Fuel cell health assessment method based on multi-impedance measurement

Abstract

The invention discloses a fuel cell health assessment method based on multi-impedance measurement. Comprising the following steps: measuring fuel cell impedances corresponding to a plurality of preset frequencies under a preset working condition on line; predicting an electrochemical impedance spectrum of the fuel cell under the same preset working condition; predicting polarization curves, cyclic volt-ampere curves and linear volt-ampere curves under different preset working conditions; limiting current, total oxygen transmission resistance, electrochemical active area and hydrogen permeation current parameters under different preset working conditions are predicted, and the health state of the fuel cell is evaluated. According to the method, only a small amount of fuel cell impedance needs to be measured on line, the polarization curve, the cyclic volt-ampere curve and the linear volt-ampere curve which need special off-line measurement traditionally are obtained on line through machine learning prediction, then fuel cell health assessment is completed, and the method has the advantages of being capable of being used anytime and anywhere, low in cost, rapid and the like.

Description

Technical Field

[0001] The present invention relates to an online health assessment method in the field of fuel cell applications, and in particular to a fuel cell health assessment method based on multi-impedance measurement. Background Art

[0002] Accurate health assessment information contributes to the high reliability and long life operation of on-site fuel cells. By measuring electrochemical impedance spectroscopy (EIS), polarization (I / V) curves, cyclic voltammetry (CV) curves, and linear voltammetry (LSV) curves, health status parameters such as limiting current, cathode total oxygen transfer resistance, electrochemical active area (ECSA), and hydrogen permeation current can be extracted, thereby enabling accurate health assessment of fuel cells at the component level. However, traditional EIS, I / V curves, CV curves, and LSV curves all require offline measurements, and some curve measurements also rely on expensive equipment and complex test conditions, which are not suitable for on-site fuel cells.

[0003] Therefore, developing a method for online acquisition of EIS, I / V curves, CV curves and LSF curves without relying on expensive equipment and complex testing conditions, and then extracting health status parameters such as limiting current, cathode total oxygen transfer resistance, ECSA and hydrogen permeation current to accurately evaluate the health status of the fuel cell is of great significance for the high reliability and long life operation of on-site fuel cells. Summary of the invention

[0004] In order to solve the problem of online health assessment of on-site fuel cells, the present invention proposes a fuel cell health assessment method based on multi-impedance measurement. The present invention first measures the impedance corresponding to multiple frequencies of on-site fuel cells under preset working conditions online, and combines machine learning algorithms to achieve accurate prediction of EIS data under the same preset working conditions. Then, the predicted EIS data and machine learning algorithms are combined to achieve accurate prediction of I / V curves, CV curves, and LSV curves under different preset working conditions. Next, the machine learning algorithm and the predicted EIS, I / V curves, CV curves, and LSV curves are combined to achieve accurate prediction of health status parameters such as limiting current, cathode total oxygen transfer resistance, ECSA, and hydrogen permeation current under different preset working conditions, and evaluate the current health status of the fuel cell.

[0005] The scheme adopted by the present invention is:

[0006] 1. A fuel cell health assessment method based on multi-impedance measurement

[0007] 1) regulating the fuel cell to operate under a preset operating condition (i.e., preset operating condition 1), and after stable operation, online measuring the real impedance value and the imaginary impedance value corresponding to multiple preset frequencies of the fuel cell;

[0008] 2) predicting and obtaining EIS data under the current preset working condition based on the real impedance values ​​and imaginary impedance values ​​corresponding to multiple preset frequencies measured under the preset working condition;

[0009] The 2) is specifically:

[0010] The real impedance values ​​and imaginary impedance values ​​corresponding to multiple preset frequencies measured under the preset working conditions are input into the EIS prediction model together, and the EIS prediction data under the current preset working conditions are output.

[0011] 3) Predicting the I / V curve, CV curve and LSV curve data under different preset working conditions based on the EIS data predicted under the current preset working conditions;

[0012] The specific aspects of 3) are:

[0013] The EIS data predicted under the current preset working conditions are respectively input into the preset working condition 2 I / V curve prediction model, the preset working condition 3 CV curve prediction model, and the preset working condition 4 LSV curve prediction model, and the I / V curve data under the preset working condition 2, the CV curve data under the preset working condition 3, and the LSF curve data under the preset working condition 4 are respectively output.

[0014] 4) Based on the predicted EIS, I / V curve, CV curve and LSF curve data, the health status of the current fuel cell is evaluated to obtain a health status evaluation result.

