CN116231010B

CN116231010B - Fault diagnosis method and system for hydrogen fuel cell system

Info

Publication number: CN116231010B
Application number: CN202310521314.5A
Authority: CN
Inventors: 齐志刚
Original assignee: Beijing Xinyan Chuangneng Technology Co ltd
Current assignee: Beijing Xinyan Chuangneng Technology Co ltd
Priority date: 2023-05-10
Filing date: 2023-05-10
Publication date: 2023-07-18
Anticipated expiration: 2043-05-10
Also published as: CN116231010A

Abstract

The invention provides a hydrogen fuel cell system fault diagnosis method and system, which are used for collecting historical fuel cell system fault data and selecting first fault data matched with a hydrogen fuel cell system from the historical fuel cell system fault data; establishing a system fault model library and a fault factor model library of the hydrogen fuel cell system according to the first fault data; acquiring current working data and current three-dimensional image data of the hydrogen fuel cell system, and determining whether abnormality exists according to the current working data and the current three-dimensional image data; if the fault exists, the current working data is input into a system fault model library to judge whether a fault exists; if the fault exists, the current working data is input into a fault factor model library to determine the cause of the fault and output a fault diagnosis report. By the scheme of the invention, the fault can be timely and accurately judged when an abnormal condition occurs, and the fault reason can be intelligently and accurately determined.

Description

Fault diagnosis method and system for hydrogen fuel cell system

Technical Field

The invention relates to the technical field of detection, in particular to a hydrogen fuel cell system fault diagnosis method and system.

Background

The hydrogen fuel cell is used as a novel green pollution-free power generation device, the requirements in production and life are continuously expanded, various faults can be generated more or less due to defects generated in the production process or changes or aging of the use environment in the operation process of the fuel cell, however, the fault diagnosis of the hydrogen fuel cell by the conventional fault diagnosis scheme of the hydrogen fuel cell system is not intelligent and accurate enough.

Disclosure of Invention

Based on the problems, the invention provides a fault diagnosis method and a fault diagnosis system for a hydrogen fuel cell system.

In view of this, an aspect of the present invention proposes a hydrogen fuel cell system failure diagnosis method, the hydrogen fuel cell system including a hydrogen fuel cell stack and an accessory assembly; the hydrogen fuel cell stack comprises a plurality of single cells and end plates, wherein the single cells comprise bipolar plates and membrane electrodes, and the membrane electrodes comprise proton exchange membranes, catalyst layers and gas diffusion layers; the accessory component comprises a hydrogen supply component, an oxygen supply component, a temperature management component and a hydrogen fuel cell system management monitoring component; the hydrogen fuel cell system fault diagnosis method includes:

Collecting historical fuel cell system fault data, and selecting first fault data matched with the hydrogen fuel cell system from the historical fuel cell system fault data;

establishing a system fault model library and a fault factor model library of the hydrogen fuel cell system according to the first fault data;

providing a plurality of groups of sensors for the hydrogen fuel cell system, and monitoring the hydrogen fuel cell stack and the accessory assembly;

acquiring current working data and current three-dimensional image data of the hydrogen fuel cell system through the plurality of groups of sensors, and determining whether abnormality exists according to the current working data and the current three-dimensional image data;

if the fault exists, the current working data is input into the system fault model library to judge whether a fault exists;

if the fault exists, the current working data is input into the fault factor model library to determine the cause of the fault;

and outputting a fault diagnosis report of the hydrogen fuel cell system.

