WO2021213989A1 - Fuel cell diagnostic apparatus and corresponding diagnostic method, vehicle, and vehicle system - Google Patents

Fuel cell diagnostic apparatus and corresponding diagnostic method, vehicle, and vehicle system Download PDF

Info

Publication number
WO2021213989A1
WO2021213989A1 PCT/EP2021/060112 EP2021060112W WO2021213989A1 WO 2021213989 A1 WO2021213989 A1 WO 2021213989A1 EP 2021060112 W EP2021060112 W EP 2021060112W WO 2021213989 A1 WO2021213989 A1 WO 2021213989A1
Authority
WO
WIPO (PCT)
Prior art keywords
fuel cell
parameter
main
cloud server
fault mode
Prior art date
Application number
PCT/EP2021/060112
Other languages
French (fr)
Inventor
Xiaoyun Zang
Xudan LIU
Kai Wang
Guozhen Zhou
Original Assignee
Robert Bosch Gmbh
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Robert Bosch Gmbh filed Critical Robert Bosch Gmbh
Publication of WO2021213989A1 publication Critical patent/WO2021213989A1/en

Links

Classifications

    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M8/00—Fuel cells; Manufacture thereof
    • H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
    • H01M8/04298—Processes for controlling fuel cells or fuel cell systems
    • H01M8/04992—Processes for controlling fuel cells or fuel cell systems characterised by the implementation of mathematical or computational algorithms, e.g. feedback control loops, fuzzy logic, neural networks or artificial intelligence
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M8/00—Fuel cells; Manufacture thereof
    • H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
    • H01M8/04298—Processes for controlling fuel cells or fuel cell systems
    • H01M8/04313—Processes for controlling fuel cells or fuel cell systems characterised by the detection or assessment of variables; characterised by the detection or assessment of failure or abnormal function
    • H01M8/04664—Failure or abnormal function
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
    • B60L58/10—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/378—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC] specially adapted for the type of battery or accumulator
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M8/00—Fuel cells; Manufacture thereof
    • H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
    • H01M8/04298—Processes for controlling fuel cells or fuel cell systems
    • H01M8/04313—Processes for controlling fuel cells or fuel cell systems characterised by the detection or assessment of variables; characterised by the detection or assessment of failure or abnormal function
    • H01M8/0432—Temperature; Ambient temperature
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M8/00—Fuel cells; Manufacture thereof
    • H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
    • H01M8/04298—Processes for controlling fuel cells or fuel cell systems
    • H01M8/04313—Processes for controlling fuel cells or fuel cell systems characterised by the detection or assessment of variables; characterised by the detection or assessment of failure or abnormal function
    • H01M8/0438—Pressure; Ambient pressure; Flow
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M8/00—Fuel cells; Manufacture thereof
    • H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
    • H01M8/04298—Processes for controlling fuel cells or fuel cell systems
    • H01M8/04313—Processes for controlling fuel cells or fuel cell systems characterised by the detection or assessment of variables; characterised by the detection or assessment of failure or abnormal function
    • H01M8/04492—Humidity; Ambient humidity; Water content
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M8/00—Fuel cells; Manufacture thereof
    • H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
    • H01M8/04298—Processes for controlling fuel cells or fuel cell systems
    • H01M8/04313—Processes for controlling fuel cells or fuel cell systems characterised by the detection or assessment of variables; characterised by the detection or assessment of failure or abnormal function
    • H01M8/04537—Electric variables
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M8/00—Fuel cells; Manufacture thereof
    • H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
    • H01M8/04298—Processes for controlling fuel cells or fuel cell systems
    • H01M8/04313—Processes for controlling fuel cells or fuel cell systems characterised by the detection or assessment of variables; characterised by the detection or assessment of failure or abnormal function
    • H01M8/04664—Failure or abnormal function
    • H01M8/04679—Failure or abnormal function of fuel cell stacks
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M2250/00—Fuel cells for particular applications; Specific features of fuel cell system
    • H01M2250/20—Fuel cells in motive systems, e.g. vehicle, ship, plane
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02E60/30—Hydrogen technology
    • Y02E60/50—Fuel cells
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/60—Other road transportation technologies with climate change mitigation effect
    • Y02T10/70—Energy storage systems for electromobility, e.g. batteries
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02T90/40—Application of hydrogen technology to transportation, e.g. using fuel cells

Definitions

  • the present invention relates to a fuel cell diagnostic apparatus for a fuel cell vehicle and a method for diagnosing a fault mode of a fuel cell system of a fuel cell vehicle. Moreover, the present invention further relates to a fuel cell vehicle which comprises such a fuel cell diagnostic apparatus, and a fuel cell vehicle system.
  • a proton exchange membrane fuel cell as a commercial fuel cell under development, has the advantages of features of a low operating temperature, short cold-start time, fast load tracking, and safe and reliable operation, and is particularly suitable for application in a fuel cell vehicle.
  • Electrochemical impedance spectroscopy can reflect a current humidity level of a proton exchange membrane fuel cell, i.e., water content of a membrane, and it is inferred thereby whether the fuel cell is in “membrane-drying” and “water-flooding” fault modes.
  • the proton exchange membrane fuel cell is a complex nonlinear system with coupling of a plurality of physical fields, and is affected by different factors and has a plurality of fault modes. Without considering other factors, such as an aging effect, that affect a diagnostic result of a fuel cell, the diagnosis with the electrochemical impedance spectroscopy technology may result in a relatively narrow fault diagnostic range, and thus an actual operation status of the fuel cell cannot be fully reflected. Moreover, in the prior art, the fault diagnosis of a fuel cell system is only based on simulation data and experimental data, and there is a relatively small amount of data volume for reference. As a result, the fault diagnosis fails to achieve the desired accuracy. l Summary of the Invention
  • the present invention provides an improved fuel cell diagnostic apparatus, and the fuel cell diagnostic apparatus can diagnose a fault mode of a fuel cell system of a fuel cell vehicle more comprehensively and accurately.
  • the present invention furthermore provides a corresponding method for diagnosing a fault mode of a fuel cell system of a fuel cell vehicle, a corresponding fuel cell vehicle, and a corresponding fuel cell vehicle system.
  • a fuel cell diagnostic apparatus for a fuel cell vehicle, and the fuel cell diagnostic apparatus is configured to diagnose a fault mode of a fuel cell system of a fuel cell vehicle, wherein the fuel cell diagnostic apparatus comprises at least:
  • main sensing unit configured to sense a main parameter that is used to at least preliminarily diagnose the fault mode
  • At least one additional sensing unit configured to sense at least one additional parameter that potentially affects a diagnostic result
  • -a fuel cell analysis and evaluation unit configured to be capable of sending the main parameter and the at least one additional parameter, and of receiving diagnostic information about the fault mode generated on the basis of the main parameter and the at least one additional parameter.
  • the diagnostic information may be a diagnostic result that directly represents a state of a fuel cell, or may be intermediate diagnostic data, so that, for example, a final diagnostic result of the fuel cell is determined by the fuel cell analysis and evaluation unit. Therefore, the diagnostic information herein should be understood in a non-limiting manner.
  • the fuel cell diagnostic apparatus can obtain the main parameter by using the main sensing unit to at least preliminarily diagnose the fault mode of the fuel cell system, and obtain the at least one additional parameter by using the at least one additional sensing unit.
  • the at least one additional parameter a fault diagnostic range of the fuel cell system can be widened, and diagnostic precision can be improved, in consideration of other possible factors, thereby affecting a diagnostic result. Therefore, the fuel cell analysis and evaluation unit of the fuel cell diagnostic apparatus can advantageously receive more accurate diagnostic information about the fault mode.
  • the fuel cell analysis and evaluation unit is configured to be capable of communicating with a cloud server in a wireless manner, so as to send data about the main parameter and the at least one additional parameter to the cloud server and receive the diagnostic information from the cloud server.
  • the cloud server is understood as a component in a cloud computing service architecture and is configured to be capable of cloud computing. It can be advantageously implemented that the fuel cell analysis and evaluation unit sends the data about the main parameter and the at least one additional parameter to the cloud server in real time and receives the diagnostic information generated on the basis of the data from the cloud server.
  • the cloud server is configured to be capable of storing the data and using a machine learning algorithm to perform data training on stored historical data, to obtain an optimized diagnostic model.
  • data training should be particularly understood as extracting a classification feature that can best reflect the fault mode of the fuel cell system by using a data mining and classification technology for a training set in big data, and thereby training a classifier, with which data of the fuel cell system to be diagnosed is classified into different fault modes.
  • the result of the data training is the establishment of an optimized diagnostic model.
  • the big data comprises at least the historical data about the main parameter and the at least one additional parameter which are sent previously by the fuel cell analysis and evaluation unit and stored by the cloud server and the corresponding fault mode.
  • the cloud server may also have other data sources and is configured to be capable of receiving and storing, for example, experimental data, empirical data, and/or data about the main parameter and the at least one additional parameter from other fuel cell vehicles. Therefore, not only is data from a single fuel cell vehicle considered, but also a larger data sample can be advantageously obtained, and data training is performed thoroughly and comprehensively without missing useful information, so that more precise statistical information can be extracted, and an optimal diagnostic model can be obtained.
  • the main parameter comprises electrochemical impedance spectroscopy.
  • electrochemical impedance spectroscopy a humidity level of the fuel cell and a related fault mode can be advantageously obtained.
  • the main sensing unit comprises a DC/DC converter
  • the DC/DC converter is configured to be capable of injecting an undulating current signal into the fuel cell system, to obtain the electrochemical impedance spectroscopy.
  • the DC/DC converter is connected to the fuel cell analysis and evaluation unit via a CAN communication module, thereby obtaining the electrochemical impedance spectroscopy of the fuel cell system in real time.
  • the at least one additional parameter is one or more selected from the following group: operating time, voltage, current, temperature, air flow rate, and gas pressure or pressure drop of the fuel cell system. Other parameters that a person skilled in the art thinks meaningful may also be considered.
  • the at least one additional parameter can potentially affect the diagnostic result.
  • “potentially affect the diagnostic result” should be particularly understood as that the at least one additional parameter can further support the preliminary diagnosis based on the main parameter or can be used to correct or refine the preliminary diagnosis, thereby obtaining a more accurate diagnostic result about the fault mode.
  • the at least one additional parameter may comprise a corresponding sensor.
  • the fault mode comprises one or more of the following group: water-flooding, membrane-drying, micro-crack, icing, and overheating.
  • Other fault modes that a person skilled in the art thinks meaningful may also be considered. Therefore, possible fault modes of the fuel cell system can be considered thoroughly and comprehensively. For example, when humidity of the fuel cell system is at a normal level, according to the method of the present invention, other faults of the fuel cell system can be diagnosed in a timely manner, such as micro-crack or temperature exception, so that a corresponding adjustment strategy is implemented to avoid more severe losses.
  • a second aspect of the present invention provides a cloud server, which is configured to be capable of receiving the main parameter and the at least one additional parameter from the fuel cell analysis and evaluation unit of the fuel cell diagnostic apparatus, and generating the diagnostic information about the fault mode on the basis of the main parameter and the at least one additional parameter.
  • a second aspect of the present invention provides a method for diagnosing a fault mode of a fuel cell system of a fuel cell vehicle, the method is implemented by a fuel cell diagnostic apparatus according to the present invention, and the method comprises at least the following steps: sensing, by a main sensing unit, a main parameter that is used to at least preliminarily diagnose the fault mode, and sensing, by at least one additional sensing unit, at least one additional parameter that potentially affects a diagnostic result; sending the main parameter and the at least one additional parameter by a fuel cell analysis and evaluation unit; and receiving, by the fuel cell analysis and evaluation unit, diagnostic information about the fault mode generated on the basis of the main parameter and the at least one additional parameter.
  • a third aspect of the present invention provides a fuel cell vehicle comprising a fuel cell diagnostic apparatus according to the present invention.
  • a fourth aspect of the present invention provides a fuel cell vehicle system comprising a plurality of fuel cell vehicles according to the present invention, and the plurality of fuel cell vehicles are all configured to be capable of communicating with a cloud server.
  • a fifth aspect of the present invention provides a fuel cell vehicle network system, wherein the fuel cell vehicle network system comprises the fuel cell vehicle system and the cloud server.
  • Fig. 1 is a schematic diagram of a fuel cell diagnostic apparatus according to an exemplary embodiment of the present invention
  • Figs. 2a and 2b are schematic graphs of electrochemical impedance spectroscopy at different operating times in a membrane-drying state and a water-flooding state;
  • Fig. 3 is a schematic flowchart of a method for diagnosing a fault mode of a fuel cell system according to the present invention.
  • Fig. 4 is a schematic diagram of a fuel cell vehicle system comprising a plurality of fuel cell vehicles according to the present invention.
  • Fig. 1 is a schematic diagram of a fuel cell diagnostic apparatus 10 according to an exemplary embodiment of the present invention.
  • the fuel cell diagnostic apparatus 10 (framed by a dashed line) comprises a main sensing unit 1, at least one additional sensing unit 2, and a fuel cell analysis and evaluation unit 3, wherein the main sensing unit 1 is configured to sense a main parameter that is used to at least preliminarily diagnose a fault mode of a fuel cell system 20, and the at least one additional sensing unit 2 is configured to sense at least one additional parameter that potentially affects a diagnostic result.
  • the fuel cell diagnostic apparatus 10 sends the main parameter and the at least one additional parameter to a cloud server C via the fuel cell analysis and evaluation unit 3 in a wireless manner, and receives, from the cloud server C, diagnostic information about a fault mode generated on the basis of the main parameter and the at least one additional parameter, thereby implementing real-time diagnosis of the fault mode of the fuel cell system 20.
  • the fuel cell analysis and evaluation unit 3 adjusts a control strategy for the fuel cell system 20 according to the received diagnostic information and exemplarily sends the control strategy to an actuator 30, so as to perform the control strategy to optimize the operation behavior of the fuel cell system 20.
  • the cloud server C has a cloud storage function and a cloud computing function.
  • Data about the main parameter and the at least one additional parameter which are previously sent by the fuel cell analysis and evaluation unit 3 and the corresponding fault mode fed back can be stored by the cloud server C.
  • the data stored in the cloud server C are also referred to as historical data.
  • the cloud server C can use a machine learning algorithm to perform data training on the historical data, to obtain an optimized diagnostic model.
  • the cloud server C can also receive and store experimental data and/or data from other fuel cell vehicles.
  • a data set stored in the cloud server C is also referred to as big data. Big data formed in this way comprises as many fault cases as possible and provides abundant data samples. With constant enrichment and data training of big data, the diagnostic model can be continuously updated to ensure that the currently used diagnostic model is optimal.
  • the machine learning algorithm is an XGBoost algorithm.
  • XGBoost XGBoost algorithm
  • a tree can be grown through constant feature splitting, so that a plurality of weak classifiers can be integrated together to form a strong classifier. Therefore, data training can be precisely performed on big data at a high iteration speed.
  • SVM support vector machine
  • the main parameter comprises electrochemical impedance spectroscopy.
  • Electrochemical impedance spectroscopy can reflect a humidity level of the fuel cell system 20. Therefore, a main sensing unit 1 comprises a DC/DC converter.
  • the DC/DC converter as an undulating current signal source, is adapted to apply small-amplitude alternating signals with different frequencies to a fuel cell system 20, measure a voltage response signal of the fuel cell system 20, and obtain electrochemical impedance spectroscopy of the fuel cell system 20 based on a relationship between the voltage response signal and the undulating current signal (for details, reference may be made to Figs. 2a and 2b). Therefore, the electrochemical impedance spectroscopy can be obtained without affecting the operation stability of the fuel cell system 20.
  • the DC/DC converter is connected to the fuel cell analysis and evaluation unit 3 through a CAN communication module.
  • the main parameter is not limited to the electrochemical impedance spectroscopy.
  • the main parameter may also comprise humidity and/or temperature measured by a humidity sensor and/or a temperature sensor of the fuel cell system 20 that can also act as the main sensing unit 1.
  • the fuel cell system is a complex nonlinear system. An operation status of the fuel cell system cannot be determined precisely with a single parameter. Therefore, the at least one additional sensing unit 2 is provided to sense the at least one additional parameter that potentially affects the diagnostic result.
  • the at least one additional parameter is one or more selected from the following group: operating time, voltage, current, temperature, air flow rate, and gas pressure or pressure drop of the fuel cell system 20.
  • operating time of a fuel cell system 20 progresses, a proton exchange membrane and/or a catalyst layer of the fuel cell system 20 is degrading and gradually aging, resulting in an aging state of the entire fuel cell system 20. In this state, the electrochemical impedance spectroscopy of the fuel cell system 20 changes.
  • the additional parameter is a parameter that affects precision or reliability of the operation status of the fuel cell system
  • the main parameter is a parameter that can directly and basically determine an operation status of the fuel cell system.
  • Figs. 2a and 2b are schematic graphs of electrochemical impedance spectroscopy of a fuel cell system at different operating times.
  • Fig. 2a shows a membrane-drying state of a fuel cell
  • Fig. 2b shows a water-flooding state of a fuel cell, wherein a horizontal axis (x axis) represents a real part of electrochemical impedance, and a vertical axis (y axis) represents an imaginary part of electrochemical impedance, units of both being W.
  • membrane-drying insufficient water content contained in a fuel cell
  • water-flooding excessively high water content in a fuel cell
  • a water-flooding fault blocks the transfer of a gaseous reactant to a reaction site, an active area of a catalyst decreases due to water covering, and activation loss and concentration difference loss of the fuel cell are significantly increased.
  • a membrane-drying fault causes electrical resistivity increase, adds to heating of the fuel cell during operation, and further causes energy conversion efficiency reduction and a more severe membrane-drying fault, which severely affects output performance and remaining life.
  • high frequency resistance and low frequency impedance of the electrochemical impedance spectroscopy may be used as a diagnostic index of the membrane-drying fault and the water-flooding fault, respectively.
  • electrochemical impedance of the fuel cell in both the membrane-drying state and the water-flooding state changes and even overlaps with each other in particular cases.
  • electrochemical impedance when the fuel cell in the membrane-drying state operates for 1200 seconds is extremely similar to electrochemical impedance when the fuel cell in the water-flooding state operates for 600 seconds (refer to a curve FI). Therefore, without considering an aging effect, an incorrect diagnostic result is very likely to be obtained on the basis of only the electrochemical impedance spectroscopy, that is, the fault mode of the fuel cell system cannot be accurately diagnosed.
  • the fuel cell system 20 further has other fault modes different from membrane-drying and water-flooding, such as micro-crack, icing, and overheating.
  • the cloud server C can obtain a corresponding precise fault mode using a diagnostic model generated on the basis of big data by means of a machine learning algorithm.
  • the electrochemical impedance spectroscopy as the main parameter indicates insufficient water contained in a membrane and the air flow rate as an additional parameter is shown as above a threshold, it should be considered that a micro-crack appears in the fuel cell system 20.
  • other additional sensing units may be used to sense other additional parameters, like gas pressure.
  • the fuel cell system 20 can be diagnosed as being in a membrane-drying fault mode with higher accuracy.
  • the at least one additional sensing unit 2 comprises a corresponding sensor, wherein the sensor is particularly integrated so as to save structural space.
  • Fig. 3 is a schematic flowchart of a method for diagnosing a fault mode of a fuel cell system according to the present invention.
  • the method comprises the following steps: in a first step SI, a main parameter that is used to at least preliminarily diagnose a fault mode is sensed by a main sensing unit 1, and at least one additional parameter that potentially affects a diagnostic result is sensed by at least one additional sensing unit 2; in a second step S2, the main parameter and the at least one additional parameter are sent by a fuel cell analysis and evaluation unit 3; and in a third step S3, diagnostic information about the fault mode generated on the basis of the main parameter and the at least one additional parameter is received by the fuel cell analysis and evaluation unit 3.
  • data about the main parameter and the at least one additional parameter and the diagnostic information generated on the basis of the data are all stored in a cloud server, so as to be used as a new data sample to perform further data training, thereby obtaining a diagnostic model updated in real time.
  • Fig. 4 is a schematic diagram of a fuel cell vehicle system 1000 comprising a plurality of fuel cell vehicles 100 according to the present invention.
  • identical reference numerals are only shown once.
  • the position and size relationships of various components in the drawings are strongly schematic and can be changed according to practical needs.
  • a fuel cell vehicle 100 according to the present invention has a fuel cell diagnostic apparatus 10 and a fuel cell system 20 according to the present invention.
  • the plurality of fuel cell vehicles 100 according to the present invention together form the distributed fuel cell vehicle system 1000, wherein the fuel cell vehicles 100 are all configured to be capable of communicating with a cloud server C in real time.
  • a fuel cell diagnostic apparatus 10 of each fuel cell vehicle 100 is capable of sending its own main parameter and at least one additional parameter about the fuel cell system 20 to a cloud server C correspondingly. Therefore, the cloud server C may receive and store a large amount of data about the main parameter and the at least one additional parameter simultaneously and form corresponding big data. This greatly enriches data samples and does not miss possible fault modes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Sustainable Energy (AREA)
  • Sustainable Development (AREA)
  • General Chemical & Material Sciences (AREA)
  • Electrochemistry (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Chemical & Material Sciences (AREA)
  • Manufacturing & Machinery (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Mathematical Physics (AREA)
  • Power Engineering (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Health & Medical Sciences (AREA)
  • Automation & Control Theory (AREA)
  • Fuzzy Systems (AREA)
  • Fuel Cell (AREA)

