trained fault diagnosis model; Determine the fault type corresponding to the center point with the closest distance as the fault type of the fuel cell to be diagnosed.

[0010] According to the second aspect of the present invention, there is provided a fuel cell fault diagnosis device, including: A first analysis module, configured to analyze the fused fault data according to the AC impedance spectrum of the newly added fuel cell; A second analysis module, configured to analyze the reliability of the fused fault data; A training module, configured to use the fused fault data to train a preset fault diagnosis model when the reliability of the fused fault data reaches the preset fusion threshold; A diagnosis module, configured to diagnose the fault type of the fuel cell through the trained fault diagnosis model.

[0011] In one embodiment, the first analysis module, the second analysis module, the training module, and the diagnosis module are controlled to execute any one of the above fuel cell fault diagnosis methods.

[0012] According to a third aspect of the present invention, there is provided an electronic device, which includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the above-mentioned fault diagnosis method for any fuel cell is implemented.

[0013] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium, characterized in that computer program instructions are stored on the computer-readable storage medium, and when the computer program instructions are executed by a processor, the above-mentioned fault diagnosis method for any fuel cell is implemented.

[0014] In summary, the present invention provides a fault diagnosis method and device for a fuel cell. The method includes: analyzing and obtaining fusion fault data according to the alternating current impedance spectrum of a newly added fuel cell; analyzing the reliability of the fusion fault data; when the reliability of the fusion fault data reaches a preset fusion threshold, using the fusion fault data to train a preset fault diagnosis model; diagnosing the fault type of the fuel cell through the trained fault diagnosis model. Through the technical solution of the present application, the fault diagnosis model can be continuously adjusted according to newly added fault data, so that the fault diagnosis model can be adaptively adjusted for the aging of the fuel cell itself and the changes in the operating environment to ensure the accuracy of the fault diagnosis result.

[0015] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained by the structures specifically pointed out in the written specification, claims, and drawings.

[0016] The technical solution of the present invention will be further described in detail below with reference to the drawings and embodiments. Description of the Drawings

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of a fault diagnosis method for a fuel cell provided by an embodiment of the present invention; Figure 2 It is a flowchart of step S11 of a fault diagnosis method for a fuel cell provided by an embodiment of the present invention; Figure 3Flow chart of step S22 of a fuel cell fault diagnosis method provided by an embodiment of the present invention; Figure 4 Flow chart of another fuel cell fault diagnosis method provided by an embodiment of the present invention; Figure 5 Flow chart of step S12 of a fuel cell fault diagnosis method provided by an embodiment of the present invention; Figure 6 Flow chart of step S14 of a fuel cell fault diagnosis method provided by an embodiment of the present invention; Figure 7 Structure diagram of a fuel cell fault diagnosis device provided by an embodiment of the present invention; Figure 8 Structure diagram of an electronic device provided by an embodiment of the present invention; Figure 9 Schematic flow diagram of obtaining an AC impedance spectrum provided by an embodiment of the present invention. Detailed implementation manners

[0019] The features and exemplary embodiments of various aspects of the present application will be described in detail below. For the purpose of making the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than limiting the present application. For those skilled in the art, the present application can be implemented without some of these specific details. The following description of the embodiments is only intended to provide a better understanding of the present application by showing examples of the present application.

[0020] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, elements defined by the statement "including..." do not exclude the presence of additional identical elements in the process, method, article or device including the said elements.

[0021] As Figure 1 shown, the present invention provides a fuel cell fault diagnosis method, and the fault diagnosis method includes: In step S11, fusion fault data is analyzed based on the AC impedance spectrum of the newly added fuel cell. In step S12, the reliability of the fusion fault data is analyzed. In step S13, when the reliability of the fusion fault data reaches a preset fusion threshold, the preset fault diagnosis model is trained using the fusion fault data. In step S14, the fault type of the fuel cell is diagnosed through the trained fault diagnosis model.