Optionally, the method further comprises:

acquiring first three-dimensional data, first image data, first production data and first test data of each functional component of the hydrogen fuel cell stack in the production process and the test process of the hydrogen fuel cell stack;

Establishing a first standard three-dimensional model library of each functional component according to the first three-dimensional data and the first image data;

establishing a first standard working model base and a first standard state model base of each functional component according to the first production data and the first test data;

acquiring second three-dimensional data, second image data, second production data and second test data of the accessory component in the production process and the test process of the accessory component;

establishing a second standard three-dimensional model library of the accessory component according to the second three-dimensional data and the second image data;

establishing a second standard working model base and a second standard state model base of each accessory component according to the second production data and the second test data;

the step of acquiring current working data and current three-dimensional image data of the hydrogen fuel cell system through the plurality of groups of sensors and determining whether abnormality exists according to the current working data and the current three-dimensional image data comprises the following steps:

acquiring first current working data of the hydrogen fuel cell stack and second current working data of the accessory component, inputting the first current working data into the first standard working model library and/or the first standard state model library, inputting the second current working data into the second standard working model library and/or the second standard state model library, and inputting the current three-dimensional image data into the first standard three-dimensional model library and the second standard three-dimensional model library to determine whether an abnormality exists;

If the abnormality exists, the step of inputting the current working data into the system fault model library to judge whether the fault exists comprises the following steps: if the fault exists, the first current working data and the second current working data are input into the system fault model library to judge whether a fault exists or not;

the step of inputting the current working data into the fault factor model library to determine the cause of the fault if the fault exists, comprising the following steps:

if a fault exists, the first current working data and the second current working data are input into the fault factor model to determine the reason for the fault.

Optionally, the step of collecting historical fuel cell system fault data and selecting first fault data matched with the hydrogen fuel cell system from the historical fuel cell system fault data includes:

acquiring the historical fuel cell system fault data of a plurality of types of fuel cell stacks from a cloud server;

extracting first attribute feature data of the hydrogen fuel cell stack from the first three-dimensional data, the first image data, the first production data, and the first test data;

Extracting second attribute feature data of the accessory component from the second three-dimensional data, the second image data, the second production data, and the second test data;

and determining the matched first fault data from the historical fuel cell system fault data according to the first attribute characteristic data and the second attribute characteristic data.

Optionally, the step of establishing a system fault model library and a fault factor model library of the hydrogen fuel cell system according to the first fault data includes:

dividing the first fault data into battery overall fault data, accessory component fault data and component fault data according to the overall fault of the fuel cell stack, accessory component fault and component fault;

training a corresponding neural network by utilizing the fuel cell stack overall fault data, the accessory component fault data and the component fault data respectively to obtain an accessory component fault model library of each accessory component and an accessory component fault model library of each functional component;

integrating the hydrogen fuel cell stack overall fault model, the accessory assembly fault model library and the component fault model library as the system fault model library;

Training a corresponding neural network by utilizing the fuel cell stack overall fault data, the accessory component fault data and the component fault data respectively to obtain the hydrogen fuel cell stack overall fault factor model, accessory component fault factor models of all the accessory components and component fault factor models of all the functional components respectively;

integrating the hydrogen fuel cell stack overall fault factor model, the sub-assembly fault factor model, and the component fault factor model as the fault factor model library.

Optionally, the end plate is provided with a ventilation device, the ventilation device comprises an air inlet pipe, an air outlet pipe and a first control valve arranged on the air inlet pipe and a second control valve arranged on the air outlet pipe, and the first control valve and the second control valve are connected to a hydrogen fuel cell system management monitoring assembly; the bipolar plate is provided with a runner; the air inlet pipe and the air outlet pipe penetrate through the whole hydrogen fuel cell stack; the pipeline walls of the air inlet pipe and the air outlet pipe are respectively provided with a first vent hole which is in butt joint with the flow channel on the bipolar plate and is communicated with the flow channel, and a switch structure which corresponds to the first vent holes one by one; the hydrogen fuel cell system management monitoring component controls the opening and closing of the switch structure through electric connection so as to realize the opening and closing of the first vent hole; sealing sleeves are respectively sleeved on the outer surfaces of the air inlet pipe and the air outlet pipe, and a second ventilation hole communicated with the first ventilation hole is formed in each sealing sleeve;

The step of providing a plurality of groups of sensors for the hydrogen fuel cell system to monitor the hydrogen fuel cell stack and the accessory assembly includes:

respectively acquiring first structural data and second structural data of the air inlet pipe and the air outlet pipe;

a first sensor group is arranged on the air inlet pipe according to a first installation mode conforming to the first structural data, and a second sensor group is arranged on the air outlet pipe according to a second installation mode conforming to the second structural data;

and acquiring third structural data of the flow channel, and arranging a third sensor group in the flow channel according to a third installation mode conforming to the third structural data.