Abstract

The present invention discloses a fuel cell diagnostic apparatus (10) for a fuel cell vehicle (100), to diagnose a fault mode of a fuel cell system (20) of the fuel cell vehicle (100). The fuel cell diagnostic apparatus at least comprises: a main sensing unit (1) configured to sense a main parameter that is used to at least preliminarily diagnose a fault mode; at least one additional sensing unit (2) configured to sense at least one additional parameter that potentially affects a diagnostic result; and a fuel cell analysis and evaluation unit (3) configured to be capable of sending the main parameter and the at least one additional parameter, and of receiving diagnostic information about a fault mode generated on the basis of the main parameter and the at least one additional parameter. A corresponding cloud server, a corresponding method for diagnosing a fault mode, a corresponding fuel cell vehicle, a corresponding fuel cell vehicle system, and a corresponding fuel cell vehicle network system are further disclosed. This makes diagnosis more reliable.

Description

Description
Fuel cell diagnostic apparatus and corresponding diagnostic method, vehicle, and vehicle system
Technical Field
The present invention relates to a fuel cell diagnostic apparatus for a fuel cell vehicle and a method for diagnosing a fault mode of a fuel cell system of a fuel cell vehicle. Moreover, the present invention further relates to a fuel cell vehicle which comprises such a fuel cell diagnostic apparatus, and a fuel cell vehicle system.
Background Art
In recent years, compared with a conventional internal combustion engine vehicle, a fuel cell vehicle has been drawing more attention due to the advantages of high energy conversion efficiency and zero emissions. A proton exchange membrane fuel cell, as a commercial fuel cell under development, has the advantages of features of a low operating temperature, short cold-start time, fast load tracking, and safe and reliable operation, and is particularly suitable for application in a fuel cell vehicle.
To diagnose a fault that occurs in a fuel cell system, an electrochemical impedance spectroscopy technology has been known in the prior art. With the electrochemical impedance spectroscopy technology, an impedance variation of a proton exchange membrane fuel cell can be obtained with fewer measurements and less computation, and the impedance variation is used as an indicator of fault diagnosis for a fuel cell. Electrochemical impedance spectroscopy can reflect a current humidity level of a proton exchange membrane fuel cell, i.e., water content of a membrane, and it is inferred thereby whether the fuel cell is in “membrane-drying” and “water-flooding” fault modes. However, the proton exchange membrane fuel cell is a complex nonlinear system with coupling of a plurality of physical fields, and is affected by different factors and has a plurality of fault modes. Without considering other factors, such as an aging effect, that affect a diagnostic result of a fuel cell, the diagnosis with the electrochemical impedance spectroscopy technology may result in a relatively narrow fault diagnostic range, and thus an actual operation status of the fuel cell cannot be fully reflected. Moreover, in the prior art, the fault diagnosis of a fuel cell system is only based on simulation data and experimental data, and there is a relatively small amount of data volume for reference. As a result, the fault diagnosis fails to achieve the desired accuracy. l Summary of the Invention
Therefore, the present invention provides an improved fuel cell diagnostic apparatus, and the fuel cell diagnostic apparatus can diagnose a fault mode of a fuel cell system of a fuel cell vehicle more comprehensively and accurately. The present invention furthermore provides a corresponding method for diagnosing a fault mode of a fuel cell system of a fuel cell vehicle, a corresponding fuel cell vehicle, and a corresponding fuel cell vehicle system.
According to a first aspect of the present invention, a fuel cell diagnostic apparatus for a fuel cell vehicle is provided, and the fuel cell diagnostic apparatus is configured to diagnose a fault mode of a fuel cell system of a fuel cell vehicle, wherein the fuel cell diagnostic apparatus comprises at least:
-a main sensing unit configured to sense a main parameter that is used to at least preliminarily diagnose the fault mode;
-at least one additional sensing unit configured to sense at least one additional parameter that potentially affects a diagnostic result; and
-a fuel cell analysis and evaluation unit configured to be capable of sending the main parameter and the at least one additional parameter, and of receiving diagnostic information about the fault mode generated on the basis of the main parameter and the at least one additional parameter.
A person skilled in the art may appreciate that the diagnostic information may be a diagnostic result that directly represents a state of a fuel cell, or may be intermediate diagnostic data, so that, for example, a final diagnostic result of the fuel cell is determined by the fuel cell analysis and evaluation unit. Therefore, the diagnostic information herein should be understood in a non-limiting manner.
Compared with the prior art, the fuel cell diagnostic apparatus according to the present invention can obtain the main parameter by using the main sensing unit to at least preliminarily diagnose the fault mode of the fuel cell system, and obtain the at least one additional parameter by using the at least one additional sensing unit. With the at least one additional parameter, a fault diagnostic range of the fuel cell system can be widened, and diagnostic precision can be improved, in consideration of other possible factors, thereby affecting a diagnostic result. Therefore, the fuel cell analysis and evaluation unit of the fuel cell diagnostic apparatus can advantageously receive more accurate diagnostic information about the fault mode.
According to an exemplary embodiment of the present invention, the fuel cell analysis and evaluation unit is configured to be capable of communicating with a cloud server in a wireless manner, so as to send data about the main parameter and the at least one additional parameter to the cloud server and receive the diagnostic information from the cloud server. In the framework of the present invention, the cloud server is understood as a component in a cloud computing service architecture and is configured to be capable of cloud computing. It can be advantageously implemented that the fuel cell analysis and evaluation unit sends the data about the main parameter and the at least one additional parameter to the cloud server in real time and receives the diagnostic information generated on the basis of the data from the cloud server.
According to an exemplary embodiment of the present invention, the cloud server is configured to be capable of storing the data and using a machine learning algorithm to perform data training on stored historical data, to obtain an optimized diagnostic model. In the framework of the present invention, “data training” should be particularly understood as extracting a classification feature that can best reflect the fault mode of the fuel cell system by using a data mining and classification technology for a training set in big data, and thereby training a classifier, with which data of the fuel cell system to be diagnosed is classified into different fault modes. The result of the data training is the establishment of an optimized diagnostic model. Herein, the big data comprises at least the historical data about the main parameter and the at least one additional parameter which are sent previously by the fuel cell analysis and evaluation unit and stored by the cloud server and the corresponding fault mode.
According to an exemplary embodiment of the present invention, the cloud server may also have other data sources and is configured to be capable of receiving and storing, for example, experimental data, empirical data, and/or data about the main parameter and the at least one additional parameter from other fuel cell vehicles. Therefore, not only is data from a single fuel cell vehicle considered, but also a larger data sample can be advantageously obtained, and data training is performed thoroughly and comprehensively without missing useful information, so that more precise statistical information can be extracted, and an optimal diagnostic model can be obtained.
According to an exemplary embodiment of the present invention, the main parameter comprises electrochemical impedance spectroscopy. According to electrochemical impedance spectroscopy, a humidity level of the fuel cell and a related fault mode can be advantageously obtained.
According to an exemplary embodiment of the present invention, the main sensing unit comprises a DC/DC converter, and the DC/DC converter is configured to be capable of injecting an undulating current signal into the fuel cell system, to obtain the electrochemical impedance spectroscopy. Exemplarily, the DC/DC converter is connected to the fuel cell analysis and evaluation unit via a CAN communication module, thereby obtaining the electrochemical impedance spectroscopy of the fuel cell system in real time. According to an exemplary embodiment of the present invention, the at least one additional parameter is one or more selected from the following group: operating time, voltage, current, temperature, air flow rate, and gas pressure or pressure drop of the fuel cell system. Other parameters that a person skilled in the art thinks meaningful may also be considered. The at least one additional parameter can potentially affect the diagnostic result. In the framework of the present invention, “potentially affect the diagnostic result” should be particularly understood as that the at least one additional parameter can further support the preliminary diagnosis based on the main parameter or can be used to correct or refine the preliminary diagnosis, thereby obtaining a more accurate diagnostic result about the fault mode. To sense the at least one additional parameter, the at least one additional parameter may comprise a corresponding sensor.
According to an exemplary embodiment of the present invention, the fault mode comprises one or more of the following group: water-flooding, membrane-drying, micro-crack, icing, and overheating. Other fault modes that a person skilled in the art thinks meaningful may also be considered. Therefore, possible fault modes of the fuel cell system can be considered thoroughly and comprehensively. For example, when humidity of the fuel cell system is at a normal level, according to the method of the present invention, other faults of the fuel cell system can be diagnosed in a timely manner, such as micro-crack or temperature exception, so that a corresponding adjustment strategy is implemented to avoid more severe losses.
A second aspect of the present invention provides a cloud server, which is configured to be capable of receiving the main parameter and the at least one additional parameter from the fuel cell analysis and evaluation unit of the fuel cell diagnostic apparatus, and generating the diagnostic information about the fault mode on the basis of the main parameter and the at least one additional parameter.
A second aspect of the present invention provides a method for diagnosing a fault mode of a fuel cell system of a fuel cell vehicle, the method is implemented by a fuel cell diagnostic apparatus according to the present invention, and the method comprises at least the following steps: sensing, by a main sensing unit, a main parameter that is used to at least preliminarily diagnose the fault mode, and sensing, by at least one additional sensing unit, at least one additional parameter that potentially affects a diagnostic result; sending the main parameter and the at least one additional parameter by a fuel cell analysis and evaluation unit; and receiving, by the fuel cell analysis and evaluation unit, diagnostic information about the fault mode generated on the basis of the main parameter and the at least one additional parameter. A third aspect of the present invention provides a fuel cell vehicle comprising a fuel cell diagnostic apparatus according to the present invention.
A fourth aspect of the present invention provides a fuel cell vehicle system comprising a plurality of fuel cell vehicles according to the present invention, and the plurality of fuel cell vehicles are all configured to be capable of communicating with a cloud server.
A fifth aspect of the present invention provides a fuel cell vehicle network system, wherein the fuel cell vehicle network system comprises the fuel cell vehicle system and the cloud server.
Brief Description of the Drawings
In the following, the principles, features and advantages of the present invention can be better understood by describing the present invention in more detail with reference to the accompanying drawings. In the drawings:
Fig. 1 is a schematic diagram of a fuel cell diagnostic apparatus according to an exemplary embodiment of the present invention;
Figs. 2a and 2b are schematic graphs of electrochemical impedance spectroscopy at different operating times in a membrane-drying state and a water-flooding state;
Fig. 3 is a schematic flowchart of a method for diagnosing a fault mode of a fuel cell system according to the present invention; and
Fig. 4 is a schematic diagram of a fuel cell vehicle system comprising a plurality of fuel cell vehicles according to the present invention.
Detailed Description of Embodiments
In order to make the technical problems to be solved by the present invention, technical solutions and beneficial technical effects more easily understood, the present invention will be described in further detail below with reference to the drawings and various exemplary embodiments. It should be understood that the specific embodiments described herein are only for the purpose of explaining the present invention and are not intended to limit the scope of protection of the present invention.
Fig. 1 is a schematic diagram of a fuel cell diagnostic apparatus 10 according to an exemplary embodiment of the present invention. As shown in Fig. 1, the fuel cell diagnostic apparatus 10 (framed by a dashed line) comprises a main sensing unit 1, at least one additional sensing unit 2, and a fuel cell analysis and evaluation unit 3, wherein the main sensing unit 1 is configured to sense a main parameter that is used to at least preliminarily diagnose a fault mode of a fuel cell system 20, and the at least one additional sensing unit 2 is configured to sense at least one additional parameter that potentially affects a diagnostic result.
As shown in Fig. 1, the fuel cell diagnostic apparatus 10 sends the main parameter and the at least one additional parameter to a cloud server C via the fuel cell analysis and evaluation unit 3 in a wireless manner, and receives, from the cloud server C, diagnostic information about a fault mode generated on the basis of the main parameter and the at least one additional parameter, thereby implementing real-time diagnosis of the fault mode of the fuel cell system 20.
According to an exemplary embodiment of the present invention, the fuel cell analysis and evaluation unit 3 adjusts a control strategy for the fuel cell system 20 according to the received diagnostic information and exemplarily sends the control strategy to an actuator 30, so as to perform the control strategy to optimize the operation behavior of the fuel cell system 20.
Herein, the cloud server C has a cloud storage function and a cloud computing function. Data about the main parameter and the at least one additional parameter which are previously sent by the fuel cell analysis and evaluation unit 3 and the corresponding fault mode fed back can be stored by the cloud server C. The data stored in the cloud server C are also referred to as historical data. The cloud server C can use a machine learning algorithm to perform data training on the historical data, to obtain an optimized diagnostic model.
According to an exemplary embodiment of the present invention, the cloud server C can also receive and store experimental data and/or data from other fuel cell vehicles. A data set stored in the cloud server C is also referred to as big data. Big data formed in this way comprises as many fault cases as possible and provides abundant data samples. With constant enrichment and data training of big data, the diagnostic model can be continuously updated to ensure that the currently used diagnostic model is optimal.
According to an exemplary embodiment of the present invention, the machine learning algorithm is an XGBoost algorithm. With this algorithm, a tree can be grown through constant feature splitting, so that a plurality of weak classifiers can be integrated together to form a strong classifier. Therefore, data training can be precisely performed on big data at a high iteration speed. Certainly, any other algorithm that a person skilled in the art thinks meaningful may also be considered in principle, such as a support vector machine (SVM) algorithm.
According to an exemplary embodiment of the present invention, the main parameter comprises electrochemical impedance spectroscopy. Electrochemical impedance spectroscopy can reflect a humidity level of the fuel cell system 20. Therefore, a main sensing unit 1 comprises a DC/DC converter. Exemplarily, the DC/DC converter, as an undulating current signal source, is adapted to apply small-amplitude alternating signals with different frequencies to a fuel cell system 20, measure a voltage response signal of the fuel cell system 20, and obtain electrochemical impedance spectroscopy of the fuel cell system 20 based on a relationship between the voltage response signal and the undulating current signal (for details, reference may be made to Figs. 2a and 2b). Therefore, the electrochemical impedance spectroscopy can be obtained without affecting the operation stability of the fuel cell system 20. Exemplarily, the DC/DC converter is connected to the fuel cell analysis and evaluation unit 3 through a CAN communication module.
Certainly, for a person skilled in the art, the main parameter is not limited to the electrochemical impedance spectroscopy. The main parameter, for example, may also comprise humidity and/or temperature measured by a humidity sensor and/or a temperature sensor of the fuel cell system 20 that can also act as the main sensing unit 1.
However, the fuel cell system is a complex nonlinear system. An operation status of the fuel cell system cannot be determined precisely with a single parameter. Therefore, the at least one additional sensing unit 2 is provided to sense the at least one additional parameter that potentially affects the diagnostic result. Exemplarily, the at least one additional parameter is one or more selected from the following group: operating time, voltage, current, temperature, air flow rate, and gas pressure or pressure drop of the fuel cell system 20. Exemplarily, as operating time of a fuel cell system 20 progresses, a proton exchange membrane and/or a catalyst layer of the fuel cell system 20 is degrading and gradually aging, resulting in an aging state of the entire fuel cell system 20. In this state, the electrochemical impedance spectroscopy of the fuel cell system 20 changes.
It should be noted herein that the additional parameter is a parameter that affects precision or reliability of the operation status of the fuel cell system, while the main parameter is a parameter that can directly and basically determine an operation status of the fuel cell system.
Figs. 2a and 2b are schematic graphs of electrochemical impedance spectroscopy of a fuel cell system at different operating times. Fig. 2a shows a membrane-drying state of a fuel cell, and Fig. 2b shows a water-flooding state of a fuel cell, wherein a horizontal axis (x axis) represents a real part of electrochemical impedance, and a vertical axis (y axis) represents an imaginary part of electrochemical impedance, units of both being W.
It should be noted herein that membrane-drying (insufficient water content contained in a fuel cell) and water-flooding (excessively high water content in a fuel cell) are the most common fault modes in a fuel cell. A water-flooding fault blocks the transfer of a gaseous reactant to a reaction site, an active area of a catalyst decreases due to water covering, and activation loss and concentration difference loss of the fuel cell are significantly increased. A membrane-drying fault causes electrical resistivity increase, adds to heating of the fuel cell during operation, and further causes energy conversion efficiency reduction and a more severe membrane-drying fault, which severely affects output performance and remaining life. Herein, high frequency resistance and low frequency impedance of the electrochemical impedance spectroscopy may be used as a diagnostic index of the membrane-drying fault and the water-flooding fault, respectively.
It can be seen clearly from Figs. 2a and 2b that, as the operating time progresses, electrochemical impedance of the fuel cell in both the membrane-drying state and the water-flooding state changes and even overlaps with each other in particular cases. Specifically, electrochemical impedance when the fuel cell in the membrane-drying state operates for 1200 seconds (refer to a curve D2) is extremely similar to electrochemical impedance when the fuel cell in the water-flooding state operates for 600 seconds (refer to a curve FI). Therefore, without considering an aging effect, an incorrect diagnostic result is very likely to be obtained on the basis of only the electrochemical impedance spectroscopy, that is, the fault mode of the fuel cell system cannot be accurately diagnosed.
According to the present invention, the fuel cell system 20 further has other fault modes different from membrane-drying and water-flooding, such as micro-crack, icing, and overheating. Through a combination of the main parameter and the at least one additional parameter, the cloud server C can obtain a corresponding precise fault mode using a diagnostic model generated on the basis of big data by means of a machine learning algorithm.
For example, according to an exemplary embodiment of the present invention, when the electrochemical impedance spectroscopy as the main parameter indicates insufficient water contained in a membrane and the air flow rate as an additional parameter is shown as above a threshold, it should be considered that a micro-crack appears in the fuel cell system 20. To further verify the correctness of the diagnostic result, other additional sensing units may be used to sense other additional parameters, like gas pressure. According to another exemplary embodiment of the present invention, when the electrochemical impedance spectroscopy as the main parameter indicates insufficient water contained in the membrane and the air flow rate and the gas pressure and the like as the additional parameters are all at a normal level, the fuel cell system 20 can be diagnosed as being in a membrane-drying fault mode with higher accuracy.
Certainly, a person skilled in the art may alternatively consider another combination of the main parameter and the at least one additional parameter. Exemplarily, the at least one additional sensing unit 2 comprises a corresponding sensor, wherein the sensor is particularly integrated so as to save structural space.
Fig. 3 is a schematic flowchart of a method for diagnosing a fault mode of a fuel cell system according to the present invention. The method comprises the following steps: in a first step SI, a main parameter that is used to at least preliminarily diagnose a fault mode is sensed by a main sensing unit 1, and at least one additional parameter that potentially affects a diagnostic result is sensed by at least one additional sensing unit 2; in a second step S2, the main parameter and the at least one additional parameter are sent by a fuel cell analysis and evaluation unit 3; and in a third step S3, diagnostic information about the fault mode generated on the basis of the main parameter and the at least one additional parameter is received by the fuel cell analysis and evaluation unit 3.
Exemplarily, data about the main parameter and the at least one additional parameter and the diagnostic information generated on the basis of the data are all stored in a cloud server, so as to be used as a new data sample to perform further data training, thereby obtaining a diagnostic model updated in real time.
For a person skilled in the art, in addition to the above steps, other steps may further be comprised, which is not limited in the present invention.
Fig. 4 is a schematic diagram of a fuel cell vehicle system 1000 comprising a plurality of fuel cell vehicles 100 according to the present invention. For brevity, identical reference numerals are only shown once. The position and size relationships of various components in the drawings are strongly schematic and can be changed according to practical needs.
As shown in Fig. 4, a fuel cell vehicle 100 according to the present invention has a fuel cell diagnostic apparatus 10 and a fuel cell system 20 according to the present invention. The plurality of fuel cell vehicles 100 according to the present invention together form the distributed fuel cell vehicle system 1000, wherein the fuel cell vehicles 100 are all configured to be capable of communicating with a cloud server C in real time.
According to the present invention, a fuel cell diagnostic apparatus 10 of each fuel cell vehicle 100 is capable of sending its own main parameter and at least one additional parameter about the fuel cell system 20 to a cloud server C correspondingly. Therefore, the cloud server C may receive and store a large amount of data about the main parameter and the at least one additional parameter simultaneously and form corresponding big data. This greatly enriches data samples and does not miss possible fault modes.
Exemplarily, through real-time communication between the fuel cell diagnostic apparatus 10 of each fuel cell vehicle 100 and the cloud server C, online and real-time fault diagnosis for the fuel cell systems 20 of the plurality of fuel cell vehicles 100 can be implemented simultaneously.
The foregoing explanation of the embodiments describes the present invention only in the framework of the examples. Features of the embodiments may, certainly, be freely combined with each other without deviating from the framework of the present invention, as long as it makes technical sense.
Other advantages and alternative embodiments of the present invention will be apparent to a person skilled in the art. Therefore, the present invention in its broader sense is not limited to the specific details, representative structures, and exemplary embodiments shown and described herein. On the contrary, a person skilled in the art may make various changes and replacements herein without departing from the spirit and scope of the present invention.

Claims

Claims
1. A fuel cell diagnostic apparatus (10) for a fuel cell vehicle (100), the fuel cell diagnostic apparatus being configured to diagnose a fault mode of a fuel cell system (20) of the fuel cell vehicle (100), wherein the fuel cell diagnostic apparatus (10) at least comprises:
-a main sensing unit (1) configured to sense a main parameter that is used to at least preliminarily diagnose the fault mode;
-at least one additional sensing unit (2) configured to sense at least one additional parameter that potentially affects a diagnostic result; and
-a fuel cell analysis and evaluation unit (3) configured to be capable of sensding the main parameter and the at least one additional parameter, and of receiving diagnostic information about the fault mode generated on the basis of the main parameter and the at least one additional parameter.
2. The fuel cell diagnostic apparatus (10) as claimed in claim 1, wherein the fuel cell analysis and evaluation unit (3) is configured to be capable of communicating with a cloud server (C) in a wireless manner, so as to send data about the main parameter and the at least one additional parameter to the cloud server (C) and receive the diagnostic information from the cloud server (C).
3. The fuel cell diagnostic apparatus (10) as claimed in claim 1 or 2, wherein the main parameter comprises electrochemical impedance spectroscopy; and/or the at least one additional parameter is one or more selected from the following group: operating time, voltage, current, temperature, air flow rate, and gas pressure or pressure drop of the fuel cell system (20); and/or the fault mode comprises one or more of the following group: water-flooding, membrane-drying, micro-crack, icing, and overheating.
4. The fuel cell diagnostic apparatus (10) as claimed in claim 3, wherein the main sensing unit (1) comprises a DC/DC converter, and the DC/DC converter is configured to be capable of injecting an undulating current signal into the fuel cell system (20), to obtain the electrochemical impedance spectroscopy.
5. A cloud server (C) configured to be capable of receiving the main parameter and the at least one additional parameter from the fuel cell analysis and evaluation unit (3) of the fuel cell diagnostic apparatus (10) as claimed in any one of claims 1 to 4, and of generating the diagnostic information about the fault mode on the basis of the main parameter and the at least one additional parameter.
6. The cloud server (C) as claimed in claim 5, wherein the cloud server (C) is configured to be capable of: receiving data about the main parameter and the at least one additional parameter from the fuel cell analysis and evaluation unit (3) and storing the data, and using a machine learning algorithm to perform data training on stored historical data, to obtain an optimized diagnostic model; and/or the cloud server (C) is configured to be capable of receiving and storing experimental data and/or data about the main parameter and the at least one additional parameter from other fuel cell vehicles.
7. A method for diagnosing a fault mode of a fuel cell system (20) of a fuel cell vehicle (100), the method being implemented by the fuel cell diagnostic apparatus (10) as claimed in any one of claims 1 to 4, and the method comprising at least the following steps:
-sensing, by a main sensing unit (1), a main parameter that is used to at least preliminarily diagnose the fault mode, and sensing, by at least one additional sensing unit (2), at least one additional parameter that potentially affects a diagnostic result;
-sending the main parameter and the at least one additional parameter by a fuel cell analysis and evaluation unit (3); and
-receiving, by the fuel cell analysis and evaluation unit (3), diagnostic information about the fault mode generated on the basis of the main parameter and the at least one additional parameter.
8. A fuel cell vehicle (100), wherein the fuel cell vehicle (100) comprises the fuel cell diagnostic apparatus (10) as claimed in any one of claims 1 to 4.
9. A fuel cell vehicle system (1000), wherein the fuel cell vehicle system (1000) comprises a plurality of fuel cell vehicles (100) as claimed in claim 8, wherein the plurality of fuel cell vehicles (100) are all configured to be capable of communicating with a cloud server (C).
10. A fuel cell vehicle network system, wherein the fuel cell vehicle network system comprises the fuel cell vehicle system (1000) as claimed in claim 9 and the cloud server (C) as claimed in claim 5 or 6.
PCT/EP2021/060112 2020-04-24 2021-04-19 Fuel cell diagnostic apparatus and corresponding diagnostic method, vehicle, and vehicle system WO2021213989A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010332463.3 2020-04-24
CN202010332463.3A CN113555591A (en) 2020-04-24 2020-04-24 Fuel cell diagnostic device and corresponding diagnostic method, vehicle and vehicle system

Publications (1)

Publication Number Publication Date
WO2021213989A1 true WO2021213989A1 (en) 2021-10-28

Family

ID=75659990

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2021/060112 WO2021213989A1 (en) 2020-04-24 2021-04-19 Fuel cell diagnostic apparatus and corresponding diagnostic method, vehicle, and vehicle system

Country Status (2)

Country Link
CN (1) CN113555591A (en)
WO (1) WO2021213989A1 (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113903954A (en) * 2021-11-17 2022-01-07 中汽研新能源汽车检验中心(天津)有限公司 Hydrogen fuel cell water fault on-line diagnosis testing arrangement
CN114492087A (en) * 2022-04-02 2022-05-13 国网浙江省电力有限公司电力科学研究院 Fault diagnosis method and device for proton exchange membrane fuel cell of hydrogen energy storage power station
CN115084593A (en) * 2022-05-31 2022-09-20 同济大学 Fuel cell fault diagnosis method based on nonlinear impedance spectrum
CN116247248A (en) * 2023-05-10 2023-06-09 北京新研创能科技有限公司 Method and system for diagnosing health state of hydrogen fuel cell stack based on emission analysis
CN117117258A (en) * 2023-10-24 2023-11-24 新研氢能源科技有限公司 Fault monitoring method and device for hydrogen fuel cell system

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114062786B (en) * 2022-01-07 2022-04-01 北京航空航天大学 EIS (electronic impedance spectroscopy) online measurement method based on digital twinning and programmable resistance
CN114675202A (en) * 2022-03-11 2022-06-28 华为数字能源技术有限公司 Battery fault diagnosis method and device

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109726452A (en) * 2018-12-12 2019-05-07 浙江大学 A kind of online Proton Exchange Membrane Fuel Cells method for diagnosing faults based on impedance spectrum
KR20190107080A (en) * 2017-01-13 2019-09-18 후아웨이 테크놀러지 컴퍼니 리미티드 Cloud-based vehicle fault diagnosis method, apparatus and system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20190107080A (en) * 2017-01-13 2019-09-18 후아웨이 테크놀러지 컴퍼니 리미티드 Cloud-based vehicle fault diagnosis method, apparatus and system
CN109726452A (en) * 2018-12-12 2019-05-07 浙江大学 A kind of online Proton Exchange Membrane Fuel Cells method for diagnosing faults based on impedance spectrum

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
LU HUAXIN ET AL: "On-line fault diagnosis for proton exchange membrane fuel cells based on a fast electrochemical impedance spectroscopy measurement", JOURNAL OF POWER SOURCES, vol. 430, 1 August 2019 (2019-08-01), CH, pages 233 - 243, XP055793552, ISSN: 0378-7753, DOI: 10.1016/j.jpowsour.2019.05.028 *
SUTHARSSAN THAMO ET AL: "A review on prognostics and health monitoring of proton exchange membrane fuel cell", RENEWABLE AND SUSTAINABLE ENERGY REVIEWS, vol. 75, 1 August 2017 (2017-08-01), pages 440 - 450, XP029978380, ISSN: 1364-0321, DOI: 10.1016/J.RSER.2016.11.009 *
WANG HANQING ET AL: "Online electrochemical impedance spectroscopy detection integrated with step-up converter for fuel cell electric vehicle", INTERNATIONAL JOURNAL OF HYDROGEN ENERGY, vol. 44, no. 2, 26 November 2018 (2018-11-26), pages 1110 - 1121, XP085564511, ISSN: 0360-3199, DOI: 10.1016/J.IJHYDENE.2018.10.242 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113903954A (en) * 2021-11-17 2022-01-07 中汽研新能源汽车检验中心(天津)有限公司 Hydrogen fuel cell water fault on-line diagnosis testing arrangement
CN114492087A (en) * 2022-04-02 2022-05-13 国网浙江省电力有限公司电力科学研究院 Fault diagnosis method and device for proton exchange membrane fuel cell of hydrogen energy storage power station
CN114492087B (en) * 2022-04-02 2022-07-19 国网浙江省电力有限公司电力科学研究院 Fault diagnosis method and device for proton exchange membrane fuel cell of hydrogen energy storage power station
CN115084593A (en) * 2022-05-31 2022-09-20 同济大学 Fuel cell fault diagnosis method based on nonlinear impedance spectrum
CN115084593B (en) * 2022-05-31 2024-05-31 同济大学 Fuel cell fault diagnosis method based on nonlinear impedance spectrum
CN116247248A (en) * 2023-05-10 2023-06-09 北京新研创能科技有限公司 Method and system for diagnosing health state of hydrogen fuel cell stack based on emission analysis
CN117117258A (en) * 2023-10-24 2023-11-24 新研氢能源科技有限公司 Fault monitoring method and device for hydrogen fuel cell system
CN117117258B (en) * 2023-10-24 2024-01-09 新研氢能源科技有限公司 Fault monitoring method and device for hydrogen fuel cell system

Also Published As

Publication number Publication date
CN113555591A (en) 2021-10-26

Similar Documents

Publication Publication Date Title
WO2021213989A1 (en) Fuel cell diagnostic apparatus and corresponding diagnostic method, vehicle, and vehicle system
US11916270B2 (en) Active fault-tolerant temperature control method for proton exchange membrane fuel cell system
CN113782778B (en) Electric pile water management regulation and control method and device based on fixed frequency impedance and gas pressure drop
CN109346745A (en) A kind of method and system judging fuel battery inside water state based on impedance
CN109342964A (en) A kind of analysis method of proton exchange film fuel cell electric piling health status
Wang et al. A comparative study of equivalent circuit model and distribution of relaxation times for fuel cell impedance diagnosis
CN107681181A (en) A kind of performance diagnogtics method of fuel cell
Li et al. Application of distribution of relaxation times method in polymer electrolyte membrane water electrolyzer
Mao et al. Selection of optimal sensors for predicting performance of polymer electrolyte membrane fuel cell
CN113488680B (en) SIMULINK-based cold start modeling simulation test method for fuel cell stack
CN112331888A (en) Fuel cell stack simulator based on simulation model
Huang et al. Experimental study of the performance degradation of proton exchange membrane fuel cell based on a multi-module stack under selected load profiles by clustering algorithm
Huang et al. Correlation analysis and prediction of PEM fuel cell voltage during start-stop operation based on real-world driving data
CN115248382A (en) Control method of proton exchange membrane fuel cell
US20140026633A1 (en) Extremum seeking algorithm in a variable time interval to detect anode pressure sensor stuck failure in a fuel cell system
CN111628195A (en) Fuel cell stack real-time state identification method based on logic reasoning
CN103575515B (en) Via heap voltage response analysis diagnosis injector fault
Yuan et al. Fault diagnosis of fuel cells by a hybrid deep learning network fusing characteristic impedance
Sun et al. Fault diagnosis method for proton exchange membrane fuel cell system based on digital twin and unsupervised domain adaptive learning
CN113780537A (en) Fault diagnosis method and device for proton exchange membrane fuel cell power generation system
Wei et al. Estimating PEMFC ohmic internal impedance based on indirect measurements
CN116706157B (en) Fuel cell vehicle and hydrogen discharge valve/drain valve fault diagnosis method and device
CN210422972U (en) Hydrogen circulating pump testing arrangement for fuel cell system
CN113707915B (en) Water management control method and device for fuel cell stack
CN113258104A (en) Method and device for determining humidity of fuel cell and server

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21721013

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21721013

Country of ref document: EP

Kind code of ref document: A1