[0022] In one embodiment, an AC voltage and current signal are applied to a DC-DC converter to collect the AC impedance spectrum of the fuel cell. The fuel cell control unit (FCU) performs fault diagnosis on the fuel cell according to the AC impedance spectrum, and performs corresponding interventions according to the fault diagnosis results to enable the fuel cell to return to a normal state. The application scenarios of the technical solution of the present application include, but are not limited to, after the fuel cell vehicle is put on the market. The AC impedance spectrum of the fuel cell is collected through the in-vehicle DC / DC. When the ratio of the number of the existing AC impedance spectrum to the newly added AC impedance spectrum reaches a preset ratio, the newly added AC impedance spectrum is labeled with the corresponding fault type to form new fault data, and the new fault data and the original fault data together constitute the fusion fault data. The coincidence rate between the fusion fault type of the existing fault data and the original fault type is used as a judgment condition for reliability. If the reliability of the fusion fault data reaches the preset fusion threshold, the preset fault diagnosis model is trained using the fusion fault data, that is, the fault diagnosis model is fitted and iterated through machine learning. Since the newly added AC impedance spectrum contains the changes of the fuel cell in a recent period of time, that is, it reflects the aging of the fuel cell itself and the changes in the operating environment, the updated fault diagnosis model can more accurately judge the fault type of the AC impedance spectrum to be detected, so as to facilitate the subsequent fault recovery strategy.

[0023] The first step of the fault recovery strategy is to determine whether the single - cell voltage of the fuel cell is lower than the threshold. If it is lower than the threshold, enter the fault diagnosis mode. The second step of the fault recovery strategy is to send instructions to the DC / DC and superimpose AC voltage and current, and calculate the AC impedance values in each frequency band to form an AC impedance spectrum. The third step of the fault recovery strategy is to input the AC impedance spectrum into the fault diagnosis model, and classify the faults according to the distance from the center points of each fault type. The fourth step of the fault recovery strategy is to terminate the fault diagnosis if the judgment result of the fault classification is in the normal state. The fifth step of the fault recovery strategy is to assume that the fault diagnosis is A, and fault A is due to the relatively dry stack membrane of the fuel cell. Then, adjust the air compressor speed or the back - pressure valve to reduce the air flow into the stack, and reduce the cooling water temperature. The sixth step of the fault recovery strategy is to assume that the fault diagnosis is B, and the occurrence of fault B is because the water content in the stack membrane of the fuel cell is relatively high. Then, adjust the air compressor speed or the back - pressure valve to increase the air flow into the stack, increase the cooling water temperature, increase the speed of the circulation pump and the opening frequency of the drain valve to increase the drainage efficiency. The seventh step of the fault recovery strategy is to determine whether the single - cell voltage of the fuel cell has returned to normal. If it has returned to normal, terminate the fault diagnosis; if not, return to the fifth step or the sixth step of the fault recovery control.

[0024] The technical solution in this embodiment can continuously adjust the fault diagnosis model according to the newly added fault data, so that the fault diagnosis model can be adaptively adjusted for the aging of the fuel cell itself and the changes in the operating environment to ensure the accuracy of the fault diagnosis results.

[0025] In one embodiment, as Figure 2 shown, step S11 includes the following steps S21 - S23: In step S21, when the data volume of the AC impedance spectrum of the newly added fuel cell and the data volume of the AC impedance spectrum of the existing fuel cell reach a preset ratio, obtain the AC impedance spectrum of the newly added fuel cell; In step S22, classify the fault types of the AC impedance spectrum of the newly added fuel cell through the clustering analysis algorithm; In step S23, associate the AC impedance spectrum of the newly added fuel cell with the fault types to form newly added fault data, and the newly added fault data and the existing fault data constitute the fused fault data.

[0026] In one embodiment, the acquisition method of the AC impedance spectrum is to apply AC voltage signals with different frequency bands to the fuel cell, and then eliminate the noise through fast Fourier transform to obtain the AC impedance values in different frequency bands. When the AC impedance values in the full frequency band are obtained, an AC impedance spectrum can be formed, as Figure 9 shown. Among them, the horizontal axis of the AC impedance spectrum is the real part, and the vertical axis is the imaginary part.

[0027] If the number of AC impedance spectra of the newly added fuel cells is too small, the impact on the original fault diagnosis model will be too small. If the number of AC impedance spectra of the newly added fuel cells is too large, the interference to the original fault diagnosis model will be too large. When the data volume of the AC impedance spectra of the newly added fuel cells and the data volume of the AC impedance spectra of the existing fuel cells reach a preset ratio, the AC impedance spectra of the newly added fuel cells are obtained, where the preferred value of this preset ratio is 20%. The existing AC impedance spectra have labels of fault types, and multiple AC impedance spectra of each fault type are relatively concentrated, and the center point of each fault type can be calculated. Through the clustering analysis algorithm, the distance between the AC impedance spectra of the newly added fuel cells and the center point of any fault type is analyzed, and the fault type corresponding to the center point with the closest distance is used to label the AC impedance spectra of the newly added fuel cells with the fault type. For example, there are fault type A, fault type B, fault type C, and normal type. If the AC impedance spectrum a of the newly added fuel cell is closest to the center point of fault type A, then the newly added fuel cell's AC impedance a will be labeled with fault type A, that is, an association between the AC impedance spectrum a of the newly added fuel cell and fault type A is formed. The AC impedance spectra associated with the fault type are the newly added fault data α. Each AC impedance spectrum of the newly added fuel cells is labeled with the corresponding fault type, forming the newly added fault data. The newly added fault data and the existing fault data are combined together to form the fused fault data.

