A method and apparatus for predicting the lifetime of a fuel cell

Abstract

The application provides a fuel cell life prediction method and device, when mechanical attenuation of a proton exchange membrane of a fuel cell is identified, key parameters of the fuel cell are obtained; the key parameters and each preset time are input into a pre-constructed mechanical attenuation model, the mechanical attenuation model responds to and performs corresponding prediction processing based on each preset time and the key parameters, and outputs a predicted leakage amount corresponding to each preset time; the predicted leakage amount corresponding to each preset time is compared with a preset failure value respectively, and a time when the predicted leakage amount is not less than the failure value is determined as a failure time; and a remaining service life of the fuel cell from a current time to the failure time is determined. In the scheme, the pre-constructed mechanical attenuation model performs prediction processing based on the key parameters of the current fuel cell, the gas leakage amount under the action of the mechanical attenuation mode is predicted, and the purpose of predicting the remaining service life of the fuel cell according to the gas leakage amount is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fuel cells, in particular to a method and device for predicting the service life of a fuel cell. BACKGROUND

[0002] In long-term operation of vehicle working conditions, the failure of the proton exchange membrane of the fuel cell is usually caused by mechanical degradation, chemical degradation and short circuit. In order to improve the performance of the fuel cell, the proton exchange membrane is required to resist mechanical degradation caused by long-term operation under complex working conditions to avoid the formation of electronic conduction and gas inter-channeling.

[0003] In the prior art, the gas channeling amount of the proton exchange membrane of the fuel cell is often obtained by testing or monitoring the hydrogen permeation current under fixed working conditions or the change of open circuit voltage. However, the gas channeling amount identified by this method is the superposition of the mechanical, chemical and short circuit degradation modes, which cannot identify whether mechanical degradation occurs, cannot distinguish the gas channeling amount under the action of the mechanical degradation mode, and cannot predict the remaining service life of the battery through the gas channeling amount under the action of the mechanical degradation mode.

[0004] Therefore, how to obtain the gas channeling amount under the action of the mechanical degradation mode and predict the remaining service life of the fuel cell according to the gas channeling amount is a problem that needs to be solved urgently. SUMMARY

[0005] Therefore, the embodiments of the present application provide a method and device for predicting the service life of a fuel cell to achieve the purpose of predicting the gas channeling amount under the action of the mechanical degradation mode and predicting the remaining service life of the fuel cell according to the gas channeling amount.

[0006] To achieve the above purpose, the embodiments of the present application provide the following technical solutions:

[0007] The first aspect of the embodiments of the present application discloses a method for predicting the service life of a fuel cell, comprising:

[0008] When it is identified that the proton exchange membrane of the fuel cell has mechanical degradation, the key parameters of the fuel cell are obtained; the key parameters include: current operating parameters, current state parameters, material characteristic parameters of the proton exchange membrane and structure characteristic parameters of the proton exchange membrane;

[0009] The key parameters and each preset time are input into a pre-constructed mechanical degradation model, the mechanical degradation model respectively responds to and is based on each preset time and the key parameters to perform corresponding prediction processing, and outputs the predicted channeling amount corresponding to each preset time;

[0010] The predicted channeling amount corresponding to each preset time is compared with a preset failure value respectively, and the time when the predicted channeling amount is not less than the failure value is determined as the failure time.

[0011] determining a remaining service life of the fuel cell from the current time to the failure time.

[0012] Preferably, the process of identifying whether the proton exchange membrane of the fuel cell has mechanical degradation comprises:

[0013] supplying hydrogen and inert gas to the anode of the fuel cell and supplying oxygen and the inert gas to the cathode of the fuel cell;

[0014] under the condition that the hydrogen partial pressure at the anode and the oxygen partial pressure at the cathode remain unchanged, changing the total gas pressure at the anode and the cathode by adjusting the flow rate and back pressure of the inert gas, so that different total gas pressure differences between the anode and the cathode are generated;

[0015] under the action of the different total gas pressure differences, respectively measuring and recording the corresponding open-circuit voltage of the fuel cell, and obtaining a change relationship of the open-circuit voltage with the total gas pressure difference;

[0016] when the change relationship meets the characteristics of mechanical degradation, it is determined that the proton exchange membrane of the fuel cell has mechanical degradation.

[0017] Preferably, the process of pre-constructing the mechanical degradation model comprises:

[0018] constructing a mechanical degradation model containing unknown parameter terms; the unknown parameter terms at least include: initial hydrogen permeation current density, standard working condition constant and sensitive working condition constant;

[0019] inputting the pre-obtained experimental data into the mechanical degradation model, the experimental data at least including: hydrogen permeation current and open-circuit voltage obtained by testing the hydrogen permeation current test condition and the open-circuit voltage test condition when the fuel cell is placed in the pre-set accelerated durability working condition or the conventional durability working condition;

[0020] based on the experimental data, calibrating the unknown parameter terms at the current time to obtain the unknown parameter terms corresponding to the current time;

[0021] verifying whether the accuracy of the mechanical degradation model meets the requirements;

[0022] if not, continue to input the experimental data into the mechanical degradation model, and calibrate the unknown parameter terms corresponding to the current time until the mechanical degradation model with the accuracy meeting the requirements is obtained;

[0023] if yes, it is determined that the mechanical degradation model training is completed.

[0024] Preferably, the verifying whether the accuracy of the mechanical degradation model meets the requirement comprises:

[0025] obtaining a key parameter at any historical moment from historical data of the fuel cell; the key parameter at any historical moment comprises: an operating parameter, a state parameter, a material characteristic parameter of the proton exchange membrane and a structural characteristic parameter of the proton exchange membrane;

[0026] inputting the key parameter and the historical moment into the mechanical degradation model, and performing simulation prediction processing by the mechanical degradation model in response to and based on the historical moment and the key parameter to obtain a simulation crossover leakage amount corresponding to the historical moment;

[0027] calculating a difference between the simulation crossover leakage amount and an actual crossover leakage amount at the historical moment; the actual crossover leakage amount at the historical moment is obtained from the historical data;

[0028] when the difference is less than or equal to a preset value, determining that the accuracy of the mechanical degradation model meets the requirement.

[0029] Preferably, the comparing the predicted crossover leakage amount corresponding to each preset moment with a preset failure value respectively to determine that a moment at which the predicted crossover leakage amount is not less than the failure value is a failure moment comprises:

[0030] comparing the predicted crossover leakage amount corresponding to each preset moment with the preset failure value respectively and sequentially according to the chronological order of the moments;

[0031] when the predicted crossover leakage amount is greater than or equal to the preset failure value, determining that the moment corresponding to the predicted crossover leakage amount is the failure moment of the fuel cell.

[0032] The second aspect of the embodiment of the present application discloses a device for predicting the service life of a fuel cell, comprising:

[0033] an obtaining unit configured to obtain key parameters of the fuel cell when mechanical degradation of a proton exchange membrane of the fuel cell is identified; the key parameters comprise: a current operating parameter, a current state parameter, a material characteristic parameter of the proton exchange membrane and a structural characteristic parameter of the proton exchange membrane;

[0034] a predicting unit configured to input the key parameters and each preset moment into a pre-constructed mechanical degradation model, and perform corresponding prediction processing by the mechanical degradation model in response to and based on each preset moment and the key parameters to output a predicted crossover leakage amount corresponding to each preset moment;

[0035] a comparing unit configured to compare the predicted crossover leakage amount corresponding to each preset moment with a preset failure value respectively to determine that a moment at which the predicted crossover leakage amount is not less than the failure value is a failure moment.

[0036] determining unit, configured to determine a remaining service life of the fuel cell from the current time to the failure time.

[0037] Preferably, the obtaining unit is specifically configured to:

[0038] hydrogen and inert gas are mixed to supply to an anode of the fuel cell, and oxygen and the inert gas are mixed to supply to a cathode of the fuel cell; under the condition that hydrogen partial pressure at the anode and oxygen partial pressure at the cathode are constant, by adjusting the inert gas flow and back pressure, the total gas pressure at the anode and the cathode is changed, so that different total gas pressure differences between the anode and the cathode are generated; under the action of each different total gas pressure difference, the corresponding open-circuit voltage of the fuel cell is measured and recorded respectively, and a change relationship of the open-circuit voltage with the total gas pressure difference is obtained; when the change relationship meets a characteristic of mechanical attenuation, it is determined that the proton exchange membrane of the fuel cell has mechanical attenuation; key parameters of the fuel cell are obtained; the key parameters include: current operating parameters, current state parameters, material characteristic parameters of the proton exchange membrane, and structure characteristic parameters of the proton exchange membrane.

[0039] Preferably, the device further comprises:

[0040] a constructing unit, configured to construct a mechanical attenuation model containing unknown parameter items; the unknown parameter items at least include: an initial hydrogen permeation current density, a standard working condition constant, and a sensitive working condition constant; pre-obtained experimental data are input into the mechanical attenuation model, the experimental data at least include: hydrogen permeation current and open-circuit voltage obtained by testing hydrogen permeation current test working conditions and open-circuit voltage test working conditions when the fuel cell is placed in a pre-set accelerated endurance working condition or a conventional endurance working condition; based on the experimental data, the unknown parameter items are calibrated at the current time to obtain unknown parameter items corresponding to the current time; if not, the experimental data are continuously input into the mechanical attenuation model to calibrate the unknown parameter items corresponding to the current time, until a mechanical attenuation model with required precision is obtained; if yes, it is determined that the mechanical attenuation model training is completed.

[0041] a verifying unit, configured to verify whether the precision of the mechanical attenuation model reaches the requirement.

[0042] Preferably, the verifying unit is specifically configured to:

[0043] acquire a key parameter at any historical moment from historical data of the fuel cell; the key parameter includes: an operating parameter, a state parameter, a material characteristic parameter of the proton exchange membrane, and a structural characteristic parameter of the proton exchange membrane; input the key parameter and the historical moment to the mechanical attenuation model, the mechanical attenuation model responds and performs simulation prediction processing based on the historical moment and the key parameter, to obtain a simulation crossover leakage amount corresponding to the historical moment; calculate a difference between the simulation crossover leakage amount and an actual crossover leakage amount at the historical moment; the actual crossover leakage amount at the historical moment is obtained from the historical data; when the difference is less than or equal to a preset value, determine that the accuracy of the mechanical attenuation model meets the requirement.

[0044] Preferably, the comparison unit is specifically used for:

[0045] compare the predicted crossover leakage amount corresponding to each preset moment with a preset failure value in sequence according to the chronological order of the moments; when the predicted crossover leakage amount is greater than or equal to the preset failure value, determine that the moment corresponding to the predicted crossover leakage amount is the failure moment of the fuel cell.

[0046] Based on the above-mentioned fuel cell life prediction method and device provided by the embodiments of the present application, when mechanical attenuation of the proton exchange membrane of the fuel cell is identified, key parameters of the fuel cell are acquired; the key parameters include: current operating parameters, current state parameters, material characteristic parameters of the proton exchange membrane, and structural characteristic parameters of the proton exchange membrane; the key parameters and each preset moment are input to a pre-constructed mechanical attenuation model, the mechanical attenuation model respectively responds and performs corresponding prediction processing based on each preset moment and the key parameters, and outputs a predicted crossover leakage amount corresponding to each preset moment; the predicted crossover leakage amount corresponding to each preset moment is compared with a preset failure value respectively, and a moment at which the predicted crossover leakage amount is not less than the failure value is determined as a failure moment; and the current moment to the failure moment is determined as the remaining service life of the fuel cell. In this scheme, the pre-constructed mechanical attenuation model is used to perform prediction processing based on the key parameters of the current fuel cell, to predict the gas crossover leakage amount under the action of the mechanical attenuation mode, and to predict the remaining service life of the fuel cell according to the gas crossover leakage amount. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on the provided drawings.

[0048] Figure 1 A flow chart of a method for predicting the remaining service life of a fuel cell according to an embodiment of the present application is disclosed;

[0049] Figure 2 A flow chart of verifying whether the precision of a mechanical attenuation model meets the requirement according to an embodiment of the present application is disclosed;

[0050] Figure 3 A simulation curve of the hydrogen permeation current caused by mechanical attenuation at different temperatures according to an embodiment of the present application is disclosed;

[0051] Figure 4 A simulation curve of the hydrogen permeation current caused by mechanical attenuation at different pressure fluctuation degrees according to an embodiment of the present application is disclosed;

[0052] Figure 5 A simulation curve of the hydrogen permeation current caused by mechanical attenuation at different humidity fluctuation degrees according to an embodiment of the present application is disclosed;

[0053] Figure 6 A simulation curve of the hydrogen permeation current caused by mechanical attenuation at different membrane reinforcement layer thicknesses according to an embodiment of the present application is disclosed;

[0054] Figure 7 A structure diagram of a device for predicting the service life of a fuel cell according to an embodiment of the present application is disclosed. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present application.

[0056] In the present application, the terms “comprising”, “containing” or any other variants thereof are intended to cover the non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement “including a…” does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0057] As known from the background, the gas channeling amount under the action of the mechanical attenuation mode cannot be predicted in the prior art, and the remaining service life of the fuel cell cannot be predicted according to the gas channeling amount.

[0058] Therefore, the embodiment of the present application discloses a kind of fuel cell life prediction method and device, when identifying that the proton exchange membrane of fuel cell occurs mechanical attenuation, the current key parameter of the fuel cell is acquired, and the mechanical attenuation model is constructed in advance according to key parameter respectively predicted each preset time's predicted gas leakage, finally determine the time when predicted gas leakage reaches failure value as failure time, according to failure time, the remaining useful life of fuel cell is calculated, the gas leakage under the action of mechanical attenuation mode is realized to predict, and the purpose of predicting the remaining useful life of fuel cell according to gas leakage is realized.

[0059] As Figure 1 As shown in the figure, the flow chart of the fuel cell remaining useful life prediction method disclosed by the embodiment of the present application, the method mainly includes the following steps:

[0060] Step S101: when identifying that the proton exchange membrane of fuel cell occurs mechanical attenuation, the key parameter of fuel cell is acquired.

[0061] In step S101, key parameter includes: current operating parameter, current state parameter, material characteristic parameter of proton exchange membrane and structure characteristic parameter of proton exchange membrane.

[0062] Among them, current operating parameter at least includes: operating temperature at different time, anode and cathode inlet and outlet pressure and anode and cathode inlet and outlet humidity.

[0063] Current state parameter at least includes the parameter reflecting the internal state of fuel cell.

[0064] Material characteristic parameter of proton exchange membrane at least includes the parameter reflecting the material of proton exchange membrane.

[0065] Structure characteristic parameter of proton exchange membrane at least includes: total thickness of membrane, membrane reinforcing layer thickness and initial hydrogen permeation current.

[0066] In the specific implementation process of step S101, fuel cell is placed in leakage mode identification test working condition, and leakage mode identification is carried out, if identifying that fuel cell occurs mechanical attenuation, the key parameter of fuel cell is acquired.

[0067] The specific process of leakage mode identification includes: hydrogen gas and inert gas are mixed to supply in the anode of fuel cell, and oxygen gas and inert gas are mixed to supply in the cathode of fuel cell.

[0068] Under the condition that anode hydrogen partial pressure and cathode oxygen partial pressure are constant, by adjusting inert gas flow and back pressure, the total pressure of anode and cathode is changed, so that different total pressure difference between anode and cathode is generated.

[0069] Under the action of different total gas pressure differences, the open circuit voltage corresponding to the fuel cell is measured and recorded respectively, and the change relationship of the open circuit voltage with the total gas pressure difference is obtained.

[0070] When the change relationship meets the characteristics of mechanical attenuation, it is determined that the proton exchange membrane of the fuel cell has mechanical attenuation.

[0071] The mixed hydrogen and inert gas can be humidified gas or non-humidified gas, and the mixed oxygen and inert gas can be humidified gas or non-humidified gas, and the inert gas includes nitrogen, helium, neon, argon, krypton, xenon and radon.

[0072] Step S102: input the key parameters and each preset time into the pre-constructed mechanical attenuation model, the mechanical attenuation model responds to and is based on each preset time and the key parameters to perform corresponding prediction processing, and outputs the predicted leakage amount corresponding to each preset time.

[0073] It should be noted that the predicted leakage amount or the leakage amount mentioned in the present application is the gas leakage amount, that is, the transmembrane permeation amount of the fuel cell anode and cathode gases.

[0074] In step S102, the construction of the mechanical attenuation model mainly includes the following steps:

[0075] Step S11: constructing a mechanical attenuation model containing unknown parameter terms.

[0076] In step S11, the unknown parameter terms at least include: initial hydrogen permeation current density, standard working condition constant and sensitive working condition constant.

[0077] Step S12: input the pre-obtained experimental data into the mechanical attenuation model.

[0078] In step S12, the experimental data at least include: hydrogen permeation current and open circuit voltage obtained by hydrogen permeation current test and open circuit voltage test when the fuel cell is placed in the pre-set accelerated durability working condition or conventional durability working condition.

[0079] The specific values of each parameter in the accelerated durability working condition are shown in Table 1.

[0080] Table 1:

[0081]

[0082] It should be noted that the accelerated durability working condition disclosed in the embodiment of the present application is only for illustration and is not limited.

[0083] Step S13: based on the experimental data, calibrate the unknown parameter terms at the current time to obtain the unknown parameter terms corresponding to the current time.

[0084] For example, based on the hydrogen permeation current and open circuit voltage in the experimental data, taking temperature as the independent variable, and hydrogen permeation current and open circuit voltage as the dependent variable, by changing the temperature, the temperature sensitivity working condition constant is obtained by measuring and based on the change relationship and rate of hydrogen permeation current and open circuit voltage, and the temperature sensitivity working condition constant is calibrated in the mechanical attenuation model.

[0085] It should be noted that the pressure fluctuation sensitivity working condition constant and the humidity fluctuation sensitivity working condition constant can also be obtained by the above example process.

[0086] Step S14: verifying whether the accuracy of the mechanical attenuation model meets the requirements. If not, step S15 is executed, and if yes, step S16 is executed.

[0087] Step S15: continue to input the experimental data into the mechanical attenuation model, and calibrate the unknown parameter term corresponding to the current time until the mechanical attenuation model with the required accuracy is obtained.

[0088] Step S16: determining that the mechanical attenuation model training is completed.

[0089] Specifically, the mechanical attenuation model expression obtained through the above mechanical attenuation model construction step is:

[0090]

[0091] Wherein, t is the time, that is, the independent variable in formula (1), and the corresponding ΔI cross (t) is the dependent variable, ΔI cross (t) is the hydrogen permeation current corresponding to the gas channeling caused by mechanical attenuation at time t, and exp represents the exponential function with e as the base.

[0092] In the embodiment of the present application, the value of t is each preset time.

[0093] It can be understood that the hydrogen permeation current is an important evaluation index of the proton exchange membrane gas channeling amount, and therefore the hydrogen permeation current and the gas channeling amount have a direct corresponding relationship, and the corresponding predicted channeling amount can be obtained based on the predicted hydrogen permeation current, or the corresponding predicted channeling amount can be calculated based on the predicted hydrogen permeation current through conventional technical means in the art.

[0094] Δp is the total pressure difference (dimensionless number, relative to 1 atmosphere) applied to the anode and cathode when testing the hydrogen permeation current under the hydrogen permeation current test condition.

[0095] t init defined as the time, is the initial hydrogen permeation current.

[0096] n is a user-defined multiple indicator, and n takes a value greater than or equal to 1, i.e., assuming t init Under the conditions of time and Δp, the hydrogen permeation current due to gas leakage caused by mechanical decay increases to n times the initial hydrogen permeation current.

[0097] based on The value of B can be obtained from Δp: Here, A is an unknown parameter, which can be understood as the correlation factor between gas leakage and Δp.

[0098] It should be noted that t init Depending on the physical properties of the proton exchange membrane and its operating conditions, different reliability analyses or failure distribution functions can be defined to obtain t. init For example, the normal distribution, the exponential distribution, and the Weibull distribution function.

[0099] This invention uses the Weibull distribution function for illustration. The Weibull distribution function is defined as follows:

[0100]

[0101] Where t is the endurance operating time, β is the shape parameter, and η is the scaling factor.

[0102] The embodiments of the present invention define F(t) init )=α,0≤α≤1, that is, we consider t init At time Δp, when the hydrogen permeation current due to gas leakage caused by membrane mechanical decay rises to n times the initial hydrogen permeation current, the probability of membrane failure due to mechanical decay is α. In this embodiment, α = 0.5.

[0103] The scaling factor η is related to the operating conditions and the material and structural properties of the proton exchange membrane. In this embodiment, the scaling factor η is defined as follows:

[0104] η=exp(α0)*exp(α1(δm-δ ePTFE ))*exp(α2δ ePTFE )*exp(α3T)*exp(α4θ P )*exp(α5θ RH )*γ(3)

[0105] Where α0 is the standard operating condition decay rate constant, α1 to α5 are the sensitivity operating condition constants for membrane resin layer thickness, membrane reinforcement layer thickness, operating temperature, operating pressure and battery humidity, respectively, and δm and δ ePTFE These represent the proton exchange membrane thickness and the reinforcement layer thickness, respectively; T is the operating temperature; θ is the temperature at which the membrane is heated. P θ represents the degree of operating pressure fluctuation. RHFor the extent of battery humidity fluctuation, gamma is defined as other material and working condition influencing factors not considered in the embodiment, for different material systems and durable working conditions, gamma can be adjusted to couple the influence of these unknown factors, the periodic changes of operating temperature, pressure and humidity in the durable working condition can be taken as the input parameters of the scaling factor η calculation.

[0106] In the specific implementation process of step S102, the preset time is taken as the independent variable t in formula (1), and the key parameters and the preset time are input into the mechanical attenuation model, that is, formula (1), the predicted hydrogen permeation current corresponding to the preset time is predicted based on the key parameters, the corresponding predicted leakage is obtained based on the predicted hydrogen permeation current, and the next preset time is input into the mechanical attenuation model for prediction processing until the predicted leakage corresponding to each preset time is predicted.

[0107] It should be noted that the hydrogen permeation current is an important evaluation index of the proton exchange membrane gas leakage, therefore, the hydrogen permeation current and the gas leakage have a direct corresponding relationship, the corresponding predicted leakage can be obtained based on the predicted hydrogen permeation current, or the corresponding predicted leakage can be calculated based on the predicted hydrogen permeation current through conventional technical means in the art.

[0108] Step S103: comparing the predicted leakage corresponding to each preset time with the preset failure value respectively, determining the time when the predicted leakage is not less than the failure value as the failure time.

[0109] In step S103, the preset failure value is the leakage value representing that the proton exchange membrane in the fuel cell reaches damage or failure.

[0110] In the specific implementation process of step S103, the predicted leakages corresponding to each preset time are compared with the preset failure value in turn according to the chronological order, when the predicted leakage is greater than or equal to the preset failure value, the time corresponding to the predicted leakage is determined as the failure time of the fuel cell.

[0111] For example, the preset failure value is 10, ABC is 3 different preset times arranged in chronological order, and the predicted leakages corresponding to A, B and C are 5, 10 and 15 respectively. First, compare the predicted leakage 5 corresponding to time A with the preset failure value 10, which does not satisfy the condition that the predicted leakage is greater than or equal to the preset failure value, then compare the predicted leakage 10 corresponding to time B with the preset failure value 10, which satisfies the condition that the predicted leakage is greater than or equal to the preset failure value, and then confirm that time B is the failure time.

[0112] Step S104: determining the remaining service life of the fuel cell from the current time to the failure time.

[0113] In step S104, the time when the key parameters of the fuel cell are acquired is the time when mechanical degradation of the proton exchange membrane of the fuel cell is identified.

[0114] Based on the above-mentioned embodiment of the application, when mechanical degradation of the proton exchange membrane of the fuel cell is identified, the current key parameters of the fuel cell are acquired, the pre-constructed mechanical degradation model is used to predict the predicted gas leakage amount at each preset time according to the key parameters, the time when the predicted gas leakage amount reaches the failure value is determined as the failure time, and the remaining service life of the fuel cell is calculated according to the failure time. In this scheme, the pre-constructed mechanical degradation model is used to perform prediction processing based on the current key parameters of the fuel cell, the gas leakage amount under the action of the mechanical degradation mode is predicted, and the purpose of predicting the remaining service life of the fuel cell according to the gas leakage amount is achieved.

[0115] As shown in Figure 2 , it is a flowchart for verifying whether the accuracy of the mechanical degradation model meets the requirements, and mainly includes the following steps:

[0116] Step S201: acquiring the key parameters at any historical time from the historical data of the fuel cell.

[0117] In step S201, the key parameters at any historical time include operating parameters, state parameters, material characteristic parameters of the proton exchange membrane, and structure characteristic parameters of the proton exchange membrane.

[0118] The operating parameters include operating temperatures at different times, anode and cathode inlet and outlet pressures, and anode and cathode inlet and outlet humidities.

[0119] The state parameters at least include parameters reflecting the internal state of the fuel cell.

[0120] The material characteristic parameters of the proton exchange membrane at least include parameters reflecting the constituent materials of the proton exchange membrane.

[0121] The structure characteristic parameters of the proton exchange membrane at least include the total thickness of the membrane, the thickness of the membrane reinforcing layer, and the initial hydrogen permeation current.

[0122] Step S202: inputting the key parameters and the historical time into the mechanical degradation model, the mechanical degradation model responding and performing simulation prediction processing based on the historical time and the key parameters to obtain the simulation gas leakage amount corresponding to the historical time.

[0123] It should be noted that the specific implementation process of step S202 is the same as that of step S102 in the embodiment shown in Figure 1 , and mutual reference is available.

[0124] Step S203: Calculate the difference between the simulated leakage amount and the actual leakage amount at historical moments.

[0125] In step S203, the actual leakage amount corresponding to the historical time is obtained from the historical data of the fuel cell.

[0126] Step S204: When the difference is less than or equal to the preset value, it is determined that the accuracy of the mechanical attenuation model meets the requirements.

[0127] It should be noted that when the difference is greater than the preset value, the accuracy of the mechanical attenuation model is determined to be unacceptable.

[0128] Based on the above-described embodiment of the present invention, a method for verifying whether the accuracy of a mechanical decay model meets the requirements is proposed. This method involves obtaining key parameters from historical data of the fuel cell at any given historical moment, inputting these key parameters and the historical moment into the mechanical decay model, and then performing simulation prediction based on the historical moment and key parameters to obtain the simulated leakage amount corresponding to that historical moment. The difference between the simulated leakage amount and the actual leakage amount at the historical moment is calculated. When the difference is less than or equal to a preset value, the accuracy of the mechanical decay model is determined to meet the requirements. In this scheme, the model accuracy is tested using the simulated predicted value and the actual value to ensure that a mechanical decay model with the required accuracy is obtained.

[0129] Based on the fuel cell lifetime prediction method disclosed in the above embodiments of the present invention, such as... Figure 3 As shown, this is a simulated curve of the hydrogen permeation current caused by mechanical decay at different temperatures, as disclosed in the embodiments of the present invention.

[0130] Specifically, the operating temperature, a key parameter in the mechanical decay model, is used as the independent variable. By changing the operating temperature while keeping other key parameters constant, the mechanical decay model is used to predict the relationship between the hydrogen permeation current and time at different temperatures.

[0131] like Figure 3 As shown, with the increase of operating temperature, the time point at which the hydrogen permeation current rapidly increases is significantly advanced.

[0132] like Figure 4 The figure shows the simulated variation curves of hydrogen permeation current caused by mechanical attenuation under different pressure fluctuation levels as disclosed in the embodiments of the present invention.

[0133] Specifically, the pressure fluctuation level, which was pre-calibrated using experimental data in the mechanical attenuation model, was used as the independent variable. The calibrated pressure fluctuation level was modified and recalibrated, while other fitting parameters remained unchanged. The mechanical attenuation model was then used to predict the relationship between the hydrogen permeation current and time under different pressure fluctuation levels.

[0134] likeFigure 4 As shown, with the increase in pressure fluctuation, the time point at which the hydrogen permeation current rapidly increases is significantly advanced.

[0135] like Figure 5 The figure shows the simulated change curves of hydrogen permeation current caused by mechanical attenuation under different humidity fluctuation levels as disclosed in the embodiments of the present invention.

[0136] Specifically, the humidity fluctuation level, which was pre-calibrated using experimental data, was used as the independent variable in the mechanical attenuation model. The calibrated humidity fluctuation level was modified and recalibrated, while other fitting parameters remained unchanged. The mechanical attenuation model was then used to predict the relationship between the hydrogen permeation current and time under different humidity fluctuation levels.

[0137] like Figure 5 As shown, with the increase in pressure fluctuation, the time point at which the hydrogen permeation current rapidly increases is significantly advanced.

[0138] like Figure 6 The figure shows the simulated variation curves of hydrogen permeation current caused by mechanical attenuation under different membrane reinforcement layer thicknesses disclosed in the embodiments of the present invention.

[0139] Specifically, the membrane reinforcement layer thickness, a key parameter in the mechanical attenuation model, is used as the independent variable. By changing the membrane reinforcement layer thickness while keeping other key parameters constant, the mechanical attenuation model is used to predict the change of hydrogen permeation current as the dependent variable over time under different membrane reinforcement layer thicknesses.

[0140] like Figure 6 As shown, as the thickness of the membrane reinforcement layer decreases, the time point at which the hydrogen permeation current rapidly increases is significantly advanced.

[0141] like Figures 3 to 6 As shown, these changes in operating conditions or membrane properties lead to greater stress and fluctuations within the membrane electrode or reduce the mechanical stability of the membrane, thus resulting in faster mechanical degradation of the membrane.

[0142] The properties of the fuel cell proton exchange membrane used in the simulation of this invention are shown in Table 2.

[0143] Table 2:

[0144]

[0145] The fitting parameters in the mechanical attenuation model used in the simulation of this invention are shown in Table 3.

[0146] It should be noted that the fitting parameters in the mechanical attenuation model were calibrated using the experimental data mentioned above.

[0147] Table 3:

[0148]

[0149] Based on the simulation application method of the mechanical attenuation model disclosed in the above embodiments of the present invention, the mechanical attenuation model is used for simulation to obtain the relationship between the hydrogen permeation current of the proton exchange membrane and the operating temperature, pressure fluctuation, humidity fluctuation, and membrane reinforcement layer thickness. In this scheme, the mechanical attenuation model is used for simulation to fully explore the characteristics of the proton exchange membrane and the influence of mechanical attenuation on the proton exchange membrane.

[0150] Based on the fuel cell lifetime prediction method disclosed in the above embodiments of the present invention, correspondingly, as... Figure 7 The diagram shown is a structural diagram of a fuel cell life prediction device disclosed in an embodiment of the present invention. The device mainly includes: an acquisition unit 701, a prediction unit 702, a comparison unit 703, and a determination unit 704.

[0151] The acquisition unit 701 is used to acquire key parameters of the fuel cell when mechanical degradation of the proton exchange membrane of the fuel cell is detected.

[0152] Specifically, the key parameters include: current operating parameters, current state parameters, material properties of the proton exchange membrane, and structural properties of the proton exchange membrane.

[0153] In one embodiment, the acquisition unit 701 is specifically used for:

[0154] Hydrogen and inert gas are mixed and supplied at the anode of the fuel cell, while oxygen and inert gas are mixed and supplied at the cathode. With the partial pressure of hydrogen at the anode and oxygen at the cathode remaining constant, the total gas pressure at the anode and cathode is changed by adjusting the inert gas flow rate and back pressure, resulting in various total gas pressure differences between the anode and cathode. Under each of these different total gas pressure differences, the open-circuit voltage of the fuel cell is measured and recorded, and the relationship between the open-circuit voltage and the total gas pressure difference is obtained. When the relationship meets the characteristics of mechanical degradation, mechanical degradation of the proton exchange membrane in the fuel cell is determined. Key parameters of the fuel cell are then obtained.

[0155] The prediction unit 702 is used to input key parameters and preset times into a pre-built mechanical attenuation model. The mechanical attenuation model responds and performs corresponding prediction processing based on each preset time and key parameter, and outputs the predicted leakage amount corresponding to each preset time.

[0156] The comparison unit 703 is used to compare the predicted leakage amount corresponding to each preset time with the preset failure value, and determine the time when the predicted leakage amount is not less than the failure value as the failure time.

[0157] In one embodiment, the comparison unit 703 is specifically used for:

[0158] The predicted leakage amount corresponding to each preset time point is compared with the preset failure value in chronological order. When the predicted leakage amount is greater than or equal to the preset failure value, the time corresponding to the predicted leakage amount is determined as the failure time of the fuel cell.

[0159] The determination unit 704 is used to determine the remaining service life of the fuel cell from the current time to the time of failure.

[0160] In one embodiment, the device further includes:

[0161] A construction unit is used to build a mechanical decay model containing unknown parameters. These unknown parameters include at least: initial hydrogen permeation current density, standard operating condition constant, and sensitivity operating condition constant. Pre-obtained experimental data is input into the mechanical decay model. This experimental data includes at least: hydrogen permeation current and open-circuit voltage obtained by placing the fuel cell under pre-set accelerated or conventional endurance conditions through hydrogen permeation current and open-circuit voltage test conditions. Based on the experimental data, the unknown parameters are calibrated at the current time to obtain the corresponding unknown parameters. If not, experimental data is continued to be input into the mechanical decay model to calibrate the corresponding unknown parameters at the current time until a mechanical decay model with the required accuracy is obtained. If yes, the mechanical decay model training is considered complete.

[0162] The verification unit is used to verify whether the accuracy of the mechanical attenuation model meets the requirements.

[0163] It should be noted that the specific implementation process of the embodiments of the present invention is different from that of the present invention. Figure 1 The embodiments shown are the same, and will not be described again here.

[0164] Based on the fuel cell lifetime prediction device disclosed in the above embodiments of the present invention, when mechanical degradation of the proton exchange membrane of the fuel cell is detected, the current key parameters of the fuel cell are obtained. A pre-constructed mechanical degradation model is used to predict the predicted leakage amount at each preset time based on the key parameters. Finally, the time when the predicted leakage amount reaches the failure value is determined as the failure time. The remaining lifetime of the fuel cell is calculated based on the failure time. In this solution, by using a pre-constructed mechanical degradation model to predict the gas leakage amount under the mechanical degradation mode, the remaining lifetime of the fuel cell is predicted based on the gas leakage amount.

[0165] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0166] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0167] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting the lifespan of a fuel cell, characterized in that, include: When mechanical degradation of the proton exchange membrane in a fuel cell is detected, key parameters of the fuel cell are obtained. The key parameters include: current operating parameters, current state parameters, material property parameters of the proton exchange membrane, and structural property parameters of the proton exchange membrane; The key parameters and each preset time are input into a pre-built mechanical attenuation model. The mechanical attenuation model responds and performs corresponding prediction processing based on each preset time and the key parameters, and outputs the predicted leakage amount corresponding to each preset time. The predicted leakage amount corresponding to each preset time is compared with the preset failure value, and the time when the predicted leakage amount is not less than the failure value is determined as the failure time. The remaining service life of the fuel cell is determined from the current time to the time of failure. The expression for the mechanical attenuation model is as follows: ; To predict the hydrogen permeation current corresponding to the amount of gas leakage caused by mechanical decay at time t, Defined as At that moment, The initial hydrogen permeation current is given by n, where n is greater than or equal to 1. A is an unknown parameter; The total pressure difference applied to the anode and cathode when testing the hydrogen permeation current under hydrogen permeation current testing conditions.

2. The method according to claim 1, characterized in that, The process of identifying whether the proton exchange membrane of the fuel cell has undergone mechanical degradation includes: Hydrogen and an inert gas are mixed and supplied at the anode of the fuel cell, and oxygen and the inert gas are mixed and supplied at the cathode of the fuel cell. With the partial pressure of hydrogen at the anode and the partial pressure of oxygen at the cathode remaining constant, the total gas pressure of the anode and the cathode is changed by adjusting the flow rate and back pressure of the inert gas, thereby creating different total gas pressure differences between the anode and the cathode. Under different total gas pressure differences, the open-circuit voltage of the fuel cell was measured and recorded respectively, and the relationship between the open-circuit voltage and the total gas pressure difference was obtained. When the changing relationship satisfies the characteristics of mechanical degradation, it is determined that the proton exchange membrane of the fuel cell has undergone mechanical degradation.

3. The method according to claim 1, characterized in that, The process of pre-constructing the mechanical attenuation model includes: Construct a mechanical attenuation model that includes unknown parameters; the unknown parameters include at least: initial hydrogen permeation current density, standard operating condition constant, and sensitivity operating condition constant; The pre-obtained experimental data is input into the mechanical decay model. The experimental data includes at least the hydrogen permeation current and open circuit voltage obtained by testing the hydrogen permeation current test condition and open circuit voltage test condition under a pre-set accelerated durability condition or a normal durability condition. Based on the experimental data, the unknown parameter items are calibrated at the current time to obtain the unknown parameter items corresponding to the current time. Verify whether the accuracy of the mechanical attenuation model meets the requirements; If not, continue to input the experimental data into the mechanical attenuation model, calibrate the unknown parameter items corresponding to the current moment, until a mechanical attenuation model with the required accuracy is obtained; If so, the mechanical attenuation model training is complete.

4. The method according to claim 3, characterized in that, The verification of whether the accuracy of the mechanical attenuation model meets the requirements includes: Key parameters at any given historical moment are obtained from the historical data of the fuel cell; the key parameters at any given historical moment include: operating parameters, state parameters, material property parameters of the proton exchange membrane, and structural property parameters of the proton exchange membrane; The key parameters and the historical time are input into the mechanical attenuation model. The mechanical attenuation model responds and performs simulation prediction processing based on the historical time and the key parameters to obtain the simulated leakage amount corresponding to the historical time. Calculate the difference between the simulated leakage amount and the actual leakage amount at the historical time; the actual leakage amount at the historical time is obtained from the historical data; When the difference is less than or equal to a preset value, it is determined that the accuracy of the mechanical attenuation model meets the requirements.

5. The method according to any one of claims 1 to 4, characterized in that, The step of comparing the predicted leakage amount corresponding to each preset time point with a preset failure value, and determining the time when the predicted leakage amount is not less than the failure value as the failure time, includes: The predicted leakage amount corresponding to each preset time is compared with the preset failure value in chronological order. When the predicted leakage amount is greater than or equal to the preset failure value, the time corresponding to the predicted leakage amount is determined as the failure time of the fuel cell.

6. A device for predicting the lifespan of a fuel cell, characterized in that, include: The acquisition unit is used to acquire key parameters of the fuel cell when mechanical degradation of the proton exchange membrane of the fuel cell is detected. The key parameters include: current operating parameters, current state parameters, material property parameters of the proton exchange membrane, and structural property parameters of the proton exchange membrane; The prediction unit is used to input the key parameters and each preset time into the pre-built mechanical attenuation model. The mechanical attenuation model responds and performs corresponding prediction processing based on each preset time and the key parameters, and outputs the predicted leakage amount corresponding to each preset time. The comparison unit is used to compare the predicted leakage amount corresponding to each preset time with the preset failure value, and determine the time when the predicted leakage amount is not less than the failure value as the failure time. A determining unit is used to determine the remaining service life of the fuel cell from the current time to the failure time; The expression for the mechanical attenuation model is as follows: ; To predict the hydrogen permeation current corresponding to the amount of gas leakage caused by mechanical decay at time t, Defined as At that moment, The initial hydrogen permeation current is given by n, where n is greater than or equal to 1. A is an unknown parameter; The total pressure difference applied to the anode and cathode when testing the hydrogen permeation current under hydrogen permeation current testing conditions.

7. The apparatus according to claim 6, characterized in that, The acquisition unit is specifically used for: Hydrogen and an inert gas are mixed and supplied at the anode of the fuel cell, and oxygen and the inert gas are mixed and supplied at the cathode. With the partial pressure of hydrogen at the anode and oxygen at the cathode remaining constant, the total gas pressure at the anode and cathode is changed by adjusting the flow rate and back pressure of the inert gas, resulting in different total gas pressure differences between the anode and cathode. Under each of these different total gas pressure differences, the open-circuit voltage of the fuel cell is measured and recorded, and the relationship between the open-circuit voltage and the total gas pressure difference is obtained. When the relationship satisfies the characteristics of mechanical degradation, it is determined that the proton exchange membrane of the fuel cell has undergone mechanical degradation. Obtain the key parameters of the fuel cell; The key parameters include: current operating parameters, current state parameters, material properties of the proton exchange membrane, and structural properties of the proton exchange membrane.

8. The apparatus according to claim 6, characterized in that, The device further includes: A construction unit is used to construct a mechanical degradation model containing unknown parameters. These unknown parameters include at least: initial hydrogen permeation current density, standard operating condition constant, and sensitivity operating condition constant. Pre-obtained experimental data is input into the mechanical degradation model. The experimental data includes at least: hydrogen permeation current and open-circuit voltage obtained by placing the fuel cell under pre-set accelerated or conventional endurance conditions through hydrogen permeation current and open-circuit voltage test conditions. Based on the experimental data, the unknown parameters are calibrated at the current time to obtain the corresponding unknown parameters. If not, the experimental data is continued to be input into the mechanical degradation model to calibrate the unknown parameters corresponding to the current time until a mechanical degradation model with the required accuracy is obtained. If yes, the mechanical degradation model training is considered complete. The verification unit is used to verify whether the accuracy of the mechanical attenuation model meets the requirements.

9. The apparatus according to claim 8, characterized in that, The verification unit is specifically used for: Key parameters are obtained from historical data of the fuel cell at any given historical moment. These key parameters include: operating parameters, state parameters, material property parameters of the proton exchange membrane, and structural property parameters of the proton exchange membrane. The key parameters and the historical moment are input into the mechanical decay model. The mechanical decay model responds and performs simulation prediction processing based on the historical moment and the key parameters to obtain the simulated leakage amount corresponding to the historical moment. The difference between the simulated leakage amount and the actual leakage amount at the historical moment is calculated. The actual leakage amount at the historical moment is obtained from the historical data. When the difference is less than or equal to a preset value, the accuracy of the mechanical decay model is determined to meet the requirements.

10. The apparatus according to any one of claims 6 to 9, characterized in that, The comparison unit is specifically used for: The predicted leakage amounts corresponding to each preset time point are compared with preset failure values ​​in chronological order. When a predicted leakage amount is greater than or equal to the preset failure value, the time corresponding to the predicted leakage amount is determined as the failure time of the fuel cell.

Images