[0015] The specific aspects of 4) are:

[0016] The predicted I / V curve prediction data under preset working condition 2 is input into the limiting current prediction model of preset working condition 5, and the model outputs the limiting current prediction value under preset working condition 5; and the EIS prediction data under preset working condition 1 is input into the total oxygen transmission resistance prediction model of preset working condition 6, and the model outputs the total oxygen transmission resistance prediction value under preset working condition 6; and the CV curve prediction data under preset working condition 3 is input into the ECSA prediction model of preset working condition 7, and the model outputs the ECSA prediction value under preset working condition 7; and the LSV curve prediction data under preset working condition 4 is input into the hydrogen permeation current prediction model of preset working condition 8, and the model outputs the hydrogen permeation current prediction value under preset working condition 8; finally, the health status of the fuel cell is evaluated based on the limiting current, total oxygen transmission resistance, ECSA and hydrogen permeation current prediction values ​​under different preset working conditions, and the health status evaluation result of the fuel cell is obtained.

[0017] The plurality of preset frequencies are generated by expert experience, filtering method, packaging method, embedding method or clustering method.

[0018] 2. A fuel cell health assessment system based on multi-impedance measurement

[0019] A fuel cell impedance data acquisition unit, used to collect and acquire real impedance values ​​and imaginary impedance values ​​corresponding to a plurality of preset frequencies of the fuel cell;

[0020] An EIS data generating unit, used to predict and obtain EIS data under the current preset working condition according to the real impedance values ​​and imaginary impedance values ​​corresponding to the multiple preset frequencies measured under the preset working condition;

[0021] An I / V curve generating unit, used for generating I / V curve data according to the predicted EIS data;

[0022] A CV curve generating unit, used for generating CV curve data according to the predicted EIS data;

[0023] An LSV curve generating unit is used to generate LSV curve data according to the predicted EIS data;

[0024] A health state parameter generating unit, used for generating health state parameters of the fuel cell according to the predicted EIS, I / V curve, CV curve and LSV curve data;

[0025] The health status evaluation result generating unit is used to evaluate the health status of the fuel cell according to the predicted health status parameters to obtain the health status evaluation result of the fuel cell.

[0026] The health status parameters of the fuel cell include limiting current, total oxygen transfer resistance, ECSA and hydrogen permeation current.

[0027] 3. A computer device

[0028] The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of the fuel cell health assessment method based on multi-impedance measurement are implemented.

[0029] 4. A computer-readable storage medium

[0030] The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the fuel cell health assessment method based on multi-impedance measurement are implemented.

[0031] 5. A computer program product

[0032] The computer program product comprises a computer program / instruction, which, when executed by a processor, implements the steps of the fuel cell health assessment method based on multi-impedance measurement.

[0033] The beneficial effects of the present invention are:

[0034] (1) Fast and low-cost. It only needs to measure the impedance of the fuel cell corresponding to a few frequencies under preset working conditions, which takes a very short time and has little impact on the normal operation of the fuel cell on site. Currently, more and more DC / DCs have integrated impedance measurement functions, and the cost of measuring impedance values ​​is low.

[0035] (2) Use anytime, anywhere. On-site fuel cell health assessment can be performed anytime and anywhere according to user needs.

[0036] (3) High precision. Based on the accurately predicted limiting current, cathode total oxygen transfer resistance, ECSA and hydrogen permeation current parameters, a more accurate health status assessment of the on-site fuel cell can be performed at the component level. The higher the accuracy of the health status assessment, the more accurate the optimization control and predictive operation and maintenance of the on-site fuel cell can be, which is more beneficial to its high reliability and long life operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is the overall flow chart of the present invention.

[0038] Figure 2 It is a schematic diagram of real impedance values ​​and imaginary impedance values ​​corresponding to two preset frequencies (f1=7943.3 Hz and f2=7.9433 Hz) under preset working condition 1 in an embodiment of the present invention.

[0039] Figure 3 It is a comparison chart between EIS prediction data and actual measurement data under preset working condition 1 in an embodiment of the present invention.

[0040] Figure 4 It is a comparison chart between the I / V curve prediction data and the actual measurement data under the preset working condition 2 in the embodiment of the present invention.

[0041] Figure 5 It is a comparison chart between the CV curve prediction data and the actual measurement data under the preset working condition 3 in the embodiment of the present invention.

[0042] Figure 6 It is a comparison chart between the LSV curve prediction data and the actual measurement data under the preset working condition 4 in the embodiment of the present invention.

[0043] Figure 7 is the limiting current (I lim )Comparison chart of predicted data and actual measured data.

[0044] Figure 8 is the total oxygen transmission resistance (R total )Comparison chart of predicted data and actual measured data.

[0045] Fig. 9It is a comparison chart between ECSA prediction data and actual measurement data under preset working condition 7 in an embodiment of the present invention.

[0046] Fig.10 is the hydrogen permeation current (I cross )Comparison chart of predicted data and actual measured data. DETAILED DESCRIPTION

[0047] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] In this embodiment, the number of preset frequencies is set to two. The two preset frequencies (f1 and f2) are specifically a value between 1Hz and 10KHz, f1 is named the first frequency, and f2 is named the second frequency. The two preset frequencies (f1 and f2) can be selected by expert experience, filtering method, packaging method, embedding method or clustering method. In this embodiment, the K-means clustering algorithm in the clustering method is used to select the two preset frequencies. Specifically, 41 data points in the high frequency part (1Hz~10KHz) of EIS are selected, and each data point contains a frequency value, a real impedance value and an imaginary impedance value. The 41 data points are divided into two clusters, and the K-means clustering algorithm is used to select two preset frequencies from the 41 frequencies corresponding to the 41 data points. Among them, the number of clusters of the K-means clustering algorithm is set to 2. The 41 data points are input into the K-means clustering algorithm for clustering to obtain the cluster label of each data point. After clustering is completed, the mean of the frequencies corresponding to all data points in each cluster is calculated. Next, in each cluster, find the data point closest to the frequency mean of the cluster, and use the frequency value corresponding to the data point as the preset frequency of the cluster.

[0049] like Figure 1 As shown, the present invention comprises the following steps:

[0050] 1) The fuel cell is regulated to operate under preset working condition 1, and after stabilization, the real impedance value and imaginary impedance value corresponding to multiple preset frequencies are measured online. Preset working condition 1 includes the fuel cell coolant outlet temperature (T out ), cathode inlet air humidity (H ca，air ), anode inlet hydrogen humidity (H an，H2 ), cathode inlet air pressure (P ca，air ), anode inlet hydrogen pressure (P an，H2 ), cathode inlet air flow (F ca，air ), anode inlet hydrogen flow rate (F an，H2 ), load current (I load ), injection current amplitude (I amp) etc. In this embodiment, the number of preset frequencies is set to two, namely f1=7943.3 Hz and f2=7.9433 Hz. out 80℃, H ca，air 100%, H an，H2 100%, P ca，air 2bara, P an，H2 2bara, P ca，air 5NLPM, F an，H2 2NLPM, I load 1.0Acm -2 ,I amp 0.1Acm -2 Under the preset working condition 1, the two real impedance measurement values ​​corresponding to the two preset frequencies (f1 and f2) are Re1=27.5076mΩ and Re2=148.1268mΩ, and the corresponding two imaginary impedance measurement values ​​are Im1=14.1192mΩ and Im2=-7.0896mΩ. Figure 2 shown.

[0051] 2) The real impedance values ​​and imaginary impedance values ​​corresponding to the multiple preset frequencies measured under the preset working condition 1 are input into the preset working condition 1 EIS prediction model, and the EIS prediction data under the preset working condition 1 is output. In this embodiment, the input of the preset working condition 1 EIS prediction model is two real impedance values ​​(Re1 and Re2) and two imaginary impedance values ​​(Im1 and Im2) corresponding to the two preset frequencies (f1 and f2) measured online under the same preset working condition 1, and the output is the EIS medium and high frequency data (1Hz~10KHz) under the preset working condition 1, such as Figure 3 As shown. The input and output data range used to train the preset working condition 1 EIS prediction model should cover the full life cycle of the fuel cell. In this embodiment, the preset working condition 1 EIS prediction model adopts a random forest (RF) regression model. The full life cycle of the fuel cell refers to the output voltage value of the fuel cell decaying from the initial 100% to 90% when it is running stably under the preset working condition 1.

[0052] 3) Input the EIS prediction data under preset working condition 1 into the I / V curve prediction model of preset working condition 2, the CV curve prediction model of preset working condition 3, and the LSV curve prediction model of preset working condition 4, and output the I / V curve prediction data under preset working condition 2 (such as Figure 4 ), CV curve prediction data under preset working condition 3 (as shown in Figure 5 ) and the LSV curve prediction data under the preset working condition 4 (as shown Figure 6The input of the preset working condition 2 I / V curve prediction model, the preset working condition 3 CV curve prediction model, and the preset working condition 4 LSV curve prediction model are all EIS prediction data under the preset working condition 1, the output of the preset working condition 2 I / V curve prediction model is the I / V curve prediction data under the preset working condition 2, the output of the preset working condition 3 CV curve prediction model is the CV curve prediction data under the preset working condition 3, and the output of the preset working condition 4 LSV curve prediction model is the LSV curve prediction data under the preset working condition 4. The input and output data ranges used to train the preset working condition 2 I / V curve prediction model, the preset working condition 3 CV curve prediction model, and the preset working condition 4 LSV curve prediction model should cover the entire life cycle of the fuel cell.

[0053] Preset operating condition 2 includes the fuel cell coolant outlet temperature (T out ), cathode inlet air humidity (H ca，air ), anode inlet hydrogen humidity (H an，H2 ), cathode inlet air pressure (P ca，air ), anode inlet hydrogen pressure (P an，H2 ), cathode inlet air flow (F ca，air ), anode inlet hydrogen flow rate (F an，H2 )、Measurement voltage range ([V1, V2]), measurement voltage interval (V r ), single voltage measurement hold time (t V )wait.

[0054] Preset operating condition 3 includes the fuel cell coolant outlet temperature (T out ), cathode inlet gas humidity (H ca，gas ), anode inlet hydrogen humidity (H an，H2 ), cathode inlet gas pressure (P ca，gas ), anode inlet hydrogen pressure (P an，H2 ), cathode inlet gas flow rate (F ca，gas ), anode inlet hydrogen flow rate (F an，H2 ), CV cycle number (n), voltage scan rate (S V ), voltage scanning range ([V1, V2]), etc.

[0055] Preset operating condition 4 includes the fuel cell coolant outlet temperature (T out ), nitrogen humidity at cathode inlet (H ca，N2 ), anode inlet hydrogen humidity (H an，H2 ), cathode inlet nitrogen pressure (P ca，N2 ), anode inlet hydrogen pressure (P an，H2 ), cathode inlet nitrogen flow rate (F ca，N2 ), anode inlet hydrogen flow rate (F an，H2 ), voltage scan rate (SV ), voltage scanning range ([V1, V2]), etc.

[0056] In this embodiment, the I / V curve prediction model of preset working condition 2, the local CV curve prediction model of preset working condition 3, and the LSF curve prediction model of preset working condition 4 all adopt the RF regression model. out 80℃, H ca，air 100%, H an，H2 100%, P ca，air 2bara, P an，H2 2bara, F ca，air 5NLPM, F an，H2 is 2NLPM, [V1, V2] is [0.2V, 0.95V], V r 0.04V, t V The T in preset working condition 3 is 5 minutes. out 80℃, H ca，gas 100%, H an，H2 100%, P ca，gas 2bara, P an，H2 2bara, F ca，gas =0NLPM, F an，H2 is 1NLPM, n is 5, S V 100mVs -1 , [V1, V2] is [0.05V, 0.95V]. T in preset working condition 4 out 80℃, H ca，N2 100%, H an，H2 100%, P ca，N2 2bara, P an，H2 2bara, P ca，N2 1NLPM, F an，H2 1NLPM, S V 1mVs -1 , [V1, V2] is [0.1V, 0.5V].

[0057] 4) Input the I / V curve prediction data under preset working condition 2 into the limiting current prediction model under preset working condition 5, and output the limiting current prediction value under preset working condition 5 (such as Figure 7 The EIS prediction data under the preset working condition 1 is input into the total oxygen transmission resistance prediction model under the preset working condition 6, and the total oxygen transmission resistance prediction value under the preset working condition 6 is output (as shown in FIG. Figure 8 The CV curve prediction data under the preset working condition 3 is input into the ECSA prediction model under the preset working condition 7, and the ECSA prediction value under the preset working condition 7 is output, such as Fig. 9As shown; the LSV curve prediction data under the preset working condition 4 is input into the hydrogen permeation current prediction model under the preset working condition 8, and the hydrogen permeation current prediction value under the preset working condition 8 is output, such as Fig.10 As shown; the health status of the fuel cell is evaluated based on the limiting current, total oxygen transfer resistance, ECSA and hydrogen permeation current predicted values ​​under different preset operating conditions.

[0058] The input of the limiting current prediction model of preset working condition 5 is the I / V curve prediction data under preset working condition 2, and the output is the limiting current prediction value under preset working condition 5; the input of the total oxygen transmission resistance prediction model of preset working condition 6 is the EIS prediction data under preset working condition 1, and the output is the total oxygen transmission resistance prediction value under preset working condition 6; the input of the ECSA prediction model of preset working condition 7 is the CV curve prediction data under preset working condition 3, and the output is the ECSA prediction value under preset working condition 7. The input of the hydrogen permeation current prediction model of preset working condition 8 is the LSV curve prediction data under preset working condition 4, and the output is the hydrogen permeation current prediction value under preset working condition 8. The input and output data ranges used to train the limiting current prediction model of preset working condition 5, the total oxygen transmission resistance prediction model of preset working condition 6, the ECSA prediction model of preset working condition 7, and the hydrogen permeation current prediction model of preset working condition 8 should cover the entire life cycle of the fuel cell. The limiting current prediction value under preset working condition 5 and the total oxygen transmission resistance prediction value under preset working condition 6 can characterize the healthy state of water content in the fuel cell catalyst layer and gas diffusion layer. The ECSA prediction value under the preset working condition 7 can characterize the aging state of the catalyst in the fuel cell catalyst layer. The hydrogen permeation current prediction value under the preset working condition 8 can characterize the aging state of the fuel cell proton exchange membrane.

[0059] Preset operating condition 5 includes the fuel cell coolant outlet temperature (T out ), cathode inlet gas humidity (H ca，gas ), anode inlet hydrogen humidity (H an，H2 ), cathode inlet gas pressure (P ca，gas ), anode inlet hydrogen pressure (P an，H2 ), cathode inlet gas flow rate (F ca，gas ), anode inlet hydrogen flow rate (F an，H2 ), cathode inlet oxygen concentration (c O2 ), voltage scanning range ([V1, V2]), etc.

[0060] Preset operating condition 6 includes the fuel cell coolant outlet temperature (T out ), cathode inlet gas humidity (H ca，gas ), anode inlet hydrogen humidity (H an，H2 ), cathode inlet gas pressure (P ca，gas ), anode inlet hydrogen pressure (P an，H2 ), cathode inlet gas flow rate (F ca，gas), anode inlet hydrogen flow rate (F an，H2 ), cathode inlet oxygen concentration (C O2 )wait.

[0061] The preset operating condition 7 includes the fuel cell coolant outlet temperature (T out ), cathode inlet gas humidity (H ca，gas ), anode inlet hydrogen humidity (H an，H2 ), cathode inlet gas pressure (P ca，gas ), anode inlet hydrogen pressure (P an，H2 ), cathode inlet gas flow rate (F ca，gas ), anode inlet hydrogen flow rate (F an，H2 ), CV cycle number (n), voltage scan rate (S V ), voltage scanning range ([V1, V2]), etc.

[0062] The preset operating condition 8 includes the fuel cell coolant outlet temperature (T out ), nitrogen humidity at cathode inlet (H ca，N2 ), anode inlet hydrogen humidity (H an，H2 ), cathode inlet nitrogen pressure (P ca，N2 ), anode inlet hydrogen pressure (P an，H2 ), cathode inlet nitrogen flow rate (F ca，N2 ), anode inlet hydrogen flow rate (F an，H2 ), voltage scan rate (S V ), voltage scanning range ([V1, V2]), etc.

[0063] In this embodiment, the limiting current prediction model of preset working condition 5, the total oxygen transmission resistance prediction model of preset working condition 6, the ECSA prediction model of preset working condition 7, and the hydrogen permeation current prediction model of preset working condition 8 all adopt the RF regression model. out 80℃, H ca，gas 100%, H an，H2 100%, P ca，gas 2bara, P an，H2 2bara, F ca，gas 5NLPM, F an，H2 is 2NLPM, c O2 1.0 mol·m -3 , [V1, V2] is [0.15V, 0.4V]. T in preset working condition 6 out 80℃, H ca，gas 100%, H an，H2 100%, P ca，gas 2bara, P an，H2 2bara, F ca，gas5NLPM, F an，H2 is 2NLPM, c O2 1.0 mol·m -3 . T in preset condition 7 out 80℃, H ca，gas 100%, H an，H2 100%, P ca，gas 2bara, P an，H2 2bara, F ca，gas =0NLPM, F an，H2 is 1NLPM, n is 5, S V 100mVs -1 , [V1, V2] is [0.05V, 0.95V]. T in preset working condition 8 out 80℃, H ca，N2 100%, H an，H2 100%, P ca，N2 2bara, P an，H2 2bara, F ca，N2 1NLPM, F an，H2 1NLPM, S V 1mVs -1 , [V1, V2] is [0.1V, 0.5V].

[0064] Finally, it should be noted that the above embodiments and explanations are only used to illustrate the technical solution of the present invention rather than to limit it. Those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope disclosed in the technical solution of the present invention, which should be included in the scope of protection of the claims of the present invention.

Claims

1. A fuel cell health assessment method based on multi-impedance measurement, characterized in that: The following steps are involved: 1) regulating the fuel cell to operate under a preset operating condition, and after stable operation, online measuring the real impedance value and the imaginary impedance value corresponding to multiple preset frequencies of the fuel cell; 2) predicting and obtaining EIS data under the current preset working condition based on the real impedance values ​​and imaginary impedance values ​​corresponding to multiple preset frequencies measured under the preset working condition; 3) Predicting the I / V curve, CV curve and LSV curve data under different preset working conditions based on the EIS data predicted under the current preset working conditions; 4) Based on the predicted EIS, I / V curve, CV curve and LSV curve data under different preset working conditions, the health status of the current fuel cell is evaluated to obtain a health status evaluation result.

2. A fuel cell health assessment method based on multi-impedance measurement according to claim 1, characterized in that: The 2) is specifically: The real impedance values ​​and imaginary impedance values ​​corresponding to multiple preset frequencies measured under the preset working conditions are input into the EIS prediction model together, and the EIS prediction data under the current preset working conditions are output.

3. A fuel cell health assessment method based on multi-impedance measurement according to claim 1, characterized in that: The specific aspects of 3) are: The EIS data predicted under the current preset working conditions are respectively input into the I / V curve prediction model, the CV curve prediction model, and the LSV curve prediction model, and the I / V curve, CV curve, and LSV curve prediction data under different preset working conditions are respectively output.

4. A fuel cell health assessment method based on multi-impedance measurement according to claim 1, characterized in that: The specific aspects of 4) are: The predicted I / V curve data is input into the limiting current prediction model, and the model outputs the limiting current prediction value; the predicted EIS data is input into the total oxygen transfer resistance prediction model, and the model outputs the total oxygen transfer resistance prediction value; the predicted CV curve data is input into the electrochemical active area (ECSA) prediction model, and the model outputs the ECSA prediction value; the LSV curve data is input into the hydrogen permeation current prediction model, and the model outputs the hydrogen permeation current prediction value; finally, the health status of the fuel cell is evaluated based on the limiting current, total oxygen transfer resistance, ECSA and hydrogen permeation current prediction values, and the health status evaluation result of the fuel cell is obtained.

5. A fuel cell health assessment method based on multi-impedance measurement according to claim 1, characterized in that: The plurality of preset frequencies are generated by expert experience, filtering method, packaging method, embedding method or clustering method.

6. A fuel cell health assessment system based on multi-impedance measurement, characterized in that: include: A fuel cell impedance data acquisition unit, used to collect and acquire real impedance values ​​and imaginary impedance values ​​corresponding to a plurality of preset frequencies of the fuel cell; An EIS data generating unit, used to predict and obtain EIS data under the current preset working condition according to the real impedance values ​​and imaginary impedance values ​​corresponding to the multiple preset frequencies measured under the preset working condition; An I / V curve generating unit, used for generating I / V curve data according to the predicted EIS data; A CV curve generating unit, used for generating CV curve data according to the predicted EIS data; An LSV curve generating unit is used to generate LSV curve data according to the predicted EIS data; A health state parameter generating unit, used for generating health state parameters of the fuel cell according to the predicted EIS, I / V curve, CV curve and LSV curve data; The health status evaluation result generating unit is used to evaluate the health status of the fuel cell according to the predicted health status parameters to obtain the health status evaluation result of the fuel cell.

7. A fuel cell health assessment system based on multi-impedance measurement according to claim 6, characterized in that: The health status parameters of the fuel cell include limiting current, total oxygen transfer resistance, ECSA and hydrogen permeation current.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a fuel cell health assessment method based on multi-impedance measurement as described in any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a fuel cell health assessment method based on multi-impedance measurement as described in any one of claims 1 to 5 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of a fuel cell health assessment method based on multi-impedance measurement as described in any one of claims 1 to 5 are implemented.

Images