[0028] In one embodiment, as Figure 3 shown, step S22 includes the following steps S31 - S32: In step S31, calculate the distance between the AC impedance spectra of the newly added fuel cells and the center points of the AC impedance spectra of each fault type; In step S32, determine the fault type of the center point with the closest distance as the fault type of the AC impedance spectra of the newly added fuel cells.

[0029] In one embodiment, according to the above embodiment, the center point of each fault type is obtained through comprehensive analysis of all the AC impedance spectra of that fault type. Calculate the distances between the AC impedance spectrum a of the newly added fuel cell and the respective center points of fault type A, fault type B, fault type C, and normal type D, which are a1, a2, a3, and a4 respectively. Compare the numerical values of a1, a2, a3, and a4. If the smallest value among them is a1, then determine fault type A as the fault type of the AC impedance spectrum a of the newly added fuel cell.

[0030] In one embodiment, as Figure 4 shown, it further includes the following steps S31 - S32: In step S31, calculate the fusion center points of each fault type of the fused fault data; In step S32, use the fusion center points to perform clustering analysis on the existing fault data to obtain the fused fault types of the existing fault data.

[0031] In one embodiment, calculate the center point of all the AC impedance spectra of any fault type in the fused fault data, and this center point is the fusion center point. Due to the difference in the calculated data, there will be a certain positional offset between the fusion center point and the center points of the AC impedance spectra of the existing fault data. For example, the center points of the AC impedance spectra of the existing fault data are point X, point Y, point Z, and point W respectively, and the fusion center points of the AC impedance spectra of the fused fault data are point X', point Y', point Z', and point W' respectively. For example, for the AC impedance spectrum b of the existing fault data, use the fusion center points of each fault type to determine the fault type, calculate the distances from point X', point Y', point Z', and point W', and the distances are b'1, b'2, b'3, and b'4 respectively. Compare the numerical values of b'1, b'2, b'3, and b'4. If the smallest value among them is b'2, then determine that fault type B is the fused fault type of the AC impedance spectrum b of the existing fault data.

[0032] In one embodiment, as Figure 5 shown, step S12 includes the following steps S51 - S53: In step S51, calculate the coincidence rate between the fused fault type of the existing fault data and the original fault type; In step S52, when the coincidence rate is greater than the preset fusion threshold, confirm that the fused fault data has reached the preset fusion threshold; In step S53, when the coincidence rate is less than or equal to the preset fusion threshold, confirm that the fused fault data has not reached the preset fusion threshold.

[0033] In one embodiment, according to the previous embodiment, each AC impedance spectrum of the existing fault data has a fused fault type and an original fault type. For example, if the preset fusion threshold is 95%, and 98% of the fused fault types and original fault types in the AC impedance spectra of the existing fault data are the same, then the coincidence rate between the fused fault type and the original fault type of the existing fault data is 98%. When the coincidence rate is greater than the preset fusion threshold, confirm that the fused fault data has reached the preset fusion threshold. Obviously, the coincidence rate of 98% is greater than the preset fusion threshold of 95%, so it is confirmed that the fused fault data has reached the preset fusion threshold. For another example, if the coincidence rate between the fused fault type and the original fault type of the existing fault data is 72%, obviously the coincidence rate of 72% is less than the preset fusion threshold of 95%, so it is confirmed that the fused fault data has not reached the preset fusion threshold.

[0034] In one embodiment, as Figure 6 shown, step S14 includes the following steps S61 - S63: In step S61, obtain the AC impedance spectrum of the fuel cell to be diagnosed; In step S62, through the trained fault diagnosis model, calculate the distances between the AC impedance spectrum of the fuel cell to be diagnosed and the center points of each fault type; In step S63, determine that the fault type corresponding to the center point with the closest distance is the fault type of the fuel cell to be diagnosed.

[0035] In one embodiment, obtain the AC impedance spectrum c of the fuel cell to be diagnosed. Through the trained fault diagnosis model, calculate the distances between the AC impedance spectrum c of the fuel cell to be diagnosed and the respective center points of fault type A, fault type B, fault type C, and normal type D, which are c1, c2, c3, and c4 respectively. If the value of c3 is the smallest, then determine that fault type C is the fault type of the AC impedance spectrum c of the fuel cell to be diagnosed. Because the fault diagnosis model has been adaptively adjusted for the aging of the fuel cell itself and the changes in the operating environment, the adjusted fault diagnosis model can more accurately judge the fault type of the AC impedance spectrum to be detected, and thus can accurately select the subsequent fault recovery strategy.

[0036] In one embodiment, Figure 7 is a block diagram of a fault diagnosis device for a fuel cell shown according to an exemplary embodiment. As Figure 7 shown, the fault diagnosis device for the fuel cell includes a first analysis module 71, a second analysis module 72, a training module 73, and a diagnosis module 74.

[0037] The first analysis module 71 is used to analyze the fused fault data according to the AC impedance spectrum of the newly added fuel cell; The second analysis module 72 is used to analyze the reliability of the fused fault data; The training module 73 is used to train the preset fault diagnosis model with the fused fault data when the reliability of the fused fault data reaches a preset fusion threshold; The diagnosis module 74 is used to diagnose the fault type of the fuel cell through the trained fault diagnosis model.

[0038] The first analysis module 71, the second analysis module 72, the training module 73, and the diagnosis module 74 included in the block diagram of the fault diagnosis device for the fuel cell are controlled to execute the fault diagnosis method of the fuel cell described in any of the above embodiments.

[0039] As Figure 8As shown, the present invention provides an electronic device 800, which includes a processor 801 and a memory 802 storing computer program instructions; When the processor 801 executes the computer program instructions, it analyzes the fused fault data according to the newly added AC impedance spectrum of the fuel cell; analyzes the reliability of the fused fault data; when the reliability of the fused fault data reaches a preset fusion threshold, uses the fused fault data to train a preset fault diagnosis model; and diagnoses the fault type of the fuel cell through the trained fault diagnosis model.

[0040] The present invention provides a computer-readable storage medium storing computer program instructions, which, when executed by a processor, analyze the fused fault data according to the newly added AC impedance spectrum of the fuel cell; analyze the reliability of the fused fault data; when the reliability of the fused fault data reaches a preset fusion threshold, use the fused fault data to train a preset fault diagnosis model; and diagnose the fault type of the fuel cell through the trained fault diagnosis model.

[0041] It should be understood that the specific features, operations, and details described above regarding the method of the present invention can be similarly applied to the apparatus and system of the present invention, or vice versa. Additionally, each step of the method of the present invention described above can be executed by the corresponding components or units of the apparatus or system of the present invention.

[0042] It should be understood that each module / unit of the apparatus of the present invention can be implemented in whole or in part by software, hardware, firmware, or a combination thereof. Each module / unit can be embedded in the processor of the computer device in the form of hardware or firmware or independent of the processor, or stored in the memory of the computer device in the form of software for the processor to call to execute the operations of each module / unit. Each module / unit can be implemented as an independent component or module, or two or more modules / units can be implemented as a single component or module.

[0043] In one embodiment, a computer device is provided, which includes a memory and a processor. Computer instructions executable by the processor are stored on the memory. When the computer instructions are executed by the processor, the processor is instructed to execute the steps of the method according to the embodiments of the present invention. The computer device can generally be a server, a terminal, or any other electronic device with necessary computing and / or processing capabilities. In one embodiment, the computer device may include a processor, a memory, a network interface, a communication interface, etc. connected through a system bus. The processor of the computer device can be used to provide necessary computing, processing, and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and an internal memory. An operating system, computer programs, etc. may be stored in or on the non-volatile storage medium. The internal memory can provide an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface and communication interface of the computer device can be used to connect and communicate with external devices through a network. When the computer program is executed by the processor, the steps of the method according to the present invention are executed.

[0044] The present invention can be implemented as a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method according to the embodiments of the present invention are caused to be executed. In one embodiment, the computer program is distributed among a plurality of network-coupled computer devices or processors, so that the computer program is stored, accessed, and executed in a distributed manner by one or more computer devices or processors. A single method step / operation, or two or more method steps / operations, can be executed by a single computer device or processor or by two or more computer devices or processors. One or more method steps / operations can be executed by one or more computer devices or processors, and one or more other method steps / operations can be executed by one or more other computer devices or processors. One or more computer devices or processors can execute a single method step / operation, or execute two or more method steps / operations.

[0045] Those of ordinary skill in the art can understand that the method steps of the present invention can be implemented by a computer program to instruct relevant hardware such as a computer device or a processor. The computer program can be stored in a non-transitory computer-readable storage medium, and when the computer program is executed, the steps of the present invention are caused to be executed. Depending on the circumstances, any reference herein to a memory, storage, database, or other medium may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0046] The technical features described above can be combined arbitrarily. Although not all possible combinations of these technical features are described, any combination of these technical features should be considered to be covered by this specification, as long as such a combination does not result in a contradiction.

[0047] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A fault diagnosis method for a fuel cell, characterized in that, Including: Analyze the fused fault data according to the AC impedance spectrum of the newly added fuel cell; Analyze the reliability of the fused fault data; When the reliability of the fused fault data reaches a preset fusion threshold, use the fused fault data to train a preset fault diagnosis model; Diagnose the fault type of the fuel cell through the trained fault diagnosis model.

2. The fault diagnosis method according to claim 1, characterized in that, The step of analyzing the fused fault data according to the AC impedance spectrum of the newly added fuel cell includes: When the data volume of the AC impedance spectrum of the newly added fuel cell and the data volume of the AC impedance spectrum of the existing fuel cell reach a preset ratio, obtain the AC impedance spectrum of the newly added fuel cell; Classify the fault types of the AC impedance spectrum of the newly added fuel cell through a clustering analysis algorithm; Associate the AC impedance spectrum of the newly added fuel cell with the fault types to form newly added fault data, and the fused fault data is composed of the newly added fault data and the existing fault data.

3. The fault diagnosis method according to claim 2, wherein, The step of classifying the fault types of the AC impedance spectrum of the newly added fuel cell through a clustering analysis algorithm includes: Calculate the distance between the AC impedance spectrum of the newly added fuel cell and the center points of the AC impedance spectra of each fault type; Determine the fault type of the center point with the closest distance as the fault type of the AC impedance spectrum of the newly added fuel cell.

4. The fault diagnosis method according to claim 2, wherein Before analyzing the reliability of the fused fault data, it includes: Calculate the fusion center points of each fault type of the fused fault data; Use the fusion center points to perform clustering analysis on the existing fault data to obtain the fused fault types of the existing fault data.

5. The fault diagnosis method according to claim 4, wherein The step of analyzing the reliability of the fused fault data includes: Calculate the coincidence rate between the fused fault types of the existing fault data and the original fault types; When the coincidence rate is greater than the preset fusion threshold, confirm that the fused fault data has reached the preset fusion threshold; When the coincidence rate is less than or equal to the preset fusion threshold, confirm that the fused fault data has not reached the preset fusion threshold.

6. The fault diagnosis method according to claim 1, wherein The step of diagnosing the fault type of the fuel cell through the trained fault diagnosis model includes: Obtain the AC impedance spectrum of the fuel cell to be diagnosed; Through the trained fault diagnosis model, calculate the distance between the AC impedance spectrum of the fuel cell to be diagnosed and the center points of each fault type; Determine the fault type corresponding to the center point with the closest distance as the fault type of the fuel cell to be diagnosed.

7. A fault diagnosis device for a fuel cell, characterized in that, Including: A first analysis module for analyzing the fused fault data according to the AC impedance spectrum of the newly added fuel cell; A second analysis module for analyzing the reliability of the fused fault data; A training module for using the fused fault data to train a preset fault diagnosis model when the reliability of the fused fault data reaches a preset fusion threshold; A diagnosis module for diagnosing the fault type of the fuel cell through the trained fault diagnosis model.

8. The adjusting device according to claim 7, characterized in that: The first analysis module, the second analysis module, the training module, and the diagnosis module are controlled to execute the fuel cell fault diagnosis method according to any one of claims 1-6.

9. A computing device, characterized in that, Including: A communication interface, a processor, and a memory; Wherein, the memory is used for storing program instructions, and when the program instructions are executed by the processor, the computing device implements the fuel cell fault diagnosis method according to any one of claims 1 to 6.

10. A computer-readable storage medium having program instructions stored thereon, characterized in that, When the program instructions are executed by a computer, the computer implements the fuel cell fault diagnosis method according to any one of claims 1 to 6.

Images