CN115320387A - Vehicle fuel cell membrane humidity prediction method and system based on multi-source information fusion - Google Patents

Vehicle fuel cell membrane humidity prediction method and system based on multi-source information fusion Download PDF

Info

Publication number
CN115320387A
CN115320387A CN202211263752.8A CN202211263752A CN115320387A CN 115320387 A CN115320387 A CN 115320387A CN 202211263752 A CN202211263752 A CN 202211263752A CN 115320387 A CN115320387 A CN 115320387A
Authority
CN
China
Prior art keywords
fuel cell
characteristic
humidity
membrane
vehicle fuel
Prior art date
Legal status (The legal status 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 status listed.)
Granted
Application number
CN202211263752.8A
Other languages
Chinese (zh)
Other versions
CN115320387B (en
Inventor
李建威
闫崇浩
万鑫铭
鲍欢欢
毛占鑫
贾博文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Technology BIT
Original Assignee
Beijing Institute of Technology BIT
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 Beijing Institute of Technology BIT filed Critical Beijing Institute of Technology BIT
Priority to CN202211263752.8A priority Critical patent/CN115320387B/en
Publication of CN115320387A publication Critical patent/CN115320387A/en
Application granted granted Critical
Publication of CN115320387B publication Critical patent/CN115320387B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • B60L3/00—Electric devices on electrically-propelled vehicles for safety purposes; Monitoring operating variables, e.g. speed, deceleration or energy consumption
    • B60L3/0023—Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train
    • B60L3/0053—Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train relating to fuel cells
    • 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
    • B60L58/30—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling fuel cells
    • 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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Sustainable Energy (AREA)
  • Sustainable Development (AREA)
  • Power Engineering (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Fuel Cell (AREA)

Abstract

The invention discloses a vehicle fuel cell membrane humidity prediction method and system based on multi-source information fusion, and relates to the technical field of vehicle fuel cell parameter prediction, wherein the method comprises the following steps: determining an amplitude spectrum according to the output voltage of the vehicle fuel cell at the current time period; determining theoretical voltage drop of an anode inlet and an anode outlet according to the output current of the vehicle fuel cell at the current time; when the theoretical pressure drop of the anode inlet and the anode outlet is smaller than the actual pressure drop of the anode inlet and the anode outlet, predicting the membrane humidity of the vehicle fuel cell at the current time according to the amplitude spectrum, the second characteristic and the membrane dry fault characteristic space of the vehicle fuel cell; and the second characteristic is the absolute value of the difference value between the theoretical voltage drop of the anode inlet and the anode outlet and the actual voltage drop of the anode inlet and the anode outlet, otherwise, the membrane humidity is predicted according to the amplitude spectrum, the second characteristic and the flooding fault characteristic space of the vehicle fuel cell. The invention can realize real-time quantitative prediction of the humidity of the internal membrane of the vehicle fuel cell, and improve the use safety and durability of the vehicle fuel cell.