Another aspect of the present invention provides a hydrogen fuel cell system failure diagnosis system including: the system comprises an Internet of things server, a hydrogen fuel cell stack and accessory components; the hydrogen fuel cell stack comprises a plurality of single cells and end plates, wherein the single cells comprise bipolar plates and membrane electrodes, and the membrane electrodes comprise proton exchange membranes, catalyst layers and gas diffusion layers; the accessory component comprises a hydrogen supply component, an oxygen supply component, a temperature management component and a hydrogen fuel cell system management monitoring component; the internet of things server is configured to:

and outputting a fault diagnosis report of the hydrogen fuel cell system.

Optionally, the internet of things server is configured to:

in the step of acquiring current working data and current three-dimensional image data of the hydrogen fuel cell system through the plurality of groups of sensors and determining whether an abnormality exists according to the current working data and the current three-dimensional image data, the internet of things server is configured to:

If the abnormality exists, the current working data is input into the system fault model library to judge whether a fault exists, and the internet of things server is configured to: if the fault exists, the first current working data and the second current working data are input into the system fault model library to judge whether a fault exists or not;

and if the fault exists, inputting the current working data into the fault factor model library to determine the cause of the fault, wherein the internet of things server is configured to:

Optionally, in the step of collecting historical fuel cell system fault data and selecting first fault data matched with the hydrogen fuel cell system from the historical fuel cell system fault data, the internet of things server is configured to:

Optionally, in the step of establishing a system fault model library and a fault factor model library of the hydrogen fuel cell system according to the first fault data, the internet of things server is configured to:

dividing the first fault data into fuel cell stack overall fault data, accessory assembly fault data and component fault data according to fuel cell stack overall fault, accessory assembly fault and component fault;

Optionally, an air breather is arranged on the end plate, the air breather comprises an air inlet pipe, an air outlet pipe, a first control valve arranged on the air inlet pipe and a second control valve arranged on the air outlet pipe, and the first control valve and the second control valve are both connected to a hydrogen fuel cell system management monitoring assembly; the bipolar plate is provided with a runner; the air inlet pipe and the air outlet pipe penetrate through the whole hydrogen fuel cell stack; the pipeline walls of the air inlet pipe and the air outlet pipe are respectively provided with a first vent hole which is in butt joint with the flow channel on the bipolar plate and is communicated with the flow channel, and a switch structure which corresponds to the first vent holes one by one; the hydrogen fuel cell system management monitoring component controls the opening and closing of the switch structure through electric connection so as to realize the opening and closing of the first vent hole; sealing sleeves are respectively sleeved on the outer surfaces of the air inlet pipe and the air outlet pipe, and a second ventilation hole communicated with the first ventilation hole is formed in each sealing sleeve;

The step of providing the hydrogen fuel cell system with a plurality of groups of sensors to monitor the hydrogen fuel cell stack and the accessory component, and the internet of things server is configured to:

By adopting the technical scheme of the invention, the hydrogen fuel cell system fault diagnosis method comprises the following steps: collecting historical fuel cell system fault data, and selecting first fault data matched with the hydrogen fuel cell system from the historical fuel cell system fault data; establishing a system fault model library and a fault factor model library of the hydrogen fuel cell system according to the first fault data; providing a plurality of groups of sensors for the hydrogen fuel cell system, and monitoring the hydrogen fuel cell stack and the accessory assembly; acquiring current working data and current three-dimensional image data of the hydrogen fuel cell system through the plurality of groups of sensors, and determining whether abnormality exists according to the current working data and the current three-dimensional image data; if the fault exists, the current working data is input into the system fault model library to judge whether a fault exists; if the fault exists, the current working data is input into the fault factor model library to determine the cause of the fault; and outputting a fault diagnosis report of the hydrogen fuel cell system. The system fault model library and the fault factor model library of the hydrogen fuel cell system are constructed by collecting the historical fuel cell system fault data so as to judge whether the hydrogen fuel cell stack has faults and the reasons for the faults, so that the system fault model library and the fault factor model library can not only timely and accurately judge whether the faults exist when abnormal conditions occur, but also intelligently and accurately determine the fault reasons.

Drawings

FIG. 1 is a flow chart of a hydrogen fuel cell system fault diagnosis method provided by one embodiment of the present invention;

fig. 2 is a schematic block diagram of a hydrogen fuel cell system failure diagnosis system provided in one embodiment of the invention.

Detailed Description

In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced otherwise than as described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.

The terms first, second and the like in the description and in the claims of the present application and in the above-described figures, are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

A fault diagnosis method and system for a hydrogen fuel cell system according to some embodiments of the present invention will be described with reference to fig. 1 to 2.

As shown in fig. 1, one embodiment of the present invention provides a hydrogen fuel cell system failure diagnosis method including: the hydrogen fuel cell system includes a hydrogen fuel cell stack and an accessory assembly; the hydrogen fuel cell stack comprises a plurality of single cells and end plates, wherein the single cells comprise bipolar plates and membrane electrodes, and the membrane electrodes comprise proton exchange membranes, catalyst layers and gas diffusion layers; the accessory component comprises a hydrogen supply component, an oxygen supply component, a temperature management component and a hydrogen fuel cell system management monitoring component; the hydrogen fuel cell system fault diagnosis method includes:

Collecting historical fuel cell system fault data, and selecting first fault data matched with the hydrogen fuel cell system from the historical fuel cell system fault data (namely determining a fuel cell stack and/or an accessory component of the fuel cell stack which are the same as (or have similar values within a preset range of) the hydrogen fuel cell stack and/or the accessory component according to the characteristic data of the hydrogen fuel cell stack and/or the accessory component);

establishing a system fault model library (including but not limited to a hydrogen fuel cell stack overall fault model, an accessory component fault model library of each accessory component, a component fault model library of each functional component, etc.) and a fault factor model library (including but not limited to a hydrogen fuel cell stack overall fault factor model, an accessory component fault factor model of each accessory component, a component fault factor model of each functional component, etc.) of the hydrogen fuel cell system based on the first fault data;

and outputting a fault diagnosis report of the hydrogen fuel cell system.

It is to be understood that in this embodiment, the individual functional components of the hydrogen fuel cell stack include, but are not limited to, end plates, bipolar plates, proton exchange membranes, catalyst layers, gas diffusion layers, and the like.

In the embodiment of the invention, firstly, whether the abnormality of the preset condition exists is primarily judged, then, whether the abnormality exists and the cause of the fault is determined is further judged, and the judgment result is accurate to avoid misjudgment by progressive layer by layer.

By adopting the technical scheme of the embodiment, the system fault model library and the fault factor model library of the hydrogen fuel cell system are constructed by collecting the historical fuel cell system fault data so as to judge whether the hydrogen fuel cell stack has faults and the cause of the faults, so that the fault can be timely and accurately judged when abnormal conditions occur, and the fault cause can be intelligently and accurately determined.

In some possible embodiments of the present invention, the method further comprises:

acquiring first three-dimensional data, first image data, first production data, first test data (including but not limited to acquiring three-dimensional data of the end plates, the bipolar plates, the proton exchange membrane, the catalyst layers, and the gas diffusion layers, image data, attribute data, material activity data, voltage data, current data, gas conversion efficiency, gas flow data, pressure data within a unit cell, coolant flow data, temperature data, etc.) of each functional component of the hydrogen fuel cell stack during production and during testing of the hydrogen fuel cell stack;

establishing a first standard three-dimensional model library (including, but not limited to, a standard three-dimensional model of a single cell, a standard three-dimensional model of an end plate, a standard three-dimensional model of a bipolar plate, a standard three-dimensional model of a proton exchange membrane, a standard three-dimensional model of a catalyst layer, a standard three-dimensional model of a gas diffusion layer, etc.) of each functional component according to the first three-dimensional data and the first image data;

establishing a first standard working model library and a first standard state model library of each functional component according to the first production data and the first test data (including but not limited to a standard working model/standard state model of a single battery, a standard working model/standard state model of an end plate, a standard working model/standard state model of a bipolar plate, a standard working model/standard state model of a proton exchange membrane, a standard working model/standard state model of a catalyst layer, a standard working model/standard state model of a gas diffusion layer, and the like);

establishing a second standard three-dimensional model library of the accessory component (including, but not limited to, a standard three-dimensional model of a hydrogen supply component, a standard three-dimensional model of an oxygen supply component, a standard three-dimensional model of a temperature management component, and a standard three-dimensional model of a hydrogen fuel cell system management monitoring component) according to the second three-dimensional data and the second image data;

establishing a second standard working model library and a second standard state model library of each accessory component (including but not limited to a standard working model/standard state model of a hydrogen supply component, a standard working model/standard state model of an oxygen supply component, a standard working model/standard state model of a temperature management component, a standard working model/standard state model of a hydrogen fuel cell system management monitoring component, etc.) according to the second production data and the second test data;

It can be understood that, in this embodiment, by acquiring the data of the multiple dimensions of each functional component and the data of the multiple dimensions of the accessory component of the hydrogen fuel cell stack, the first standard three-dimensional model library, the first standard working model library, the first standard state model library, the second standard three-dimensional model library, the second standard working model library, and the second standard state model library of each functional component and combining the current working data and the current three-dimensional image data, the present working data and the current three-dimensional image data are determined to determine whether the fault is abnormal, so that not only the accuracy of the abnormality determination can be further improved, but also the accurate data support can be improved for the subsequent fault location.

In some possible embodiments of the present invention, the step of collecting historical fuel cell system fault data and selecting first fault data matched with the hydrogen fuel cell system from the historical fuel cell system fault data includes:

It can be appreciated that in order to obtain historical fault data conforming to a hydrogen fuel cell stack to facilitate subsequent large data analysis and modeling and to obtain accurate analysis structures and models, in this embodiment, the historical fuel cell system fault data of multiple types of fuel cell stacks are obtained from a cloud server using its data acquisition capability and data processing analysis capability; extracting first attribute feature data of the hydrogen fuel cell stack from the first three-dimensional data, the first image data, the first production data and the first test data (namely extracting feature data including image feature, material feature, structural feature, material chemical feature, model feature, component specification feature, working state feature, pressure feature and the like from three-dimensional data of the end plate/the bipolar plate/the proton exchange membrane/the catalyst layer/the gas diffusion layer, image data, attribute data, material activity data, voltage data, current data, gas conversion efficiency, gas circulation data, pressure data in a single cell, coolant circulation data, temperature data and the like according to a pre-trained hydrogen fuel cell stack feature extraction model); extracting second attribute feature data of the accessory component from the second three-dimensional data, the second image data, the second production data, and the second test data (i.e., extracting second attribute feature data from the foregoing data according to a pre-trained accessory component feature extraction model); and determining matched first fault data (namely selecting fault data of corresponding fault components/assemblies/elements, which are the same as or similar to the hydrogen fuel cell stack and accessory components in the aspects of model, specification, structure, material chemical property, working performance, function and the like and reach a preset threshold value) from the historical fault data of the fuel cell system according to the first attribute characteristic data and the second attribute characteristic data.

In some possible embodiments of the present invention, the step of establishing a system fault model library and a fault factor model library of the hydrogen fuel cell system according to the first fault data includes:

It will be appreciated that, in order to obtain an accurate fault determination model and a fault factor model so as to be accurate and quick in final fault determination and fault cause determination, in this embodiment, the first fault data is classified and model-trained to obtain the overall fault model of the hydrogen fuel cell stack, the sub-assembly fault model library of each sub-assembly, the component fault model library of each functional assembly, and the overall fault factor model of the hydrogen fuel cell stack, the sub-assembly fault factor model of each sub-assembly, and the component fault factor model of each functional assembly, respectively, and by refining the models, more refined fault diagnosis can be provided.

In some possible embodiments of the present invention, a ventilation device is disposed on the end plate, where the ventilation device includes an intake pipe, an exhaust pipe, and a first control valve disposed on the intake pipe and a second control valve disposed on the exhaust pipe, and both the first control valve and the second control valve are connected to a hydrogen fuel cell system management and monitoring assembly; the bipolar plate is provided with a runner; the air inlet pipe and the air outlet pipe penetrate through the whole hydrogen fuel cell stack; the pipeline walls of the air inlet pipe and the air outlet pipe are respectively provided with a first vent hole which is in butt joint with the flow channel on the bipolar plate and is communicated with the flow channel, and a switch structure which corresponds to the first vent holes one by one; the hydrogen fuel cell system management monitoring component controls the opening and closing of the switch structure through electric connection so as to realize the opening and closing of the first vent hole; sealing sleeves are respectively sleeved on the outer surfaces of the air inlet pipe and the air outlet pipe, and a second ventilation hole communicated with the first ventilation hole is formed in each sealing sleeve;

acquiring first and second structural data (including, but not limited to, cavity capacity, length, and setting data of the first vent hole) of the intake pipe and the exhaust pipe, respectively;

a first sensor group is arranged on the air inlet pipe according to a first installation mode (including but not limited to installation intervals among sensors, installation quantity, connection mode and the like) conforming to the first structural data, and a second sensor group is arranged on the air outlet pipe according to a second installation mode (including but not limited to installation intervals among sensors, installation quantity, connection mode and the like) conforming to the second structural data;

and acquiring third structural data (including but not limited to shape, width, height, length and the like) of the flow channel, and arranging a third sensor group in the flow channel according to a third installation mode (including but not limited to installation interval between sensors, installation number, connection mode and the like) conforming to the third structural data.

It will be appreciated that in order to accurately and rapidly obtain real-time data of the hydrogen fuel cell system, in this embodiment, in addition to the various sensors provided on the outside of the hydrogen fuel cell stack and the accessory components, various sensors are provided inside the hydrogen fuel cell stack, and the inside and outside of the hydrogen fuel cell stack are combined to obtain more comprehensive data of the hydrogen fuel cell system for comprehensive and accurate fault diagnosis. It should be noted that, when the sensors are set for the air inlet pipe, the air outlet pipe and the flow channel, the internet of things server may extract three-dimensional model data of the air inlet pipe, the air outlet pipe and the flow channel from the first standard three-dimensional model library to obtain first structural data, second structural data and third structural data, and then generate corresponding first, second and third installation modes according to attribute features such as functions, performances, volumes, installation modes and connection modes of the sensors to be installed.

Referring to fig. 2, another embodiment of the present invention provides a hydrogen fuel cell system fault diagnosis system, comprising: the system comprises an Internet of things server, a hydrogen fuel cell stack and accessory components; the hydrogen fuel cell stack (not shown) includes a plurality of unit cells including bipolar plates and membrane electrodes including proton exchange membranes, catalyst layers, and gas diffusion layers, and end plates; the accessory component comprises a hydrogen supply component, an oxygen supply component, a temperature management component and a hydrogen fuel cell system management monitoring component; the internet of things server is configured to:

establishing a system fault model library (including but not limited to a hydrogen fuel cell stack overall fault model, an accessory component fault model library of each of the accessory components, a component fault model library of each of the functional components, etc.) and a fault factor model library (including but not limited to a hydrogen fuel cell stack overall fault factor model, an accessory component fault factor model of each of the accessory components, a component fault factor model of each of the functional components, etc.) of the hydrogen fuel cell system based on the first fault data;

and outputting a fault diagnosis report of the hydrogen fuel cell system.

It should be noted that the block diagram of the hydrogen fuel cell system failure diagnosis system shown in fig. 2 is only illustrative, and the number of the illustrated modules does not limit the scope of the present invention.

In some possible embodiments of the present invention, the internet of things server is configured to:

establishing a second standard three-dimensional model library of the accessory component (including but not limited to a standard three-dimensional model of a hydrogen supply component, a standard three-dimensional model of an oxygen supply component, a standard three-dimensional model of a temperature management component, a standard three-dimensional model of a hydrogen fuel cell system management monitoring component, etc.) according to the second three-dimensional data and the second image data;

In some possible embodiments of the present invention, in the step of collecting historical fuel cell system failure data and selecting first failure data matching the hydrogen fuel cell system from the historical fuel cell system failure data, the internet of things server is configured to:

In some possible embodiments of the present invention, in the step of establishing a system fault model library and a fault factor model library of the hydrogen fuel cell system according to the first fault data, the internet of things server is configured to:

In some possible embodiments of the present invention, a ventilation device is disposed on the end plate, and the ventilation device includes an intake pipe, an exhaust pipe, and a first control valve disposed on the intake pipe and a second control valve disposed on the exhaust pipe, where the first control valve and the second control valve are both connected to a hydrogen fuel cell system management and monitoring assembly; the bipolar plate is provided with a runner; the air inlet pipe and the air outlet pipe penetrate through the whole hydrogen fuel cell stack; the pipeline walls of the air inlet pipe and the air outlet pipe are respectively provided with a first vent hole which is in butt joint with the flow channel on the bipolar plate and is communicated with the flow channel, and a switch structure which corresponds to the first vent holes one by one; the hydrogen fuel cell system management monitoring component controls the opening and closing of the switch structure through electric connection so as to realize the opening and closing of the first vent hole; sealing sleeves are respectively sleeved on the outer surfaces of the air inlet pipe and the air outlet pipe, and a second ventilation hole communicated with the first ventilation hole is formed in each sealing sleeve;

It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, such as the above-described division of units, merely a division of logic functions, and there may be additional manners of dividing in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, or may be in electrical or other forms.

The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units described above, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the above-mentioned method of the various embodiments of the present application. And the aforementioned memory includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Those of ordinary skill in the art will appreciate that all or a portion of the steps in the various methods of the above embodiments may be implemented by a program that instructs associated hardware, and the program may be stored in a computer readable memory, which may include: flash disk, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk.

The foregoing has outlined rather broadly the more detailed description of embodiments of the present application, wherein specific examples are provided herein to illustrate the principles and embodiments of the present application, the above examples being provided solely to assist in the understanding of the methods of the present application and the core ideas thereof; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

Although the present invention is disclosed above, the present invention is not limited thereto. Variations and modifications, including combinations of the different functions and implementation steps, as well as embodiments of the software and hardware, may be readily apparent to those skilled in the art without departing from the spirit and scope of the invention.

Claims

1. A hydrogen fuel cell system failure diagnosis method, characterized in that the hydrogen fuel cell system includes a hydrogen fuel cell stack and an accessory assembly; the hydrogen fuel cell stack comprises a plurality of single cells and end plates, wherein the single cells comprise bipolar plates and membrane electrodes, and the membrane electrodes comprise proton exchange membranes, catalyst layers and gas diffusion layers; the accessory component comprises a hydrogen supply component, an oxygen supply component, a temperature management component and a hydrogen fuel cell system management monitoring component; the end plate is provided with a ventilation device, the ventilation device comprises an air inlet pipe, an air outlet pipe, a first control valve arranged on the air inlet pipe and a second control valve arranged on the air outlet pipe, and the first control valve and the second control valve are both connected to the hydrogen fuel cell system management monitoring assembly; the bipolar plate is provided with a runner; the air inlet pipe and the air outlet pipe penetrate through the whole hydrogen fuel cell stack; the pipeline walls of the air inlet pipe and the air outlet pipe are respectively provided with a first vent hole which is in butt joint with the flow channel on the bipolar plate and is communicated with the flow channel, and a switch structure which corresponds to the first vent holes one by one; the hydrogen fuel cell system management monitoring component controls the opening and closing of the switch structure through electric connection so as to realize the opening and closing of the first vent hole; sealing sleeves are respectively sleeved on the outer surfaces of the air inlet pipe and the air outlet pipe, and a second ventilation hole communicated with the first ventilation hole is formed in each sealing sleeve; the hydrogen fuel cell system fault diagnosis method includes:

providing a plurality of sets of sensors for the hydrogen fuel cell system, monitoring the hydrogen fuel cell stack and the accessory assembly, comprising: respectively acquiring first structural data and second structural data of the air inlet pipe and the air outlet pipe; a first sensor group is arranged on the air inlet pipe according to a first installation mode conforming to the first structural data, and a second sensor group is arranged on the air outlet pipe according to a second installation mode conforming to the second structural data; acquiring third structural data of the flow channel, and arranging a third sensor group in the flow channel according to a third installation mode conforming to the third structural data;

and outputting a fault diagnosis report of the hydrogen fuel cell system.

2. The hydrogen fuel cell system failure diagnosis method according to claim 1, characterized by further comprising:

3. The hydrogen fuel cell system failure diagnosis method according to claim 2, wherein the step of collecting historical fuel cell system failure data, selecting first failure data matching the hydrogen fuel cell system from the historical fuel cell system failure data, comprises:

4. The hydrogen fuel cell system failure diagnosis method according to claim 3, characterized in that the step of creating a system failure model library and a failure factor model library of the hydrogen fuel cell stack from the first failure data includes:

5. A hydrogen fuel cell system failure diagnosis system, characterized by comprising: the system comprises an Internet of things server, a hydrogen fuel cell stack and accessory components; the hydrogen fuel cell stack comprises a plurality of single cells and end plates, wherein the single cells comprise bipolar plates and membrane electrodes, and the membrane electrodes comprise proton exchange membranes, catalyst layers and gas diffusion layers; the accessory component comprises a hydrogen supply component, an oxygen supply component, a temperature management component and a hydrogen fuel cell system management monitoring component; the end plate is provided with a ventilation device, the ventilation device comprises an air inlet pipe, an air outlet pipe, a first control valve arranged on the air inlet pipe and a second control valve arranged on the air outlet pipe, and the first control valve and the second control valve are both connected to the hydrogen fuel cell system management monitoring assembly; the bipolar plate is provided with a runner; the air inlet pipe and the air outlet pipe penetrate through the whole hydrogen fuel cell stack; the pipeline walls of the air inlet pipe and the air outlet pipe are respectively provided with a first vent hole which is in butt joint with the flow channel on the bipolar plate and is communicated with the flow channel, and a switch structure which corresponds to the first vent holes one by one; the hydrogen fuel cell system management monitoring component controls the opening and closing of the switch structure through electric connection so as to realize the opening and closing of the first vent hole; sealing sleeves are respectively sleeved on the outer surfaces of the air inlet pipe and the air outlet pipe, and a second ventilation hole communicated with the first ventilation hole is formed in each sealing sleeve; the internet of things server is configured to:

and outputting a fault diagnosis report of the hydrogen fuel cell system.

6. The hydrogen fuel cell system fault diagnosis system according to claim 5, wherein the internet of things server is configured to:

7. The hydrogen fuel cell system fault diagnosis system according to claim 6, wherein in the step of collecting historical fuel cell system fault data and selecting first fault data matching the hydrogen fuel cell system from the historical fuel cell system fault data, the internet of things server is configured to:

8. The hydrogen fuel cell system fault diagnosis system according to claim 7, wherein in the step of establishing a system fault model library and a fault factor model library of the hydrogen fuel cell system from the first fault data, the internet of things server is configured to: