A method and system for predicting aging life of fuel cells

By measuring the instability of the electric energy output of the fuel cell and the degree of electrode corrosion, and compensating the service life error with the strength of environmental influence, the problem of low data quality of aging factor in the existing technology is solved, and the accuracy of the fuel cell aging life prediction is improved.

CN118566752BActive Publication Date: 2024-11-01ZHANGJIAGANG GEJU INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411059935.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-05
Publication Date
2024-11-01
Estimated Expiration
2044-08-05

AI Technical Summary

Technical Problem

The prior art only relies on neural network methods in fuel cell aging life prediction, and fails to effectively consider the overall data changes and the impact of electrode material corrosion, resulting in low data quality and insufficient prediction accuracy.

Method used

By combining current and voltage fluctuations, the degree of electrode corrosion is calculated by calculating the power output instability, and the service life error compensation is performed based on the intensity of environmental influence, the aging factor is corrected, and the neural network model is used for prediction.

Benefits of technology

It improves the accuracy of fuel cell aging life prediction, and provides more accurate service life prediction by comprehensively considering the stability of electrical energy output, electrode corrosion and environmental factors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118566752B_ABST
    Figure CN118566752B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of battery aging measurement technology, and in particular to a method and system for predicting the aging life of a fuel cell. The present invention first measures the instability of the power output of a fuel cell according to the fluctuation of current and voltage based on the characteristic that the power output of a fuel cell with a longer life is relatively stable; further, based on the characteristic that the corrosion of the electrode material of the fuel cell will affect the electrode reaction rate and thus indirectly affect the aging trend of the fuel cell, the degree of electrode corrosion is calculated with the help of electrochemical impedance spectroscopy technology; then, the authenticity of the corrosion is verified with the environmental impact strength obtained by the temperature and humidity of the fuel cell during operation; thereby, the fuel cell aging factor is corrected by combining the service life error compensation obtained by combining the instability of power output, the degree of electrode corrosion and the environmental impact strength, so that the accuracy of the prediction of the aging life of the fuel cell is higher.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of battery aging measurement, and in particular to a method and system for predicting the aging life of a fuel cell. Background Art

[0002] Fuel cells convert part of the Gibbs free energy in the chemical energy of fuel into electrical energy through electrochemical reactions. Since they are not limited by the Carnot cycle effect, the corresponding efficiency is usually high. Fuel cells use fuel and oxygen as raw materials and have no mechanical transmission parts, so they emit very few harmful gases and have a long service life. Therefore, from the perspective of saving energy and protecting the ecological environment, fuel cells are a power generation technology with great potential for power generation. In order to ensure reliable long-term operation and maximize the utilization of fuel cells, it is usually necessary to accurately predict their aging life, so as to formulate a reasonable maintenance plan, replace and repair battery components in a timely manner, so as to extend the battery life and reduce maintenance costs.

[0003] The existing technology usually combines the neural network method to input various dimensional data generated during the operation of the fuel cell, such as current output value, voltage output value, operating temperature and operating humidity, into the trained fuel cell aging factor neural network model to obtain the corresponding fuel cell aging life factor, thereby predicting the aging life of the fuel cell based on the time series change of the fuel cell aging life factor.

[0004] However, the process of obtaining the aging life factor of each fuel cell only combines the fuel cell status data at each moment, without taking into account the changes in the data of various dimensions during the overall aging process of the fuel cell, and the corrosion of the electrode material of the fuel cell will also affect the aging process of the fuel cell; therefore, the prior art only combines the fuel cell aging factor obtained by the neural network method, which has high limitations and the corresponding data quality is low, resulting in low accuracy in the prediction of the aging life of the fuel cell. Summary of the invention

[0005] The present application provides a method and system for predicting the aging life of a fuel cell. First, based on the characteristic that the power output of a fuel cell with a longer life is relatively stable, the instability of the power output of the fuel cell is measured according to the fluctuations of current and voltage. Further, based on the characteristic that the corrosion of the electrode material of the fuel cell will affect the electrode reaction rate and thus indirectly affect the aging trend of the fuel cell, the degree of electrode corrosion is calculated with the help of electrochemical impedance spectroscopy technology. Then, the authenticity of the corrosion is verified with the environmental impact strength obtained by the temperature and humidity of the fuel cell during operation. Thus, the fuel cell aging factor is corrected by using the service life error compensation obtained by combining the instability of power output, the degree of electrode corrosion and the environmental impact strength, thereby solving the problem that the fuel cell aging factor obtained by the prior art only in combination with the neural network method has high limitations and the corresponding data quality is low, thereby making the prediction of the aging life of the fuel cell more accurate.

[0006] The first aspect of the present application provides a method for predicting the aging life of a fuel cell, comprising:

[0007] Obtain the current output value and voltage output value at each sampling moment during the operation of the fuel cell;

[0008] Determine the instability of the power output of the fuel cell according to the fluctuation of the current output value and the voltage output value of the fuel cell at all sampling moments;

[0009] Determine the degree of electrode corrosion of the fuel cell based on the changes in the electrochemical response of the electrode material surface of the fuel cell under the electrochemical impedance spectroscopy technology; determine the environmental impact intensity corresponding to the fuel cell based on the overall temperature and humidity of the fuel cell during operation;

[0010] The service life error compensation of the fuel cell is determined according to the instability of the power output, the degree of electrode corrosion and the intensity of the environmental impact; and the aging life of the fuel cell is predicted according to the service life error compensation combined with a neural network model.

[0011] In an embodiment of the first aspect of the present application, the method for obtaining the instability of electric energy output includes:

[0012] The product of the current output value range and the current output value variance of the fuel cell at all sampling moments is taken as the current fluctuation degree of the fuel cell;

[0013] The product of the voltage output value range and the voltage output value variance of the fuel cell at all sampling moments is taken as the voltage fluctuation degree of the fuel cell;

[0014] Determine the overall deviation of the rated current of the fuel cell according to the deviation of the current output value at each sampling moment relative to the rated current value of the fuel cell;

[0015] The instability of the power output of the fuel cell is determined based on the current fluctuation degree, the voltage fluctuation degree and the overall deviation of the rated current; the current fluctuation degree, the voltage fluctuation degree and the overall deviation of the rated current are all positively correlated with the instability of the power output.

[0016] In an embodiment of the first aspect of the present application, the method for obtaining the overall deviation of the rated current includes:

[0017] According to the difference between the current output value at each sampling moment and the rated current value of the fuel cell, the rated current local deviation of the current output value at each sampling moment is determined; according to the average of the rated current local deviations corresponding to all sampling moments, the rated current overall deviation of the fuel cell is determined.

[0018] In an embodiment of the first aspect of the present application, the method for determining the instability of the power output of the fuel cell according to the current fluctuation degree, the voltage fluctuation degree and the overall deviation of the rated current includes:

[0019] The product of the positive correlation mapping value of the sum of the square of the current fluctuation degree and the voltage fluctuation degree and the overall deviation of the rated current is taken as the instability of the power output of the fuel cell.

[0020] In an embodiment of the first aspect of the present application, the method for obtaining the electrode corrosion degree includes:

[0021] Using electrochemical impedance spectroscopy to monitor the electrode materials of fuel cells and determine the Nyquist plot of fuel cells;

[0022] The radius length of the arc curve portion in the curve of the Nyquist diagram is used as the charge transfer resistance corresponding to the fuel cell;

[0023] The average value of the tangent slopes corresponding to all data points in the other curve parts outside the arc curve is used as the electrode double layer capacitance corresponding to the fuel cell;

[0024] The degree of electrode corrosion of the fuel cell is determined according to the charge transfer resistance and the electrode double layer capacitance; the charge transfer resistance is positively correlated with the degree of electrode corrosion; and the electrode double layer capacitance is negatively correlated with the degree of electrode corrosion.

[0025] In an embodiment of the first aspect of the present application, the method for obtaining the environmental impact strength includes:

[0026] The operating temperature of the fuel cell at each sampling time is collected by a temperature sensor; the operating humidity of the fuel cell at each sampling time is collected by a humidity sensor;

[0027] Calculate the average operating temperature and the average operating humidity of the fuel cell at all sampling times; use the ratio between the average operating temperature and the preset normal operating temperature as a reference temperature ratio; use the ratio between the average operating humidity and the preset normal operating humidity as a reference humidity ratio; the preset normal operating temperature and the preset normal operating humidity are both greater than 0;

[0028] The environmental impact intensity corresponding to the fuel cell is determined according to the product of the reference temperature ratio and the reference humidity ratio.

[0029] In an embodiment of the first aspect of the present application, the method for obtaining the service life error compensation includes:

[0030] The positive correlation mapping value of the normalized value of the product between the electrode corrosion degree and the environmental impact strength is used as the stability compensation coefficient of the fuel cell; and the service life error compensation of the fuel cell is determined according to the product between the stability compensation coefficient and the instability of the electric energy output.

[0031] In an embodiment of the first aspect of the present application, the method for predicting the aging life of a fuel cell based on the service life error compensation combined with a neural network model includes:

[0032] The current output value, voltage output value, operating temperature and operating humidity of the fuel cell at each sampling time are input into the trained fuel cell aging factor neural network model, and the fuel cell aging factor at each sampling time of the fuel cell is output;

[0033] The product of the fuel cell aging factor and the service life error compensation is used as the compensation aging factor of the fuel cell at each sampling moment; the compensation aging factors of the fuel cell at all sampling moments are arranged in time sequence to determine a compensation aging factor time series curve;

[0034] The aging life of the fuel cell is predicted according to the compensation aging factor time series curve.

[0035] In an embodiment of the first aspect of the present application, the method for predicting the aging life of a fuel cell according to the compensation aging factor time series curve includes:

[0036] According to the compensation aging factor time series curve, data prediction is performed through the ARIMA model to obtain the predicted aging life factor of the fuel cell; and the aging life of the fuel cell is predicted according to the predicted aging life factor.

[0037] In a second aspect, the present application provides an aging life prediction system for a fuel cell, the system comprising:

[0038] A data acquisition module, used to obtain the current output value and the voltage output value at each sampling moment during the operation of the fuel cell;

[0039] A first determination module is used to determine the instability of the power output of the fuel cell according to the fluctuation of the current output value and the voltage output value of the fuel cell at all sampling moments;

[0040] The second determination module is used to determine the degree of electrode corrosion of the fuel cell according to the change of electrochemical response of the surface of the electrode material of the fuel cell under the electrochemical impedance spectroscopy technology; and determine the environmental impact intensity corresponding to the fuel cell according to the overall temperature and humidity of the fuel cell during operation;

[0041] The aging life prediction module is used to determine the service life error compensation of the fuel cell according to the instability of the power output, the degree of electrode corrosion and the intensity of the environmental impact; and to predict the aging life of the fuel cell according to the service life error compensation combined with the neural network model.

[0042] In a third aspect, the present application provides a computer device, comprising a memory and a processor. The memory is used to store computer program code, and the processor is used to call and run the computer program code from the memory to execute the method of the first aspect of the present application or any embodiment of the first aspect.

[0043] In a fourth aspect, the present application provides a computer program product, comprising a computer program code, which, when executed, performs the method of the first aspect of the present application or any embodiment of the first aspect.

[0044] In a fifth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program code. When the computer program code is executed, the method of the first aspect or any embodiment of the first aspect of the present application is executed.

[0045] This application has the following beneficial effects:

[0046] The corresponding power output of a fuel cell with a longer life is usually more stable. The stronger the volatility of the corresponding power output, the more unstable the working state of the fuel cell is, that is, the more unhealthy it is, and the more serious the aging of the fuel cell is, that is, the shorter the remaining service life is. Therefore, the instability of the power output of the fuel cell is first measured according to the fluctuations of current and voltage, thereby indirectly reflecting the impact of the stability characteristics of the power output on the aging of the fuel cell.

[0047] Furthermore, the corrosion of the fuel cell electrode material will lead to a decrease in the electrode reaction rate, thereby affecting the electrochemical performance of the fuel cell, increasing the resistance of the electrochemical reaction, affecting the electron and ion transmission rate, and indirectly aggravating the aging trend of the fuel cell. Therefore, the electrode corrosion degree is calculated based on the changes in the electrochemical response of the electrode material surface of the fuel cell under the electrochemical impedance spectroscopy technology. In order to further improve the credibility of the electrode corrosion degree, the environmental factors that may cause electrode corrosion are further combined, and the credibility of the electrode corrosion degree is measured according to the environmental impact intensity obtained from the overall temperature and humidity of the fuel cell during operation; thus, the fuel cell aging factor is corrected by combining the service life error compensation obtained by combining the instability of power output, the electrode corrosion degree and the environmental impact intensity, so that the aging life prediction of the fuel cell is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A flow chart of a method for predicting aging life of a fuel cell provided by one embodiment of the present invention;

[0050] Figure 2 A flow chart of a method for obtaining power output instability in a method for predicting the aging life of a fuel cell provided by an embodiment of the present invention;

[0051] Figure 3 A schematic diagram of a curve of a Nyquist diagram of a fuel cell determined by monitoring the electrode material of a fuel cell using electrochemical impedance spectroscopy technology provided by one embodiment of the present invention;

[0052] Figure 4 A structural diagram of an aging life prediction system for a fuel cell provided by one embodiment of the present invention;

[0053] Figure 5 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the aging life prediction method and system for fuel cells proposed according to the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment, and the specific features, structures or characteristics in one or more embodiments may be combined in any suitable form. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0055] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0056] The following is a detailed description of a method and system for predicting the aging life of a fuel cell provided by the present invention in conjunction with the accompanying drawings.

[0057] The present application provides a method for predicting the aging life of a fuel cell. Figure 1 , which shows a flow chart of a method for predicting aging life of a fuel cell provided by an embodiment of the present invention, the method comprising:

[0058] Step S101: obtaining the current output value and the voltage output value at each sampling time during the operation of the fuel cell.

[0059] Considering that the stability of the power output of the fuel cell will affect its life change trend, and the power output of the fuel cell is reflected in the current output and voltage output; therefore, it is necessary to collect the current output value and voltage output value of the fuel cell at each sampling moment. In a specific implementation of the embodiment of the present invention, the current output value at each sampling moment is collected during the operation of the fuel cell by a current sensor, and the current output value at each sampling moment is collected during the operation of the fuel cell by a voltage sensor; and the sampling frequency is set to collect once every 10 minutes, and in order to ensure the integrity of the data, the sampling time period is set to the time period corresponding to 24 hours before the current moment. The implementer can adjust the sampling frequency according to the specific implementation environment, and no further elaboration is made here.

[0060] Step S102: determining the instability of the power output of the fuel cell according to the fluctuation of the current output value and the voltage output value of the fuel cell at all sampling moments.

[0061] The corresponding power output of a fuel cell with a longer life is usually more stable. The stronger the volatility of the corresponding power output, the more unstable the working state of the fuel cell is, that is, the more unhealthy it is, and the more serious the aging of the fuel cell is, that is, the shorter the remaining service life is. Therefore, the instability of the power output of the fuel cell is first measured according to the fluctuations of current and voltage, thereby indirectly reflecting the impact of the stability characteristics of the power output on the aging of the fuel cell; the greater the corresponding power output instability, the more unhealthy the working state of the fuel cell is, and the more serious the aging of the corresponding fuel cell is.

[0062] Step S103: Determine the degree of electrode corrosion of the fuel cell according to the change in electrochemical response of the electrode material surface of the fuel cell under electrochemical impedance spectroscopy technology; determine the environmental impact intensity corresponding to the fuel cell according to the overall temperature and humidity of the fuel cell during operation.

[0063] The corrosion of the electrode material of the fuel cell will lead to a decrease in the electrode reaction rate, thereby affecting the electrochemical performance of the fuel cell, increasing the resistance of the electrochemical reaction, affecting the electron and ion transmission rate, and indirectly aggravating the aging trend of the fuel cell. Therefore, the electrode corrosion degree is calculated based on the changes in the electrochemical response of the electrode material surface of the fuel cell under the electrochemical impedance spectroscopy technology; the greater the corresponding electrode corrosion degree, the more serious the actual aging of the fuel cell. To further improve the credibility of the electrode corrosion degree, further combine the environmental factors that may cause electrode corrosion, and measure the credibility of the electrode corrosion degree based on the environmental impact intensity obtained from the overall temperature and humidity of the fuel cell during operation, so that the electrode corrosion influence obtained after weighting the electrode corrosion degree in combination with the environmental impact intensity is more accurate. The greater the corresponding environmental impact intensity and the greater the electrode corrosion degree, the more serious the corrosion of the fuel cell electrode, and the more obvious the corresponding aging trend should be, that is, the aging degree of the fuel cell is relatively greater.

[0064] Step S104: Determine the service life error compensation of the fuel cell according to the instability of power output, the degree of electrode corrosion and the intensity of environmental influence; and predict the aging life of the fuel cell according to the service life error compensation combined with the neural network model.

[0065] Further, based on the relationship between the instability of power output, the degree of electrode corrosion and the intensity of environmental impact and the aging of the fuel cell, a service life error compensation that comprehensively characterizes the aging of the fuel cell is obtained; thus, based on the service life error compensation, the output result of the neural network model corresponding to the prior art is improved, making the prediction of the aging life of the fuel cell more accurate.

[0066] Preferably, in some possible implementations of the embodiments of the present invention, the specific implementation process of the method for obtaining the instability of the power output in step S102 includes: Figure 2 , which shows a flow chart of a method for obtaining power output instability of a method for predicting the aging life of a fuel cell provided by an embodiment of the present invention, the method comprising:

[0067] Step S201: The product of the current output value range and the current output value variance of the fuel cell at all sampling moments is taken as the current fluctuation degree of the fuel cell.

[0068] The range represents the fluctuation range of a set of data. Therefore, the larger the range of the current output value, the larger the fluctuation range of the current output value, and the corresponding current fluctuation degree is also greater; while the variance represents the volatility of a set of data. Therefore, the larger the variance of the current output value, the larger the corresponding current fluctuation degree is also. Therefore, the product of the current output value range and the current output value variance is combined to obtain the current fluctuation degree.

[0069] In a specific implementation of the embodiment of the present invention, the process of obtaining the current fluctuation degree is expressed by the formula: JI=(I max -I min )×SI; where JI is the current fluctuation degree of the fuel cell; I max is the maximum current output value of the fuel cell at all sampling times; I min is the minimum current output value of the fuel cell at all sampling times; SI is the variance of the current output value of the fuel cell at all sampling times.

[0070] Step S202: The product of the voltage output value range and the voltage output value variance of the fuel cell at all sampling moments is taken as the voltage fluctuation degree of the fuel cell.

[0071] Analogously to the principle of obtaining the current fluctuation degree in step S201 , the current output value is replaced with the voltage output value, thereby determining the voltage fluctuation degree of the fuel cell.

[0072] In a specific implementation of the embodiment of the present invention, the process of obtaining the voltage fluctuation degree is expressed by the formula: JU=(U max -U min )×SU; JU is the voltage fluctuation of the fuel cell; U max is the maximum voltage output value of the fuel cell at all sampling times; U min is the minimum voltage output value of the fuel cell at all sampling times; SU is the variance of the voltage output value of the fuel cell at all sampling times.

[0073] Step S203: determining the overall deviation of the rated current of the fuel cell according to the deviation of the current output value at each sampling moment relative to the rated current value of the fuel cell.

[0074] Under normal circumstances, that is, when the fuel cell is in healthy working condition, the corresponding current output value is usually equal to or close to the rated current. Therefore, the greater the total deviation of the current output value relative to the rated current of the fuel cell, that is, the greater the overall deviation of the rated current, the unhealthier the working condition of the fuel cell is, and the more unstable the corresponding power output is.

[0075] Preferably, in some possible implementations of the embodiments of the present invention, the specific implementation process of the method for obtaining the overall deviation of the rated current in step S203 includes:

[0076] According to the difference between the current output value at each sampling moment and the rated current value of the fuel cell, the rated current local deviation of the current output value at each sampling moment is determined; according to the mean of the rated current local deviations corresponding to all sampling moments, the rated current overall deviation of the fuel cell is determined. The larger the rated current local deviation, the more abnormal the current output value at the corresponding sampling moment is relative to the rated current value of the fuel cell. The rated current local deviations at all sampling moments are combined from an overall perspective to obtain a more comprehensive and accurate overall rated current deviation that characterizes the instability of the fuel cell output. It should be noted that the rated current value of the fuel cell is related to the model of the specific fuel cell in the specific implementation environment, and needs to be adjusted according to the specific implementation environment. In a specific implementation method of an embodiment of the present invention, the maximum value of the current output value at all sampling moments is used as the rated current value of the fuel cell, so that the robustness of the obtained rated current local deviation is better.

[0077] In a specific implementation of the embodiment of the present invention, the process of obtaining the overall deviation of the rated current is expressed by the formula: ; Where ΔI is the overall deviation of the rated current of the fuel cell; M is the total number of sampling moments; I m is the current output value of the fuel cell at the mth sampling moment; is the rated current value of the fuel cell; is the local deviation of the rated current of the fuel cell at the mth sampling moment; || is the absolute value symbol.

[0078] Step S204: determining the instability of the power output of the fuel cell according to the current fluctuation degree, the voltage fluctuation degree and the overall deviation of the rated current.

[0079] Since the greater the current fluctuation, the greater the voltage fluctuation, and the greater the overall deviation of the rated current, the more unstable the corresponding power output of the fuel cell, the current fluctuation, the voltage fluctuation and the overall deviation of the rated current are all positively correlated with the instability of the power output.

[0080] Preferably, in some possible implementations of the embodiments of the present invention, the method for determining the instability of the power output of the fuel cell according to the current fluctuation degree, the voltage fluctuation degree and the overall deviation of the rated current includes:

[0081] The product of the positive correlation mapping value of the sum of the squares of the current fluctuation degree and the voltage fluctuation degree and the overall deviation of the rated current is used as the instability of the power output of the fuel cell. The larger the sum of the squares of the current fluctuation degree and the voltage fluctuation degree, the worse the performance of the fuel cell during operation; further combined with the relationship between the overall deviation of the rated current and the power output stability, the power output instability required by the embodiment of the present invention is obtained by combining them in the form of a product.

[0082] In a specific implementation of the embodiment of the present invention, the process of obtaining the instability of the power output is expressed by the formula: ; Where W is the instability of the power output of the fuel cell; JI is the current fluctuation of the fuel cell; JU is the voltage fluctuation of the fuel cell; ΔI is the overall deviation of the rated current of the fuel cell; is a positive correlation mapping value of the sum of the squares of the current fluctuation degree and the voltage fluctuation degree, that is, the Euclidean norm between the voltage fluctuation degree and the current fluctuation degree of the fuel cell. In other specific implementations of the embodiments of the present invention, the product or sum of the current fluctuation degree, the voltage fluctuation degree and the overall deviation of the rated current can also be used as the instability of the power output, which will not be further elaborated here.

[0083] Preferably, in some possible implementations of the embodiments of the present invention, the specific implementation process of the method for obtaining the electrode corrosion degree in step S103 includes:

[0084] At the present moment, the electrode material of the fuel cell is monitored by electrochemical impedance spectroscopy to determine the Nyquist diagram of the fuel cell. It should be noted that the electrochemical impedance spectroscopy (EIS) technology is a technical means commonly used by those skilled in the art to measure the corrosion of the electrode surface, and will not be further described here.

[0085] In electrochemical impedance spectroscopy technology, the x-axis of the Nyquist diagram represents the real impedance, and the y-axis represents the imaginary impedance. The corresponding data points are divided into the arc curve part in the low-frequency area and the part close to the constant slope straight line corresponding to the high-frequency area outside the arc curve after curve fitting; according to the principle of electrochemical impedance spectroscopy technology, the charge transfer resistance of the fuel cell is usually represented by the radius length of the arc curve part of the corresponding Nyquist diagram, so the radius length of the arc curve part in the curve of the Nyquist diagram is used as the charge transfer resistance corresponding to the fuel cell.

[0086] In a specific implementation of an embodiment of the present invention, in the arc curve portion of the curve of the Nyquist diagram, the distance between the two data points farthest apart is taken as the arc diameter, and half of the arc diameter is taken as the radius length of the arc curve portion of the curve of the Nyquist diagram; in other specific implementations of the embodiment of the present invention, the arc radius length can also be calculated directly based on the arc curve portion, which will not be further elaborated here.

[0087] The average of the tangent slopes corresponding to all data points in the other curve parts outside the arc curve is used as the electrode double-layer capacitance corresponding to the fuel cell. According to the principle of electrochemical impedance spectroscopy technology, the high-frequency region is usually expressed as an approximate oblique line, and the overall slope of the corresponding oblique line characterizes the size of the double-layer capacitance of the electrode. Therefore, the embodiment of the present invention takes into account the situation that it may not be completely an oblique line segment, and improves the accuracy and robustness of the calculated electrode double-layer capacitance by taking the average of the tangent slopes corresponding to all data points in the other curve parts outside the arc curve.

[0088] See also Figure 3 , which shows a curve schematic diagram of a Nyquist diagram of a fuel cell determined by monitoring the electrode material of a fuel cell using electrochemical impedance spectroscopy technology provided by an embodiment of the present invention, wherein the arc curve portion, that is, the area approximately similar to a semicircular arc before the extreme point, corresponds to the low-frequency portion, and the radius length of the semicircular arc area is the charge transfer resistance; the oblique line after the arc curve portion corresponds to the high-frequency portion, and the overall slope of the oblique line represents the size of the electrode double-layer capacitance; and the x-axis represents the real impedance, and the y-axis represents the imaginary impedance.

[0089] For the electrode material of the fuel cell, the larger the corresponding charge transfer resistance and the smaller the corresponding electrode double-layer capacitance, the more seriously the fuel cell electrode is corroded. Therefore, the degree of electrode corrosion of the fuel cell is further determined based on the charge transfer resistance and the electrode double-layer capacitance. The charge transfer resistance is positively correlated with the degree of electrode corrosion; the electrode double-layer capacitance is negatively correlated with the degree of electrode corrosion.

[0090] In a specific implementation of the embodiment of the present invention, the product of the negative correlation mapping value of the electrode double layer capacitance and the charge transfer resistance is used as the electrode corrosion degree of the fuel cell. In a specific implementation of the embodiment of the present invention, the process of obtaining the electrode corrosion degree is expressed by the formula: ; Wherein, F is the degree of electrode corrosion of the fuel cell; R is the charge transfer resistance corresponding to the fuel cell; C is the electrode double layer capacitance corresponding to the fuel cell; α is a preset adjustment parameter used to prevent the denominator from being 0, which is set to 0.1 and can be adjusted according to the specific implementation environment; In other specific implementations of the present invention, the implementer may also use the reciprocal of the value mapped by the exponential function with the natural constant as the base of the motor double-layer capacitance as the negative correlation mapping value of the motor double-layer capacitance.

[0091] Preferably, in some possible implementations of the embodiments of the present invention, the specific implementation process of the method for obtaining the environmental impact strength in step S103 includes:

[0092] The operating temperature of the fuel cell at each sampling time is collected by a temperature sensor; the operating humidity of the fuel cell at each sampling time is collected by a humidity sensor; the average operating temperature and the average operating humidity of the fuel cell at all sampling times are calculated; the overall operating temperature of the fuel cell is represented by the average operating temperature, and similarly, the overall operating humidity of the fuel cell is represented by the average operating humidity, so as to perform a more comprehensive characterization of the environmental impact strength based on the overall operating temperature and the overall operating humidity.

[0093] High temperature will increase the chemical reaction rate on the motor surface, while high humidity will aggravate the corrosion of the electrode surface. Both will promote the oxidation, corrosion or chemical reaction of the motor material, resulting in an increase in the charge transfer resistance. Therefore, the larger the average operating temperature and the average operating humidity are, the higher the credibility of the corresponding electrode corrosion degree, that is, the greater the environmental impact. The ratio between the average operating temperature and the preset normal operating temperature is used as the reference temperature ratio; the ratio between the average operating humidity and the preset normal operating humidity is used as the reference humidity ratio; the preset normal operating temperature and the preset normal operating humidity are both greater than 0.

[0094] By comparing the preset normal operating temperature with the preset normal operating humidity, the value of the environmental impact degree obtained later is more reasonable, eliminating the influence of the dimension. It should be noted that the preset normal operating temperature is the temperature requirement of the fuel cell under ideal operating conditions, and the preset normal operating humidity is the humidity requirement of the fuel cell under ideal operating conditions; in a specific implementation of an embodiment of the present invention, in order to improve the robustness of the obtained environmental impact strength, the minimum operating temperature at all sampling moments is used as the preset normal operating temperature, and the minimum operating humidity at all sampling moments is used as the preset normal operating humidity, and when the preset normal operating temperature or the preset normal operating humidity is 0, it is replaced by 0.1 to prevent the denominator from being 0. The larger the corresponding reference humidity ratio and the larger the reference temperature ratio, the larger the operating temperature and operating humidity of the fuel cell are relative to the normal situation, and the corresponding environmental impact is greater. Therefore, the environmental impact strength corresponding to the fuel cell is determined according to the product between the reference temperature ratio and the reference humidity ratio.

[0095] In a specific implementation of the embodiment of the present invention, the process of obtaining the environmental impact strength is expressed by the formula: ; Where E is the environmental impact intensity corresponding to the fuel cell; is the average operating temperature of the fuel cell at all sampling times; is the average operating humidity of the fuel cell at all sampling times; The preset normal operating temperature; It is the preset normal operating humidity. When the preset normal operating temperature or the preset normal operating humidity reaches 0, it is replaced by 0.1 to prevent the denominator from being 0.

[0096] Preferably, in some possible implementations of the embodiments of the present invention, the specific implementation process of the method for obtaining the service life error compensation in step S104 includes:

[0097] The positive correlation mapping value of the normalized value of the product between the electrode corrosion degree and the environmental impact strength is used as the stability compensation coefficient of the fuel cell. Since the environmental impact strength characterizes the credibility of the electrode corrosion degree, the electrode corrosion degree is weighted by the environmental impact strength, and the dimension effect is eliminated by normalization; further, according to the relationship between the instability of power output and the aging of the fuel cell, the service life error compensation of the fuel cell is determined according to the product between the stability compensation coefficient and the instability of power output; the larger the corresponding service life error compensation, the greater the aging degree of the corresponding fuel cell.

[0098] In a specific implementation of the embodiment of the present invention, the process of obtaining the service life error compensation of the fuel cell is expressed by the formula: ;in, is the service life error compensation of the fuel cell; W is the instability of the power output of the fuel cell; E is the environmental impact strength corresponding to the fuel cell; F is the electrode corrosion degree of the fuel cell; the normalized value of the product of the electrode corrosion degree and the environmental impact strength is added to the real number 1 for positive correlation mapping, so that the service life error compensation obtained after combining the instability of the power output is more reasonable, and the implementer can adjust it according to the specific implementation environment.

[0099] Preferably, in some possible implementations of the embodiments of the present invention, the specific implementation process of the method for predicting the aging life of the fuel cell according to the service life error compensation combined with the neural network model in step S104 includes:

[0100] The current output value, voltage output value, operating temperature and operating humidity of the fuel cell at each sampling time are input into the trained fuel cell aging factor neural network model, and the fuel cell aging factor at each sampling time of the fuel cell is output. In a specific implementation of the embodiment of the present invention, in the process of training the fuel cell aging factor neural network model, the features are scored and evaluated by manual scoring according to the current output value, voltage output value, operating temperature and operating humidity of the fuel cell in the training sample. The lower the score, the more obvious the aging trend of the fuel cell, and the smaller the corresponding fuel cell aging life factor.

[0101] Therefore, the smaller the fuel cell aging factor at each sampling moment output by the fuel cell aging factor neural network model, the more obvious the aging trend of the fuel cell measured by the current output value, voltage output value, operating temperature and operating humidity at the corresponding moment. However, the fuel cell aging factor obtained by this method only combines the instantaneous data of each dimension of the fuel cell at the corresponding moment, so it is necessary to optimize it in combination with the obtained service life error compensation to obtain a more accurate compensation aging factor; the product of the fuel cell aging factor and the service life error compensation is used as the compensation aging factor at each sampling moment of the fuel cell; further considering that the purpose of the embodiment of the present invention is to predict the aging life of the fuel cell, the compensation aging factors of the fuel cell at all sampling moments are arranged in time order to determine the compensation aging factor timing curve; further, the aging life of the fuel cell is predicted according to the timing change characteristics based on the compensation aging factor timing curve.

[0102] In a specific implementation of an embodiment of the present invention, a method for predicting the aging life of a fuel cell according to a compensation aging factor time series curve includes:

[0103] According to the compensation aging factor time series curve, the data is predicted through the ARIMA model to obtain the predicted aging life factor of the fuel cell; the aging life of the fuel cell is predicted based on the predicted aging life factor. It should be noted that the ARIMA model is a time series prediction model commonly used by technicians in this field. The implementer can adopt other prediction models or prediction methods according to the specific implementation environment. No further limitation or elaboration is made here. According to the principle of the fuel cell aging factor neural network model, the larger the corresponding predicted aging life factor, the larger the service life factor of the fuel cell, and the longer the service life of the fuel cell; further, the predicted aging life factor can be used to measure whether the fuel cell needs to be maintained or replaced to ensure the reliability, safety and economics of the fuel cell system.

[0104] In summary, a method for predicting the aging life of a fuel cell first measures the instability of the power output of the fuel cell according to the fluctuations of current and voltage based on the fact that the power output of a fuel cell with a longer life is relatively stable; further, based on the fact that the corrosion of the fuel cell electrode material will affect the electrode reaction rate and thus indirectly affect the aging trend of the fuel cell, the degree of electrode corrosion is calculated with the help of electrochemical impedance spectroscopy technology; then, the authenticity of the corrosion is verified with the environmental impact strength obtained by the temperature and humidity of the fuel cell during operation; and the fuel cell aging factor is corrected by combining the service life error compensation obtained by combining the instability of the power output, the degree of electrode corrosion and the environmental impact strength, so that the accuracy of the aging life prediction of the fuel cell is higher.

[0105] This application also provides a fuel cell aging life prediction system, see Figure 4 , which shows a structural diagram of an aging life prediction system for a fuel cell provided by an embodiment of the present invention, the system includes: a data acquisition module 401, a first determination module 402, a second determination module 403 and an aging life prediction module 404.

[0106] The data acquisition module 401 is used to acquire the current output value and the voltage output value at each sampling time during the operation of the fuel cell;

[0107] A first determination module 402 is used to determine the instability of the power output of the fuel cell according to the fluctuation of the current output value and the voltage output value of the fuel cell at all sampling moments;

[0108] The second determination module 403 is used to determine the degree of electrode corrosion of the fuel cell according to the change of electrochemical response of the electrode material surface of the fuel cell under the electrochemical impedance spectroscopy technology; and determine the environmental impact intensity corresponding to the fuel cell according to the overall temperature and humidity of the fuel cell during operation;

[0109] The aging life prediction module 404 is used to determine the service life error compensation of the fuel cell according to the instability of power output, the degree of electrode corrosion and the intensity of environmental influence; and to predict the aging life of the fuel cell according to the service life error compensation combined with the neural network model.

[0110] It should be noted that the system provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the aging life prediction system for fuel cells provided in the above embodiment and the aging life prediction method embodiment for fuel cells belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0111] The present application also provides a computer device. Figure 5 , which shows a schematic diagram of the structure of a computer device provided by an embodiment of the present invention, the computer device includes a memory 501, a processor 502, and a computer program 503 stored in the memory 501 and running on the processor 502, wherein when the processor 502 executes the computer program 503, the computer device can execute any one of the above-mentioned aging life prediction methods for fuel cells.

[0112] The embodiment of the present application also provides a computer program product. When the computer program product is run on a computer device, the computer device can execute any one of the above-mentioned methods for predicting the aging life of a fuel cell.

[0113] An embodiment of the present application also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer device, the computer device can execute any of the above-mentioned methods for predicting the aging life of a fuel cell.

[0114] In the embodiments provided in the present application, it should be understood that the provided computer device, computer program product and computer-readable storage medium are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the methods provided above and will not be repeated here.

[0115] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0116] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for predicting the aging life of a fuel cell, characterized in that: The method comprises: Obtain the current output value and voltage output value at each sampling moment during the operation of the fuel cell; Determine the instability of the power output of the fuel cell according to the fluctuation of the current output value and the voltage output value of the fuel cell at all sampling moments; Determine the degree of electrode corrosion of the fuel cell based on the changes in the electrochemical response of the electrode material surface of the fuel cell under the electrochemical impedance spectroscopy technology; determine the environmental impact intensity corresponding to the fuel cell based on the overall temperature and humidity of the fuel cell during operation; Determine the service life error compensation of the fuel cell according to the instability of the power output, the degree of electrode corrosion and the intensity of the environmental impact; predict the aging life of the fuel cell according to the service life error compensation combined with a neural network model; The method for obtaining the electrode corrosion degree includes: Using electrochemical impedance spectroscopy to monitor the electrode materials of fuel cells and determine the Nyquist plot of fuel cells; The radius length of the arc curve portion in the curve of the Nyquist diagram is used as the charge transfer resistance corresponding to the fuel cell; The average value of the tangent slopes corresponding to all data points in the other curve parts outside the arc curve is used as the electrode double layer capacitance corresponding to the fuel cell; Determining the degree of electrode corrosion of the fuel cell according to the charge transfer resistance and the electrode double layer capacitance; the charge transfer resistance is positively correlated with the degree of electrode corrosion; and the electrode double layer capacitance is negatively correlated with the degree of electrode corrosion; The method for obtaining the service life error compensation includes: The positive correlation mapping value of the normalized value of the product between the electrode corrosion degree and the environmental impact strength is used as the stability compensation coefficient of the fuel cell; the service life error compensation of the fuel cell is determined according to the product between the stability compensation coefficient and the instability of the electric energy output; The process of obtaining the fuel cell service life error compensation is expressed by the formula: ; in, is the service life error compensation of the fuel cell; W is the instability of the power output of the fuel cell; E is the environmental impact strength corresponding to the fuel cell; F is the degree of electrode corrosion of the fuel cell; Norm ( ) is the normalization function.

2. The method for predicting the aging life of a fuel cell according to claim 1, characterized in that: The method for obtaining the instability of electric energy output comprises: The product of the current output value range and the current output value variance of the fuel cell at all sampling moments is taken as the current fluctuation degree of the fuel cell; The product of the voltage output value range and the voltage output value variance of the fuel cell at all sampling moments is taken as the voltage fluctuation degree of the fuel cell; Determine the overall deviation of the rated current of the fuel cell according to the deviation of the current output value at each sampling moment relative to the rated current value of the fuel cell; The instability of the power output of the fuel cell is determined based on the current fluctuation degree, the voltage fluctuation degree and the overall deviation of the rated current; the current fluctuation degree, the voltage fluctuation degree and the overall deviation of the rated current are all positively correlated with the instability of the power output.

3. The method for predicting the aging life of a fuel cell according to claim 2, characterized in that: The method for obtaining the overall deviation of the rated current includes: According to the difference between the current output value at each sampling moment and the rated current value of the fuel cell, the rated current local deviation of the current output value at each sampling moment is determined; according to the average of the rated current local deviations corresponding to all sampling moments, the rated current overall deviation of the fuel cell is determined.

4. The method for predicting the aging life of a fuel cell according to claim 2, characterized in that: The method for determining the instability of the power output of the fuel cell according to the current fluctuation degree, the voltage fluctuation degree and the rated current overall deviation comprises: The product of the positive correlation mapping value of the sum of the square of the current fluctuation degree and the voltage fluctuation degree and the overall deviation of the rated current is taken as the instability of the power output of the fuel cell.

5. The method for predicting the aging life of a fuel cell according to claim 1, characterized in that: The method for obtaining the environmental impact strength includes: The operating temperature of the fuel cell at each sampling time is collected by a temperature sensor; the operating humidity of the fuel cell at each sampling time is collected by a humidity sensor; Calculate the average operating temperature and the average operating humidity of the fuel cell at all sampling times; use the ratio between the average operating temperature and the preset normal operating temperature as a reference temperature ratio; use the ratio between the average operating humidity and the preset normal operating humidity as a reference humidity ratio; the preset normal operating temperature and the preset normal operating humidity are both greater than 0; The environmental impact intensity corresponding to the fuel cell is determined according to the product of the reference temperature ratio and the reference humidity ratio.

6. The method for predicting the aging life of a fuel cell according to claim 5, characterized in that: The method for predicting the aging life of a fuel cell based on the service life error compensation combined with a neural network model includes: The current output value, voltage output value, operating temperature and operating humidity of the fuel cell at each sampling time are input into the trained fuel cell aging factor neural network model, and the fuel cell aging factor at each sampling time of the fuel cell is output; The product of the fuel cell aging factor and the service life error compensation is used as the compensation aging factor of the fuel cell at each sampling moment; the compensation aging factors of the fuel cell at all sampling moments are arranged in time sequence to determine a compensation aging factor time series curve; The aging life of the fuel cell is predicted according to the compensation aging factor time series curve.

7. A method for predicting the aging life of a fuel cell according to claim 6, characterized in that: The method for predicting the aging life of a fuel cell according to the compensation aging factor time series curve includes: According to the compensation aging factor time series curve, data prediction is performed through the ARIMA model to obtain the predicted aging life factor of the fuel cell; and the aging life of the fuel cell is predicted according to the predicted aging life factor.

8. A fuel cell aging life prediction system, characterized in that: The system comprises: A data acquisition module, used to obtain the current output value and the voltage output value at each sampling moment during the operation of the fuel cell; A first determination module is used to determine the instability of the power output of the fuel cell according to the fluctuation of the current output value and the voltage output value of the fuel cell at all sampling moments; The second determination module is used to determine the degree of electrode corrosion of the fuel cell according to the change of electrochemical response of the electrode material surface of the fuel cell under the electrochemical impedance spectroscopy technology; and determine the environmental impact intensity corresponding to the fuel cell according to the overall temperature and humidity of the fuel cell during operation; The method for obtaining the electrode corrosion degree includes: Using electrochemical impedance spectroscopy to monitor the electrode materials of fuel cells and determine the Nyquist plot of fuel cells; The radius length of the arc curve portion in the curve of the Nyquist diagram is used as the charge transfer resistance corresponding to the fuel cell; The average value of the tangent slopes corresponding to all data points in the other curve parts outside the arc curve is used as the electrode double layer capacitance corresponding to the fuel cell; Determining the degree of electrode corrosion of the fuel cell according to the charge transfer resistance and the electrode double layer capacitance; the charge transfer resistance is positively correlated with the degree of electrode corrosion; and the electrode double layer capacitance is negatively correlated with the degree of electrode corrosion; An aging life prediction module is used to determine the service life error compensation of the fuel cell according to the instability of the power output, the degree of electrode corrosion and the intensity of the environmental impact; and to predict the aging life of the fuel cell according to the service life error compensation combined with a neural network model; The method for obtaining the service life error compensation includes: The positive correlation mapping value of the normalized value of the product between the electrode corrosion degree and the environmental impact strength is used as the stability compensation coefficient of the fuel cell; the service life error compensation of the fuel cell is determined according to the product between the stability compensation coefficient and the instability of the electric energy output; The process of obtaining the fuel cell service life error compensation is expressed by the formula: ; in, is the service life error compensation of the fuel cell; W is the instability of the power output of the fuel cell; E is the environmental impact strength corresponding to the fuel cell; F is the degree of electrode corrosion of the fuel cell; Norm ( ) is the normalization function.