Description

Vehicle fuel cell membrane humidity prediction method and system based on multi-source information fusion
Technical Field
The invention relates to the technical field of vehicle fuel cell parameter prediction, in particular to a vehicle fuel cell membrane humidity prediction method and system based on multi-source information fusion.
Background
In the process of fuel cell automobile industrialization and popularization and use, the service life problem of the automobile fuel cell is a complex system problem related to materials, structures, auxiliary systems and control strategies. When the vehicle fuel cell runs, the internal humidity is a very important state parameter, and the performance of the vehicle fuel cell directly influences the transmission process of protons, so that the internal resistance is changed, the output voltage, current, power and the like are greatly reduced, and the output characteristic of the vehicle fuel cell is seriously influenced; in severe cases, the proton exchange membrane module may also be damaged, leading to failure of the vehicle fuel cell.
The humidity of the vehicle fuel cell is monitored and predicted in real time, so that the operation performance of the vehicle fuel cell is certainly benefited, the safety and the reliability of the vehicle fuel cell are further improved in an auxiliary mode, and the service life of the vehicle fuel cell is finally prolonged. However, due to the sealed structure of the vehicle fuel cell itself, it is impossible to mount a sensor inside thereof; meanwhile, the existence of the sensor can change the structural characteristics of the vehicle fuel cell, and further directly influences the working performance of the vehicle fuel cell. Meanwhile, from the practical operation point of view, the average thickness of the proton exchange membrane of the vehicle fuel cell is generally 10-200 because the proton exchange membrane is very thinμmRange, and therefore sensor placement and installation, is also very difficult. Therefore, with the conventional means and method, it is difficult to directly obtain the internal humidity parameter or the state characteristic thereof of the fuel cell for a vehicle.
Disclosure of Invention
The invention aims to provide a method and a system for predicting the membrane humidity of a vehicle fuel cell based on multi-source information fusion, which can realize real-time quantitative prediction of the internal membrane humidity of the vehicle fuel cell and improve the use safety and durability of the vehicle fuel cell.
In order to achieve the purpose, the invention provides the following scheme:
in a first aspect, the invention provides a method for predicting membrane humidity of a vehicle fuel cell based on multi-source information fusion, which comprises the following steps:
acquiring the state information of the vehicle fuel cell at the current time period; the state information of the vehicle fuel cell at the current time period at least comprises output voltage, output current and actual voltage drop of an anode inlet and an anode outlet;
determining a first characteristic of the vehicle fuel cell in the current time period according to the output voltage of the vehicle fuel cell in the current time period; the first characteristic is an amplitude spectrum;
determining the theoretical voltage drop of the anode inlet and the anode outlet of the vehicle fuel cell at the current time according to the output current of the vehicle fuel cell at the current time;
when the theoretical pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period is smaller than the actual pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period, calculating a second characteristic of the vehicle fuel cell in the current time period, and predicting the membrane humidity of the vehicle fuel cell in the current time period according to the first characteristic of the vehicle fuel cell in the current time period, the second characteristic of the vehicle fuel cell in the current time period and the membrane dry failure characteristic space of the vehicle fuel cell; the second characteristic is a first absolute value; the first absolute value is the absolute value of the difference value between the theoretical voltage drop of the anode inlet and the outlet of the vehicle fuel cell in the current time period and the actual voltage drop of the anode inlet and the outlet of the vehicle fuel cell in the current time period;
when the theoretical pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period is larger than the actual pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period, calculating a second characteristic of the vehicle fuel cell in the current time period, and predicting the membrane humidity of the vehicle fuel cell in the current time period according to the first characteristic of the vehicle fuel cell in the current time period, the second characteristic of the vehicle fuel cell in the current time period and the water-logging fault characteristic space of the vehicle fuel cell;
the membrane dry failure characteristic space of the vehicle fuel cell is a two-dimensional space constructed by the membrane dry failure characteristic and the first membrane humidity; the first film humidity is a relative film humidity of less than 100%; the dry film fault characteristic is a first characteristic and a second characteristic corresponding to the first film humidity;
the water-logging fault feature space of the vehicle fuel cell is a two-dimensional space constructed by the water-logging fault feature and the humidity of the second membrane; the second film humidity is a relative film humidity greater than 100%; the water flooding fault characteristic is a first characteristic and a second characteristic corresponding to the humidity of the second membrane.
In a second aspect, the present invention provides a system for predicting membrane humidity of a vehicle fuel cell based on multi-source information fusion, comprising:
the state information acquisition module is used for acquiring the state information of the vehicle fuel cell at the current time period; the state information of the vehicle fuel cell at the current time period at least comprises output voltage, output current and actual voltage drop of an anode inlet and an anode outlet;
the first characteristic calculation module is used for determining first characteristics of the vehicle fuel cell in the current time period according to the output voltage of the vehicle fuel cell in the current time period; the first characteristic is an amplitude spectrum;
the anode inlet and outlet theoretical voltage drop calculation module is used for determining the anode inlet and outlet theoretical voltage drop of the vehicle fuel cell in the current time period according to the output current of the vehicle fuel cell in the current time period;
a membrane humidity prediction module to:
when the theoretical pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period is smaller than the actual pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period, calculating a second characteristic of the vehicle fuel cell in the current time period, and predicting the membrane humidity of the vehicle fuel cell in the current time period according to the first characteristic of the vehicle fuel cell in the current time period, the second characteristic of the vehicle fuel cell in the current time period and a membrane dry fault characteristic space of the vehicle fuel cell; the second characteristic is a first absolute value; the first absolute value is the absolute value of the difference between the theoretical voltage drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period and the actual voltage drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period;
when the theoretical pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period is larger than the actual pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period, calculating a second characteristic of the vehicle fuel cell in the current time period, and predicting the membrane humidity of the vehicle fuel cell in the current time period according to the first characteristic of the vehicle fuel cell in the current time period, the second characteristic of the vehicle fuel cell in the current time period and a water flooding fault characteristic space of the vehicle fuel cell;
the membrane dry failure characteristic space of the vehicle fuel cell is a two-dimensional space constructed by the membrane dry failure characteristic and the first membrane humidity; the first film humidity is a relative film humidity of less than 100%; the dry film fault characteristic is a first characteristic and a second characteristic corresponding to the first film humidity;
the water-logging fault feature space of the vehicle fuel cell is a two-dimensional space constructed by the water-logging fault feature and the humidity of the second membrane; the second film humidity is a relative film humidity above 100%; the water flooding fault characteristic is a first characteristic and a second characteristic corresponding to the humidity of the second membrane.
In a third aspect, the invention provides a method for predicting humidity of a vehicle fuel cell membrane based on multi-source information fusion, which comprises the following steps:
acquiring the state information of the vehicle fuel cell at the current time; the state information of the vehicle fuel cell at the current time period at least comprises output voltage, output current and actual voltage drop of an anode inlet and an anode outlet;
predicting the state information of the vehicle fuel cell at the next time period according to the state information of the vehicle fuel cell at the current time period and a machine learning algorithm;
determining a first characteristic of the fuel cell for the vehicle in the next period according to the output voltage of the fuel cell for the vehicle in the next period; the first characteristic is an amplitude spectrum;
determining the theoretical voltage drop of the anode inlet and the anode outlet of the fuel cell for the vehicle at the next period according to the output current of the fuel cell for the vehicle at the next period;
when the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the vehicle in the next period is smaller than the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the vehicle in the next period, calculating a second characteristic of the fuel cell for the vehicle in the next period, and predicting the membrane humidity of the fuel cell for the vehicle in the next period according to the first characteristic of the fuel cell for the vehicle in the next period, the second characteristic of the fuel cell for the vehicle in the next period and a membrane dry fault characteristic space of the fuel cell for the vehicle in the next period; the second characteristic is a first absolute value; the first absolute value is the absolute value of the difference between the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the vehicle in the next period and the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the vehicle in the next period;
when the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time is larger than the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time, calculating a second characteristic of the fuel cell for the next period of time, and predicting the membrane humidity of the fuel cell for the next period of time according to the first characteristic of the fuel cell for the next period of time, the second characteristic of the fuel cell for the next period of time and the water flooding fault feature space of the fuel cell for the vehicle;
the membrane dry failure characteristic space of the vehicle fuel cell is a two-dimensional space constructed by the membrane dry failure characteristic and the first membrane humidity; the first film humidity is a relative film humidity of less than 100%; the dry film fault characteristic is a first characteristic and a second characteristic corresponding to the first film humidity;
the water-logging fault feature space of the vehicle fuel cell is a two-dimensional space constructed by the water-logging fault feature and the humidity of the second membrane; the second film humidity is a relative film humidity above 100%; the water flooding fault characteristic is a first characteristic and a second characteristic corresponding to the humidity of the second membrane.
In a fourth aspect, the present invention provides a system for predicting membrane humidity of a vehicle fuel cell based on multi-source information fusion, comprising:
the state information acquisition module is used for acquiring the state information of the vehicle fuel cell at the current time period; the state information of the vehicle fuel cell at the current time period at least comprises output voltage, output current and actual voltage drop of an anode inlet and an anode outlet;
the state information prediction module is used for predicting the state information of the vehicle fuel cell at the next time period according to the state information of the vehicle fuel cell at the current time period and a machine learning algorithm;
a first characteristic calculation module for determining a first characteristic of the fuel cell for the vehicle at the next period based on an output voltage of the fuel cell for the vehicle at the next period; the first characteristic is an amplitude spectrum;
the anode inlet and outlet theoretical voltage drop calculation module is used for determining the anode inlet and outlet theoretical voltage drop of the fuel cell for the vehicle in the next period according to the output current of the fuel cell for the vehicle in the next period;
a membrane humidity prediction module to:
when the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the vehicle in the next period is smaller than the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the vehicle in the next period, calculating a second characteristic of the fuel cell for the vehicle in the next period, and predicting the membrane humidity of the fuel cell for the vehicle in the next period according to the first characteristic of the fuel cell for the vehicle in the next period, the second characteristic of the fuel cell for the vehicle in the next period and a membrane dry fault characteristic space of the fuel cell for the vehicle in the next period; the second characteristic is a first absolute value; the first absolute value is the absolute value of the difference value between the theoretical pressure drop of the anode inlet and the outlet of the fuel cell for the vehicle in the next period and the actual pressure drop of the anode inlet and the outlet of the fuel cell for the vehicle in the next period;
when the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time is larger than the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time, calculating a second characteristic of the fuel cell for the next period of time, and predicting the membrane humidity of the fuel cell for the next period of time according to the first characteristic of the fuel cell for the next period of time, the second characteristic of the fuel cell for the next period of time and the water flooding fault feature space of the fuel cell for the vehicle;
the membrane dry failure characteristic space of the vehicle fuel cell is a two-dimensional space constructed by the membrane dry failure characteristic and the first membrane humidity; the first film humidity is a relative film humidity of less than 100%; the dry film fault characteristic is a first characteristic and a second characteristic corresponding to the first film humidity;
the water-logging fault feature space of the vehicle fuel cell is a two-dimensional space constructed by the water-logging fault feature and the humidity of the second membrane; the second film humidity is a relative film humidity greater than 100%; the water flooding fault characteristic is a first characteristic and a second characteristic corresponding to the humidity of the second membrane.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
research shows that, to a certain extent, the change condition of the internal humidity of the vehicle fuel cell can be reflected by the output voltage characteristic and the anode inlet and outlet voltage drop of the vehicle fuel cell. In view of the above, the invention provides a method and a system for predicting membrane humidity of a vehicle fuel cell based on multi-source information fusion, and aims to obtain real-time dynamic data information of stack operation by performing online measurement on output voltage and anode inlet/outlet voltage drop of the vehicle fuel cell, input the data information into a vehicle fuel cell water flooding fault feature space and a vehicle fuel cell membrane dry fault feature space constructed by adopting an information fusion technology after data preprocessing, predict membrane humidity of the vehicle fuel cell, realize real-time quantitative prediction of internal membrane humidity of the vehicle fuel cell, and improve use safety and durability of the vehicle fuel cell.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for predicting membrane humidity of a vehicle fuel cell based on multi-source information fusion according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for constructing a membrane dry fault feature space and a water-flooding fault feature space of a vehicle fuel cell according to an embodiment of the present invention;
FIG. 3 shows the output voltage of the fuel cell for vehicle under the NEDC condition according to the embodiment of the present inventionV 25 And the output voltageV 100 A comparative drawing and a partially enlarged drawing; in FIG. 3 a) is a comparison; b) in FIG. 3 is an enlarged view;
FIG. 4 shows an output voltage according to an embodiment of the present inventionV 25 And the output voltageV 100 The absolute value of the difference value of (2) and the vehicle speed map;
FIG. 5 shows the output voltages of the present inventionV 25 And the output voltageV 100 A second derivative graph of the absolute value of the difference and a local enlarged view of the acceleration section; in FIG. 5 a) is a graph of second derivative; b) in fig. 5 is a partial enlarged view of the acceleration section;
FIG. 6 shows an output voltage according to an embodiment of the present inventionV 25 And the output voltageV 100 The second derivative of the absolute value of the difference value is transferred to a frequency domain, and then an amplitude spectrogram is extracted;
FIG. 7 is a graph of anode drop for a vehicle fuel cell with different membrane humidity failures in accordance with an embodiment of the present invention;
FIG. 8 shows a schematic diagram of an embodiment of the present inventionAS i AndD piΔ a scatter diagram is established for the coordinate axis;
FIG. 9 is a schematic diagram of a membrane stem failure feature space of a vehicular fuel cell according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of a water-flooding fault feature space of a vehicle fuel cell according to an embodiment of the present invention;
fig. 11 is a schematic view of a construction process of a feature space vector of a membrane stem fault of a vehicle fuel cell according to an embodiment of the present invention;
fig. 12 is a schematic diagram illustrating a construction process of a feature space vector of a water-flooding fault of a vehicle fuel cell according to an embodiment of the present invention;
fig. 13 is a schematic diagram of a quantized prediction strategy for a vehicle fuel cell according to an embodiment of the present invention;
FIG. 14 is a schematic structural diagram of a vehicular fuel cell membrane humidity prediction system based on multi-source information fusion according to an embodiment of the present invention;
fig. 15 is a flowchart of a fuel cell membrane humidity measurement prediction and warning method according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention more comprehensible, the present invention is described in detail with reference to the accompanying drawings and the detailed description thereof.
Example one
The humidity fault of the membrane of the fuel cell for the vehicle is reflected on multi-source information, for example, the output pressure of the fuel cell for the vehicle is reduced, the cathode and anode voltage drop is increased, and the like. In order to improve the accuracy and stability of the humidity fault prediction of the membrane of the vehicle fuel cell, the embodiment adopts an information fusion technology to gather multi-aspect information, and considers the electrical quantity of the output voltage of the vehicle fuel cell and the non-electrical quantity of the anode voltage drop together for the measurement prediction of the membrane humidity.
As shown in fig. 1, the method for predicting membrane humidity of a vehicle fuel cell based on multi-source information fusion provided in this embodiment includes the following steps.
Step 100: acquiring the state information of the vehicle fuel cell at the current time period; the state information of the vehicle fuel cell at the current time period at least comprises output voltage, output current and actual voltage drop of an anode inlet and an anode outlet.
Step 200: determining a first characteristic of the vehicle fuel cell in the current time period according to the output voltage of the vehicle fuel cell in the current time period; the first feature is an amplitude spectrum.
Step 300: and determining the theoretical voltage drop of the anode inlet and the anode outlet of the vehicle fuel cell at the current time according to the output current of the vehicle fuel cell at the current time.
Step 400: when the theoretical pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period is smaller than the actual pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period, calculating a second characteristic of the vehicle fuel cell in the current time period, and predicting the membrane humidity of the vehicle fuel cell in the current time period according to the first characteristic of the vehicle fuel cell in the current time period, the second characteristic of the vehicle fuel cell in the current time period and the membrane dry failure characteristic space of the vehicle fuel cell; the second characteristic is a first absolute value; the first absolute value is an absolute value of a difference value between the theoretical voltage drop of the anode inlet and the theoretical voltage drop of the anode of the vehicle fuel cell in the current time period and the actual voltage drop of the anode inlet and the anode of the vehicle fuel cell in the current time period.
Step 500: and when the theoretical pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell at the current time interval is larger than the actual pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell at the current time interval, calculating the second characteristic of the vehicle fuel cell at the current time interval, and predicting the membrane humidity of the vehicle fuel cell at the current time interval according to the first characteristic of the vehicle fuel cell at the current time interval, the second characteristic of the vehicle fuel cell at the current time interval and the water-logging fault characteristic space of the vehicle fuel cell.
The membrane dry failure characteristic space of the vehicle fuel cell is a two-dimensional space constructed by the membrane dry failure characteristic and the first membrane humidity; the first film humidity is a relative film humidity of less than 100%; the dry film failure characteristic is a first characteristic and a second characteristic corresponding to the first film humidity.
The water-logging fault feature space of the vehicle fuel cell is a two-dimensional space constructed by the water-logging fault feature and the humidity of the second membrane; the second film humidity is a relative film humidity greater than 100%; the water flooding fault characteristic is a first characteristic and a second characteristic corresponding to the humidity of the second membrane.
As a preferred embodiment of step 200, specifically, the method includes:
step 201: the output voltage of the vehicle fuel cell in normal operation is acquired.
Step 202: calculating a second absolute value; the second absolute value is an absolute value of a difference between the output voltage of the vehicle fuel cell at the present time period and the output voltage of the vehicle fuel cell at the normal operation.
Step 203: determining an absolute value of an acceleration section according to the second absolute value; and the absolute value of the acceleration section is a second absolute value under the working condition of the acceleration section.
Step 204: and calculating a second derivative of the absolute value of the acceleration section, and performing Fourier transform on the second derivative of the absolute value of the acceleration section to obtain a frequency domain signal.
Step 205: and extracting the amplitude spectrum of the vehicle fuel cell in the current time period according to the frequency domain signal.
In this embodiment, the state information of the vehicle fuel cell at the current time period further includes operating condition information; the operating condition information comprises the width of the cathode water flow channel, the depth of the cathode water flow channel, the length of the cathode water flow channel, the number of the cathode water flow channels, the hydrogen pressure at the anode inlet, the hydrogen saturation pressure at the anode inlet, the hydrogen stoichiometric number and the operating temperature of the fuel cell.
As a preferred implementation manner of step 300, specifically, the method includes:
and calculating the theoretical voltage drop of the anode inlet and the anode outlet of the vehicle fuel cell at the current time according to the output current and the working condition information of the vehicle fuel cell at the current time.
Further, the method disclosed in this embodiment further includes: and constructing a membrane dry fault characteristic space and a water-flooded fault characteristic space of the vehicle fuel cell.
The method for constructing the membrane dry fault characteristic space of the vehicle fuel cell and the water-logging fault characteristic space of the vehicle fuel cell specifically comprises the following steps:
step (1): acquiring state information of the vehicle fuel cell in a history stage; the state information of the vehicle fuel cell in the historical stage comprises working condition information, output voltage, output current and actual voltage drop of an anode inlet and an anode outlet corresponding to different membrane humidities.
Step (2): and determining first characteristics corresponding to different membrane humidities according to the output voltage of the vehicle fuel cell in the historical stage.
And (3): and determining the theoretical pressure drop of the anode inlet and the anode outlet corresponding to different membrane humidities according to the output current and the working condition information of the vehicle fuel cell in the historical stage.
And (4): and determining second characteristics corresponding to different membrane humidities according to the theoretical pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell and the actual pressure drop of the anode inlet and the anode outlet in the historical stage.
And (5): determining first sample data and second sample data; the first sample data is a first characteristic and a second characteristic corresponding to different first film humidities; the second sample data is a first characteristic and a second characteristic corresponding to different second membrane humidities.
And (6): and constructing a membrane dry fault feature space of the vehicle fuel cell according to the first sample data.
And (7): and constructing a water-logging fault feature space of the vehicle fuel cell according to the second sample data.
Wherein, the step (6) specifically comprises:
step 2): expressing the first characteristics and the second characteristics corresponding to different first film humidities in a coordinate mode to obtain different first film humidity coordinates; the abscissa of the first film humidity coordinate is a first characteristic; the ordinate of the first film humidity coordinate is a second characteristic;
and step 3): carrying out averaging operation on a plurality of first membrane humidity coordinates corresponding to the same first membrane humidity to obtain average value coordinates corresponding to different first membrane humidities; wherein one of said first membrane humidities corresponds to one mean coordinate;
step 4): drawing the different mean value coordinates in a two-dimensional coordinate system to obtain a membrane trunk fault characteristic space of the vehicle fuel cell; and in the direction of increasing the coordinate value of the X axis in the membrane dry fault feature space of the vehicle fuel cell, the humidity of the first membrane corresponding to the mean coordinate is increased progressively.
Since the implementation process of step (7) is similar to that of step (6), redundant description is omitted here.
The following describes a process for constructing a membrane dry failure feature space and a water-flooded failure feature space of a vehicle fuel cell by using a specific example.
One example is: as shown in fig. 2, the construction process of the membrane dry fault feature space and the water-flooded fault feature space of the vehicle fuel cell is as follows.
A first part: and (4) multi-source information preprocessing.
Firstly, acquiring output voltage (NEDC) of a fuel cell vehicle under the condition that relative membrane humidity is 25%, 50%, 75%, 100%, 125%, 150% and 175% under the New European Driving Cycle (NEDC) Cycle working condition of the fuel cell vehicleV i ) An output current (I i ) Actual anode inlet-outlet pressure drop (
Figure DEST_PATH_IMAGE001
) Whereini=25. 50, 75, 100, 125, 150, 175, and a signal acquisition time of 1180 seconds. Determining operating condition information of vehicle fuel cells, e.g. cathode flow channel width: (C w ) Depth of cathode water flow channel: (C d ) Length of cathode flow channelL) The number of cathode flow channels: (n) Anode inlet hydrogen pressure (p in ) Anode inlet hydrogen saturation pressure: (p sat ) Hydrogen stoichiometry: (
Figure 207408DEST_PATH_IMAGE002
) And fuel cell operating temperature (T) The summary is shown in table 1 below.
TABLE 1 Multi-Source information data sheet
Figure 812832DEST_PATH_IMAGE004
Secondly, the output voltage of the vehicle fuel cell under different membrane humidity faults is lower than the output voltage of the vehicle fuel cell under normal operation (AS shown in fig. 3, the relative membrane humidity is 25% for example, other membrane humidity faults are similar), absolute values of the difference between the two are respectively calculated (AS shown in fig. 4), and it can be known from fig. 4 that the difference between the fault output voltage of the vehicle fuel cell under acceleration condition with membrane humidity fault and the output voltage of the vehicle fuel cell under normal operation is obvious, so that the absolute value of the difference between the two in the acceleration section, namely the output voltage drop, is extracted, a second derivative is obtained (AS shown in fig. 5), then the second derivative of the output voltage drop is converted to a frequency domain by fourier transform (AS shown in formula (1), and an amplitude spectrum is extracted (AS the extracted feature one, namely AS shown in fig. 6). Respectively acquiring data of the characteristics of the vehicle fuel cell with 3 types of membrane dry faults and 3 types of water flooding faults, namely respectivelyAS 25、 AS 50、 AS 75、 AS 125、 AS1 150、 AS 175 。
Figure DEST_PATH_IMAGE005
Wherein the content of the first and second substances,f(t)in the form of a time-domain signal,
Figure 825919DEST_PATH_IMAGE006
in the form of a frequency-domain signal,
Figure DEST_PATH_IMAGE007
in order to integrate the transform kernel,dti.e. to timetThe integration is carried out in such a way that,F[ ]representing a fourier transform.
A third step of measuring the output current (C) based on the measured output currentI i ) Width of cathode water flow channelC w ) Depth of cathode water flow channelC d ) Length of cathode water flow channel (c)L) And the number of cathode water flow channelsn) Anode inlet hydrogen pressure (c)p in ) Anode inlet hydrogenSaturation pressure (a)p sat ) Stoichiometric amount of hydrogen gas (
Figure 101174DEST_PATH_IMAGE008
) And fuel cell operating temperature (T) And (3) waiting for signals, acquiring the theoretical voltage drop of the inlet and the outlet of the anode under the state:
Figure DEST_PATH_IMAGE009
（273K≤T≤313K） （2）；
Figure 405903DEST_PATH_IMAGE010
（313K<T≤373K） （3）；
wherein, the first and the second end of the pipe are connected with each other,i=25. 50, 75, 100, 125, 150 and 175, and acquiring the actual anode inlet and outlet voltage drop of the vehicle fuel cell under different membrane humidity faults through signal acquisition
Figure DEST_PATH_IMAGE011
、
Figure 955964DEST_PATH_IMAGE012
、…
Figure 682611DEST_PATH_IMAGE013
(ii) a The actual pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell is higher than the theoretical pressure drop of the anode inlet and the anode outlet under the flooding fault, and the pressure drop value is almost kept unchanged due to little water quantity under the membrane dry fault, so that the actual pressure drop of the anode inlet and the anode outlet is smaller than the theoretical pressure drop of the anode inlet and the anode outlet (as shown in fig. 7).
Calculating the absolute value of the difference value between the theoretical pressure drop of the anode inlet and the anode outlet and the actual pressure drop of the anode inlet and the anode outlet under different membrane humidities of the vehicle fuel cell, and taking the absolute value as the second extracted characteristic, namely: to represent
Figure DEST_PATH_IMAGE014
（4）；
Wherein the content of the first and second substances,
Figure 594679DEST_PATH_IMAGE015
the absolute value of the difference value of the theoretical pressure drop of the anode inlet and the anode outlet and the actual pressure drop of the anode inlet and the anode outlet is represented;
Figure DEST_PATH_IMAGE016
representing the actual pressure drop of the inlet and the outlet of the anode when the relative membrane humidity is i%;
Figure 508409DEST_PATH_IMAGE017
and the theoretical pressure drop of the inlet and the outlet of the anode is shown.
A second part: and establishing a feature space.
For the first feature extracted from the electrical signal:AS i and a non-electrical signal characteristic two:
Figure 393319DEST_PATH_IMAGE015
，i=25. 50, 75, 100, 125, 150 and 175, which are plotted in a two-dimensional space as horizontal and vertical axes, so as to respectively establish a membrane dry fault characteristic space and a water flooding fault characteristic space of the fuel cell for the vehicle.
First, the method comprisesAS i And
Figure 443315DEST_PATH_IMAGE015
and (3) carrying out normalization treatment:
Figure DEST_PATH_IMAGE018
wherein the content of the first and second substances,x p the normalized data is represented as a result of the normalization,x q as the original data, it is the original data,x qmin andx qmax representing the minimum and maximum values in the raw data, respectively.
Second step of obtainingAS 25、 AS 50、 AS 75 AndD p25Δ、 D p50Δ、 D p75Δ and drawing the data in a two-dimensional coordinate system (as shown in fig. 8) to form a scatter diagram, and then extracting a mean value point (as shown in fig. 9) of three membrane humidity fault values in the drawn scatter diagram to complete the establishment of the membrane dry fault feature space of the vehicle fuel cell.
Third, obtainingAS 125 、AS 150 、AS 175 AndD p125Δ 、D p150Δ 、D p175Δ and drawing the data in a two-dimensional coordinate system to form a scatter diagram, and extracting a mean value point (shown in figure 10) of three membrane humidity fault values in the drawn scatter diagram to complete the establishment of the water-flooded fault characteristic space of the vehicle fuel cell.
In step 400, the steps: predicting the membrane humidity of the vehicle fuel cell in the current time period according to the first characteristic of the vehicle fuel cell in the current time period, the second characteristic of the vehicle fuel cell in the current time period and the membrane dry fault characteristic space of the vehicle fuel cell, which specifically comprises the following steps:
step 401: constructing a membrane humidity vector in the membrane dry fault characteristic space of the vehicle fuel cell; the film humidity vector is a vector of which the first coordinate points to the second coordinate; the first film humidity corresponding to the first coordinate is adjacent to the first film humidity corresponding to the second coordinate, and the first film humidity corresponding to the first coordinate is smaller than the first film humidity corresponding to the second coordinate.
Step 402: selecting a first target coordinate and a second target coordinate which are closest to the unknown point coordinate in the flooding fault feature space of the vehicle fuel cell; the unknown point coordinates are coordinates constructed by taking the first characteristic of the fuel cell for the vehicle in the current time period as an abscissa and taking the second characteristic of the fuel cell for the vehicle in the current time period as an ordinate.
Step 403: and comparing the first film humidity corresponding to the first target coordinate with the first film humidity corresponding to the second target coordinate, and determining the target coordinate corresponding to the smaller first film humidity as the starting point coordinate.
Step 404: constructing a target membrane humidity vector corresponding to the unknown point coordinate; and the target film humidity vector is a vector of the starting point coordinate pointing to the unknown point coordinate.
Step 405: predicting the membrane humidity of the vehicle fuel cell at the current time according to the membrane humidity vector corresponding to the initial point coordinate and the target membrane humidity vector corresponding to the unknown point coordinate; the film humidity vector corresponding to the starting point coordinate is a vector of which the starting point coordinate points to a third coordinate; and the first film humidity corresponding to the starting point coordinate is adjacent to the first film humidity corresponding to the third coordinate, and the first film humidity corresponding to the starting point coordinate is smaller than the first film humidity corresponding to the third coordinate.
Further, step 405 specifically includes:
according to equation (6):
Figure 51583DEST_PATH_IMAGE019
predicting the membrane humidity of the vehicle fuel cell in the current time period; wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE020
the first membrane humidity corresponding to the starting point coordinate is obtained;
Figure 124712DEST_PATH_IMAGE021
a first film humidity corresponding to the third coordinate;
Figure DEST_PATH_IMAGE022
the target membrane humidity vector corresponding to the unknown point coordinate is obtained;
Figure 279226DEST_PATH_IMAGE023
the membrane humidity vector corresponding to the starting point coordinate is obtained;
Figure DEST_PATH_IMAGE024
indicating a modulo.
Since the step 500 of predicting the membrane humidity of the vehicle fuel cell at the current time period according to the first characteristic of the vehicle fuel cell at the current time period, the second characteristic of the vehicle fuel cell at the current time period, and the water-logging fault feature space of the vehicle fuel cell is similar to the step 400 of predicting the membrane humidity of the vehicle fuel cell at the current time period according to the first characteristic of the vehicle fuel cell at the current time period, the second characteristic of the vehicle fuel cell at the current time period, and the dry membrane fault feature space of the vehicle fuel cell, redundant description is omitted here.
The following describes a process for predicting the membrane humidity of the vehicle fuel cell in the current time period by using a specific example.
One example is: since fuel cell membrane humidity is difficult to measure with sensors, this example indirectly quantifies fuel cell membrane humidity by constructing vectors and projections between vectors within the feature space.
Firstly, respectively constructing membrane humidity vectors in a membrane dry fault characteristic space and a membrane water-flooding fault characteristic space of the vehicle fuel cell; for the dry failure characteristic space of the membrane of the fuel cell for the vehicle, vectors are sequentially constructed, the relative membrane humidity is 25% point and 50% point of the relative membrane humidity, 50% point of the relative membrane humidity and 75% point of the relative membrane humidity, and the vector direction is the membrane humidity increasing direction (the relative membrane humidity is 25% point points to 50% point of the relative membrane humidity, 50% point of the relative membrane humidity points to 75% point of the relative membrane humidity, as shown in fig. 11); similarly, vectors are sequentially constructed for the flooding fault feature space of the vehicle fuel cell, wherein the relative membrane humidity is 125% point and the relative membrane humidity is 150% point, the relative membrane humidity is 150% point and the relative membrane humidity is 175% point, and the vector direction is the membrane humidity increasing direction (the relative membrane humidity is 125% point points point and the relative membrane humidity is 150% point and the relative membrane humidity is 175% point, as shown in fig. 12).
And secondly, making a film moisture quantification prediction strategy.
First, taking a certain fuel cell membrane dry failure as an example, as shown in fig. 13, in a vehicle fuel cell membrane dry failure feature space, using coordinates of unknown membrane humidity points and horizontal and vertical coordinates of three known membrane humidity points for constructing the vehicle fuel cell membrane dry failure feature space, euclidean distances between the coordinates of the unknown points and the coordinates of the three known points are calculated.
Figure 386990DEST_PATH_IMAGE025
Wherein the content of the first and second substances, (ii) (x 1 ，y 1 ) Is a known point coordinate, ((ii))x 2 ，y 2 ) Is an unknown point coordinate.
Then, two known point coordinates with the minimum Euclidean distance from the unknown point coordinates are screened out, and a vector is established with a point with relatively small membrane humidity in the two known points, wherein the vector direction is that the known point coordinates point to the unknown point (namely, the point with relatively small membrane humidity in the two known membrane humidity points with the minimum Euclidean distance from the unknown point of the membrane humidity points to the unknown point of the membrane humidity). As shown in fig. 13, the two known point coordinates with the smallest euclidean distance from the unknown point coordinate are a point with a relative film humidity of 25% and a point with a relative film humidity of 50%, respectively, construct a vector with a point with a relative film humidity of 25% and a point with a direction of 25% relative film humidity points to the unknown point, i.e., construct a vector
Figure 565162DEST_PATH_IMAGE022
The film humidity was then quantified according to the projected length:
Figure DEST_PATH_IMAGE026
（8）；
wherein the content of the first and second substances,
Figure 125587DEST_PATH_IMAGE023
the point corresponding to 25% relative membrane humidity corresponds to the membrane humidity vector.
Example two
In order to implement the method corresponding to the above embodiment to achieve the corresponding functions and technical effects, the following provides a membrane humidity prediction system for a vehicle fuel cell based on multi-source information fusion.
As shown in fig. 14, the present embodiment provides a system for predicting membrane humidity of a vehicle fuel cell based on multi-source information fusion, including:
the state information acquisition module 1 is used for acquiring the state information of the vehicle fuel cell at the current time period; the state information of the vehicle fuel cell at the current time period at least comprises output voltage, output current and actual voltage drop of an anode inlet and an anode outlet.
A first characteristic calculating module 2, configured to determine a first characteristic of the vehicle fuel cell in the current period according to the output voltage of the vehicle fuel cell in the current period; the first characteristic is an amplitude spectrum.
And the anode inlet and outlet theoretical voltage drop calculating module 3 is used for determining the anode inlet and outlet theoretical voltage drop of the vehicle fuel cell in the current time period according to the output current of the vehicle fuel cell in the current time period.
A membrane humidity prediction module 4 for:
when the theoretical pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period is smaller than the actual pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period, calculating a second characteristic of the vehicle fuel cell in the current time period, and predicting the membrane humidity of the vehicle fuel cell in the current time period according to the first characteristic of the vehicle fuel cell in the current time period, the second characteristic of the vehicle fuel cell in the current time period and the membrane dry failure characteristic space of the vehicle fuel cell; the second characteristic is a first absolute value; the first absolute value is the absolute value of the difference between the theoretical voltage drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period and the actual voltage drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period;
when the theoretical pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period is larger than the actual pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period, calculating the second characteristic of the vehicle fuel cell in the current time period, and predicting the membrane humidity of the vehicle fuel cell in the current time period according to the first characteristic of the vehicle fuel cell in the current time period, the second characteristic of the vehicle fuel cell in the current time period and the water flooding fault characteristic space of the vehicle fuel cell.
The membrane dry fault feature space of the vehicle fuel cell is a two-dimensional space constructed by the membrane dry fault feature and first membrane humidity; the first film humidity is a relative film humidity of less than 100%; the dry film failure characteristic is a first characteristic and a second characteristic corresponding to the first film humidity.
The water-logging fault feature space of the vehicle fuel cell is a two-dimensional space constructed by the water-logging fault feature and the humidity of the second membrane; the second film humidity is a relative film humidity greater than 100%; the water flooding fault characteristic is a first characteristic and a second characteristic corresponding to the humidity of the second membrane.
EXAMPLE III
The embodiment provides a vehicle fuel cell membrane humidity prediction method based on multi-source information fusion, which comprises the following steps:
step a: acquiring the state information of the vehicle fuel cell at the current time; the state information of the vehicle fuel cell at the current time period at least comprises output voltage, output current and actual voltage drop of an anode inlet and an anode outlet.
Step b: and predicting the state information of the vehicle fuel cell at the next time period according to the state information of the vehicle fuel cell at the current time period and a machine learning algorithm.
Step c: determining a first characteristic of the fuel cell for the vehicle in the next period according to the output voltage of the fuel cell for the vehicle in the next period; the first characteristic is an amplitude spectrum.
Step d: and determining the theoretical voltage drop of the anode inlet and the anode outlet of the fuel cell for the vehicle in the next period according to the output current of the fuel cell for the vehicle in the next period.
Step e: when the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the vehicle in the next period is smaller than the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the vehicle in the next period, calculating a second characteristic of the fuel cell for the vehicle in the next period, and predicting the membrane humidity of the fuel cell for the vehicle in the next period according to the first characteristic of the fuel cell for the vehicle in the next period, the second characteristic of the fuel cell for the vehicle in the next period and a membrane dry fault characteristic space of the fuel cell for the vehicle in the next period; the second characteristic is a first absolute value; the first absolute value is the absolute value of the difference value between the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time and the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time.
Step f: and when the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time is larger than the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time, calculating the second characteristic of the fuel cell for the next period of time, and predicting the membrane humidity of the fuel cell for the next period of time according to the first characteristic of the fuel cell for the next period of time, the second characteristic of the fuel cell for the next period of time and the flooding fault characteristic space of the fuel cell for the vehicle.
The membrane dry failure characteristic space of the vehicle fuel cell is a two-dimensional space constructed by the membrane dry failure characteristic and the first membrane humidity; the first film humidity is a relative film humidity of less than 100%; the dry film failure characteristic is a first characteristic and a second characteristic corresponding to the first film humidity.
The water-logging fault feature space of the vehicle fuel cell is a two-dimensional space constructed by the water-logging fault feature and the humidity of the second membrane; the second film humidity is a relative film humidity greater than 100%; the water flooding fault characteristic is a first characteristic and a second characteristic corresponding to the humidity of the second membrane.
As shown in fig. 15, the output voltage signal, the current signal, and the anode drop signal are collected for the fuel cell to be predicted and time-series prediction is performed using an autoregressive moving average model.
An autoregressive Moving Average Model, also known as the ARMA Model, is one of the time series analyses.
And respectively inputting the collected output voltage, output current, anode voltage drop signals and signals for time series prediction based on the three signals into the constructed characteristic space to finish the quantitative prediction of the membrane humidity. Not only can predict the membrane humidity state of the fuel cell at the moment, but also can give early warning to future membrane humidity faults, adjust and control the temperature, the air inlet humidity and the like of the fuel cell in time, maintain the membrane humidity of the fuel cell in a normal range, reduce the damage of the fuel cell and prolong the service life.
Example four
In order to implement the method corresponding to the above embodiment to achieve the corresponding functions and technical effects, the following provides a vehicle fuel cell membrane humidity prediction system based on multi-source information fusion.
The utility model provides a vehicular fuel cell membrane humidity prediction system based on multisource information fusion, includes:
the state information acquisition module is used for acquiring the state information of the vehicle fuel cell at the current time period; the state information of the vehicle fuel cell at the current time period at least comprises output voltage, output current and actual voltage drop of an anode inlet and an anode outlet.
And the state information prediction module is used for predicting the state information of the vehicle fuel cell at the next time period according to the state information of the vehicle fuel cell at the current time period and a machine learning algorithm.
The first characteristic calculating module is used for determining first characteristics of the fuel cell for the vehicle in the next period according to the output voltage of the fuel cell for the vehicle in the next period; the first feature is an amplitude spectrum.
And the anode inlet and outlet theoretical voltage drop calculation module is used for determining the anode inlet and outlet theoretical voltage drop of the fuel cell for the vehicle in the next period according to the output current of the fuel cell for the vehicle in the next period.
A membrane humidity prediction module to:
when the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time is smaller than the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time, calculating a second characteristic of the fuel cell for the next period of time, and predicting the membrane humidity of the fuel cell for the next period of time according to the first characteristic of the fuel cell for the next period of time, the second characteristic of the fuel cell for the next period of time and the membrane dry failure characteristic space of the fuel cell for the vehicle; the second characteristic is a first absolute value; the first absolute value is the absolute value of the difference between the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the vehicle in the next period and the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the vehicle in the next period;
and when the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time is larger than the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time, calculating the second characteristic of the fuel cell for the next period of time, and predicting the membrane humidity of the fuel cell for the next period of time according to the first characteristic of the fuel cell for the next period of time, the second characteristic of the fuel cell for the next period of time and the flooding fault characteristic space of the fuel cell for the vehicle.
The membrane dry failure characteristic space of the vehicle fuel cell is a two-dimensional space constructed by the membrane dry failure characteristic and the first membrane humidity; the first film humidity is a relative film humidity of less than 100%; the dry film failure characteristic is a first characteristic and a second characteristic corresponding to the first film humidity.
The water-logging fault feature space of the vehicle fuel cell is a two-dimensional space constructed by the water-logging fault feature and the humidity of the second membrane; the second film humidity is a relative film humidity greater than 100%; the water flooding fault characteristic is a first characteristic and a second characteristic corresponding to the humidity of the second membrane.
Compared with the prior art, the invention has the following technical effects:
firstly, an information fusion technology is adopted, and the stability and the accuracy of the humidity quantification prediction of the membrane of the vehicle fuel cell are improved by considering the electric quantity of the output voltage of the vehicle fuel cell and the non-electric quantity of the anode voltage drop, which can represent the membrane humidity.
And secondly, a membrane humidity value which cannot be directly measured by using a sensor is obtained by formulating a vehicle fuel cell membrane humidity quantification prediction strategy, so that the safe operation of the vehicle fuel cell is guaranteed, and effective support is provided for controlling the membrane humidity of the vehicle fuel cell to be in a normal interval.
Thirdly, online quantitative prediction of the membrane humidity of the fuel cell for the vehicle can be realized, and the prediction cost is low and the efficiency is high. The humidity control method can predict based on the acquired time sequence data, can early warn the humidity change rule of the membrane of the vehicle fuel cell, can act in advance, and can regulate relevant parameters according to the membrane humidity value quantization so as to quickly and efficiently control the membrane humidity within an ideal range, control the membrane humidity of the vehicle fuel cell within a non-irreversible damage range, and prolong the service life of the vehicle fuel cell.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.

Claims (10)

1. A vehicle fuel cell membrane humidity prediction method based on multi-source information fusion is characterized by comprising the following steps:
acquiring the state information of the vehicle fuel cell at the current time period; the state information of the vehicle fuel cell at the current time period at least comprises output voltage, output current and actual voltage drop of an anode inlet and an anode outlet;
determining a first characteristic of the vehicle fuel cell in the current time period according to the output voltage of the vehicle fuel cell in the current time period; the first characteristic is an amplitude spectrum;
determining the theoretical voltage drop of the anode inlet and the anode outlet of the vehicle fuel cell at the current time according to the output current of the vehicle fuel cell at the current time;
when the theoretical pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period is smaller than the actual pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period, calculating a second characteristic of the vehicle fuel cell in the current time period, and predicting the membrane humidity of the vehicle fuel cell in the current time period according to the first characteristic of the vehicle fuel cell in the current time period, the second characteristic of the vehicle fuel cell in the current time period and the membrane dry failure characteristic space of the vehicle fuel cell; the second characteristic is a first absolute value; the first absolute value is the absolute value of the difference value between the theoretical voltage drop of the anode inlet and the outlet of the vehicle fuel cell in the current time period and the actual voltage drop of the anode inlet and the outlet of the vehicle fuel cell in the current time period;
when the theoretical pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period is larger than the actual pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period, calculating a second characteristic of the vehicle fuel cell in the current time period, and predicting the membrane humidity of the vehicle fuel cell in the current time period according to the first characteristic of the vehicle fuel cell in the current time period, the second characteristic of the vehicle fuel cell in the current time period and the water-logging fault characteristic space of the vehicle fuel cell;
the membrane dry failure characteristic space of the vehicle fuel cell is a two-dimensional space constructed by the membrane dry failure characteristic and the first membrane humidity; the first film humidity is a relative film humidity of less than 100%; the dry film fault characteristic is a first characteristic and a second characteristic corresponding to the first film humidity;
the water-logging fault feature space of the vehicle fuel cell is a two-dimensional space constructed by the water-logging fault feature and the humidity of the second membrane; the second film humidity is a relative film humidity greater than 100%; the water flooding fault characteristic is a first characteristic and a second characteristic corresponding to the humidity of the second membrane.
2. The method for predicting membrane humidity of the vehicle fuel cell based on multi-source information fusion according to claim 1, wherein the determining a first characteristic of the vehicle fuel cell at the current time according to the output voltage of the vehicle fuel cell at the current time specifically comprises:
acquiring the output voltage of the vehicle fuel cell during normal operation;
calculating a second absolute value; the second absolute value is an absolute value of a difference between the output voltage of the vehicle fuel cell in the current period and the output voltage of the vehicle fuel cell in the normal operation;
determining an absolute value of an acceleration section according to the second absolute value; the absolute value of the acceleration section is a second absolute value under the working condition of the acceleration section;
calculating a second derivative of the absolute value of the acceleration section, and performing Fourier transform on the second derivative of the absolute value of the acceleration section to obtain a frequency domain signal;
and extracting the amplitude spectrum of the vehicle fuel cell in the current time period according to the frequency domain signal.
3. The method for predicting the membrane humidity of the vehicle fuel cell based on the multi-source information fusion of the claim 1, wherein the state information of the vehicle fuel cell at the current time period further comprises working condition information; the working condition information comprises the width of the cathode water flow channel, the depth of the cathode water flow channel, the length of the cathode water flow channel, the number of the cathode water flow channels, the hydrogen pressure at the anode inlet, the hydrogen saturation pressure at the anode inlet, the hydrogen stoichiometric number and the operating temperature of the fuel cell; the determining the theoretical voltage drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current period according to the output current of the vehicle fuel cell in the current period specifically includes:
and calculating the theoretical voltage drop of the anode inlet and the anode outlet of the vehicle fuel cell at the current time according to the output current and the working condition information of the vehicle fuel cell at the current time.
4. The method for predicting membrane humidity of the vehicular fuel cell based on multi-source information fusion according to claim 1, further comprising: constructing a membrane dry fault characteristic space and a water flooding fault characteristic space of the vehicle fuel cell;
the method for constructing the membrane dry fault characteristic space of the vehicle fuel cell and the water-logging fault characteristic space of the vehicle fuel cell specifically comprises the following steps:
acquiring state information of the vehicle fuel cell in a history stage; the state information of the vehicle fuel cell in the historical stage comprises working condition information, output voltage and output current corresponding to different membrane humidities and actual voltage drop of an anode inlet and an anode outlet;
determining first characteristics corresponding to different membrane humidities according to the output voltage of the vehicle fuel cell in the historical stage;
according to the output current and working condition information of the vehicle fuel cell in the history stage, determining the theoretical pressure drop of the anode inlet and the anode outlet corresponding to different membrane humidities;
determining second characteristics corresponding to different membrane humidities according to the theoretical pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell and the actual pressure drop of the anode inlet and the anode outlet in the historical stage;
determining first sample data and second sample data; the first sample data is a first characteristic and a second characteristic corresponding to different first film humidities; the second sample data is a first characteristic and a second characteristic corresponding to different second membrane humidities;
constructing a membrane dry fault feature space of the vehicle fuel cell according to the first sample data;
and constructing a water logging fault feature space of the vehicle fuel cell according to the second sample data.
5. The method for predicting the humidity of the membrane of the fuel cell for the vehicle based on the multi-source information fusion according to claim 4, wherein the constructing a membrane dry failure feature space of the fuel cell for the vehicle according to the first sample data specifically comprises:
expressing the first characteristics and the second characteristics corresponding to different first film humidities in a coordinate mode to obtain different first film humidity coordinates; the abscissa of the first film humidity coordinate is a first characteristic; the ordinate of the first film humidity coordinate is a second characteristic;
carrying out averaging operation on a plurality of first membrane humidity coordinates corresponding to the same first membrane humidity to obtain average value coordinates corresponding to different first membrane humidities; wherein one of said first membrane humidities corresponds to one mean coordinate;
drawing different mean value coordinates in a two-dimensional coordinate system to obtain a membrane stem fault characteristic space of the vehicle fuel cell; and in the direction of increasing the X-axis coordinate value of the membrane dry failure characteristic space of the vehicle fuel cell, the humidity of the first membrane corresponding to the mean value coordinate is increased progressively.
6. The method for predicting membrane humidity of the vehicular fuel cell based on multi-source information fusion according to claim 1, wherein the predicting the membrane humidity of the vehicular fuel cell at the current time according to the first characteristic of the vehicular fuel cell at the current time, the second characteristic of the vehicular fuel cell at the current time and the membrane dry failure feature space of the vehicular fuel cell at the current time specifically comprises:
constructing a membrane humidity vector in the membrane dry fault characteristic space of the vehicle fuel cell; the film humidity vector is a vector of which the first coordinate points to the second coordinate; the first film humidity corresponding to the first coordinate is adjacent to the first film humidity corresponding to the second coordinate, and the first film humidity corresponding to the first coordinate is smaller than the first film humidity corresponding to the second coordinate;
selecting a first target coordinate and a second target coordinate which are closest to the unknown point coordinate in the flooding fault feature space of the vehicle fuel cell; the unknown point coordinates are coordinates constructed by taking the first characteristic of the vehicle fuel cell at the current time as an abscissa and taking the second characteristic of the vehicle fuel cell at the current time as an ordinate;
comparing the first film humidity corresponding to the first target coordinate with the first film humidity corresponding to the second target coordinate, and determining the target coordinate corresponding to the smaller first film humidity as a starting point coordinate;
constructing a target membrane humidity vector corresponding to the unknown point coordinate; the target film humidity vector is a vector of the starting point coordinate pointing to an unknown point coordinate;
predicting the membrane humidity of the vehicle fuel cell at the current time period according to the membrane humidity vector corresponding to the starting point coordinate and the target membrane humidity vector corresponding to the unknown point coordinate; the film humidity vector corresponding to the starting point coordinate is a vector of which the starting point coordinate points to a third coordinate; and the first film humidity corresponding to the starting point coordinate is adjacent to the first film humidity corresponding to the third coordinate, and the first film humidity corresponding to the starting point coordinate is smaller than the first film humidity corresponding to the third coordinate.
7. The method for predicting the membrane humidity of the automotive fuel cell based on the multi-source information fusion according to claim 6, wherein the predicting the membrane humidity of the automotive fuel cell at the current time period according to the membrane humidity vector corresponding to the starting point coordinate and the target membrane humidity vector corresponding to the unknown point coordinate specifically comprises:
according to the formula:
Figure 91488DEST_PATH_IMAGE001
predicting the membrane humidity of the vehicle fuel cell in the current time period;
wherein the content of the first and second substances,
Figure 680732DEST_PATH_IMAGE002
the first membrane humidity corresponding to the starting point coordinate is obtained;
Figure 866994DEST_PATH_IMAGE003
the first film humidity corresponding to the third coordinate;
Figure 199887DEST_PATH_IMAGE004
the target membrane humidity vector corresponding to the unknown point coordinate is obtained;
Figure 214591DEST_PATH_IMAGE005
the film humidity vector corresponding to the starting point coordinate is obtained;
Figure 709158DEST_PATH_IMAGE006
indicating a modulo.
8. A vehicular fuel cell membrane humidity prediction system based on multi-source information fusion is characterized by comprising:
the state information acquisition module is used for acquiring the state information of the vehicle fuel cell at the current time period; the state information of the vehicle fuel cell at the current time period at least comprises output voltage, output current and actual voltage drop of an anode inlet and an anode outlet;
the first characteristic calculation module is used for determining a first characteristic of the vehicle fuel cell in the current time period according to the output voltage of the vehicle fuel cell in the current time period; the first characteristic is an amplitude spectrum;
the anode inlet and outlet theoretical voltage drop calculation module is used for determining the anode inlet and outlet theoretical voltage drop of the vehicle fuel cell in the current time period according to the output current of the vehicle fuel cell in the current time period;
a membrane humidity prediction module to:
when the theoretical pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period is smaller than the actual pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period, calculating a second characteristic of the vehicle fuel cell in the current time period, and predicting the membrane humidity of the vehicle fuel cell in the current time period according to the first characteristic of the vehicle fuel cell in the current time period, the second characteristic of the vehicle fuel cell in the current time period and a membrane dry fault characteristic space of the vehicle fuel cell; the second characteristic is a first absolute value; the first absolute value is the absolute value of the difference value between the theoretical voltage drop of the anode inlet and the outlet of the vehicle fuel cell in the current time period and the actual voltage drop of the anode inlet and the outlet of the vehicle fuel cell in the current time period;
when the theoretical pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period is larger than the actual pressure drop of the anode inlet and the anode outlet of the vehicle fuel cell in the current time period, calculating a second characteristic of the vehicle fuel cell in the current time period, and predicting the membrane humidity of the vehicle fuel cell in the current time period according to the first characteristic of the vehicle fuel cell in the current time period, the second characteristic of the vehicle fuel cell in the current time period and a water flooding fault characteristic space of the vehicle fuel cell;
the membrane dry failure characteristic space of the vehicle fuel cell is a two-dimensional space constructed by the membrane dry failure characteristic and the first membrane humidity; the first film humidity is a relative film humidity of less than 100%; the dry film fault characteristic is a first characteristic and a second characteristic corresponding to the first film humidity;
the water-logging fault feature space of the vehicle fuel cell is a two-dimensional space constructed by the water-logging fault feature and the humidity of the second membrane; the second film humidity is a relative film humidity greater than 100%; the water flooding fault characteristic is a first characteristic and a second characteristic corresponding to the humidity of the second membrane.
9. A vehicle fuel cell membrane humidity prediction method based on multi-source information fusion is characterized by comprising the following steps:
acquiring the state information of the vehicle fuel cell at the current time period; the state information of the vehicle fuel cell at the current time period at least comprises output voltage, output current and actual voltage drop of an anode inlet and an anode outlet;
predicting the state information of the vehicle fuel cell at the next time period according to the state information of the vehicle fuel cell at the current time period and a machine learning algorithm;
determining a first characteristic of the fuel cell for the vehicle in the next period according to the output voltage of the fuel cell for the vehicle in the next period; the first characteristic is an amplitude spectrum;
determining the theoretical voltage drop of the anode inlet and the anode outlet of the fuel cell for the vehicle at the next period according to the output current of the fuel cell for the vehicle at the next period;
when the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time is smaller than the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time, calculating a second characteristic of the fuel cell for the next period of time, and predicting the membrane humidity of the fuel cell for the next period of time according to the first characteristic of the fuel cell for the next period of time, the second characteristic of the fuel cell for the next period of time and the membrane dry failure characteristic space of the fuel cell for the vehicle; the second characteristic is a first absolute value; the first absolute value is the absolute value of the difference value between the theoretical pressure drop of the anode inlet and the outlet of the fuel cell for the vehicle in the next period and the actual pressure drop of the anode inlet and the outlet of the fuel cell for the vehicle in the next period;
when the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time is larger than the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time, calculating a second characteristic of the fuel cell for the next period of time, and predicting the membrane humidity of the fuel cell for the next period of time according to the first characteristic of the fuel cell for the next period of time, the second characteristic of the fuel cell for the next period of time and the flooding fault characteristic space of the fuel cell for the vehicle;
the membrane dry failure characteristic space of the vehicle fuel cell is a two-dimensional space constructed by the membrane dry failure characteristic and the first membrane humidity; the first film humidity is a relative film humidity of less than 100%; the dry film fault characteristic is a first characteristic and a second characteristic corresponding to the first film humidity;
the water-logging fault feature space of the vehicle fuel cell is a two-dimensional space constructed by the water-logging fault feature and the humidity of the second membrane; the second film humidity is a relative film humidity greater than 100%; the water flooding fault characteristic is a first characteristic and a second characteristic corresponding to the humidity of the second membrane.
10. A vehicular fuel cell membrane humidity prediction system based on multi-source information fusion is characterized by comprising:
the state information acquisition module is used for acquiring the state information of the vehicle fuel cell at the current time period; the state information of the vehicle fuel cell at the current time period at least comprises output voltage, output current and actual voltage drop of an anode inlet and an anode outlet;
the state information prediction module is used for predicting the state information of the vehicle fuel cell at the next time period according to the state information of the vehicle fuel cell at the current time period and a machine learning algorithm;
a first characteristic calculation module for determining a first characteristic of the fuel cell for the vehicle at the next period based on an output voltage of the fuel cell for the vehicle at the next period; the first characteristic is an amplitude spectrum;
the anode inlet and outlet theoretical voltage drop calculation module is used for determining the anode inlet and outlet theoretical voltage drop of the fuel cell for the vehicle in the next period according to the output current of the fuel cell for the vehicle in the next period;
a membrane humidity prediction module to:
when the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the vehicle in the next period is smaller than the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the vehicle in the next period, calculating a second characteristic of the fuel cell for the vehicle in the next period, and predicting the membrane humidity of the fuel cell for the vehicle in the next period according to the first characteristic of the fuel cell for the vehicle in the next period, the second characteristic of the fuel cell for the vehicle in the next period and a membrane dry fault characteristic space of the fuel cell for the vehicle in the next period; the second characteristic is a first absolute value; the first absolute value is the absolute value of the difference value between the theoretical pressure drop of the anode inlet and the outlet of the fuel cell for the vehicle in the next period and the actual pressure drop of the anode inlet and the outlet of the fuel cell for the vehicle in the next period;
when the theoretical pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time is larger than the actual pressure drop of the anode inlet and the anode outlet of the fuel cell for the next period of time, calculating a second characteristic of the fuel cell for the next period of time, and predicting the membrane humidity of the fuel cell for the next period of time according to the first characteristic of the fuel cell for the next period of time, the second characteristic of the fuel cell for the next period of time and the flooding fault characteristic space of the fuel cell for the vehicle;
the membrane dry failure characteristic space of the vehicle fuel cell is a two-dimensional space constructed by the membrane dry failure characteristic and the first membrane humidity; the first film humidity is a relative film humidity of less than 100%; the dry film fault characteristic is a first characteristic and a second characteristic corresponding to the first film humidity;
the water-logging fault feature space of the vehicle fuel cell is a two-dimensional space constructed by the water-logging fault feature and the humidity of the second membrane; the second film humidity is a relative film humidity above 100%; the water flooding fault characteristic is a first characteristic and a second characteristic corresponding to the humidity of the second membrane.
CN202211263752.8A 2022-10-17 2022-10-17 Vehicle fuel cell membrane humidity prediction method and system based on multi-source information fusion Active CN115320387B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211263752.8A CN115320387B (en) 2022-10-17 2022-10-17 Vehicle fuel cell membrane humidity prediction method and system based on multi-source information fusion

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211263752.8A CN115320387B (en) 2022-10-17 2022-10-17 Vehicle fuel cell membrane humidity prediction method and system based on multi-source information fusion

Publications (2)

Publication Number Publication Date
CN115320387A true CN115320387A (en) 2022-11-11
CN115320387B CN115320387B (en) 2022-12-13

Family

ID=83913207

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211263752.8A Active CN115320387B (en) 2022-10-17 2022-10-17 Vehicle fuel cell membrane humidity prediction method and system based on multi-source information fusion

Country Status (1)

Country Link
CN (1) CN115320387B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115494401A (en) * 2022-11-14 2022-12-20 湖北工业大学 Power battery cloud end data cleaning method based on information fusion
CN115632141A (en) * 2022-12-22 2023-01-20 潍柴动力股份有限公司 Vehicle-mounted fuel cell stack self-humidification control method and vehicle

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170012305A1 (en) * 2014-01-30 2017-01-12 Nissan Motor Co., Ltd. Fuel cell system
CN106848351A (en) * 2016-12-26 2017-06-13 天津大学 The method that proton exchange film fuel battery performance forecast model is set up
CN108321415A (en) * 2018-02-05 2018-07-24 吉林大学 Fuel cell condition monitoring and early warning system and the method for convergence communication information
KR20200011003A (en) * 2018-07-23 2020-01-31 도요타 지도샤（주） Fuel cell system and liquid water amount estimating method
CN114843560A (en) * 2022-05-19 2022-08-02 上海捷氢科技股份有限公司 Method and device for diagnosing water flooding fault of fuel cell system
CN114976128A (en) * 2021-12-03 2022-08-30 华北水利水电大学 PEMFC fault prediction and health management system and method based on five-dimensional digital twin technology

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170012305A1 (en) * 2014-01-30 2017-01-12 Nissan Motor Co., Ltd. Fuel cell system
CN106848351A (en) * 2016-12-26 2017-06-13 天津大学 The method that proton exchange film fuel battery performance forecast model is set up
CN108321415A (en) * 2018-02-05 2018-07-24 吉林大学 Fuel cell condition monitoring and early warning system and the method for convergence communication information
KR20200011003A (en) * 2018-07-23 2020-01-31 도요타 지도샤（주） Fuel cell system and liquid water amount estimating method
CN114976128A (en) * 2021-12-03 2022-08-30 华北水利水电大学 PEMFC fault prediction and health management system and method based on five-dimensional digital twin technology
CN114843560A (en) * 2022-05-19 2022-08-02 上海捷氢科技股份有限公司 Method and device for diagnosing water flooding fault of fuel cell system

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115494401A (en) * 2022-11-14 2022-12-20 湖北工业大学 Power battery cloud end data cleaning method based on information fusion
CN115494401B (en) * 2022-11-14 2023-03-10 湖北工业大学 Power electricity Chi Yun end data cleaning method based on information fusion
CN115632141A (en) * 2022-12-22 2023-01-20 潍柴动力股份有限公司 Vehicle-mounted fuel cell stack self-humidification control method and vehicle
CN115632141B (en) * 2022-12-22 2023-05-23 潍柴动力股份有限公司 Self-humidification control method for vehicle-mounted fuel cell stack and vehicle

Also Published As

Publication number Publication date
CN115320387B (en) 2022-12-13

Similar Documents

Publication Publication Date Title
CN115320387B (en) Vehicle fuel cell membrane humidity prediction method and system based on multi-source information fusion
CN109524693B (en) Model predictive control method for fuel cell air supply system
Hissel et al. Diagnostic & health management of fuel cell systems: Issues and solutions
KR101592704B1 (en) Method for diagnosing state of fuel cell stack and controlling fuel cell system
CN108352548B (en) Fuel cell system and control method thereof
CN111261903B (en) Model-based proton exchange membrane fuel cell impedance online estimation method
CN108957335B (en) SOC online estimation method of 2kW/10 kW.h all-vanadium redox flow battery
CN111310306B (en) Online observation method for nitrogen concentration of anode of proton exchange membrane fuel cell
CN112563542B (en) Fuel cell online detection method and detection system
CN112415413B (en) Diagnosis method and diagnosis system of fuel cell
CN110112442B (en) Fuel cell system control method and device
Li et al. Application of distribution of relaxation times method in polymer electrolyte membrane water electrolyzer
CN109542157B (en) Direct calculation and tracking method for maximum power point of fuel cell
KR101315764B1 (en) Method for detecting fail of hydrogen supply system for fuel cell
Li et al. Quantitative diagnosis of PEMFC membrane humidity with a vector-distance based characteristic mapping approach
CN113299951B (en) Method for observing cathode pressure and flow of proton exchange membrane fuel cell
US8722264B2 (en) Algorithm for stack current controller based on polarization curve estimation of a fuel cell stack
CN112213370B (en) Method and device for detecting stoichiometric sensitivity of hydrogen fuel cell stack
Jacome et al. A review of model-based prognostic for proton exchange membrane fuel cell under automotive load cycling
Nitsche et al. Onboard diagnostics concept for fuel cell vehicles using adaptive modelling
Yuan et al. Fault Diagnosis of Fuel Cells by a Hybrid Deep Learning Network Fusing Characteristic Impedance
Kahia et al. Neural network based diagnostic of PEM fuel cell
CN114583221B (en) Method for measuring and calculating attenuation life of galvanic pile
CN113161586A (en) Operation control method and system for fuel cell system
Ma et al. Development of Online Fault Diagnosis Method for PEM Fuel Cell Based on Impedance at Optimal Frequency

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant